Tsang Ing Ren

• PhD
• Professor at Federal University of Pernambuco

AI algorithms have become valuable in aiding professionals in healthcare. The increasing confidence obtained by these models is helpful in critical decision demands. In clinical dermatology, classification models can detect malignant lesions on patients' skin using only RGB images as input. However, most learning-based methods employ data acquired...

Background: Facial analysis for orthognathic surgery aims to identify facial features and determine how occlusion should be corrected to achieve facial balance. Several artificial neural networks have been developed to detect facial landmarks; however, no publications have reported the application of neural networks to measure facial pro- portions...

Style transfer is an application that has increased interest, primarily because of the impressive results obtained using neural networks. However, this application demands a lot of computational resources, thus preventing its use in low-end mobiles. The patch-based approach is an interesting alternative that consumes less memory. This work uses two...

The Cell Tracking Challenge is an ongoing benchmarking initiative that has become a reference in cell segmentation and tracking algorithm development. Here, we present a significant number of improvements introduced in the challenge since our 2017 report. These include the creation of a new segmentation-only benchmark, the enrichment of the dataset...

The 2D Simulation League (SIM2D) is one of the most accessible RoboCup leagues, since there are no hardware costs included, and codebases from which you can build a new team are readily available for free. The league, however, still has a notable barrier of entry: its setup. The setup process for the SIM2D environment can be daunting for newcomers,...

An important part of ensuring continuous development and betterment of performance of a robot soccer team is the process of analyzing past matches and generating insights about possible causes for good or bad outcomes the team has in the field. RoboCup robot soccer matches from leagues such as the 2D Simulation League generate log files that can he...

Computer vision research involving street and road detection methods usually focuses on driving assistance and autonomous vehicle systems. In this context, street segmentation occurs in real-time, based on images centered on the street. This work, on the other hand, uses street segmentation for urban planning research to classify pavement types of...

The objective of this work is to analyze which features are most important in the recognition of facial expressions. To achieve this, we built a facial expression recognition system that learns from a controlled capture data set. The system uses different representations and combines them from a learned model. We studied the most important features...

In this article, we argue that the unsatisfactory out-of-distribution (OOD) detection performance of neural networks is mainly due to the SoftMax loss anisotropy and propensity to produce low entropy probability distributions in disagreement with the principle of maximum entropy. On the one hand, current OOD detection approaches usually do not dire...

In state-of-the-art text-independent speaker verification systems, a discriminative deep neural network (DNN) model learns speaker-discriminative representations (x-vectors) for utterances using labeled data. For the verification task, a Probabilistic Linear Discriminant Analysis (PLDA) model is used to decide whether two x-vectors come from the sa...

The IEEE Very Small Size Soccer (VSSS) is a robot soccer competition in which two teams of three small robots play against each other. Traditionally, a deterministic coach agent will choose the most suitable strategy and formation for each adversary's strategy. Therefore, the role of a coach is of great importance to the game. In this sense, this p...

The quality of the images obtained from mobile cameras has been an important feature for modern smartphones. The camera Image Signal Processing (ISP) is a significant procedure when generating high-quality images. However, the existing algorithms in the ISP pipeline need to be tuned according to the physical resources of the image capture, limiting...

The Bayes classifier depends on the conditional densities and the prior probabilities. Among many density functions, the Gaussian density has received more attention mainly motivated by its analytical tractability. The parameters of the Bayes classifier for the Gaussian distribution data are generally unknown, and approximations are calculated for...

Digital cameras can only capture a limited range of real-world scenes' luminance, producing images with saturated pixels. Existing single image high dynamic range (HDR) reconstruction methods attempt to expand the range of luminance, but are not able to hallucinate plausible textures, producing results with artifacts in the saturated areas. In this...

Digital cameras can only capture a limited range of real-world scenes' luminance, producing images with saturated pixels. Existing single image high dynamic range (HDR) reconstruction methods attempt to expand the range of luminance, but are not able to hallucinate plausible textures, producing results with artifacts in the saturated areas. In this...

We propose a new loss formulation to further advance the multiclass segmentation of cluttered cells under weakly supervised conditions. When adding a Youden's J statistic regularization term to the cross entropy loss we improve the separation of touching and immediate cells, obtaining sharp segmentation boundaries with high adequacy. This regulariz...

We propose a deep metric learning model to create embedded sub-spaces with a well defined structure. A new loss function that imposes Gaussian structures on the output space is introduced to create these sub-spaces thus shaping the distribution of the data. Having a mixture of Gaussians solution space is advantageous given its simplified and well e...

Este trabalho foca no desenvolvimento de sistemas de verificação de locutores independente de texto, cujo principal desafio provém das chamadas incompatibilidades que podem ocorrer na aquisição dos sinais de voz. As técnicas propostas para suavizá-las são chamadas de técnicas de compensação e três são os domínios onde elas podem operar: no processo...

We propose a new loss formulation to further advance the multiclass segmentation of cluttered cells under weakly supervised conditions. We improve the separation of touching and immediate cells, obtaining sharp segmentation boundaries with high adequacy, when we add Youden's $J$ statistic regularization term to the cross entropy loss. This regulari...

We present a weakly supervised deep learning method to perform instance segmentation of cells present in microscopy images. Annotation of biomedical images in the lab can be scarce, incomplete, and inaccurate. This is of concern when supervised learning is used for image analysis as the discriminative power of a learning model might be compromised...

We propose a new incremental aggregation algorithm for multi-image deblurring with automatic image selection. The primary motivation is that current burst deblurring methods do not handle well situations in which misalignment or out-of-context frames are present in the burst. These real-life situations result in poor reconstructions or manual selec...

Multi-Focus Image Fusion seeks to improve the quality of an acquired burst of images with different focus planes. For solving the task, an activity level measurement and a fusion rule are typically established to select and fuse the most relevant information from the sources. However, the design of this kind of method by hand is really hard and som...

We present a weakly supervised deep learning method to perform instance segmentation of cells present in microscopy images. Annotation of biomedical images in the lab can be scarce, incomplete, and inaccurate. This is of concern when supervised learning is used for image analysis as the discriminative power of a learning model might be compromised...

Finite mixture models have been widely used for image segmentation in many computer vision and pattern recognition problems. While images of natural scenes are difficult to model, we can employ emerging concepts from statistical physics to achieve better representations. This paper introduces a new class of finite mixture models for solving such pr...

We present a new end-to-end network architecture for facial expression recognition with an attention model. It focuses attention in the human face and uses a Gaussian space representation for expression recognition. We devise this architecture based on two fundamental complementary components: (1) facial image correction and attention and (2) facia...

Endoscopy images show part of the gastrointestinal tract or other parts of the human body. Due to the complex environment in which this tract is located in the human body and the limitations of the image acquisition equipment, endoscopy images may present blur and specular highlights that are common types of degradation. In this paper, we present a...

Background: The Corvis ST provides measurements of intraocular pressure (IOP) and a biomechanically-corrected IOP (bIOP). IOP influences corneal deflection amplitude (DA), which may affect the diagnosis of keratoconus. Compensating for IOP in DA values may improve the detection of keratoconus. Methods: 195 healthy eyes and 136 eyes with keratoco...

Several supervised machine learning applications are commonly represented as multi-class problems, but it is harder to distinguish several classes rather than just two classes. In contrast to the approaches one-against-all and all-pairs that transform a multi-class problem into a set of binary problems, Dichotomy Transformation (DT) converts a mult...

We present a new end-to-end network architecture for facial expression recognition with an attention model. It focuses attention in the human face and uses a Gaussian space representation for expression recognition. We devise this architecture based on two fundamental complementary components: (1) facial image correction and attention and (2) facia...

We presented a 2D/3D MV image registration method based on a Convolutional Neural Network. Most of the traditional image registration method intensity-based, which use optimization algorithms to maximize the similarity between to images. Although these methods can achieve good results for kilovoltage images, the same does not occur for megavoltage...

ColorCheckers are reference standards that professional photographers and filmmakers use to ensure predictable results under every lighting condition. The objective of this work is to propose a new fast and robust method for automatic ColorChecker detection. The process is divided into two steps: (1) ColorCheckers localization and (2) ColorChecker...

Dynamic classifier selection systems aim to select a group of classifiers that is most adequate for a specific query pattern. This is done by defining a region around the query pattern and analyzing the competence of the classifiers in this region. However, the regions are often surrounded by noise which can difficult the classifier selection. This...

We propose a new incremental aggregation algorithm for multi-image deblurring with automatic image selection. The primary motivation is that current bursts deblurring methods do not handle well situations in which misalignment or out-of-context frames are present in the burst. These real-life situations result in poor reconstructions or manual sele...

ColorCheckers are reference standards that professional photographers and filmmakers use to ensure predictable results under every lighting condition. The objective of this work is to propose a new fast and robust method for automatic ColorChecker detection. The process is divided into two steps: (1) ColorCheckers localization and (2) ColorChecker...

We propose a new multiclass weighted loss function for instance segmentation of cluttered cells. We are primarily motivated by the need of developmental biologists to quantify and model the behavior of blood T -cells which might help us in understanding their regulation mechanisms and ultimately help researchers in their quest for developing an eff...

Dynamic ensemble selection systems work by estimating the level of competence of each classifier from a pool of classifiers. Only the most competent ones are selected to classify a given test sample. This is achieved by defining a criterion to measure the level of competence of a base classifier, such as, its accuracy in local regions of the featur...

We propose a new multiclass weighted loss function for instance segmentation of cluttered cells. We are primarily motivated by the need of developmental biologists to quantify and model the behavior of blood T-cells which might help us in understanding their regulation mechanisms and ultimately help researchers in their quest for developing an effe...

In this paper, we propose a framework for defining feature extraction techniques, called Pixel Clustering. It is an extension of feature extraction with Wavelets. We propose two linear feature extraction techniques using Pixel Clustering: IntensityPatches and RegionPatches. We assess the methods in color and grayscale image datasets: two face datas...

X-ray Computed Tomography (CT) has been applied in agriculture engineering for quality and defect control in food products. However, conventional CT systems are neither cost effective nor flexible, making the deployment of such technology unfeasible for many industrial environments. In this work, we propose a simple and cost effective X-ray imaging...

Text categorization systems are designed to classify documents into a fixed number of predefined categories. Bag-of-words is one of the most used approaches to represent a document. However, it generates high-dimensional sparse data matrix with a high feature-to-instance ratio. An aggressive feature selection can alleviate these drawbacks, but such...

In this work, we investigate speaker-specific filter banks for text-independent speaker verification. The proposed method performs an heuristic search for the best filter-bank configuration using the Artificial Bee Colony (ABC) algorithm and a proper fitness function for the standard i-vectors/PLDA-based speaker verification system. Furthermore, fi...

This work proposes a theoretical framework for an unsupervised feature extraction called Pixel Clustering. The main idea is based on the clustering of the pixels in order to mitigate the multicollinearity issue and a new feature is extracted for each cluster of similar pixels. This allows to define feature extraction techniques by setting just thre...

In this paper, we propose a novel facial expression recognition method based on features of the motion, Facial Expression Recognition based on Motion Estimation (FERME). The proposed approach encodes the directional information of the facial expression. The facial motion is encoded by using the motion estimation between different images from the sa...

Within-class multimodality happens when the scattering of the patterns having the same class label follows more than one modal distribution. In this multimodal scenario, it is important to preserve the intrinsic information of the classes when reducing the dimensionality of the data. However, many feature extraction techniques are incapable of deal...

Speed is an important parameter of an inspection system. Inline computed tomography systems exist but are generally expensive. Moreover, their throughput is limited by the speed of the reconstruction algorithm. In this work, we propose a Neural Network-based Hilbert transform Filtered Backprojection (NN-hFBP) method to reconstruct objects in an inl...

MATLAB implementation of our algorithm. (ZIP)

Image segmentation of retinal blood vessels is a process that can help to predict and diagnose cardiovascular related diseases, such as hypertension and diabetes, which are known to affect the retinal blood vessels' appearance. This work proposes an unsupervised method for the segmentation of retinal vessels images using a combinedmatched filter, F...

Adaptive video streaming has become prominent due to the rising diversity of Web-enabled personal devices. Common limitations in bandwidth and decoding power challenge the efficiency of content encoders to preserve visual quality at reduced data rates over a wide range of display resolutions. Objective assessment of perceptual video quality has gre...

This paper presents three new efficient 2×2 block-based algorithms for connected components labeling: a two-scan which assigns provisional labels to blocks, a two-scan which assigns provisional labels to pixels and a one-and-a-half-scan which assigns provisional labels to blocks. A new stripe image representation is designed in order to perform the...

The nearest neighbor (NN) is one of the most well known classifiers in pattern recognition. Despite the high classification accuracy, the NN has several drawbacks: high storage requirements, bad time of response, and high noise sensitivity. Prototype Generation (PG) is one of the most well-known solutions to tackle these shortcomings. In supervised...

We propose a bootstrap-based iterative method for generating classifier ensembles called Iterative Classifier Selection Bagging (ICS-Bagging). Each iteration of ICS-Bagging has two phases: i) bootstrap sampling to generate a pool of classifiers; and, ii) selection of the best classifier of the pool using a fitness function based on the ensemble acc...

The proposed Fractional Eigenfaces method is a feature extraction technique for high dimensional data. It is related to Fractional PCA (FPCA), which is based on the theory of fractional covariance matrix, and it is an extension of the classical Eigenfaces. Like FPCA, it computes projections for a low dimensional space from the fractional covariance...

Autoassociative artificial neural networks have been used in many different computer vision applications. However, it is difficult to define the most suitable neural network architecture because this definition is based on previous knowledge and depends on the problem domain. To address this problem, we propose a constructive autoassociative neural...

This paper proposes the use of the type-2 fuzzy GMM (T2FGMM) framework in order to improve the verification rates of the standard GMM-UBM text-independent speaker verification system in noisy environments. Based on type-2 fuzzy sets, the T2FGMM framework describes GMMs with uncertain parameters and provides likelihood intervals for them. The propos...

This paper presents a solution for the RecSys Challenge 2014 by performing a clustering in a bipartite graph whose vertices are of two types: user and item, having the edges as the engagement given to a tweet. The Modularity metric, which is well-known in the area of complex networks to quantify how good the groups of nodes are defined in the netwo...

Modular Neural Network (MNN) divides a problem into smaller and easier sub-problems, and each sub-problem is solved by a neural network called expert. In previous MNN architectures, all experts used the same set of features. This work proposes a modular neural network architecture in which a specialized set of features is selected per expert. As ea...

Endoscopy is a minimally invasive medical diagnostic procedure that is used to provide a realistic view of the surfaces of organs inside human body. Images taken during such procedures largely show tissues of human organs. Due to the presence of mucosa of the gastrointestinal tract or other characteristics of the human body, these surfaces usually...

This paper presents a reconstruction method for a conveyor belt X-ray scanning geometry, consisting of a static X-ray source/detector system and an object in uniform motion. Applying conventional reconstruction methods to data acquired in this geometry leads to severe artefacts. We show that by incorporating prior knowledge of the material as well...

This article proposes a real-time Head Pose Estimation (HPE) technique designed to be used in mobile devices. The method enables the interaction between the user and mobile devices using the device's inbuilt camera. The proposed technique is composed of different computer vision methods, which were optimized to operate in a restricted environment....

Instance reduction techniques can improve generalization, reduce storage requirements and execution time of instance-based learning algorithms. This paper presents an instance reduction algorithm called Adaptive Threshold-based Instance Selection Algorithm (ATISA). ATISA aims to preserve important instances based on a selection criterion that uses...

Receptive fields and autoassociative memory are brain concepts that have individually inspired many artificial models, but models using both ideas have not been deeply studied. In this paper, we propose the AutoAssociative Pyramidal Neural Network (AAPNet), which is an artificial neural network for one-class classification that uses autoassociative...

Image segmentation is one of the basic steps in image analysis. Clustering methods are an unsupervised way to provide image segmentation. This paper proposes a clustering algorithm for contextual image segmentation, called spatially variant finite mixture model (SVFMM). For the case of spatially varying mixture of Gaussian density functions with un...

This work proposes an optimization technique based on binary particle swarm optimization that performs feature selection and feature weighting simultaneously. In the optimization process, each member of the population is described as a vector having three parts: i) one weight per feature (feature weighting), ii) one binary value per feature indicat...

In deblurring an image, we seek to recover the original sharp image. However, without knowledge of the blurring process, we cannot expect to recover the image perfectly. We propose a deblurring method of a single-image where the blur kernel is directly estimated from highlight spots or streaks with high intensity value. These highlighted points can...

Pedestrian detection is a very promising area in computer vision, since it enables interesting and a variety of applications such as car assistance, surveillance systems and robot vision. During the last years, a variety of new techniques were proposed which greatly improved the detection rates. However, the performance of such systems rapidly dete...

This paper presents a motion compensation technique applied in the permutation-based digital video encryption and compression method introduced by Socek et al. The encryption method is based in permutations that can improve the spatial correlation on each video frame, making them more compressible by a spatial encoder. However, the compression perf...

We present a combined features approach for speaker segmentation task. This approach utilizes different acoustic features extracted from audio stream. The Bayesian Information Criterion (BIC) is used for each acoustic feature as a distance measure to verify the merging of two audio segments. An Artificial Neural Network (ANN) combines the time inde...

This paper proposes the use of a type-2 fuzzy framework in the standard GMM-UBM based text-independent speaker verification systems. Based on type-2 fuzzy sets, the framework provides pertinence intervals for the models. The decision process is obtained using a Support Vectors Machine (SVM) that processes the interval likelihoods. A Voice Activity...

The “no free lunch” theorem has stated that learning algorithms cannot be universally good. An alternative to alleviate the weakness of using only one classifier is to combine several of them. Mixture of Experts is a learning algorithm that combines classifiers, in which each classifier or expert is dedicated to solve part of the problem. The parti...

Block-based algorithms are considered the fastest approach to label connected components in binary images. However, the existing algorithms are two-scan which would need more comparisons if they were used as one-and-a-half-scan algorithms. Here, we proposed a new mask that enables the design of a block-based one-and-a-half-scan algorithm without an...

Proposed is a technique for fingerprint spoof detection, the spatial surface coarseness analysis. This approach improves the wavelet analysis of the fingertip surface texture by introducing spatial features to the model. Thus, the accuracy of the fingerprint classification is increased to 70.09% compared with the original solution.

The human visual system is one of the most fascinating and complex mechanisms of the central nervous system that enables our capacity to see. It is through the visual system that we are able to accomplish from the most simple task such as object recognition to the most complex visual interpretation, understanding and perception. Inspired by this so...

Some real world datasets have different proportions of classes, too many instances of the majority classes and only a few of the minority classes, those are called imbalanced datasets. Many applications, like medical diagnosis and risk analysis, are interested in the under-represented class, but classifiers and prototype generation techniques usual...

In this paper, we present an efficient method for facial expression recognition. Three features extraction methods are combined to form a model representation for facial expressions. Once the feature and the model representation are defined a Support Vector Machine (SVM) is used for the classification task. The proposed method is tested using the Y...