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

World University root node

Information Fusion

Special issue on information fusion in biometrics

In various pattern classification problems, semi-supervised discriminant analysis has shown its effectiveness in utilizing unlabeled data to yield better performance than linear discriminant analysis. However, many of these semi-supervised classifiers operate in batch-mode and do not allow to incrementally update the existing model, which is one of the major limitations. This paper presents an incremental semi-supervised discriminant analysis algorithm, which utilizes the unlabeled data for enabling incremental learning. The major contributions of this research are (1) utilizing large unlabeled training set to estimate the total scatter matrix, (2) incremental learning approach that requires updating only the between-class scatter matrix and not the total scatter matrix, and (3) utilizing manifold regularization for robust estimation of total variability and sufficient spanning set representation for incremental learning. Using face recognition as the case study, evaluation is performed on the CMU-PIE, CMU-MultiPIE, and NIR-VIS-2.0 datasets. The experimental results show that the incremental model is consistent with the batch counterpart and reduces the training time significantly. © 2015 Elsevier Ltd. All rights reserved.

Pattern Recognition

On incremental semi-supervised discriminant analysis

Fulltext

IEEE Access

Editorial: IEEE access special section editorial: Applying four D's of machine learning to advance biometrics

This paper presents an efficient combination of two well-known tracking algorithms, Tracking-Learning-Detection (TLD) and Compressive Tracking (CT) to devise an algorithm which takes advantages of both and outperforms them on their short-ends by virtue of other. TLD fails in cases including full out-of-plane rotation, fast motion and articulated object tracking. While CT fails in resuming tracking once the object leaves the frame and comes back. We propose a combining algorithm mentioned as Algorithm 1, which robustly handles all the tracking challenges. Different thresholds are set which can be varied to weigh each component as required. The proposed algorithm is tested on different test sequences involving challenging tracking scenarios such as fast motion and their success rates are calculated in Table I. The proposed algorithm works favourably against both algorithms in terms of robustness and success rate. © 2015 IEEE.

2015 5th National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics, NCVPRIPG 2015

Integrated algorithm for different tracking challenges

In this paper, we propose a particle-filter-based technique for the analysis of a reconstructed interference field. The particle filter and its variants are well proven as tracking filters in non-Gaussian and nonlinear situations. We propose to apply the particle filter for direct estimation of phase and its derivatives from digital holographic interferometric fringes via a signal-tracking approach on a Taylor series expanded state model and a polarto-Cartesian-conversion-based measurement model. Computation of sample weights through non-Gaussian likelihood forms the major contribution of the proposed particle-filter-based approach compared to the existing unscented-Kalman-filter-based approach. It is observed that the proposed approach is highly robust to noise and outperforms the state-of-the-art especially at very low signal-to-noise ratios (i.e., especially in the range of -5 to 20 dB). The proposed approach, to the best of our knowledge, is the only method available for phase estimation from severely noisy fringe patterns even when the underlying phase pattern is rapidly varying and has a larger dynamic range. Simulation results and experimental data demonstrate the fact that the proposed approach is a better choice for direct phase estimation. © 2016 Optical Society of America.

Journal of the Optical Society of America A: Optics and Image Science, and Vision

Particle-filter-based phase estimation in digital holographic interferometry

Though visual object tracking algorithms are capable of handling various challenging scenarios individually, still none of them is robust enough to handle all the challenges simultaneously. This paper aims at proposing a novel robust tracking algorithm by elegantly fusing the frame level detection strategy of Tracking Learning & Detection (TLD) with systematic model update strategy of Kernelized Correlation Filter tracker (KCF). The motivation behind the selection of trackers is their complementary nature in handling tracking challenges. The proposed algorithm efficiently combines the two tracking algorithms based on conservative correspondence measure with strategic model updates, which takes advantages of both and outperforms them on their short-ends by the virtue of other. The proposed fusion approach is quite general and any complimentary tracker (not just KCF) can be fused with TLD to leverage the best performance. Extensive evaluation of the proposed method based on different metrics is carried out on the datasets ALOV300++, Online Tracking Benchmark (OTB) and Visual Object Tracking (VOT2015) and demonstrated its superiority in terms of robustness and success rate by comparing with state-of-the-art trackers. © 2016 ACM.

ACM International Conference Proceeding Series

Complementary tracker's fusion for robust visual tracking

Face recognition algorithms have been extensively researched for the last 3 decades or so. Even after years of research, the algorithms developed achieve practical success only under controlled environments. Their performance usually takes a dip under unconstrained scene conditions like the presence of background clutter, non-uniform illumination etc. This paper explores the contrast in performance of standard recognition algorithms under controlled and uncontrolled environments. It proposes a way to combine 3 subspace learning algorithms, namely Eigenfaces (1DPCA), 2 dimensional Principal Component Analysis (2DPCA) and Row Column 2DPCA (RC2DPCA) with a color-based segmentation approach in order to boost the recognition rates under unconstrained scene conditions. A series of steps are performed that extract all possible facial regions from an image, following which the algorithm segregates the largest candidate for a probable face, and puts a bounding box on the blob in order to isolate only the face. It was found that the proposed algorithms, formed by the combination of such segmentationmethods obtain a higher level of accuracy than the standard recognition techniques. Moreover, it serves as a general framework wherein much more robust recognition techniques could be combined to achieve boosted accuracies. © Springer International Publishing Switzerland 2016.

Advances in Intelligent Systems and Computing

Enhancing face recognition under unconstrained background clutter using color based segmentation

We discuss the signal tracking approach based phase estimation in digital holographic interferometry and its potential application for continuous evaluation of out-offplane 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

Over the years, significant research has been undertaken to improve the performance of face recognition in the presence of covariates such as variations in pose, illumination, expressions, aging, and use of disguises. This paper highlights the effect of illicit drug abuse on facial features. An Illicit Drug Abuse Face (IDAF) database of 105 subjects has been created to study the performance on two commercial face recognition systems and popular face recognition algorithms. The experimental results show the decreased performance of current face recognition algorithms on drug abuse face images. This paper also proposes projective Dictionary learning based illicit Drug Abuse face Classification (DDAC) framework to effectively detect and separate faces affected by drug abuse from normal faces. This important pre-processing step stimulates researchers to develop a new class of face recognition algorithms specifically designed to improve the face recognition performance on faces affected by drug abuse. The highest classification accuracy of 88.81% is observed to detect such faces by the proposed DDAC framework on a combined database of illicit drug abuse and regular faces. © 2016 IEEE.

2016 IEEE Winter Conference on Applications of Computer Vision, WACV 2016

Effect of illicit drug abuse on face recognition

In this work, we revisit the security analysis of hashing modes instantiated with AES-128. We use biclique cryptanalysis as the basis for our evaluation. In Asiacrypt’11, Bogdanov et al. had proposed biclique technique for key recovery attacks on full AES-128. Further, they had shown application of this technique to find preimage for compression function instantiated with AES-128 with a complexity of 2125. 56. However, this preimage attack on compression function cannot be directly converted to preimage attack on hash function. This is due to the fact that the initialization vector (IV) is a publically known constant in the hash function settings and the attacker is not allowed to change it, whereas the compression function attack using bicliques introduced differences in the chaining variable. We extend the application of biclique technique to the domain of hash functions and demonstrate second preimage attack on all 12 PGV modes. The complexities of finding second preimages in our analysis differ based on the PGV construction chosen-the lowest being 2126.3 and the highest requiring 2126.6 compression function calls. We implement C programs to find the best biclique trails (that guarantee the lowest time complexity possible) and calculate the above mentioned values accordingly. Our security analysis requires only 2 message blocks and works on full 10 rounds of AES-128 for all 12 PGV modes. This improves upon the previous best result on AES-128 based hash functions by Sasaki at FSE’11 where the maximum number of rounds attacked is 7. Though our results do not significantly decrease the attack complexity factor as compared to brute force but they highlight the actual security margin provided by these constructions against second preimage attack. © Springer International Publishing Switzerland 2016.