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

This paper addresses the problem of local change detection in an underwater environment. A spatio-contextual framework based frame difference algorithm has been proposed, which uses five consecutive video frames to extract the object. This is a two-stage method. In the first stage, frame differencing is carried out using the spatio-contextual framework, whereas in the second stage a knowledge-based analysis is proposed to detect the moving objects region. The results obtained using the proposed method is compared with the existing background subtraction methods and found to be a far better approach. The performance of the proposed scheme is evaluated by the help of three evaluation measures, such as Precision, Recall, and F-measure. © 2017 IEEE.

World University root node

2017 4th International Conference on Image Information Processing, ICIIP 2017

A novel five-frame difference scheme for local change detection in underwater video

Classical OCRs based on isolated character (symbol) recognition have been the fundamental way of generating textual representations, particularly for Indian scripts, until the time transcription-based approaches gained momentum. Though the former approaches have been criticized as prone to failures, their accuracy has nevertheless been fairly decent in comparison with the newer transcription-based approaches. Analysis of isolated character recognition OCRs for Hindi and Bangla revealed most errors were generated in converting the output of the classifier to valid Unicode sequences, i.e., script grammar generation. Linguistic rules to generate scripts are inadequately integrated, thus resulting in a rigid Unicode generation scheme which is cumbersome to understand and error prone in adapting to new Indian scripts. In this paper we propose a machine learning-based classifier symbols to Unicode generation scheme which outperforms the existing generation scheme and improves accuracy for Devanagari and Bangla scripts. © 2017 IEEE.

Proceedings of the International Conference on Document Analysis and Recognition, ICDAR

Improving Classical OCRs for Brahmic Scripts Using Script Grammar Learning

Biometrics based user authentication for mobile devices is now popular with face and fingerprints being the primary modalities. Fingerphoto, an image of a person's finger captured using inbuilt smartphone camera, based user authentication is an attractive and cost-effective alternative. Existing research focuses on constrained or semi-constrained environment; whereas, challenges such as user cooperation, number of fingers, background, orientation, and deformation are important to address before fingerphoto authentication becomes usable. This paper presents the first publicly available unconstrained fingerphoto database, termed as UNconstrained FIngerphoTo (UNFIT) database, which contains fingerphoto images acquired in unconstrained environments. We also present baseline results with deep learning based segmentation as well as CompCode and ResNet50 representation based matching approaches. We assert that the availability of the proposed database can encourage research in this important domain. © 2018 IEEE.

IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops

Unconstrained fingerphoto database

Enhancing low resolution images via super-resolution or synthesis algorithms for cross-resolution face recognition has been well studied. Several image processing and machine learning paradigms have been explored for addressing the same. In this research, we propose Synthesis via Hierarchical Sparse Representation (SHSR) algorithm for synthesizing a high resolution face image from a low resolution input image. The proposed algorithm learns multilevel sparse representation for both high and low resolution gallery images, along with identity aware dictionaries and a transformation function between the two representations for face identification scenarios. With low resolution test data as input, a high resolution test image is synthesized using the identity aware dictionaries and transformation, which is then used for face recognition. The performance of the proposed SHSR algorithm is evaluated on four datasets, including one real world dataset. Experimental results and comparison with seven existing algorithms demonstrate the efficacy of the proposed algorithm in terms of both face identification and image quality measures. © 2018 IEEE.

Identity aware synthesis for cross resolution face recognition

Deep learning models are widely used for various purposes such as face recognition and speech recognition. However, researchers have shown that these models are vulnerable to adversarial attacks. These attacks compute perturbations to generate images that decrease the performance of deep learning models. In this research, we have developed a toolbox, termed as SmartBox, for benchmarking the performance of adversarial attack detection and mitigation algorithms against face recognition. SmartBox is a python based toolbox which provides an open source implementation of adversarial detection and mitigation algorithms. In this research, Extended Yale Face Database B has been used for generating adversarial examples using various attack algorithms such as DeepFool, Gradient methods, Elastic-Net, and L2 attack. SmartBox provides a platform to evaluate newer attacks, detection models, and mitigation approaches on a common face recognition benchmark. To assist the research community, the code of SmartBox is made available11http://iab-rubric.org/resources/SmartBox.html. © 2018 IEEE.

2018 IEEE 9th International Conference on Biometrics Theory, Applications and Systems, BTAS 2018

SmartBox: Benchmarking adversarial detection and mitigation algorithms for face recognition

Plastic surgery and disguise variations are two of the most challenging co-variates of face recognition. The stateof-art deep learning models are not sufficiently successful due to the availability of limited training samples. In this paper, a novel framework is proposed which transfers fundamental visual features learnt from a generic image dataset to supplement a supervised face recognition model. The proposed algorithm combines off-the-shelf supervised classifier and a generic, task independent network which encodes information related to basic visual cues such as color, shape, and texture. Experiments are performed on IIITD plastic surgery face dataset and Disguised Faces in the Wild (DFW) dataset. Results showcase that the proposed algorithm achieves state of the art results on both the datasets. Specifically on the DFW database, the proposed algorithm yields over 87% verification accuracy at 1% false accept rate which is 53.8% better than baseline results com- puted using VGG Face. © 2018 IEEE.

On matching faces with alterations due to plastic surgery and disguise

The M-channel transmultiplexer's for geo communication satellite are design and simulation in this paper. The mathematical description has been discussed in detail. Modified Discrete Fourier Transform(MDFT) and andcosined Discrete Transform(DCT) have chosen for advanced communication satellite. MDFT and DCT provide perfect reconstruction. The theory of filter bank satisfying the perfect reconstruction using proto FIR filter of length N= 2∗M∗m+1; where M = No. of channel. A new set of objective functions has been derived to satisfy the transmultiplexer's requirements based on these approaches. This work is done under the technology development program of ISRO. In this paper a comparison of the MDFT and DCT approaches are also described. © 2018 IEEE.

2018 3rd IEEE International Conference on Recent Trends in Electronics, Information and Communication Technology, RTEICT 2018 - Proceedings

Design and comparison of lossless polyphase decomposition using filter bank for onboard digital signal processing payload

Estimation of phase from the complex interference field has become an emerging area of research for last few decades. The phase values obtained by using arctan function are limited to the interval (-π, π]. Such phase map is known as wrapped phase. The unwrapping process, which produces continuous phase map from the wrapped phase, becomes tedious in presence of noise. In this paper, we propose a preprocessing technique that removes the noise from the interference field, thereby improving the performance of naive unwrapping algorithms. For de-noising of the complex field, real part and imaginary parts of the field are processed separately. Real-valued images (real and imaginary parts) are processed using non-local means filter with non-Euclidian distance measure. The de-noised real and imaginary parts are then combined to form a clean interference field. MATLAB’s unwrap function is used as unwrapping algorithm to get the continuous phase from the cleaned interference field. Comparison with the Frost’s filter validates the applicability of proposed approach for processing the noisy interference field. © 2018, Springer Nature Singapore Pte Ltd.

Advances in Intelligent Systems and Computing

Effective denoising with non-local means filter for reliable unwrapping of digital holographic interferometric fringes

We present an improved clustering based, unsu-pervised anomalous trajectory detection algorithm for crowded scenes. The proposed work is based on four major steps, namely, extraction of trajectories from crowded scene video, extraction of several features from these trajectories, independent mean-shift clustering and anomaly detection. First, the trajectories of all moving objects in a crowd are extracted using a multi feature video object tracker. These trajectories are then transformed into a set of feature spaces. Mean shift clustering is applied on these feature matrices to obtain distinct clusters, while a Shannon Entropy based anomaly detector identifies corresponding anomalies. In the final step, a voting mechanism identifies the trajectories that exhibit anomalous characteristics. The algorithm is tested on crowd scene videos from datasets. The videos represent various possible crowd scenes with different motion patterns and the method performs well to detect the expected anomalous trajectories from the scene. © 2018 IEEE.

2018 13th International Conference on Industrial and Information Systems, ICIIS 2018 - Proceedings

Unsupervised Anomalous Trajectory Detection for Crowded Scenes

There is a growing demand for high speed error control decoders with improved BER performance in digital communication systems. Turbo codes with its excellent error correcting performance finds wide usage in wireless communication systems. Turbo decoding architecture designs that improve the speed of decoding with acceptable performance is facilitated by efficient and high speed design approaches for the component Max-log-MAP decoders. This paper deals with the design of an efficient high speed Max-log-MAP decoder. High speed operation is achieved by the use of sliding window technique that overcomes the limitation of long decoding delays and improved performance in high SNR regions is obtained by the use of multiple computation units in parallel. This results in an improved architecture that achieves lower latency together with an improved performance. This is significant in applications including mobile communication and wireless sensor networks. The proposed work is implemented in Nexys4 DDR Artix-7 FPGA board and the results are discussed. © 2018 IEEE.