Deep learning models have provided dramatic performance improvement for various computer vision tasks. These models, however, require huge amounts of labeled data to perform well. Collecting and labeling large datasets is often nontrivial and requires significant human effort. Crowd counting is one such task that demands a large amount of labeled training data. This labeling process requires a human annotator to manually mark a dot at the center of the head of each person present in the image, which is a laborious and tedious task, especially in densely crowded scenes. In this work, we investigate an active learning framework for crowd counting. Evaluations on mainstream datasets demonstrate the effectiveness of the proposed framework in reducing the annotation effort significantly with minimal compromise on count performance. Our method surpasses existing methods that focus on counting with limited labeled data

High-resolution fingerprint recognition is mainly centred around local descriptors created using pore patches. Although these methods provide good verification performance, they are not well-suited for identification due to poor computational performance and variable and large template size caused by the variable number of useful pore patches. We present a deep learning model that overcomes this problem by learning to generate a fixed-sized global descriptor while also taking into account the finer level-3 features by infusing domain knowledge using a multi-task architecture. Our approach employs a CNN with two branches simultaneously trained to generate descriptors and pore-intensity maps. We have augmented a publicly available dataset (IITI-HRF) for performance evaluation. Our method compares favorably to the state-of-the-art in terms of accuracy, while being significantly faster ($\sim 24\times$ for verification and $\sim 518000\times$ for identification) and having a smaller template size.

Automated chest X-ray analysis has a great potential for diagnosing thorax diseases since errors in diagnosis have always been a concern among radiologists. Being a multi-label classification problem, achieving accurate classification remains challenging. Several studies have focused on accurately segmenting the lung regions from the chest X-rays to deal with the challenges involved. The features extracted from the lung regions typically provide precise clues for diseases like nodules. However, such methods ignore the features outside the lung regions, which have been shown to be crucial for diagnosing conditions like cardiomegaly. Therefore, in this work, we explore a dual-branch network-based framework that relies on features extracted from the lung regions as well as the entire chest X-rays. The proposed framework uses a novel network named R-I UNet for segmenting the lung regions. The dual-branch network in the proposed framework employs two pre-trained AlexNet models to extract discriminative features, forming two feature vectors. Each feature vector is fed into a recurrent neural network consisting of a stack of gated recurrent units with skip connections. Finally, the resulting feature vectors are concatenated for classification. The proposed models achieve state-of-the-art performance for both segmentation and classification tasks on the benchmark datasets. Specifically, our lung segmentation model achieves a 5-fold cross-validation accuracy of 98.18 % and 99.14 % on Montgomery (MC) and JSRT datasets. For classification, the proposed approach achieves state-of-the-art AUC for 9 out of 14 diseases with a mean AUC of 0.842 on the NIH ChestXray14 dataset.

Periocular recognition has been an active area of research in the past few years. In spite of the advancements made in this area, the cross-spectral matching of visible (VIS) and near-infrared (NIR) periocular images remains a challenge. In this paper, we propose a method based on illumination normalization of VIS and NIR periocular images. Specifically, the approach involves normalizing the images using the difference of Gaussian (DoG) filtering, followed by the computation of a descriptor that captures structural details in the illumination normalized images using histogram of oriented gradients (HOG). Finally, the feature vectors corresponding to the query and the enrolled image are compared using the cosine similarity metric to generate a matching score. Performance of our algorithm has been evaluated on three publicly available benchmark databases of cross-spectral periocular images. Our approach yields significant improvement in performance over the existing approach.

In recent years, software-based face presentation attack detection (PAD) methods have seen a great progress. However, most existing schemes are not able to generalize well in more realistic conditions. The objective of this competition is to evaluate and compare the generalization performances of mobile face PAD techniques under some real-world variations, including unseen input sensors, presentation attack instruments (PAI) and illumination conditions, on a larger scale OULU-NPU dataset using its standard evaluation protocols and metrics. Thirteen teams from academic and industrial institutions across the world participated in this competition. This time typical liveness detection based on physiological signs of life was totally discarded. Instead, every submitted system relies practically on some sort of feature representation extracted from the face and/or background regions using hand-crafted, learned or hybrid descriptors. Interesting results and findings are presented and discussed in this paper.

This work presents the 2ndCross-Spectrum Iris/Periocular Recognition Competition (Cross-Eyed2017). The main goal of the competition is to promote and evaluate advances in cross-spectrum iris and periocular recognition. This second edition registered an increase in the participation numbers ranging from academia to industry: five teams submitted twelve methods for the periocular task and five for the iris task. The benchmark dataset is an enlarged version of the dual-spectrum database containing both iris and periocular images synchronously captured from a distance and within a realistic indoor environment. The evaluation was performed on an undisclosed test-set. Methodology, tested algorithms, and obtained results are reported in this paper identifying the remaining challenges in path forward.

The electroencephalogram (EEG) signals are commonly used for diagnosis of epilepsy. In this paper, we present a new methodology for EEG-based automated diagnosis of epilepsy. Our method involves detection of key points at multiple scales in EEG signals using a pyramid of difference of Gaussian filtered signals. Local binary patterns (LBPs) are computed at these key points and the histogram of these patterns are considered as the feature set, which is fed to the support vector machine (SVM) for the classification of EEG signals. The proposed methodology has been investigated for the four well-known classification problems namely, 1) normal and epileptic seizure, 2) epileptic seizure and seizure free, 3) normal, epileptic seizure, and seizure free, and 4) epileptic seizure and nonseizure EEG signals using publically available university of Bonn EEG database. Our experimental results in terms of classification accuracies have been compared with existing methods for the classification of the aforementioned problems. Further, performance evaluation on another EEG dataset shows that our approach is effective for classification of seizure and seizure-free EEG signals. The proposed methodology based on the LBP computed at key points is simple and easy to implement for real-time epileptic seizure detection.

Automated human authentication using features extracted from palmprint images has been studied extensively in the literature. Primary focus of the studies thus far has been the improvement of matching performance. As more biometric systems get deployed for wide range of applications, the threat of impostor attacks on these systems is on the rise. The most common among various types of attacks is the sensor level spoof attack using fake hands created using different materials. This paper investigates an approach for securing palmprint based biometric systems against spoof attacks that use photographs of the human hand for circumventing the system. The approach is based on the analysis of local texture patterns of acquired palmprint images for extracting discriminatory features. A trained binary classifier utilizes the discriminating information to determine if the input image is of real hand or a fake one. Experimental results, using 611 palmprint images corresponding to 100 subjects in the publicly available IITD palmprint image database, show that 1) palmprint authentication systems are highly vulnerable to spoof attacks and 2) the proposed spoof detection approach is effective for discriminating between real and fake image samples. In particular, the proposed approach achieves the best classification accuracy of 97.35%.

Two-dimensional (2-D) hand-geometry features carry limited discriminatory information and therefore yield moderate performance when utilized for personal identification. This paper investigates a new approach to achieve performance improvement by simultaneously acquiring and combining three-dimensional (3-D) and 2-D features from the human hand. The proposed approach utilizes a 3-D digitizer to simultaneously acquire intensity and range images of the presented hands of the users in a completely contact-free manner. Two new representations that effectively characterize the local finger surface features are extracted from the acquired range images and are matched using the proposed matching metrics. In addition, the characterization of 3-D palm surface using SurfaceCode is proposed for matching a pair of 3-D palms. The proposed approach is evaluated on a database of 177 users acquired in two sessions. The experimental results suggest that the proposed 3-D hand-geometry features have significant discriminatory information to reliably authenticate individuals. Our experimental results demonstrate that consolidating 3-D and 2-D hand-geometry features results in significantly improved performance that cannot be achieved with the traditional 2-D hand-geometry features alone. Furthermore, this paper also investigates the performance improvement that can be achieved by integrating five biometric features, i.e., 2-D palmprint, 3-D palmprint, finger texture, along with 3-D and 2-D hand-geometry features, that are simultaneously extracted from the user's hand presented for authentication.

This paper presents a novel approach for hand matching that achieves significantly improved performance even in the presence of large hand pose variations. The proposed method utilizes a 3-D digitizer to simultaneously acquire intensity and range images of the user's hand presented to the system in an arbitrary pose. The approach involves determination of the orientation of the hand in 3-D space followed by pose normalization of the acquired 3-D and 2-D hand images. Multimodal (2-D as well as 3-D) palmprint and hand geometry features, which are simultaneously extracted from the user's pose normalized textured 3-D hand, are used for matching. Individual matching scores are then combined using a new dynamic fusion strategy. Our experimental results on the database of 114 subjects with significant pose variations yielded encouraging results. Consistent (across various hand features considered) performance improvement achieved with the pose correction demonstrates the usefulness of the proposed approach for hand based biometric systems with unconstrained and contact-free imaging. The experimental results also suggest that the dynamic fusion approach employed in this work helps to achieve performance improvement of 60% (in terms of EER) over the case when matching scores are combined using the weighted sum rule.

This paper presents a new evolutionary approach for adaptive combination of multiple biometrics to ensure the optimal performance for the desired level of security. The adaptive combination of multiple biometrics is employed to determine the optimal fusion strategy and the corresponding fusion parameters. The score-level fusion rules are adapted to ensure the desired system performance using a hybrid particle swarm optimization model. The rigorous experimental results presented in this paper illustrate that the proposed score-level approach can achieve significantly better and stable performance over the decision-level approach. There has been very little effort in the literature to investigate the performance of an adaptive multimodal fusion algorithm on real biometric data. This paper also presents the performance of the proposed approach from the real biometric samples which further validate the contributions from this paper.

This paper presents a new evolutionary approach for adaptive combination of multiple biometrics to dynamically ensure the performance for the desired level of security. The adaptive combination of multiple biometrics is achieved at the matching score level. The score level fusion rules are adapted to ensure the required/desired system performance using particle swarm optimization. The experimental results presented in this paper illustrates two main advantages of the proposed score-level approach over the decision level approach; better performance and stable performance that require smaller number of iterations. There has not been any effort in the literature to investigate the performance of adaptive multimodal fusion algorithm on real biometric data. This paper also presents the performance of the proposed algorithm on real biometric data which further validates contributions from this paper.

We note that there are some discrepancies in the results reported in the previous titled paper. Our experiments indicate that the authors have considered only a subset of all possible fusion rules, contradicting the statement that all possible rules have been considered. Moreover, the authors state that only monotonic rules can be optimal, and therefore, all other rules can be ignored. However, our experimental results examining all possible rules demonstrate that a nonmonotonic rule can also be an optimum fusion rule.