Article

Hierarchical information fusion for decision making in craniofacial superimposition

Authors:
To read the full-text of this research, you can request a copy directly from the authors.

Abstract

Craniofacial superimposition is one of the most important skeleton-based identification methods. The process studies the possible correspondence between a found skull and a candidate (missing person) through the superimposition of the former over a variable number of images of the face of the latter. Within craniofacial superimposition we identified three different stages, namely: (1) image acquisition-processing and landmark location; (2) skull-face overlay; and (3) decision making. While we have already proposed and validated an automatic skull-face overlay technique in previous works, the final identification stage, decision making, is still performed manually by the expert. This consists of the determination of the degree of support for the assertion that the skull and the ante-mortem image belong to the same person. This decision is made through the analysis of several criteria assessing the skull-face anatomical correspondence based on the resulting skull-face overlay. In this contribution, we present a hierarchical framework for information fusion to support the anthropologist expert in the decision making stage. The main goal is the automation of this stage based on the use of several skull-face anatomical criteria combined at different levels by means of fuzzy aggregation functions. We have implemented two different experiments for our framework. The first aims to obtain the most suitable aggregation functions for the system and the second validates the proposed framework as an identification system. We tested the framework with a dataset of 33 positive and 411 negative identification instances. The present proposal is the first automatic craniofacial superimposition decision support system evaluated in an objective and statistically meaningful way.

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the authors.

... Recently, in [178,182,183], the authors present a hierarchical system to evaluate the anatomical consistence of morphological criteria between the face and the skull and give support to the forensic expert decision-making process. From a series of SFOs of the same individual, the computer-assisted decision support system (CADSS) provides to the forensic expert a quantitative output value that is indicative of the morphological matching consistency of a given CFS problem. ...
... The mean value of the results of the 26 experts, the result of the three best experts, and the outcomes of their automatic CADSS are shown in Table 4. The designed CADSS can be considered the first automatic tool for classifying couples of unknown faces and skulls as positive or negative cases with accuracy similar to the best performing forensic experts [182]. However, one of the reached conclusions was that the identification results based on the performance of the CADSS could be strongly influenced by the poor quality of some SFOs. ...
... Table 4. The table shows the mean value of the results of the 26 experts, the results of the three best experts, and the outcome of the CADSS presented in [182]. Detailed performance indicators are shown, such as the percentage of correct decisions, the number of positive and negative decisions given in each case, and the corresponding rate of true and false positives and true and false negatives. ...
Article
Full-text available
This paper represents the first survey on the application of AI techniques for the analysis of biomedical images with forensic human identification purposes. Human identification is of great relevance in today’s society and, in particular, in medico-legal contexts. As consequence, all technological advances that are introduced in this field can contribute to the increasing necessity for accurate and robust tools that allow for establishing and verifying human identity. We first describe the importance and applicability of forensic anthropology in many identification scenarios. Later, we present the main trends related to the application of computer vision, machine learning and soft computing techniques to the estimation of the biological profile, the identification through comparative radiography and craniofacial superimposition, traumatism and pathology analysis, as well as facial reconstruction. The potentialities and limitations of the employed approaches are described, and we conclude with a discussion about methodological issues and future research.
... Information fusion is a formal framework, which uses mathematical methods and technical tools to synthesize different information, in order to get high-quality and useful information [5][6][7][8]. Compared with the single-source independent processing, the advantages of information fusion include: improving detectability and credibility, expanding the space-time sensing range, reducing the degree of reasoning ambiguity, improving the detection accuracy and other performance, increasing the target feature dimension, improving spatial resolution, enhancing the system fault-tolerant ability and white adaptability, so as to improve the whole system performance. ...
... The literature cited is [1][2][3][4][5][6][7][8]42,43] gives many excellent researches on multiple information fusions. By comparing with the literature [1][2][3][4][5][6][7][8]42,43]. ...
... The literature cited is [1][2][3][4][5][6][7][8]42,43] gives many excellent researches on multiple information fusions. By comparing with the literature [1][2][3][4][5][6][7][8]42,43]. The research given by the contributions of this article are as following: two new concepts of information fusion are presented by using mathematical methods to understand the concept and characteristics of information fusion: information redundancy fusion and Information supplementation fusion. ...
Article
Full-text available
The development of information technology brings the challenge of data redundancy and data shortage to information fusion. Based on the dynamic boundary characteristics of p-set, this paper analyzes the structure and generation of p-augmented matrix, and then analyzes the dynamic generation of information equivalence class, and then proposes an intelligent acquisition algorithm of information equivalence class based on matrix reasoning. In addition, this paper analyzes two types of information fusion, namely information redundancy fusion and information supplement fusion. Then, the relationship among redundant information fusion, supplementary information fusion, and information equivalence classes is analyzed. Finally, this paper presents the application of intelligent acquisition of information equivalence class in information retrieval.
... Recently, we have also developed a theoretical framework for decision making [37], [38]. This hierarchical DSS represents the first automatic system for human identification by CFS. ...
... In [38], we proposed a complete framework for a DSS in CFS (See Fig. 2). The system develops fusion of information concerning skull-face anatomical correspondence at three different levels: criterion evaluation, SFO evaluation, and CFS evaluation. ...
... It also summarizes the methodology for the CV methods which achieve the best results in each case. These methods were used in [38] at the criterion evaluation level. In that contribution, we also described all the aspects and considerations included in the decision making process in CFS. ...
Article
Full-text available
Craniofacial superimposition (CFS) is a forensic identification technique which studies the anatomical and morphological correspondence between a skull and a face. It involves the process of overlaying a variable number of facial images with the skull. This technique has great potential since nowadays the wide majority of the people have photographs where their faces are clearly visible. In addition, the skull is a bone that hardly degrades under the effect of fire, humidity, temperature changes, etc. Three consecutive stages for the CFS process have been distinguished: the acquisition and processing of the materials; the skull-face overlay; and the decision making. This final stage consists of determining the degree of support for a match based on the previous overlays. The final decision is guided by different criteria depending on the anatomical relations between the skull and the face. In previous approaches, we proposed a framework for automating this stage at different levels taking into consideration all the information and uncertainty sources involved. In this study, we model new anatomical skull-face regions and we tackle the last level of the hierarchical decision support system. For the first time, we present a complete system which provides a final degree of craniofacial correspondence. Furthermore, we validate our system as an automatic identification tool analyzing its capabilities in closed (known information or a potential list of those involved) and open lists (little or no idea at first who may be involved) and comparing its performance with the manual results achieved by experts, obtaining a remarkable performance. The proposed system has been demonstrated to be valid for sortlisting a given data set of initial candidates (in 62,5% of the cases the positive one is ranked in the first position) and to serve as an exclusion method (97,4% and 96% of true negatives in training and test, respectively). IEEE
... There is thus a need of (semi) automatic forensic identification methods. 55 Meanwhile the automation of the craniofacial identification technique has been the subject of research throughout many works [14][15][16], there are just a few computerized approaches for CR. In particular, geometric morphometric techniques (such as elliptical Fourier analysis [17]) have been employed to compare radiographs of frontal sinus [18], cranial vault [9], teeth [19,20], clavicles [21], 60 and patellae [13]. ...
... curves [60] to study the identification capabilities of the proposal as done in [16]. A CMC curve measures the probability that the correct match for a identification case is present in a candidate list of the r best matches, where r denotes the position in the rank. ...
Article
Comparative radiography is a forensic identification technique traditionally involving the manual comparison of ante-mortem and post-mortem radiographs, thus being time consuming and error prone. The main objective is to propose and validate a computer-aided comparative radiography paradigm based on the 3D bone scan-2D radiograph superimposition process of any bone or cavity. The proposal follows an image registration methodology to automatically search for the ante-mortem radiograph acquisition parameters from the forensic object's silhouette considering occlusions. The underlying optimization problem is complex since a close initialization cannot be assumed and the image intensities are not reliable or not captured. Several experiments were performed to validate the method. First, we study its accuracy and robustness with synthetic images of clavicles, patellae and frontal sinuses. Second, we study how optimization performance and both variability and differences in the segmentation performed by human operators affect the identification using synthetic and real images of frontal sinuses.
... Notice that these results are obtained with the simplest decision-making method based only on the registration error. Therefore, a more complex decision-making method based on multiple forensic criteria and metrics, as the one depicted in [63] for the craniofacial identification technique, can further improve the identification capabilities of the proposal. ...
Article
Real-coded evolutionary algorithms have solved numerous real-world optimization problems. In this work, we aim to analyze the behavior and robustness of several real-coded evolutionary algorithms from the state of the art in a challenging real world optimization problem. This optimization problem consists on the superimposition of 3D and 2D images of skeletal structures (i.e. bones and cavities) based on their silhouette. This task is required for the automation of a forensic identification technique known as comparative radiography, via the generation of the best projection of the 3D image with respect to the 2D image. This superimposition problem was tackled in a recent proposal using an evolutionary 3D–2D image registration method based on differential evolution. However, the results obtained were insufficient for its use in real scenarios, due to: (1) the complexity and multi-modality of search space, despite the reduced number of parameters to be optimized (7 in its simple version and 9 in a more complex one, proposed in this work); and (2) the high computational cost of generating and evaluating a superimposition. Particularly, we have performed a rigorous comparative study of six state-of-the-art real-coded evolutionary algorithms (DE, L-SHADE, CMA-ES, BIPOP-CMA-ES, CRO-SL, and MVMO-SH) with synthetic images of three forensic anatomical structures (frontal sinuses, clavicles, and patellae), showing that the best results are always obtained by MVMO-SH in terms of precision, robustness and computational cost. Furthermore, we have validated the quality of the superimpositions obtained by the evolutionary image registration method using MVMO-SH with real images of frontal sinuses. We have performed the comparison of 50 head radiographs and 50 3D images, resulting in 2,500 cross-comparisons (50 positive and 2,450 negatives). The obtained results are promising since the superimpositions obtained allowed us to filter out 88% of the possible candidates with 0 error rate in a fully automatic manner, showing the high quality of the superimposition obtained.
... The estimation of the transformation parameters using the evolutionary techniques has not adapted with the anthropological parameters in order to attain a good enlargement and orientation. 2. The sophisticated procedures involved in the registration of the existing CAS [8][9][10] are seen limited only to the frontal plane of the face. This is probably due to the limited areas of measurement since we are comparing two objects of different nature. ...
Article
Full-text available
Identification of human remains via craniofacial superimposition (CS) is one of the prominent research areas in the forensic sciences. CS makes use of imaging techniques to identify an unknown skull by matching it with the available face photographs of missing individuals. Life-size enlargement of the face image and orientating the skull to correspond to the posture seen in the face photograph are the two main problems that affect identification accuracy with both the conventional and the computer-aided methods. Unlike the existing techniques, this research proposes a 3D skull–3D face model superimposition (3D–3D) approach to address the above two issues. The proposed method commences by reconstructing the 3D face model from a given 2D face image using the mean simplified generic elastic model, followed by registering the face model to a 3D skull along the jaw line using the analytical curvature B-spline (AC B-spline). The accuracy index of the registration is then evaluated to suggest the degree to which the face image corresponds to a skull. The superimpositions of positive and negative cases were conducted on a set of 3D skulls versus a set of 2D face images. The accuracy indices of the registration results suggest that the AC B-spline is more robust in 3D–3D superimposition compared to the other existing methods. The full experimental results have demonstrated the potential of the proposed method as an assistive tool to the forensic scientists for craniofacial identifications.
... Campomanes-Alvarez et al. (2018) [51,52] tested their automated system using fuzzy aggregation functions for craniofacial superimposition using known materials. The statistical analysis of testing results suggested the system was effective to support decision-making. ...
Article
Full-text available
Craniofacial superimposition is a technique used in the field of forensic anthropology to assist in the analysis of an unknown skull. The process involves superimposing an image of the recovered skull over an ante mortem image of the suspected individual. In the past two decades, there has been a decline in the application due to the development of molecular analysis as a more precise and accurate identification technique. Despite its decrease in use, there has been significant development in superimposition techniques in the past five years, specifically to standardize procedures. One project, MEPROCS (The New Methodologies and Protocols of Forensic Identification by Craniofacial Superimposition), has attempted to establish a framework for solving the problems of past superimposition techniques. Future researchers should consider integrating information gleaned from clinical practices with the statistical and technical advances of craniofacial superimposition for better facilitating its use in forensic anthropology. Keywords: Forensic science, Anthropology, Craniofacial superimposition
... In particular, the design of 25 computer-aided CFS methods has experienced a boom over the past twenty years [24]. The most recent approaches use 3D models of the skull and soft computing (SC) methods for the first two CFS stages [26,27,5] and include computer vision (CV) techniques to support the final decision [7,8]. These methods allow us to both automate some tasks and handle their inherent un- 30 certainty. ...
Article
Full-text available
Craniofacial superimposition (CFS) is a skeleton-based technique that aims to provide identity to a skull through its superimposition with one or more photographs of candidate missing people. While traditionally performed by forensic experts, computer-aided CFS methods can now provide substantial speedups and are quickly progressing towards a large degree of automation. A current major limitation concerns the position of the mandible, which is required to be manually set by the expert beforehand in order to reproduce the facial expression of the subject in each available photograph. This is time-consuming and prone to errors. In this work, we address this issue by extending the state-of-the-art genetic algorithm-based method with the ability to allocate the mandible in the right position according to an anatomical model. Based on a dataset of simulated ante-mortem images with different mandible apertures and facial poses, we prove experimentally that the proposed method is able to effectively tackle cases displaying a much larger range of mandible positions. In fact, thanks to the new genetic design, it is able to outperform the original method, even when the mandible aperture is very small.
Article
Full-text available
In 2017, a series of human remains corresponding to the executed leaders of the “January Uprising” of 1863–1864 were uncovered at the Upper Castle of Vilnius (Lithuania). During the archeological excavations, 14 inhumation pits with the human remains of 21 individuals were found at the site. The subsequent identification process was carried out, including the analysis and cross-comparison of post-mortem data obtained in situ and in the lab with ante-mortem data obtained from historical archives. In parallel, three anthropologists with diverse backgrounds in craniofacial identification and two students without previous experience attempted to identify 11 of these 21 individuals using the craniofacial superimposition technique. To do this, the five participants had access to 18 3D scanned skulls and 14 photographs of 11 different candidates. The participants faced a cross-comparison problem involving 252 skull-face overlay scenarios. The methodology follows the main agreements of the European project MEPROCS and uses the software Skeleton-ID™. Based on MEPROCS standard, a final decision was provided within a scale, assigning a value in terms of strong, moderate, or limited support to the claim that the skull and the facial image belonged (or not) to the same person for each case. The problem of binary classification, positive/negative, with an identification rate for each participant was revealed. The results obtained in this study make the authors think that both the quality of the materials used and the previous experience of the analyst play a fundamental role when reaching conclusions using the CFS technique.
Article
Due to the successful applications in abundant practical application problems involving fuzzy sets and systems, overlap functions on unit closed interval have attracted continuous attentions of many scholars since they were proposed. In particular, recently, the author extended the concept of overlap functions on unit closed interval to the so-called quasi-overlap functions on bounded partially ordered sets. In this paper, we pay attention to the extension constructions of quasi-overlap functions and their derivative concepts on function spaces with bounded partially ordered sets as underlying sets. Specifically, first, based on quasi-overlap functions and their derivative concepts on any bounded partially ordered set, we give the way to construct quasi-overlap functions and their derivative concepts on function space composed of all fuzzy sets with that bounded partially ordered set as the truth values set along with the function space composed of all order-preserving functions from arbitrary sup semilattice to that bounded partially ordered set, respectively. Second, we introduce the concepts of representable quasi-overlap functions and representable derivative concepts of quasi-overlap functions on function spaces and obtain their equivalent characterizations. Third, we discuss some vital properties of representable quasi-overlap functions and representable derivative concepts of quasi-overlap functions on function spaces. Fourth, it should be mentioned that the obtained results cover the cases of quasi-overlap functions and their derivative concepts on function spaces composed of all interval-valued fuzzy sets and type-2 fuzzy sets when the underlying bounded partially ordered set is taken as the corresponding truth values set, respectively.
Article
As a kind of emerging binary continuous aggregation operator that has been successfully applied in many practical application problems, overlap functions on the unit closed interval have been considered by scholars on different truth values sets lately. At the same time, studying aggregation operators on finite chains, especially for commonly used binary aggregation operators, is a meaningful and hot topic in the research field of aggregation operators. In this paper, we pay attention to overlap functions on finite chains, which are called discrete overlap functions. Specifically, first, we introduce the notions of discrete overlap functions on the finite chain L with n+2 elements and its arbitrary subchains along with an extended form of them. Second, we study some basic properties of discrete overlap functions on L, especially for the idempotent property, Archimedean property and cancellation law. In particular, we obtain some new properties which are different from those of the overlap functions on other truth values sets, for instance, every discrete overlap function on L takes the greatest element on L as the neutral element. Third, we discuss the construction methods of discrete overlap functions on L. Finally, it is worth mentioning that the results obtained in this paper provide a theoretical basis and more possibilities for the potential applications of overlap functions in other fields besides their known applications, especially for the situation of that the reasoning of experts are described by linguistic terms or labels, such as in expert systems, fuzzy control and etc..
Article
In recent years, overlap functions, as a class of bivariate aggregation operators that are widely used in various application problems (see, e.g., in decision-making, image processing, classifications etc.), have been generalized to many forms. In particular, Paiva et al. (R. Paiva, E. Palmeira, R. Santiago, B. Bedregal, Lattice-valued overlap and quasi-overlap functions, Information Sciences 562 (2021) 180–199.) have generalized the overlap functions to the so-called quasi-overlap functions lately. In the meantime, considering aggregation operators on finite chains, especially the commonly bivariate aggregation operators (see, e.g., t-norms, t-conorms, uninorms, t-operators etc.) has become an important research topic in the fields of aggregation operators. In this paper, we take into account this research topic for quasi-overlap functions. First of all, we give the concept of quasi-overlap functions on a finite chain L with n+2 elements and its arbitrary subchains together with three generalized forms of quasi-overlap functions on any subchain of L. And then, we show some examples of quasi-overlap functions on L along with some of its specific subchains and study the idempotent property, Archimedean property and cancellation law of quasi-overlap functions on L. Finally, we obtain two construction methods of quasi-overlap functions on L, one of them is the ordinal sum construction.
Article
Comparative radiography (CR) is the forensic anthropology technique in which ante-mortem (AM) and post-mounknown 2021 0.823 on a dataset composed of 234 skull radiographs. Second, an evolutionary-based 2D-3D IR method, that searches for the best alignment of segmented AM and PM images using a real-coded evolutionary algorithm. The proposed system is evaluated on a real multiple-comparison identification scenario including 10 X-ray images and 10 CTs, where manual and automatic segmentation approaches are compared. The global results shows that the proposed system is able to filter 50% of the sample. These preliminary results suggest that our system can reliably keep the true positive identity in the first half of the sample, allowing for a significant reduction of forensic experts’ workload and shortening identification times.
Article
INTRODUCTION: Comparative radiography is a forensic identification technique based on the comparison of skeletal structures in ante-mortem and post-mortem radiographic data to determine the identity of a deceased person. Several works have tackled its automation using different approaches but all of them require the manual segmentation of the skeletal structure’s silhouette. MATERIALS AND METHODS: The radiograph segmentation task has been automated using convolutional neural networks. We have developed a deep network able to accurately segment the skeletal structure of interest within a radiograph. It requires only 200 labelled radiographs to be trained, and has been applied to two problems: (1) the segmentation of clavicles in chest radiographs using the JSRT dataset; and (2) the segmentation of frontal sinuses in head radiographs provided by the Hospital de Castilla-La Mancha (Spain). RESULTS AND DISCUSSION: We achieve human-competitive performance in the segmentation of clavicles in chest radiographs (average Dice Similarity Coefficient 0.939) and high-quality segmentation results in the segmentation of frontal sinuses in head radiographs (0.823). The automatic segmentations of frontal sinuses obtain similar results to manual ones for the decision-making task. Specifically, both manual and automatic segmentation allows 50% of the sample to be filtered. In fact, the positive match is always located among the best first 5 matches provided by our system. CONCLUSIONS: This automatic segmentation framework comprises a first step towards a computer-aided decision support system in comparative radiography, where the resulting segmentation is employed in an image registration pipeline as part of the decision-making process.
Chapter
Skeleton-based forensic identification techniques involve the assessment of human osseous remains to identify the deceased person’s identity and cause of death. Craniofacial superimposition (CFS) is one of the most extended techniques of such kind. It involves the superimposition of an image of a skull with a number of ante-mortem face images of an individual and the analysis of their morphological correspondence. Designing automatic methods to address CFS and support the forensic anthropologist remains a challenge. Our research group has a long-term collaboration track with the University of Granada’s Physical Anthropology Lab and some other international forensic labs to automate the whole CFS identification process. The procedure is affected by different sources of uncertainty and thus fuzzy set theory becomes an appealing approach to automate this task. The current contribution reviews these developments specifically focusing on the fuzzy set-based solutions applied to deal with each of the uncertainty sources inherent to the process.
Article
Full-text available
This study presents a craniofacial superimposition consisting of filtering, feature extraction, classification for skull modeling. Initially, the Gaussian filter removes the noise and Otsu thresholding extracts the features. The extracted features is sent as a trained data to the Convolutional Neural Network (CNN). The experiment is carried out on 100 input image set that encompasses both the cranial and facial image. The experiment is conducted on new input image and it is then applied directly to the CNN classifier. The experimental results show that the CNN classifier achieves higher classification rate for 2D landmark and skull modelling than the existing methods.
Article
In 2013, Barrenechea et al. used the Choquet integral as an aggregation function in the fuzzy reasoning method (FRM) of fuzzy rule-based classification systems. After that, starting from 2016, new aggregation-like functions generalizing the Choquet integral have appeared in the literature, in particular in the works by Lucca et al. Those generalizations of the Choquet integral, namely CT-integrals (by t-norm T), CF-integrals (by a fusion function F satisfying some specific properties), CC-integrals (by a copula C), CF1F2-integrals (by a pair of fusion functions (F1, F2) under some specific constraints) and their generalization gCF1F2-integrals, achieved excellent results in classification problems. The works by Lucca et al. showed that the aggregation task in a FRM may be performed by either aggregation, pre-aggregation or just ordered directional monotonic functions satisfying some boundary conditions, that is, it is not necessary to have an aggregation function to obtain competitive results in classification. The aim of this paper is to present and discuss such generalizations of the Choquet integral, offering a general panorama of the state of the art, showing the relations and intersections among such five classes of generalizations. First, we present them from a theoretical point of view. Then, we also summarize some applications found in the literature.
Article
Craniofacial superimposition aims to identify a missing person by comparing its skull with photos of possible candidates. Among the difficult tasks involved, this requires superimposing the skull over each photo, matching the pose of the skull with that of the face, a problem known as skullface overlay (SFO). Several computerized methods for SFO have been proposed, in an effort to relieve forensic experts of this complex, time-consuming and subjective task. A system to generate artificial SFO data from computed tomography images has been also introduced, providing researchers with data to test and compare their techniques more reliably. This paper improves the state of the art on both fronts. We introduce a novel SFO algorithm that is substantially more accurate, more reliable and much faster than existing methods. An extensive experimental study and statistical analysis validates our findings. Moreover, we propose an improved method to simulate SFO data which, by replacing real photos with simulated ones, is able to generate a wider range of scenarios. This module provides complete control over the pose of the subject and the camera parameters, and even the ability to reproduce inter-expert errors in processing the input data, leading to a more controlled and thorough testing under realistic conditions. IEEE
Article
Full-text available
Craniofacial superimposition has the potential to be used as an identification method when other traditional biological techniques are not applicable due to insufficient quality or absence of ante-mortem and post-mortem data. Despite having been used in many countries as a method of inclusion and exclusion for over a century it lacks standards. Thus, the purpose of this research is to provide forensic practitioners with standard criteria for analysing skull-face relationships. Thirty-seven experts from 16 different institutions participated in this study, which consisted of evaluating 65 criteria for assessing skull-face anatomical consistency on a sample of 24 different skull-face superimpositions. An unbiased statistical analysis established the most objective and discriminative criteria. Results did not show strong associations , however, important insights to address lack of standards were provided. In addition, a novel methodology for understanding and standardizing identification methods based on the observation of morphological patterns has been proposed. Crown
Conference Paper
Full-text available
Craniofacial superimposition is a forensic identification method involving the overlay of a skull over the available ante-mortem photographs of a candidate missing person face and the subsequent analysis of their anatomical correspondence. Within this process, the decision making stage focuses on determining the degree of support of being the same person or not based on the analysis of some criteria assessing the skull-face morphological correspondence. That decision is usually obtained in a non automatic and subjective way. We aim to automate the decision making process using computer vision and soft computing methods to assist the forensic anthropologist. In this work, we present a first approach to model one of the criteria followed by forensic experts: the analysis of the consistency of bony and facial chin outlines. We show some preliminary results over 82 skull-face overlay instances and discuss future research directions.
Article
Full-text available
Craniofacial superimposition is one of the most relevant skeleton-based identification techniques. Within this process, the skull-face overlay stage focuses on achieving the best possible overlay of a skull found and an ante mortem image of a candidate person. In previous work, we proposed an automatic skull-face overlay method, based on evolutionary algorithms and fuzzy sets. The following stage, decision making, consists of determining the degree of support of being the same person or not. This decision is based on the analysis of some criteria assessing the skull-face morphological correspondence through the resulting skull-face overlay. In this work, we take a first step to design a decision support system for craniofacial superimposition. To do so, we consider the modeling of two of the most discriminative criteria for assessing craniofacial correspondence: the morphological and spatial relationship between the bony and facial chin, and the relative position of the orbits and the eyeballs. For each criterion, different computer vision-based approaches have been studied. The accuracy of each method has been calculated as its capability to discriminate in a cross-comparison identification scenario. Sugeno integral has been used to aggregate the results of the different methods taking into account the corresponding individual accuracy index. This allows us to provide a single global output specifying the matching of each criterion while combining the capabilities of different methods. Finally, the performance of the designed criteria and methods have been tested on 172 skull-face overlay problem instances of positive and negative cases to illustrate the discriminative power of each criterion. It has been shown that thanks to the use of Sugeno integral for aggregating different methods, a more robust measurement output is achieved.
Article
Full-text available
As part of the scientific tasks coordinated throughout The 'New Methodologies and Protocols of Forensic Identification by Craniofacial Superimposition (MEPROCS)' project, the current study aims to analyse the performance of a diverse set of CFS methodologies and the corresponding technical approaches when dealing with a common dataset of real-world cases. Thus, a multiple-lab study on craniofacial superimposition has been carried out for the first time. In particular, 26 participants from 17 different institutions in 13 countries were asked to deal with 14 identification scenarios, some of them involving the comparison of multiple candidates and unknown skulls. In total, 60 craniofacial superimposition problems divided in two set of females and males. Each participant follow her/his own methodology and employed her/his particular technological means. For each single case they were asked to report the final identification decision (either positive or negative) along with the rationale supporting the decision and at least one image illustrating the overlay/superimposition outcome. This study is expected to provide important insights to better understand the most convenient characteristics of every method included in this study. Copyright © 2015 Elsevier Ireland Ltd. All rights reserved.
Article
Full-text available
Craniofacial superimposition involves the process of overlaying a skull with a number of ante-mortem images of an individual and the analysis of their morphological correspondence. Within the craniofacial superimposition process, the skull-face overlay stage focuses on achieving the best possible overlay of the skull and a single ante-mortem image of a missing person. This technique has been commonly applied following a non automatic trial-and-error approach. Automatic skull-face overlay methods have been developed obtaining promising results. In this work, we present two new variants that are an extension of existing 3D-2D methods to automatically superimpose a skull 3D model on a facial photograph. We have modeled the imprecision related to the facial soft tissue depth between corresponding pairs of cranial and facial landmarks which typically guide the automatic approaches. As an illustration of the model’s performance, the soft tissue distances associated to studies for Mediterranean population have been considered for dealing with this landmark matching uncertainty. Hence, we directly incorporate the corresponding landmark spatial relationships within the automatic skull-face overlay procedure. We have tested the performance of our proposal on 18 skull-face overlay instances from a ground truth dataset obtaining valuable results. The current proposal is thus the first automatic skull-face overlay method evaluated in a reliable and unbiased way.
Article
Full-text available
In this manuscript, the past, present and future of the identification of human remains based on craniofacial superimposition is reviewed. An analysis of the different technological approaches developed over time is offered in conjunction with a new classification based on the technology implemented throughout the diverse phases of the process. The state of the art of the technique, in the academic and forensic realms, is reflected in an extensive international survey that includes over one hundred experts worldwide. The results of the survey indicate the current relative importance of the technique, despite of its controversial nature within the scientific community. Finally, the future challenges to be faced to justify the use of this technique for either profiling, exclusion or identification purposes are discussed. Copyright © 2015. Published by Elsevier Ireland Ltd.
Article
Full-text available
Craniofacial superimposition can provide evidence to support that some human skeletal remains belong or not to a missing person. It involves the process of overlaying a skull with a number of ante mortem images of an individual and the analysis of their morphological correspondence. Within the craniofacial superimposition process, the skull-face overlay stage just focuses on achieving the best possible overlay of the skull and a single ante mortem image of the suspect. Although craniofacial superimposition has been in use for over a century, skull-face overlay is still applied by means of a trial-and-error approach without an automatic method. Practitioners finish the process once they consider that a good enough overlay has been attained. Hence, skull-face overlay is a very challenging, subjective, error prone, and time consuming part of the whole process. Though the numerical assessment of the method quality has not been achieved yet, computer vision and soft computing arise as powerful tools to automate it, dramatically reducing the time taken by the expert and obtaining an unbiased overlay result. In this manuscript, we justify and analyze the use of these techniques to properly model the skull-face overlay problem. We also present the automatic technical procedure we have developed using these computational methods and show the four overlays obtained in two craniofacial superimposition cases. This automatic procedure can be thus considered as a tool to aid forensic anthropologists to develop the skull-face overlay, automating and avoiding subjectivity of the most tedious task within craniofacial superimposition.
Article
Full-text available
Objective, and unbiased validation studies over a significant number of cases are required to get a more solid picture on Craniofacial Superimposition reliability. It will not be possible to compare the performance of existing and upcoming methods for Craniofacial Superimposition without a common forensic database available for research community. Skull-face overlay is a key task within Craniofacial Superimposition that has a direct influence on the subsequent task devoted to evaluate the skull-face relationships. In this work, we present the procedure to create for the first time such a data set. We have also created a database with 19 skull-face overlay cases for which we are trying to overcome legal issues that allow us to make it public. The quantitative analysis made in the segmentation and registration stages, together with the visual assessment of the 19 face-to-face overlays, allow us to conclude that the results can be considered as a gold standard. With such a ground truth dataset a new horizon is opened for the development of new automatic methods whose performance could be now objectively measured and compared against previous and future proposals. Additionally, other uses are expected to be explored to better understand the visual evaluation process of craniofacial relationships in craniofacial identification. It could be very useful also as a starting point for further studies on the prediction of the resulting facial morphology after corrective or reconstructive interventionism in maxillo-facial surgery.
Article
Full-text available
The morphological assessment of facial features using photographs has played an important role in forensic anthropology. The analysis of anthropometric landmarks for determining facial dimensions and angles has been considered in diverse forensic areas. Hence, the quantification of the error associated to the location of facial landmarks seems to be necessary when photographs become a key element of the forensic procedure. In this work, we statistically evaluate the inter- and intra-observer dispersions related to the facial landmark identification on photographs. In the inter-observer experiment, a set of 18 facial landmarks was provided to 39 operators. They were requested to mark only those that they could precisely place on 10 photographs with different poses (frontal, oblique, and lateral views). The frequency of landmark location was studied together with their dispersion. Regarding the intra-observer evaluation, three participants identified 13 facial points on five photographs classified in the frontal and oblique views. Each landmark location was repeated five times at intervals of at least 24 h. The frequency results reveal that glabella, nasion, subnasale, labiale superius, and pogonion obtained the highest location frequency in the three image categories. On the contrary, the lowest rate corresponds to labiale inferius and menton. Meanwhile, zygia, gonia, and gnathion were significantly more difficult to locate than other facial landmarks. They produced a significant effect on the dispersion depending on the pose of the image where they were placed, regardless of the type of observer that positioned them. In particular, zygia and gonia presented a statistically greater variation in the three image poses, while the location of gnathion is less precise in oblique view photographs. Hence, our findings suggest that the latter landmarks tend to be highly variable when determining their exact position.
Article
Full-text available
Craniofacial superimposition is a forensic process where photographs or video shots of a missing person are compared with the skull that is found. By projecting both photographs on top of each other (or, even better, matching a scanned three-dimensional skull model against the face photo/video shot), the forensic anthropologist can try to establish whether that is the same person. The whole process is influenced by inherent uncertainty mainly because two objects of different nature (a skull and a face) are involved. In previous work, we categorized the different sources of uncertainty and introduced the use of imprecise landmarks to tackle most of them. In this paper, we propose a novel approach, a cooperative coevolutionary algorithm, to deal with the use of imprecise cephalometric landmarks in the skull–face overlay process, the main task in craniofacial superimposition. Following this approach we are able to look for both the best projection parameters and the best landmark locations at the same time. Coevolutionary skull–face overlay results are compared with our previous fuzzy-evolutionary automatic method. Six skull–face overlay problem instances corresponding to three real-world cases solved by the Physical Anthropology Lab at the University of Granada (Spain) are considered. Promising results have been achieved, dramatically reducing the run time while improving the accuracy and robustness.
Article
Full-text available
Craniofacial superimposition is a forensic process in which a photograph of a missing person is compared with a skull found to determine its identity. After one century of development, craniofacial superimposition has become an interdisciplinary research field where computer sciences have acquired a key role as a complement of forensic sciences. Moreover, the availability of new digital equipment (such as computers and 3D scanners) has resulted in a significant advance in the applicability of this forensic identification technique. The purpose of this contribution is twofold. On the one hand, we aim to clearly define the different stages involved in the computer-aided craniofacial superimposition process. Besides, we aim to clarify the role played by computers in the methods considered. In order to accomplish these objectives, an up-to-date review of the recent works is presented along with a discussion of advantages and drawbacks of the existing approaches, with an emphasis on the automatic ones. Future case studies will be easily categorized by identifying which stage is tackled and which kind of computer-aided approach is chosen to face the identification problem. Remaining challenges are indicated and some directions for future research are given.
Article
Full-text available
Craniofacial superimposition (CS) is a forensic process where photographs or video shots of a missing person are compared with the skull that is found. By projecting both photographs on top of each other (or, even better, matching a scanned 3-D skull model against the face photo/video shot), the forensic anthropologist can try to establish whether it is the same person. The whole process is influenced by inherent uncertainty, mainly because two objects of different nature (a skull and a face) are involved. In this paper, we extend our previous evolutionary-algorithm-based method to automatically superimpose the 3-D skull model and the 2-D face photo with the aim to overcome the limitations that are associated with the different sources of uncertainty, which are present in the problem. Two different approaches to handle the imprecision will be proposed: weighted and fuzzy-set-theory-based landmarks. The performance of the new proposal is analyzed, considering five skull-face overlay problem instances that correspond to three real-world cases solved by the Physical Anthropology Laboratory, University of Granada, Granada, Spain. The experimental study that is developed shows how the fuzzy-set-based approach clearly outperforms the previous crisp solution. Finally, the proposed method is validated by the comparison of its outcomes with respect to those manually achieved by the forensic experts in nine skull-face overlay problem instances.
Article
Full-text available
Photographic supra-projection is a forensic process that aims to identify a missing person from a photograph and a skull found. One of the crucial tasks throughout all this process is the craniofacial superimposition which tries to find a good fit between a 3D model of the skull and the 2D photo of the face. This photographic supra-projection stage is usually carried out manually by forensic anthropologists. It is thus very time consuming and presents several difficulties. In this paper, we aim to demonstrate that real-coded evolutionary algorithms are suitable approaches to tackle craniofacial superimposition. To do so, we first formulate this complex task in forensic identification as a numerical optimization problem. Then, we adapt three different evolutionary algorithms to solve it: two variants of a real-coded genetic algorithm and the state of the art evolution strategy CMA-ES. We also consider an existing binary-coded genetic algorithm as a baseline. Results on several superimposition problems of real-world identification cases solved by the Physical Anthropology lab at the University of Granada (Spain) are considered to test our proposals.
Article
Full-text available
Age-at-death estimation of an individual skeleton is important to forensic and biological anthropologists for identification and demographic analysis, but it has been shown that the current aging methods are often unreliable because of skeletal variation and taphonomic factors. Multifactorial methods have been shown to produce better results when determining age-at-death than single indicator methods. However, multifactorial methods are difficult to apply to single or poorly preserved skeletons, and they rarely provide the investigator with information about the reliability of the estimate. The goal of this research is to examine the validity of the Sugeno fuzzy integral as a multifactorial method for modeling age-at-death of an individual skeleton. This approach is novel because it produces an informed decision of age-at-death utilizing multiple age indicators while also taking into consideration the accuracies of the methods and the condition of the bone being examined. Additionally, the Sugeno fuzzy integral does not require the use of a population and it qualitatively produces easily interpreted graphical results. Examples are presented applying three commonly used aging methods on a known-age skeletal sample from the Terry Anatomical Collection. This method produces results that are more accurate and with smaller intervals than single indicator methods.
Article
Craniofacial superimposition (CFS) involves the process of overlaying a skull with a number of ante-mortem images of an individual and the analysis of their morphological correspondence. The lack of unified working protocols and the absence of commonly accepted standards, led to contradictory consensus regarding its reliability. One of the more important aims of ‘New Methodologies and Protocols of Forensic Identification by Craniofacial Superimposition (MEPROCS)’ project was to propose a common framework for CFS, what can be considered the first international standard in the field. The framework aimed to serve as a roadmap for avoiding particular assumptions that could bias the process. At the same time, it provides some empirical support to certain practices, technological means, and morphological criteria expected to facilitate the application of the CFS task and to improve its reliability. In order to confirm the utility and potential benefits of the framework use, there is a need to empirically evaluate it in CFS identification scenarios as close as possible to the reality. Thus, the purpose of this study is to validate the CFS framework developed. For that aim 12 participants were asked to report about a variable number of CFS following all the recommendations of the framework. The results are analysed and discussed according to the framework understanding and fulfilment, the participants’ performance, and the correlation between expected decisions and those given by the participants. In view of the quantitative results and qualitative examination criteria we can conclude that those who follow the MEPROCS recommendations improve their performance.
Article
The promotion of CCTV surveillance and identity cards, along with ever heightened security at airports, immigration control and institutional access, has seen a dramatic increase in the use of automated and manual recognition. In addition, several recent disasters have highlighted the problems and challenges associated with current disaster victim identification. Discussing the latest advances and key research into identification from the face and skull, this book draws together a wide range of elements relating to craniofacial analysis and identification. It examines all aspects of facial identification, including the determination of facial appearance from the skull, comparison of the skull with the face and the verification of living facial images. With sections covering the identification of the dead and of the living, it provides a valuable review of the current state of play along with the latest research advances in this constantly evolving field.
Conference Paper
Craniofacial superimposition is a forensic process that aims to identify a missing person from a photograph and an unknown dead's skull. One of the crucial steps is skull-face overlay in consistent with photographic space according to the face photo. Thus parameter estimation of perspective projection becomes key problem. In this paper, we employ a method of camera calibration based on vanishing point(VPBC) to estimate relevant parameters including perspective angle, orientation of camera and photographic object distance. Firstly, according to two vanishing points in image calculate the perspective angle and focal length using photo-geography theory, then evaluate camera direction and photographic object distance based on equal focal length, finally, map the 3D skull according to above known parameters, and implement skull-face overlay process. Result shows that this approach is effective, efficient and accurate for follow-up research work.
Article
This paper describes a computerized clavicle identification system primarily designed to resolve the identities of unaccounted-for U.S. soldiers who fought in the Korean War. Elliptical Fourier analysis is used to quantify the clavicle outline shape from skeletons and postero-anterior antemortem chest radiographs to rank individuals in terms of metric distance. Similar to leading fingerprint identification systems, shortlists of the top matching candidates are extracted for subsequent human visual assessment. Two independent tests of the computerized system using 17 field-recovered skeletons and 409 chest radiographs demonstrate that true-positive matches are captured within the top 5% of the sample 75% of the time. These results are outstanding given the eroded state of some field-recovered skeletons and the faintness of the 1950's photofluorographs. These methods enhance the capability to resolve several hundred cold cases for which little circumstantial information exists and current DNA and dental record technologies cannot be applied.
Article
Methods for constructing simultaneous confidence intervals for all possible linear contrasts among several means of normally distributed variables have been given by Scheffé and Tukey. In this paper the possibility is considered of picking in advance a number (say m) of linear contrasts among k means, and then estimating these m linear contrasts by confidence intervals based on a Student t statistic, in such a way that the overall confidence level for the m intervals is greater than or equal to a preassigned value. It is found that for some values of k, and for m not too large, intervals obtained in this way are shorter than those using the F distribution or the Studentized range. When this is so, the experimenter may be willing to select the linear combinations in advance which he wishes to estimate in order to have m shorter intervals instead of an infinite number of longer intervals.
Article
The properties of several measures of similarity of fuzzy values are presented and compared. The measures examined include the measure based on the union and intersection, the one based on the maximum difference and the one based on the differences as well as the sum of corresponding grades of membership. It is shown that several properties are common to all measures. However, some properties do not hold for all of them.
Conference Paper
Computer aided craniofacial reconstruction plays an important role in criminal investigation. By comparing the 3D facial model produced by this technology with the picture database of missing persons, the identity of an unknown skull can be determined. In this paper, we propose a method to quantitatively analyze the quality of the facial landmarks for skull identification. Based on the quality analysis of landmarks, a new landmark-based algorithm, which takes fully into account the different weights of the landmarks in the recognition, is proposed. Moreover, we can select an optimal recognition subset of landmarks to boost the recognition rate according to the recognition quality of landmarks. Experiments validate the proposed method. KeywordsSkull identification–landmark quality–3D-2D face recognition–optimal recognition subset–Q-weighted algorithm
Conference Paper
A Sugeno and a Choquet integrals are com- monly used fuzzy integrals for aggregation. As a generalization of both integrals, the twofold integral is induced. The twofold in- tegral enables us to interpret two measures from a different semantics viewpoint. One corresponds to the Choquet integral and the other corresponds to the Sugeno integral. Our work is about building models for the twofold integrals from examples. In this work, we formulate the problem of learning measures from examples, and pro- pose a method for obtaining the two fuzzy measures used in twofold integrals. This method is based on an alternate optimiza- tion.
Article
This paper discusses a range of regression techniques specifically tailored to building aggregation operators from empirical data. These techniques identify optimal parameters of aggregation operators from various classes (triangular norms, uninorms, copulas, OWA, generalised means, compensatory and general aggregation operators), while allowing one to preserve specific properties, such as commutativity or associativity.
Article
One of the aims of forensic science is to determine the identities of victims of crime. In some cases the investigators may have ideas as to the identities of the victims and in these situations, ante mortem photographs of the victims could be used in order to try and establish identity through skull-photo superimposition. The aim of this study was to evaluate the accuracy of a newly developed digital photographic superimposition technique on a South African sample of cadaver photographs and skulls. Forty facial photographs were selected and for each photo, 10 skulls (including the skull corresponding to the photo) were used for superimposition. The investigator did not know which of the 10 skulls corresponded to the photograph in question. The skulls were scanned 3-dimensionally, using a Cyberware™ Model 3030 Colour-3D Scanhead scanner. The photos were also scanned. Superimposition was done in 3D Studio Max and involved a morphological superimposition, whereby a skull is superimposed over the photo and assessed for a morphological match. Superimposition using selected anatomical landmarks was also performed to assess the match. A total of 400 skull-photo superimpositions were carried out using the morphological assessment and another 400 using the anatomical landmarks. In 85% of cases the correct skull was included in the possible matches for a particular photo using morphological assessment. However, in all of these cases, between zero and three other skulls out of 10 possibilities could also match a specific photo. In the landmark based assessment, the correct skull was included in 80% of cases. Once again, however, between one and seven other skulls out of 10 possibilities also matched the photo. This indicates that skull-photo superimposition has limited use in the identification of human skeletal remains, but may be useful as an initial screening tool. Corroborative techniques should also be used in the identification process.
Article
With the ever increasing production of average soft tissue depth studies, data are becoming increasingly complex, less standardized, and more unwieldy. So far, no overarching review has been attempted to determine: the validity of continued data collection; the usefulness of the existing data subcategorizations; or if a synthesis is possible to produce a manageable soft tissue depth library. While a principal components analysis would provide the best foundation for such an assessment, this type of investigation is not currently possible because of a lack of easily accessible raw data (first, many studies are narrow; second, raw data are infrequently published and/or stored and are not always shared by some authors). This paper provides an alternate means of investigation using an hierarchical approach to review and compare the effects of single variables on published mean values for adults whilst acknowledging measurement errors and within-group variation. The results revealed: (i) no clear secular trends at frequently investigated landmarks; (ii) wide variation in soft tissue depth measures between different measurement techniques irrespective of whether living persons or cadavers were considered; (iii) no clear clustering of non-Caucasoid data far from the Caucasoid means; and (iv) minor differences between males and females. Consequently, the data were pooled across studies using weighted means and standard deviations to cancel out random and opposing study-specific errors, and to produce a single soft tissue depth table with increased sample sizes (e.g., 6786 individuals at pogonion).
Article
The authors present a methodology for human identification based on digital superimposition techniques. This methodology computes a fast, near optimal fit between a three-dimensional skull surface mesh and a two-dimensional digitized facial photograph. Since this is done digitally, (1) the photograph can be enhanced to reduce or eliminate motion blur, overexposure or underexposure, and out-of-focus distortions; (2) previous problems with skull/photograph scaling and alignment are minimized or eliminated; and (3) the photograph and skull can be numerically correlated. Two of several test cases produced from an implementation of this methodology are also presented.
Article
By means of X-ray photography tests were made of 224 (100 males and 124 females) volunteer Chinese adults of Han nationality to study the related regular patterns of superimposed projection of face landmarks onto the skull. On the basis of these tests, the present article reveals from a forensic anthropology angle the related regular patterns of plane projection of the human face with its skull. Study shows that there exist a strict individual identity and exclusiveness in relation between the human face and skull. The related regularity of displacement of face landmarks appears in projection of the skull with the human head at different photographic positions and angles. On the basis of this discovery, 52 indexes in 4 groups were established as a standard for judging the identification of a skull's body origin by means of skull-image superimposition. Based on forensic anthropology, the technique has raised to a great extent the credibility of unknown skull identification. In the past 8 years, 89 unknown skulls have been identified with their body origins which provided important and accurate evidence for the solution of murders with dismembered bodies, skeletonized bodies, and unidentified dead bodies.
Article
Using 52 skulls in forensic cases, the anatomical consistency of cranio-facial superimposition images was investigated for evaluating the validity in personal identification by the superimposition method. In 35 out of 52 cases the unknown skull was positively identified as the missing person by matching of the outline and anatomical relation in skull and face images taken from frontal, oblique and lateral directions. The unknown skull in two cases was exclusive of the presumed person since the outline of the skull was not anatomically consistent with that of the face. In the remaining 15 cases, the skull in question was examined using only a frontal face photograph of the missing person and matched with it because of the lack of other photographs taken from different angles, giving a probable identification. From our practical examination, it is stated that the outline from the trichion to the gnathion in the lateral or oblique view is the preferable portion for personal identification, and the cranio-facial super-imposition method is reliable for individualization when two or more facial photographs taken from different angles are used in the examination.
Article
The accuracy of video superimposition methods for identifying unknown human skulls was examined. Three identified human skulls were each compared to 97 lateral view and 98 frontal view "mug shot" photographs using two television cameras, an electronic signal mixer, and a video monitor. The skulls were not from individuals represented by the photographs. All comparisons were done without using anterior dentition. The results found that 9.6% of the lateral view and 8.5% of the frontal view superimpositions were classified as a consistent fit based on the criteria that were identified. The incidence of false matches was reduced to 0.6% of the sample when a frontal view and lateral view photograph of the same individual were both compared to one skull. It was concluded that without anterior dentition, skull/photograph superimposition is reliable when two or more photographs, clearly depicting the facial features from different angles, are used in the comparison.
Article
This system consists of two main units, namely a video superimposition system and a computer-assisted skull identification system. The video superimposition system is comprised of the following five parts: a skull-positioning box having a monochrome CCD camera, a photo-stand having a color CCD camera, a video image mixing device, a TV monitor and a videotape recorder. The computer-assisted skull identification system is composed of a host computer including our original application software, a film recorder and a color printer. After the determination of the orientation and size of the skull to those of the facial photograph using the video superimposition system, the skull and facial photograph images are digitized and stored within the computer, and then both digitized images are superimposed on the monitor. For the assessment of anatomical consistency between the digitized skull and face, the distance between the landmarks and the thickness of soft tissue of the anthropometrical points are semi-automatically measured on the monitor. The wipe images facilitates the comparison of positional relationships between the digitized skull and face. The software includes the polynomial functions and Fourier harmonic analysis for evaluating the match of the outline such as the forehead and mandibular line in both the digitized images.
Article
Skull-photograph superimposition continues to be the most prevalent method employed for identifying a skull recovered in a criminal case as that belonging to a putative victim whose face photograph is available. The reliability of identification achieved has been shown to be 91%, indicating the possibility of a skull mismatching with a face photograph belonging to a person other than the actual deceased. This lack of reliability dampens the confidence of the expert and in turn confounds the mind of the judge. It has been shown that the variations in the shape of the facial organs are influenced by the corresponding variations in the skeletal elements of the facial skull. "Cranio-facial morphanalysis", a new anthroposcopic method proposed here for evaluating the shape correlations between a skull and a face photograph, when applied conjointly with skull-photograph superimposition is shown to increase the reliability in forensic skull identification.
Article
It has been attempted to develop an economised craniofacial identification system, as a special automated version of photo/video superimposition technique, that can deal with common cases of personal identification with the aid of a skull and a nearly front view face photograph of the suspected victim. The proposed method is economic in respect of (i) cost of hardware configuration, (ii) processing time as well as (iii) manual labour involved. Over and above, it has got a capability to take care of ambiguities due to soft tissue thickness during the selection of facial features, which is a part of the procedure. In order to reconstruct a 2-D cranial image, superimposable over the facial one, the new method does not need any reconstruction of a digitised 3-D cranial image. It works simply by a suitable segment-wise processing of a 2-D cranial image with the aid of the symmetry perceiving adaptive neuronet (SPAN), that has recently been introduced in connection with nearly front view facial image recognition. The final comparison of the facial and the superimposable cranial images is as versatile as the same for facial image recognition by SPAN.A practical application of this extended version of SPAN has been demonstrated in the present paper.
Article
The present study introduces a new approach to computer-assisted face/skull matching used for personal identification purposes in forensic anthropology. In this experiment, the authors formulated an algorithm able to identify the face of a person suspected to have disappeared, by comparing the respective person's facial image with the skull radiograph. A total of 14 subjects were selected for the study, from which a facial photograph and skull radiograph were taken and ultimately compiled into a database, saved to the hard drive of a computer. The photographs of the faces and corresponding skull radiographs were then drafted using common photographic software, taking caution not to alter the informational content of the images. Once computer generated, the facial images and menu were displayed on a color monitor. In the first phase, a few anatomic points of each photograph were selected and marked with a cross to facilitate and more accurately match the face with its corresponding skull. In the second phase, the above mentioned cross grid was superimposed on the radiographic image of the skull and brought to scale. In the third phase, the crosses were transferred to the cranial points of the radiograph. In the fourth phase, the algorithm calculated the distance of each transferred cross and the corresponding average. The smaller the mean value, the greater the index of similarity between the face and skull.A total of 196 cross-comparisons were conducted, with positive identification resulting in each case. Hence, the algorithm matched a facial photograph to the correct skull in 100% of the cases.
Article
We report on the application of video skull-photo superimposition as an identification method in a case from Ajo, Arizona in which five individuals died after crossing into southern Arizona from Mexico. Initial analyses at the Pima County Forensic Science Center in Tucson, Arizona determined that the disarticulated skeletal remains represented two adult Hispanic males and three adult Hispanic females. Based on biological profiles, both the males and one of the females were tentatively identified and assigned names. The other two females were too similar in age and height, making skeletal separation and identification difficult. As a result, the Michigan State University Forensic Anthropology Laboratory assisted in the identification efforts by performing video skull-photo superimposition on the two unknown females. The skulls were compared to a photograph reported to be one of the missing females. By evaluating facial proportionality and by comparing a number of morphological features of the face and skulls, one skull was excluded as a possible match and one skull was not excluded as a match to the antemortem photo. Because this case was presumed to be a closed disaster, the exclusion of one skull and the failure to exclude the other represented circumstantial identifications.
A method of evidence fusion, based on the fuzzy integral, is developed. This technique nonlinearly combines objective evidence, in the form of a fuzzy membership function, with subjective evaluation of the worth of the sources with respect to the decision. Various new theoretical properties of this technique are developed, and its applicability to information fusion in computer vision is demonstrated through simulation and with object recognition data from forward-looking infrared imagery
The bertillon system of identification, McClaughry
  • A Bertillon
A. Bertillon, The bertillon system of identification, McClaughry, Ed., Chicago, IL.
Shape analytical morphometry in computer-aided skull identification via video superimposition, Iscan MY, Helmer RP. Forensic analysis of the skull: craniofacial analysis, reconstruction, and identification
  • D V Pesce
  • E Vacca
  • F Potente
  • T Lettini
  • M Colonna
D. V. Pesce, E. Vacca, F. Potente, T. Lettini, M. Colonna, Shape analytical morphometry in computer-aided skull identification via video superimposition, Iscan MY, Helmer RP. Forensic analysis of the skull: craniofacial analysis, reconstruction, and identification. New York: Wiley-Liss, 1993.
The Bertillon System of Identification
  • Bertillon
Shape analytical morphometry in computer-aided skull identification via video superimposition
  • Pesce