Maneet Singh

On Recognizing Face Images With Weight and Age Variations

With the increase in age, there are changes in skeletal structure, muscle mass, and body fat. For recognizing faces with age variations, researchers have generally focused on the skeletal structure and muscle mass. However, the effect of change in body fat has not been studied with respect to face recognition. In this paper, we incorporate weight information to improve the performance of face recognition with age variations. The proposed algorithm utilizes neural network and random decision forest to encode age variations across different weight categories. The results are reported on the WhoIsIt database prepared by the authors containing 1109 images from 110 individuals with age and weight variations. The comparison with existing state-of-the-art algorithms and commercial system on WhoIsIt and FG-Net databases shows that the proposed algorithm outperforms existing algorithms significantly.

Regularized Deep Learning for Face Recognition With Weight Variations

Body weight variations are an integral part of a persons aging process. However, the lack of association between the age and the weight of an individual makes it challenging to model these variations for automatic face recognition. In this paper, we propose a regularizer-based approach to learn weight invariant facial representations using two different deep learning architectures, namely, sparse-stacked denoising autoencoders and deep Boltzmann machines. We incorporate a body-weight aware regularization parameter in the loss function of these architectures to help learn weight-aware features. The experiments performed on the extended WIT database show that the introduction of weight aware regularization improves the identification accuracy of the architectures both with and without dropout.

Transfer Learning Based Evolutionary Algorithm for Composite Face Sketch Recognition

Matching facial sketches to digital face images has widespread application in law enforcement scenarios. Recent advancements in technology have led to the availability of sketch generation tools, minimizing the requirement of a sketch artist. While these sketches have helped in manual authentication, matching composite sketches with digital mugshot photos automatically show high modality gap. This research aims to address the task of matching a composite face sketch image to digital images by proposing a transfer learning based evolutionary algorithm. A new feature descriptor, Histogram of Image Moments, has also been presented for encoding features across modalities. Moreover, IIITD Composite Face Sketch Database of 150 subjects is presented to fill the gap due to limited availability of databases in this problem domain. Experimental evaluation and analysis on the proposed dataset show the effectiveness of the transfer learning approach for performing cross-modality recognition.

Low rank group sparse representation based classifier for pose variation

Face recognition under uncontrolled environment persists to be an unresolved problem having challenges such as varying pose, illumination, occlusion etc. In this research, we propose an algorithm for identification of faces with pose and illumination variations. An adaptive dictionary learning framework built upon group sparse representation classifier is presented in order to learn dictionary parameters and pose invariant sparse codes for given images. Low rank regularization is utilized for dictionary learning, to address the noise present in training samples that can hinder the discriminative power of the learnt dictionary. Experimental results illustrate state-of-the-art performance on the CMU Multi-PIE dataset.

Cross-spectral cross-resolution video database for face recognition

Advancing state of the art in face recognition and bridging the gap between laboratory and real-world scenarios require the availability of challenging databases. One of the challenging applications of face recognition is surveillance, where unconstrained video data is captured both in day and night time (visible and near infrared spectrum). These videos have multiple subjects in each frame, which are matched with good quality gallery images. Due to the lack of an existing database for such a cross spectral cross resolution video-to-still face recognition application, this is still an open research problem. This paper presents a video database that can be utilized to benchmark face recognition algorithms addressing cross spectral cross resolution matching. The proposed Cross-Spectral Cross-Resolution Video dataset (CSCRV) contains videos pertaining to 160 subjects with an open-set protocol. We present baseline results with two commercial matchers for two experimental scenarios, where we observe very low performance of both the matchers. It is our assertion that this dataset can help researchers develop robust face recognition algorithms to handle real world surveillance scenarios.

Regularizing deep learning architecture for face recognition with weight variations

Several mathematical models have been proposed for recognizing face images with age variations. However, effect of change in body-weight is also an interesting covariate that has not been much explored. This paper presents a novel approach to incorporate the weight variations during feature learning process. In a deep learning architecture, we propose incorporating the body-weight in terms of a regularization function which helps in learning the latent variables representative of different weight categories. The formulation has been proposed for both Autoencoder and Deep Boltzmann Machine. On extended WIT database of 200 subjects, the comparison with a commercial system and an existing algorithm show that the proposed algorithm outperforms them by more than 9% at rank-10 identification accuracy.

Are you eligible? Predicting adulthood from face images via Class Specific Mean Autoencoder

Predicting if a person is an adult or a minor has several applications such as inspecting underage driving, preventing purchase of alcohol and tobacco by minors, and granting restricted access. The challenging nature of this problem arises due to the complex and unique physiological changes that are observed with age progression. This paper presents a novel deep learning based formulation, termed as Class Specific Mean Autoencoder, to learn the intra-class similarity and extract class-specific features. We propose that the feature of a particular class if brought similar/closer to the mean feature of that class can help in learning class-specific representations. The proposed formulation is applied for the task of adulthood classification which predicts whether the given face image is of an adult or not. Experiments are performed on two large databases and the results show that the proposed algorithm yields higher classification accuracy compared to existing algorithms and a Commercial-Off-The-Shelf system.

Residual Codean Autoencoder for Facial Attribute Analysis

Facial attributes can provide rich ancillary information which can be utilized for different applications such as targeted marketing, human computer interaction, and law enforcement. This research focuses on facial attribute prediction using a novel deep learning formulation, termed as R-Codean autoencoder. The paper first presents Cosine similarity based loss function in an autoencoder which is then incorporated into the Euclidean distance based autoencoder to formulate R-Codean. The proposed loss function thus aims to incorporate both magnitude and direction of image vectors during feature learning. Further, inspired by the utility of shortcut connections in deep models to facilitate learning of optimal parameters, without incurring the problem of vanishing gradient, the proposed formulation is extended to incorporate shortcut connections in the architecture. The proposed R-Codean autoencoder is utilized in facial attribute prediction framework which incorporates patch-based weighting mechanism for assigning higher weights to relevant patches for each attribute. The experimental results on publicly available CelebA and LFWA datasets demonstrate the efficacy of the proposed approach in addressing this challenging problem.

Region-specific fMRI dictionary for decoding face verification in humans

This paper focuses on decoding the process of face verification in the human brain using fMRI responses. 2400 fMRI responses are collected from different participants while they perform face verification on genuine and imposter stimuli face pairs. The first part of the paper analyzes the responses covering both cognitive and fMRI neuro-imaging results. With an average verification accuracy of 64.79% by human participants, the results of the cognitive analysis depict that the performance of female participants is significantly higher than the male participants with respect to imposter pairs. The results of the neuro-imaging analysis identifies regions of the brain such as the left fusiform gyrus, caudate nucleus, and superior frontal gyrus that are activated when participants perform face verification tasks. The second part of the paper proposes a novel two-level fMRI dictionary learning approach to predict if the stimuli observed is genuine or imposter using the brain activation data for selected regions. A comparative analysis with existing machine learning techniques illustrates that the proposed approach yields at least 4.5% higher classification accuracy than other algorithms. It is envisioned that the result of this study is the first step in designing brain-inspired automatic face verification algorithms.

Class representative autoencoder for low resolution multi-spectral gender classification

Gender is one of the most common attributes used to describe an individual. It is used in multiple domains such as human computer interaction, marketing, security, and demographic reports. Research has been performed to automate the task of gender recognition in constrained environment using face images, however, limited attention has been given to gender classification in unconstrained scenarios. This work attempts to address the challenging problem of gender classification in multi-spectral low resolution face images. We propose a robust Class Representative Autoencoder model, termed as AutoGen for the same. The proposed model aims to minimize the intra-class variations while maximizing the inter-class variations for the learned feature representations. Results on visible as well as near infrared spectrum data for different resolutions and multiple databases depict the efficacy of the proposed model. Comparative results with existing approaches and two commercial off-the-shelf systems further motivate the use of class representative features for classification.