Department of Computer Science & Engineering

&ldquo;IIT Jodhpur is committed to impart quality education to facilitate the creation of qualified, competent and responsible human resources to meet the emerging technological challenges of the world. It is working towards creating an equitable learning platform that is positive, accessible and effective in the face of the modern societal and scientific advancements.

Flexibility in curriculum, in all its academic programs, encompassing elements of teaching, research, creativity, innovation and entrepreneurship is the most unique feature of IIT Jodhpur. The Department of Science and Technology (DST), under the National Mission on Cyber Physical Systems, has identified IIT Jodhpur as a Technology &amp; Innovation Hub in the area of Augmented Reality and Virtual Reality. The institute has also been nominated as the coordinator for the Jodhpur City and Knowledge Cluster by the Office of Principal Scientific Adviser, Government of India.

The sprawling 852-acre IIT Jodhpur campus is a majestic tribute to the deep-rooted diverse cultural heritage of the region. The campus is an architectural masterpiece, which is slated to become an international exemplar of sustainability with net-zero energy, and advanced water and waste management strategies.&rdquo;

IIT Jodhpur

Low cost RGB-D cameras are gaining significant popularity in surveillance scenarios. While RGB images contain good quality discriminative information, depth images captured in uncontrolled environment at a distance does not provide accurate depth map. In this research, we present a learning based reconstruction and mapping algorithm to generate a feature rich representation from the RGB images. These reconstructed images are then used for face identification. The experiments performed on both IIITD RGB-D database and the challenging Kasparov database show that the proposed algorithm yields significant improvements compared to when the original depth map is used for identification. Comparison with existing state-of-the-art algorithm also demonstrates the efficacy of the proposed architecture. © 2016 IEEE.

World University root node

2016 IEEE 8th International Conference on Biometrics Theory, Applications and Systems, BTAS 2016

RGB-D face recognition via learning-based reconstruction

Ocular recognition algorithms, including iris matching, have been used in several applications including large scale national ID projects such as India's Aadaar. Deployment of large-scale biometric systems is expected to rely on using multiple devices including mobile devices to ensure widespread adoption of biometric recognition systems. Ocular images captured using mobile devices may have challenges such as uncontrolled illumination, complex background, and geometric distortions. Further, among many enrollees of large scale biometrics program, some may have ocular diseases. One of the most common ocular disease in elderly is cataract. While it is established that iris recognition may be challenging due to ocular diseases, this paper investigates periocular recognition with pre and post cataract surgery images. In this research, we present a mobile periocular database of 145 subjects1. Baseline results also include a framework that achieves over 69% rank-10 accuracy and around 24% genuine accept rate at 1% false accept rate in inter-session experiments. © 2016 IEEE.

Proceedings - International Conference on Image Processing, ICIP

Mobile periocular matching with pre-post cataract surgery

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. © 2016 IEEE.

Low rank group sparse representation based classifier for pose variation

In surveillance applications, a video can be an advantageous alternative to traditional still image face recognition. In order to extract discriminative features from a video, frame based processing is preferred; however, not all frames are suitable for face recognition. While some frames are distorted due to noise, blur, and occlusion, others might be affected by the presence of covariates such as pose, illumination, and expression. Frames affected by imaging artifacts such as noise and blur may not contain reliable facial information and may affect the recognition performance. In an ideal scenario, such frames should not be considered for feature extraction and matching. Furthermore, video contains a large amount of frames and adjacent frames contain largely redundant information and processing all the frames from a video increases the computational complexity. Instead of utilizing all the frames from a video, frame selection can be performed to determine a subset of frames which is best suited for face recognition. Several frame selection algorithms have been proposed in the literature to address these concerns. In this chapter, we discuss the role and importance of frame selection in video face recognition, provide an overview of existing techniques, present an entropy based frame selection algorithm with the results and analysis on Point-and-Shoot-Challenge which is a recent benchmark database, and also propose a new paradigm for frame selection algorithms as a path forward. © Springer International Publishing Switzerland 2016.

Advances in Face Detection and Facial Image Analysis

On frame selection for video face recognition

This study presents supervised framework for automatic recognition and retrieval of interactions (SAFARRIs), a supervised learning framework to recognise interactions such as pushing, punching, and hugging, between a pair of human performers in a video shot. The primary contribution of the study is to extend the vectors of locally aggregated descriptors (VLADs) as a compact and discriminative video encoding representation, to solve the complex class partitioning problem of recognising human interaction. An initial codebook is generated from the training set of video shots, by extracting feature descriptors around the spatiotemporal interest points computed across frames. A bag of action words is generated by encoding the first-order statistics of the visual words using VLAD. Support vector machine classifiers (1 against all) are trained using these codebooks. The authors have verified SAFARRI's accuracy for classification and retrieval (query by example). SAFARRI is free from tracking or recognition of body parts and capable of identifying the region of interaction in video shots. It gives superior retrieval and classification performances over recently proposed methods, on two publicly available human interaction datasets. © The Institution of Engineering and Technology 2016.

IET Computer Vision

Supervised framework for automatic recognition and retrieval of interaction: A framework for classification and retrieving videos with similar human interactions

Shoulder injuries are very common in sports and certain labour intensive occupations. While some injuries are minor and full recovery is within 1-2 weeks, some major injuries requires the person to consult a physiotherapist and follow an exercise plan for months for full recovery. With the advent of consumer accessible motion capture (MoCap) technologies, the task of conducting daily rehabilitation routine and evaluation which was previously done by a trained physiotherapist can be now done with computers which can be set up in home. In this paper, we propose a system for medical rehabilitation of patients suffering from shoulder injuries. We use Hidden Markov Models (HMM) for recognition and a histogram-based comparison for computing the accuracy score. The Microsoft Kinect sensor is used to obtain 3D coordinates of human joints. Important features are extracted from the skeletal coordinates which are then quantized into 16 intermediate upper-body poses. The temporal patterns of these upper-body poses are modelled by training an HMM for each exercise. Our system recognizes different exercises performed by the patient and assigns an accuracy score for each exercise carried out in a session. It intends to help the patient by keeping track of daily exercise routine, advising for improvements and maintaining records for doctor to access. © 2015 IEEE.

Proceedings of 2015 3rd International Conference on Image Information Processing, ICIIP 2015

Development of a kinect-based physical rehabilitation system

We discuss the signal tracking approach based phase estimation in digital holographic interferometry and its potential application for continuous evaluation of out-off plane thermal expansion of a metallic surface as a case study. © OSA 2016.

Optics InfoBase Conference Papers

Signal tracking approach based phase estimation for analysis of thermal expansion by digital holographic interferometry

Safe landing of small unmanned aerial vehicles (UAVs) is not an easy task due to complex external aiding devices. Likewise external piloting also involves risks of false landings. Hu's moment based vision algorithms that AIDS automatic landing of UAVs prove to be satisfying regarding speed but lack accuracy and efficiency. This paper proposes Randomized Hough transform (RHT) based vision algorithm for accurate landing of small UAVs employing an inflated bag. Uniqueness of the airbag's color and shape are well exploited for its detection from any viewing angle. Color based detection of the airbag is soon followed by Randomized Hough transform based shape detection. The accuracy of proposed method and Hu's method is tested in a series of flight trials and the results are tabulated. © 2015 IEEE.

2015 IEEE International Conference on Computer Graphics, Vision and Information Security, CGVIS 2015

Randomized Hough transform-based vision algorithm for small unmanned aerial vehicles using an airbag

Deep Learning (DL) methods extract complex set of features using architectures containing hierarchical set of layers. The features so learned have high discriminative power and thus represents the input to the network in the most efficient manner. Convolutional Neural Networks (CNN) are one of the deep learning architectures, extracts structural features with little invariance to smaller translational, scaling and other forms of distortions. In this paper, the learning capabilities of CNN's are explored towards providing improvement in rotational invariance to its architecture. We propose a new CNN architecture with an additional layer formed by differential excitation against distance for the improvement of rotational invariance and is called as RICNN. Moreover, we show that the proposed method is giving superior performance towards invariance to rotations against the original CNN architecture (training samples with different orientations are not considered) without disturbing the invariance to smaller translational, scaling and other forms of distortions. Different profiles like training time, testing time and accuracies are evaluated at different percentages of training data for comparing the performance of the proposed configuration with original configuration. © 2016 ACM.