Conference Paper

A Tongue-Print Image Database for Recognition

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

Abstract

The tongue is a unique organ in that it can be stuck out of mouth for inspection, in this act offering a proof of life, and yet it is otherwise well protected in the mouth and is difficult to forge. The tongue also presents both geometric shape information and physiological texture information which are potentially useful in identity verification applications. Furthermore, the act of physically reaching or thrusting out is a convincing proof for the liveness. Despite these obvious advantages, little work has hitherto been done on tongue features. A primary factor for preventing such research is the lack of an available 3D tongue image database. In this paper, we present a newly developed 3D tongue image database, which includes both tongue geometric shape and surface textures of 134 subjects. This is the first attempt at making a 3D tongue image database available for the research community, with the ultimate goal of fostering the research on tongue biometrics. The new database can be a valuable resource for algorithm assessment, comparison and evaluation.

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.

... Biometrics refers to a real-time identification system that is used in the identification of a person using a specific physical or behavioral characteristic which is compared with a library of characteristics of many other people. [1] This is done using a biometric scanning device (tongue-print scan) which captures the user's biometric data such as the tongue-print scan and converts it into a digital information that the computer interprets and verifies. There is a higher level of assurance in this type of identification process. ...
... [6] Therefore, the use of tongue prints as a biometric authentication system is gaining a lot of momentum. In the past 10 years, research has been targeted towards developing a tongue print recognition system, and the first of its kind was proposed by Liu et al. in 2007. [1] Recently, tongue recognition systems based on 2D dual-tree complex wavelet transform have been proposed by Bade et al. [7] Tongue scanners are under research and being tested. ...
... In the past 10 years, research has been targeted towards developing a tongue print recognition system, and the first of its kind was proposed by Liu et al. in 2007. [1] Recently, tongue recognition systems based on 2D dual-tree complex wavelet transform have been proposed by Bade et al. [7] Tongue scanners are under research and being tested. [8] In India, this system of identification is still in the grassroot level and needs more quantum of research and planning to implement the same. ...
Article
Full-text available
Background and Objectives: Biometric authentication is an important process for the identification and verification of individuals for security purposes. There are many biometric systems that are currently in use and also being researched. Tongue print is a new biometric authentication tool that is unique and cannot be easily forged because no two tongue prints are similar. The present study aims to evaluate the common morphological features of the tongue and its variations in males and females. The usefulness of alginate impression and dental cast in obtaining the lingual impression was also evaluated. Materials and Methods: The study sample included twenty participants. The participants were subjected to visual examination following which digital photographs of the dorsal surface of the tongue were taken. Alginate impressions of the tongue were made, and casts were prepared using dental stone. The photographs and the casts were analyzed by two observers separately for the surface morphology including shape, presence or absence of fissures and its pattern of distribution. Three reference points were considered to determine the shape of the tongue. Results: The most common morphological feature on the dorsum of the tongue was the presence of central fissures. Multiple vertical fissures were observed in males whereas single vertical fissure was a common finding in females. The fissures were predominantly shallow in males and deep in females. The tongue was predominantly U shaped in males and females. V-shaped tongue was observed in 25% of females. Conclusion: Tongue prints are useful in biometric authentication. The methodology used in the study is simple, easy and can be adopted by dentists on a regular basis. However, large-scale studies are required to validate the results and also identify other features of the tongue that can be used in forensics and biometric authentication process.
... [3,4] Human identification is one of the most challenging tasks faced by physicians in forensic sciences, and identification of people depends on remarkable physiological parameters such as a fingerprint, retinal scan, radiographs, bite marks, etc. [5] Research on the tongue print framework was first proposed by Liu et al. in 2007. [6] The geometric state of the tongue is generally steady, and the surface fluctuates because of obsessive changes in the body. [6,7] With this foundation, an impression-based analysis was intended to analyze on varieties in morphological qualities of the tongue as saw on the tongue cast and to survey the data recorded on a replica on the tongue for human identification. ...
... [6] The geometric state of the tongue is generally steady, and the surface fluctuates because of obsessive changes in the body. [6,7] With this foundation, an impression-based analysis was intended to analyze on varieties in morphological qualities of the tongue as saw on the tongue cast and to survey the data recorded on a replica on the tongue for human identification. ...
Article
Context: The human tongue, a unique organ with complex architecture, exhibits significant morphological variations in the human body consistent with its complex role. Its morphological characteristic features and varieties can go about as proof of life and can be used for personal identification. The morphology and surface highlights of the tongue are qualities of each person, and these characteristics can be utilized as legal distinguishing proof of each person. Aims: This study is aimed to analyze varieties in morphological qualities of the tongue and to find out gender differences. Settings and Design: This study was conducted on 206 (Group I consist of 105 females and Group II consist of 101 male) participants with an age range of 21–30 years for 4 months who had visited the Department of Oral Medicine and Radiology. Subjects and Methods: The tongue was exposed to visual assessment following which alginate impression of the dorsal surface of the tongue was taken to make tongue cast and to assess distinct morphological features of the tongue and its variations in males and females. Statistical Analysis Used: The discrete (categorical) data were summarized in number (n) and percentage (%) and compared using the Chi-square (χ2) test. Results: A total of 206 participants in both groups, the U-shaped tongue, was the most common findings in males, as well as in females followed by a V-shaped tongue with a sharp tip that was observed more in females compared to males. Scalloped borders and multiple fissures were more common in males as compared to females. Conclusions: Variations of tongue shape and surface properties can be used as personal human identification in forensic odontology, and tongue prints can also be used as a standard method for the collection of data. The collected data of tongue prints may be used as a professional recognition database to ease human identification and to avoid future scams.
... Tongue biometrics was first proposed by Zhi Liu and Jing-Qi Yan et al in 2007. For 134 subjects 3D tongue image database was created and it was observed that contour of tongue is constant over a period of time and can be used for verification (human authentication) 5) . In tongue biometrics, numerous techniques like 2D Dual Tree Complex Wavelet Transform 10) , WLD (Weber Law Descriptors) 11) and combination of techniques like Histogram with SIFT (Scale invariant feature transform) 12) , Local binary pattern with Linear Support Vector Machine technique, 13) were studied to increase the precision of authentication. ...
Article
Full-text available
... Many researchers have performed experiments on identification system using tongue traits. For instance, the authors in [11] presented a newly developed 3D tongue image database, they provide both tongue shape and tongue textures. That was the first attempt at making a 3D tongue image database available for the research, with the ultimate goal of fostering the research on tongue biometrics. ...
Article
Full-text available
There are many biometric authentication systems that have used different human traits either physiological or behavioural which are liable to forgery. Thus, the human tongue promises to deliver a level of uniqueness that other biometrics cannot match because it is immune to forgery. However, literature has revealed that a single feature extraction technique was not sufficient for effective and efficient treatment of biometrics because of lapses imposed by individual technique. This paperpresents the development of a tongue recognition system using Gabor filter and particle swarm optimization. One hundred and twenty tongue images of human tongues of different individuals, six tongue images with different expressions were captured each per person with a digital camera. The tongue images were pre-processed through extraction of region of interest and normalization usingbinary mask and histogram equalization; Gabor filter was used for feature extraction and particle swarm optimization (PSO) was used to select salient features.Some samples tongue images were matched with the stored extracted tongue images using Euclidean distance classifier. The results show that at threshold value of 0.50, G-PSO has a sensitivity, specificity and accuracy rate of 100.00%, 94.44% and 98.08% respectively compared to Gabor which has 94.12%, 88.89% and 92.31% respectively and PSO which has 97.06%, 88.89% and 94.23% respectively.
... Tongue is a vital organ which performs multiple actions such as articulation of speech, perception of taste, and formation of food bolus. 1 The tongue is the only internal organ which can be easily drawn out and displayed for inspection and palpation purposes. 2 By means of its shape and texture, its aspect and color analyzed in a particular moment, this organ is helpful due to its exposed portion comprising information with visible differences from one individual to another, and may be easily called and used as a "lingual impression". 3 The individual lingual shape is consistent and the physiological texture is invariable. ...
Article
Full-text available
INTRODUCTION: Tongue is a vital internal organ enclosed within the oral cavity and is well protected from the external environment. The color, shape, and surface features are characteristic of every individual, and this serves as a tool for identification. The search for a new personal identification method secure has led to the use of the tongue print as a method of biometric verification.AIM AND OBJECTIVE: To analyze the shape, margins, texture of tongue prints and compare these between males and females. Also, formulate a working classification system for these tongue prints.MATERIAL AND METHODS: Subjects were asked to protrude tongue in relaxed position. After this tongue images were captured using Nikon digital camera to evaluate the shape, texture, margins, and papillations of tongue patterns.RESULT: The most common pattern seen in males and females was Patternless, with majority of subjects showing scalloped lateral margins, prominent papillations with short and broad tongue. Mostly female patients had pointed tip of tongue. Also, we in this paper have formulated a working classification system for easily categorizing the tongue print patterns in individuals.CONCLUSION: The human tongue is unique and delivers relevant information about shape, size, color, texture, margins and is suitable for forensic case identification.
... Every individual has unique tongue in terms of shape and surface textures. It is the only internal organ that can be stuck out of mouth for inspection, and yet it is otherwise well protected in the mouth and is difficult to forge [2]. It presents both geometric shape information and physiological texture information which are potentially useful in identity verification applications [3]. ...
Article
Full-text available
Forensic odontology is a branch of dentistry that mainly deals with the identification based on individual’s oral structures. The tongue is a unique structure that presents both geometric shape as well as physiological texture information that may be potentially useful in identity verification. The present research was taken over the people to study and analyse the morphological shape and texture of the tongue and demonstrate their importance as an aid in human identification. For the study, clinical examination, photographs and impressions were taken of the tongue. The undertaken study showed a qualitative result among different sex and age groups. It can be opined that the human tongue promises to deliver a level of uniqueness in shape, texture and is suitable for the use in identity recognition.
... Down and Sands[1]explained that the physiological characteristics refer to the inherited traits that are shaped in the early embryonic stages of the human development. Physical biometrics include, among other things, DNA, fingerprints, hand geometry, vein patterns, face structure, skin luminescence, palm prints, iris patterns, periocular features, retina patterns, ear shape, lip prints, heartbeats, tongue prints, and body odor/scent[2]?[8]. Behavioral characteristics are not inherited but acquired and learned throughout the life of the individual[1]. ...
Article
Biometrics are the unique characteristics of the individual that differentiate him or her from any other person. Down and Sands [1] explained that the physiological characteristics refer to the inherited traits that are shaped in the early embryonic stages of the human development. Physical biometrics include, among other things, DNA, fingerprints, hand geometry, vein patterns, face structure, skin luminescence, palm prints, iris patterns, periocular features, retina patterns, ear shape, lip prints, heartbeats, tongue prints, and body odor/scent [2]?[8]. Behavioral characteristics are not inherited but acquired and learned throughout the life of the individual [1]. These include, but also are not limited to, signature, handwriting, vocal prints, keystroke dynamics, and gait?body motion [3]. As a result, the biometrics of a person cannot be stolen, forgotten, or forged. It is what we are [2].
... Zanuy [15] explained limitations of unimodal systems and how to overcome those limitations and explained different levels of fusion. Liu [16], Naaz [17] and Diwakar [18] have worked on a unique organ tongue for Biometrics and work in itself is unique. They have explained how to collect samples for tongue and how features can be extracted. ...
... Tongue: Like fingerprint and palm print even human tongue print is unique. The tongue is a unique organ in that it can be stuck out of mouth for inspection, in this act offering a proof of life, and yet it is otherwise well protected in the mouth and is difficult to forge [10]. ...
Conference Paper
Full-text available
In this Information Age, security of personal data is one of the biggest issues faced by most of the nations. Biometrics provides substantial help in guarding against attempts to establish fraudulent multiple identities or prevent identity fraud. The greatest advantage that the biometric data of an individual remains constant acts as its biggest liability. Once the attacker gets biometric password of an individual then security of his data becomes a big problem. This paper comes with a unique solution which will allow people to change their biometric password and helps to overcome some of the present issues in biometric systems. The biometric password is created by hashing the biometric data of the user. Merging of biometrics and cryptography proves to be more secure and helps to provide a better authentication system for the society.
... A biometric system is a real-time identification system which identifies a person by measuring a particular physical or behavioural characteristic and later comparing it to a library of characteristics belonging to many people [1]. Fingerprint and other biometric devices consist of a reader or scanning device, software that converts the scanned information into digital form, and wherever the data is to be analyzed, a database that stores the biometric data for comparison with previous records. ...
Article
Human identification by virtue of dental identification is on the increase in the past few years and has served as a major adjunct in the identification process. The science associated with the dealing of evidences from dental, oral, and paraoral structures-Forensic Odontology, is a boon in itself. It has been seen that the role of forensic odontology has increased as most of the times teeth and other orally associated structures remain the only means of identification in the worst of scenarios where the conventional biometrics such as fingerprint, iris scan, palm print, etc., may be lost and are therefore not reliable enough to resolve the purpose of identification. There are various important aspects in forensic odontology which are associated with the study of tooth prints, i.e., ameloglyphics, radiographs, the study of palatal rugae patterns, i.e., rugoscopy, cheiloscopy, i.e., the study of lip patterns, tongue prints which can serve as an important biometric tool to aid in the human identification process. Dental biometrics helps to determine several parameters that serve in the interest of forensics such as type of specimen, population affinity, sex, age, stature, race, and various other individualization factors. So, comparative dental identifications with the help of a biometric recognition system will play a major role in identifying deceased individuals in disasters, crimes, or any other mass tragedies. How to cite this article: Kaul B, Vaid V, Gupta S, et al. Forensic Odontological Parameters as Biometric Tool: A Review. Int J Clin Pediatr Dent 2021;14(3):416-419.
Article
Full-text available
Tongue recognition is a biometric technique that can be applied to different areas of expression of human identity. Recognition of the tongue is a difficult and complex problem that is important for surveillance, security, and intelligent interaction between computers and humans. The main idea of proposed system rely that on that any image of a person’s tongue has multiple unique features. Those features vary from on tongue to another. The system proposed in this paper uses group, the Extract the characteristics based on the wavelet Transform where it uses information color (color space RGB) at a certain form of detailed wavelet transforms (discrete wavelet transform), and use of Bhattacharyya distance for comparison between persons. The tongue datasets that are used for of the suggested system are gathered from 30 volunteers of various samples; 4 have been from every individual, images have been captured in various expressions, illuminations, orientations, skin colors, backgrounds, varied in the age) from male and female, results indicated the discrimination rate for waveleting 72%, persons were recognized using Bhattacharyya distance by 93%.
Article
Full-text available
Tongue is a vital internal organ well encased within the oral cavity and protected from the environment. It has unique features which differ from individual to individual and even between identical twins. The color, shape, and surface features are characteristic of every individual, and this serves as a tool for identification. Many modes of biometric systems have come into existence such as fingerprint, iris scan, skin color, signature verification, voice recognition, and face recognition. The search for a new personal identification method secure has led to the use of the lingual impression or the tongue print as a method of biometric authentication. Tongue characteristics exhibit sexual dimorphism thus aiding in the identification of the person. Emerging as a novel biometric tool, tongue prints also hold the promise of a potential forensic tool. This review highlights the uniqueness of tongue prints and its superiority over other biometric identification systems. The various methods of tongue print collection and the classification of tongue features are also elucidated.
Article
Full-text available
By means of the present study we intend to analyse lingual morphological aspects and demonstrate their importance and reliability as main criteria with force of evidence in using forensic dentistry to identify a person. To that end, we conducted the examination of 270 female and male adults between 21 and 40 years old, whose tongues were photographed front and side view. The purpose of the direct examination of the tongue was to emphasize morphological features: shape, type, characteristics of the longitudinal medial septum and the related grooves, as well as the lingual apex type, all of these being preserved using the alginate moulding, which helped taking the impression of the dorsal surface through direct application (from the level of the oral commissures up to the lingual tip) and that of the lateral lingual edges up to the lingual apex level. Thus, we demonstrated that the lingual impression, next to its photographic image, may constitute secure methods for forensic dentistry identification, showing that the inspection of the tongue is a real proof of life and genetic independence, in the sense that there are no two tongues with shape and texture, since lingual morphological aspects are difficult to copy and display stability over time.
Article
BACKGROUND: Traditional Chinese medicine glossoscopy observes tongue image by vision, and to diagnose diseases by physicians' clinical experiences, which lacks of objective diagnostic methods and criteria, finally resulting in affecting the effectiveness of this diagnostic method. Therefore, it is necessary to realize quantitive and objective glossoscopy using techniques such as computer vision. Tongue body segmentation is the premise of the tongue image recognition diagnostic system. The quality of segmentation directly affects the sequent work. At present, there are many methods of tongue body segmentation, but obtained results cannot ensure the accuracy, and the anti-interference ability is poor. OBJECTIVE: To design a new method of tongue image segmentation, and effectively isolate tongue body. METHODS: According to tongue-images gray and color's features, a segmentation method of combining gray projection and threshold-adaptive way is presented in this paper. By this method, the intensity image of a colorful tongue-image is firstly projected at horizontal and vertical direction to locate the tongue-body area, and then threshold-adaptive way Otsu is used to segment the located area. RESULTS AND CONCLUSION: Tongue-body segmentation is the basis of automatic tongue-images analysis. The following 281 tongue-images segmentation experiments show the efficiency of this method.
Conference Paper
The importance of utilizing biometrics to establish personal authenticity and to detect imposters is growing in the present scenario of global security concern. Also the Development of a biometric system for personal identification, which fulfills the requirement for access control of secured areas and other applications like identity validation for social welfare, crime detection, ATM access, computer security, etc. is felt to be the need of the day. The human tongue promises to deliver a level of uniqueness to identification applications that other biometrics cannot match in context of that it is well protected in mouth and is difficult to forge. The tongue also presents both geometric shape information and physiological texture information which are potentially useful in identity verification applications. The 3D scanning of human tongue is an important tool to acquire accurate shape and texture information of tongue for recognition purposes. As we use biometrics mainly for security purpose so preserving the privacy of digital biometric data (e.g. tongue prints) stored in a central database has become of paramount importance, for this we are using visual cryptography while using it in biometric authentication system. This paper proposes the tongue biometric with visual cryptography technique to increase the efficiency of the proposed tongue biometric authentication system (banking system) using 3D database.
Article
The human tongue promises to deliver a level of uniqueness to identification applications that other biometrics cannot match in context of that it is well protected in mouth and is difficult to forge. the tongue also presents both geometric shape information and physiological texture information which are potentially useful in identity verification applications like banking system, airport security, workstations, network and domain access, data protection, national security system (such as defence, nuclear power station etc). A leading concern in the development of such applications however is how to avoid rejecting valid users or approving imposters. Tongue biometric can function as an extremely reliable means for personal identification and act as a general biometric in all applications. This paper demonstrate how Tongue image can be extracted from face image using ASM and how tongue biometric can be use in public use banking system using tongue database.
Article
Full-text available
We describe a database of static images and video clips of human faces and people that is useful for testing algorithms for face and person recognition, head/eye tracking, and computer graphics modeling of natural human motions. For each person there are nine static "facial mug shots" and a series of video streams. The videos include a "moving facial mug shot," a facial speech clip, one or more dynamic facial expression clips, two gait videos, and a conversation video taken at a moderate distance from the camera. Complete data sets are available for 284 subjects and duplicate data sets, taken subsequent to the original set, are available for 229 subjects.
Conference Paper
Full-text available
Tongue diagnosis is an important diagnosis method in traditional Chinese medicine (TCM) and recently the development of automated tongue image analysis technology has been carried out. Automated tongue segmentation is difficult due to the complexity of pathological tongue, variance of tongue shape and interference of the lips. In this paper, we present a novel method for automated tongue segmentation by combining polar edge detector and active contour model. First, a novel polar edge detector is proposed to effectively extract the edge of the tongue body. We then introduce a method to filter out the edge that is useless for tongue segmentation. A local adaptive edge bi-thresholding technique is also proposed. Finally, an initialization and active contour model are proposed to segment the tongue body from the image. Experimental results demonstrate that the novel tongue segmentation can segment the tongue accurately. A quantitative evaluation on 50 images indicates that the mean DCP (the distance to the closest point) of the proposed method is 5,86 pixels, and the average true positive (TP) percent is 97.2%.
Article
Full-text available
In the Fall of 2000, we collected a database of more than 40,000 facial images of 68 people. Using the Carnegie Mellon University 3D Room, we imaged each person across 13 different poses, under 43 different illumination conditions, and with four different expressions. We call this the CMU pose, illumination, and expression (PIE) database. We describe the imaging hardware, the collection procedure, the organization of the images, several possible uses, and how to obtain the database.
Article
Full-text available
Two of the most critical requirements in support of producing reliable face-recognition systems are a large database of facial images and a testing procedure to evaluate systems. The Face Recognition Technology (FERET) program has addressed both issues through the FERET database of facial images and the establishment of the FERET tests. To date, 14,126 images from 1,199 individuals are included in the FERET database, which is divided into development and sequestered portions of the database. In September 1996, the FERET program administered the third in a series of FERET face-recognition tests. The primary objectives of the third test were to 1) assess the state of the art, 2) identify future areas of research, and 3) measure algorithm performance.
Conference Paper
Human tongue is the only organ of human, which can be laid out. It takes an important role in traditional Chinese medicine (TCM) because of its abundant biomedical information. With the progress of modernization of TCM, computerization of tongue diagnosis attracts the researchers' interesting. Thus, how to get an accurate tongue region becomes a key of automatic tongue diagnosis. However, tongue images segmentation is difficult for some physiological properties: tongue is non-rigid and has a high degree of variability in size, shape, color and texture. This paper presents a novel tongue detection method based on B-spline. Applying this method to tongue image, we can get the satisfying results with the respect to robust and veracity
Conference Paper
Between October 2000 and December 2000, we collected a database of over 40,000 facial images of 68 people. Using the CMU (Carnegie Mellon University) 3D Room, we imaged each person across 13 different poses, under 43 different illumination conditions, and with four different expressions. We call this database the CMU Pose, Illumination and Expression (PIE) database. In this paper, we describe the imaging hardware, the collection procedure, the organization of the database, several potential uses of the database, and how to obtain the database
Conference Paper
Two of the most critical requirements in support of producing reliable face-recognition systems are a large database of facial images and a testing procedure to evaluate systems. The Face Recognition Technology (FERET) program has addressed both issues through the FERET database of facial images and the establishment of the FERET tests. To date, 14,126 images from 1199 individuals are included in the FERET database, which is divided into development and sequestered portions. In September 1996, the FERET program administered the third in a series of FERET face-recognition tests. The primary objectives of the third test were to (1) assess the state of the art, (2) identify future areas of research, and (3) measure algorithm performance on large databases
The FERET evaluation methodology for face recognition algorithm 2238 Authorized licensed use limited to: Hong Kong Polytechnic University
  • P Phillips
  • H Moon
  • P Rauss
P. Phillips, H. Moon, P. Rauss, et al., The FERET evaluation methodology for face recognition algorithm, IEEE Trans. PAMI, 22 (10), 2000. 2238 Authorized licensed use limited to: Hong Kong Polytechnic University. Downloaded on March 30, 2009 at 05:09 from IEEE Xplore. Restrictions apply.
  • A Jain
  • R Bolle
  • S Pankanti
A. Jain, R. Bolle, and S. Pankanti, Biometrics: Personal Identification in Networked Society, Kluwer Academic, Boston, 1998.