Human hand not only possesses distinctive feature for gender information, it is also considered one of the primary biometric traits used to identify a person. Unlike face images, which are usually unconstrained, an advantage of hand images is they are usually captured under a controlled position. Most state-of-the-art methods, that rely on hand images for gender recognition or biometric identification, employ handcrafted features to train an off-the-shelf classifier or be used by a similarity metric for biometric identification. In this work, we propose a deep learning-based method to tackle the gender recognition and biometric identification problems. Specifically, we design a two-stream convolutional neural network (CNN) which accepts hand images as input and predicts gender information from these hand images. This trained model is then used as a feature extractor to feed a set of support vector machine classifiers for biometric identification. As part of this effort, we propose a large dataset of human hand images, 11K Hands, which contains dorsal and palmar sides of human hand images with detailed ground-truth information for different problems including gender recognition and biometric identification. By leveraging thousands of hand images, we could effectively train our CNN-based model achieving promising results. One of our findings is that the dorsal side of human hands is found to have effective distinctive features similar to, if not better than, those available in the palmar side of human hand images. To facilitate access to our 11K Hands dataset, the dataset, the trained CNN models, and our Matlab source code are available at (
 https://goo.gl/rQJndd
 ).

11K Hands: Gender recognition and biometric identification using a large dataset of hand images

The human hand possesses distinctive features which can reveal gender information. In addition, the hand is considered one of the primary biometric traits used to identify a person. In this work, we propose a large dataset of human hand images with detailed ground-truth information for gender recognition and biometric identification. The proposed dataset comprises of 11,076 hand images (dorsal and palmar sides), from 190 subjects of different ages under the same lighting conditions. Using this dataset, a convolutional neural network (CNN) can be trained effectively for the gender recognition task. Based on this, we design a two-stream CNN to tackle the gender recognition problem. This trained model is then used as a feature extractor to feed a set of support vector machine classifiers for the biometric identification task. To facilitate access to the proposed dataset and replication of our experiments, the dataset, trained CNN models, and Matlab source code are available at (this https URL).

Gender recognition and biometric identification using a large dataset of hand images.

In recent years, fingerprint authentication systems have been extensively deployed in various applications, including attendance systems, authentications on smartphones, mobile payment authorizations, as well as various safety certifications. However, similar to the other biometric identification technologies, fingerprint recognition is vulnerable to artificial replicas made from cheap materials, such as silicon, gelatin, etc. Thus, it is especially necessary to distinguish whether a given fingerprint is a live or a spoof one prior to such authentication. In order to solve the problems above, a novel local descriptor named Weber local binary descriptor for fingerprint liveness detection (FLD) has been proposed in this paper. The method consists of two components: the local binary differential excitation component that extracts intensity-variance features and the local binary gradient orientation component that extracts orientation features. The co-occurrence probability of the two components is calculated to construct a discriminative feature vector, which is fed into support vector machine (SVM) classifiers. The effectiveness of the proposed method is intuitively analyzed on the image samples and numerically demonstrated by Mahalanobis distance. Experiments are performed on two public databases from FLD competitions from 2011 and 2013. The results have proved that the proposed method obtains the best detection accuracy among the existing image local descriptors in FLD.

A Novel Weber Local Binary Descriptor for Fingerprint Liveness Detection

Numerous behavioral or physiological biometric traits, including iris, signature, hand geometry, speech, palm print, face, etc. have been used to discriminate individuals in a number of security applications over the last 30 years. Among these, hand-based biometric systems have come to the attention of researchers worldwide who utilize them for low- to medium-security applications such as financial transactions, access control, law enforcement, border control, computer security, time and attendance systems, dormitory meal plan access, etc. Several approaches for biometric recognition have been summarized in the literature. The survey in this article focuses on the interface between various hand modalities, summary of inner- and dorsal-knuckle print recognition, and fusion techniques. First, an overview of various feature extraction and classification approaches for knuckle print, a new entrant in the hand biometrics family with a higher user acceptance and invariance to emotions, is presented. Next, knuckle print fusion schemes with possible integration scenarios, and traditional capturing devices have been discussed. The economic relevance of various biometric traits, including knuckle print for commercial and forensic applications is debated. Finally, conclusions related to the scope of knuckle print as a biometric trait are drawn and some recommendations for the development of hand-based multimodal biometrics have been presented.

Knuckle Print Biometrics and Fusion Schemes -- Overview, Challenges, and Solutions

Identification and authentication are ubiquitous questions which pan across various systems. In certain domains, they are of paramount importance. Like, security forces deploy various human identifications systems to discern potential wrongdoers. They constitute a vital part of various government social welfare schemes. The efficacy of the schemes is greatly impacted by them. Being pervasive and eminent, they demand more dedicated and focused research. Now-a-days, most of the systems incorporate a biometric system to address identification and authentication. The biometric system employs disparate traits like face, signature, iris, fingerprint, palmprint, speech, etc. for identification and authentication. A biometric trait must possess the following fundamental aspects; It should be able to identify an individual uniquely. For an individual, it should be consistent. To acquire it should be easy, cost-effective, time-efficient and automated. On such account, fingerprint trait is of outstanding merit. It has been widely studied and is an integral part of the many present biometric systems. However, fingerprints are subject to occupational hazard. The fingerprint is of abysmal quality for hand labourer, blacksmith, etc. due to the nature of their work. If a fingerprint based biometric system has a large number of such users then its precision is greatly affected. In such scenario, an alternate is to use finger-knuckle-print which possess almost comparable feature as fingerprint while being unaffected by such occupational hazards. In this paper, we propose a novel finger-knuckle-print based biometric system which could be deployed where a large number of user base is rural. Initially, ROI of finger knuckle image has been extracted, enhanced and transformed using the proposed Bubble ordinal pattern (BOP), STAR ordinal pattern (SOP), and Image ray transform (IRT) based locally adapted procedures. A novel DeepMatching technique has been used to perform non-rigid distortion free matching between multiple features of two Finger Knuckle Images (FKI). Finally, the performance of proposed system has been evaluated using score level fusion rule, revealing improvement in the results.

DeepKnuckle: revealing the human identity

Deep convolutional neural networks (CNNs) have shown a strong ability in mining discriminative object pose and parts information for image recognition. For fine-grained recognition, context-aware rich feature representation of object/scene plays a key role since it exhibits a significant variance in the same subcategory and subtle variance among different subcategories. Finding the subtle variance that fully characterizes the object/scene is not straightforward. To address this, we propose a novel context-aware attentional pooling (CAP) that effectively captures subtle changes via sub-pixel gradients, and learns to attend informative integral regions and their importance in discriminating different subcategories without requiring the bounding-box and/or distinguishable part annotations. We also introduce a novel feature encoding by considering the intrinsic consistency between the informativeness of the integral regions and their spatial structures to capture the semantic correlation among them. Our approach is simple yet extremely effective and can be easily applied on top of a standard classification backbone network. We evaluate our approach using six state-of-the-art (SotA) backbone networks and eight benchmark datasets. Our method significantly outperforms the SotA approaches on six datasets and is very competitive with the remaining two.

Context-aware Attentional Pooling (CAP) for Fine-grained Visual Classification

This paper presents a novel keypoints-based attention mechanism for visual recognition in still images. Deep Convolutional Neural Networks (CNNs) for recognizing images with distinctive classes have shown great success, but their performance in discriminating fine-grained changes is not at the same level. We address this by proposing an end-to-end CNN model, which learns meaningful features linking fine-grained changes using our novel attention mechanism. It captures the spatial structures in images by identifying semantic regions (SRs) and their spatial distributions, and is proved to be the key to modelling subtle changes in images. We automatically identify these SRs by grouping the detected keypoints in a given image. The ``usefulness'' of these SRs for image recognition is measured using our innovative attentional mechanism focusing on parts of the image that are most relevant to a given task. This framework applies to traditional and fine-grained image recognition tasks and does not require manually annotated regions (e.g. bounding-box of body parts, objects, etc.) for learning and prediction. Moreover, the proposed keypoints-driven attention mechanism can be easily integrated into the existing CNN models. The framework is evaluated on six diverse benchmark datasets. The model outperforms the state-of-the-art approaches by a considerable margin using Distracted Driver V1 (Acc: 3.39%), Distracted Driver V2 (Acc: 6.58%), Stanford-40 Actions (mAP: 2.15%), People Playing Musical Instruments (mAP: 16.05%), Food-101 (Acc: 6.30%) and Caltech-256 (Acc: 2.59%) datasets.

Attend and Guide (AG-Net): A Keypoints-driven Attention-based Deep Network for Image Recognition

A finger biometric system at an unconstrained environment is presented in this paper. A technique for hand image normalization is implemented at the preprocessing stage that decomposes the main hand contour into finger-level shape representation. This normalization technique follows subtraction of transformed binary image from binary hand contour image to generate the left-side of finger profiles (LSFPs). Then, XOR is applied to LSFP image and hand contour image to produce the right side of finger profiles. During feature extraction, initially, 30 geometric features are computed from every normalized finger. The rank-based forward–backward greedy algorithm is followed to select relevant features and to enhance classification accuracy. Two different subsets of features containing 9 and 12 discriminative features per finger are selected for two separate experimentations those use the ${k}$ -nearest neighbor and the random forest (RF) for classification on the Bosphorus hand database. The experiments with the selected features of four fingers except the thumb have obtained improved performances compared to features extracted from five fingers and also other existing methods evaluated on the Bosphorus database. The best identification accuracies of 96.56% and 95.92% using the RF classifier have been achieved for the right- and left-hand images of 638 subjects, respectively. An equal error rate of 0.078 is obtained for both types of the hand images.

Human Identification Using Selected Features From Finger Geometric Profiles

This article presents a novel keypoints-based attention mechanism for visual recognition in still images. Deep Convolutional Neural Networks (CNNs) for recognizing images with distinctive classes have shown great success, but their performance in discriminating fine-grained changes is not at the same level. We address this by proposing an end-to-end CNN model, which learns meaningful features linking fine-grained changes using our novel attention mechanism. It captures the spatial structures in images by identifying semantic regions (SRs) and their spatial distributions, and is proved to be the key to modeling subtle changes in images. We automatically identify these SRs by grouping the detected keypoints in a given image. The “usefulness” of these SRs for image recognition is measured using our innovative attentional mechanism focusing on parts of the image that are most relevant to a given task. This framework applies to traditional and fine-grained image recognition tasks and does not require manually annotated regions (e.g. bounding-box of body parts, objects, etc.) for learning and prediction. Moreover, the proposed keypoints-driven attention mechanism can be easily integrated into the existing CNN models. The framework is evaluated on six diverse benchmark datasets. The model outperforms the state-of-the-art approaches by a considerable margin using Distracted Driver V1 (Acc: 3.39%), Distracted Driver V2 (Acc: 6.58%), Stanford-40 Actions (mAP: 2.15%), People Playing Musical Instruments (mAP: 16.05%), Food-101 (Acc: 6.30%) and Caltech-256 (Acc: 2.59%) datasets.

Asish Bera

Papers

Context-aware Attentional Pooling (CAP) for Fine-grained Visual Classification

Attend and Guide (AG-Net): A Keypoints-driven Attention-based Deep Network for Image Recognition

Context-aware Attentional Pooling (CAP) for Fine-grained Visual Classification

Human Identification Using Selected Features From Finger Geometric Profiles

Attend and Guide (AG-Net): A Keypoints-Driven Attention-Based Deep Network for Image Recognition