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

Multimodal biometrics technology consolidates information obtained from multiple sources at sensor level, feature level, match score level, and decision level. It is used to increase robustness and provide broader population coverage for inclusion. Due to the inherent challenges involved with feature-level fusion, combining multiple evidences is attempted at score, rank, or decision level where only a minimal amount of information is preserved. In this paper, we propose the Group Sparse Representation based Classifier (GSRC) which removes the requirement for a separate feature-level fusion mechanism and integrates multi-feature representation seamlessly into classification. The performance of the proposed algorithm is evaluated on two multimodal biometric datasets. Experimental results indicate that the proposed classifier succeeds in efficiently utilizing a multi-feature representation of input data to perform accurate biometric recognition. © 2015 Elsevier B.V. All rights reserved.

World University root node

Information Fusion

Group sparse representation based classification for multi-feature multimodal biometrics

This paper focuses on extending the capabilities of relevance vector machine which is a probabilistic, sparse, and linearly parameterized classifier. It has been shown that both relevance vector machine and support vector machine have similar generalization performance but RVM requires significantly fewer relevance vectors. However, RVM has certain limitations which limits its applications in several pattern recognition problems including biometrics such as (1) slow training process, (2) difficult to train with large training samples, and (3) may not be suitable to handle large class imbalance. To address these limitations, we propose iGRVM which incorporates incremental and granular learning in RVM. The proposed classifier is evaluated in context to multimodal biometrics score classification using the NIST BSSR1, CASIA-Iris-Distance V4, and Biosecure DS2 databases. The experimental analysis illustrates that the proposed classifier can be a good alternative for biometric score classification with faster testing time. © 2015 Elsevier Ltd

Pattern Recognition

Incremental granular relevance vector machine: A case study in multimodal biometrics

In this work, we apply Transfer Learning for a Multimodal Deep learning network for fast and robust object recognition using RGB-D dataset. The ability for a network to train quickly and recognize objects robustly is very important in the field of Robotics. The Multimodal deep learning network avoids time-consuming hand-crafted features and makes use of a RGB-D architecture for robust object recognition. Our architecture has two important features. First, it makes use of both RGB and Depth information of an image to recognize it. To achieve this, our architecture has two CNN processing streams, one for RGB modality and the other for the depth modality. This enables the network to achieve higher accuracy than normal single stream RGB network. We encoded the depth image into colour image before passing it into the CNN stream. The other important feature is the speed of training and improving the accuracy further. To achieve this, we made use of Transfer learning. Firstly we trained a CNN network with 10 classes of different objects and then we transfer the parameters to RGB and depth CNN network. This enables the network to train faster and also achieve higher accuracy for a given number of epochs. © 2016 IEEE.

2016 International Conference on Advances in Computing, Communications and Informatics, ICACCI 2016

Application of transfer learning in RGB-D object recognition

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

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.

Gender classification using RGB-D videos

Handbook of Iris Recognition

Ophthalmic Disorder Menagerie and Iris Recognition

Opportunistic Routing (OR) is a new encouraging routing technique that is an efficient and enhanced routing scheme for wireless networks. It is an approach which takes a certain number of best forwarder nodes (i.e., candidate nodes) at each hop by taking the advantage of the broadcast nature of the wireless networks to reach the destination from the source node. When a lot of candidate nodes receive the package from the source node, they coordinate with each other to compute out which one node has to forward the packet toward the destination from the intermediate nodes. In our proposed approach, we deal with the node mobility means the dynamic nature of mobile nodes and a performance metric which considers the geographical location of the candidate nodes, at least one candidate node must be transfer the data packet, no candidate will receives the duplicate packet, the link delivery probability between the nodes, the number of the neighboring nodes of the candidate, and the predicted geographical position of nodes. Our simulation results show that proposed protocol improves the performance in terms of the packet delivery ratio, end-to-end delay, and expected number of data packet transmissions in terms of random waypoint mobility models. The computational complexity of the proposed scheme is in the order of O(n2). © 2016 ACM.

ACM International Conference Proceeding Series

Efficient algorithm for routing in dynamic wireless networks

Social network being one of the most disruptive innovation has gathered a huge amount of attention of the people within the last decade. The posts of the users on the social media are used by many companies in the world to find the mentality of the users, the current trend of the market and many more things. But still there is a latent potential in social network. One of the aspect that we were able to discover was of finding the relationship between the users (especially, the negative link) on the social network using the posts that the users make and the reaction of the other users towards it. The prediction of negative link can be applied in cyber-security field, to observe the aberrations in the network and further find the malicious nodes in the social network; say, if two nodes are are having a link between them even though there is no relation between them. It can also be used for improving the recommendation system in social media, as if there is some probability between the two nodes of being enemy or disliking each other then we can remove them from each other's recommendation list or could assign a lower weight to them in our recommendation algorithm. To achieve all this relationship between the nodes we first need to find whether the user is posting posts with positive emotion (like happy, excited, etc.) or negative emotion (like angry, sad, etc.) so that we can further analyze the mentality of the user and use it to recommend the people who we have previously classified with the similar personality. For that we have used the sentimental analysis which divides the users into five simple categories: Highly Positive, Positive, Neutral, Negative and Highly Negative. This research paper explains the methodologies that we have used to achieve the prediction of negative links between the nodes in the social network. © 2016 ACM.

Algorithm for prediction of links using sentiment analysis in social networks

We propose an approach for emptying of bin using a combination of Image and Range sensor. Offering a complete solution: calibration, segmentation and pose estimation, along with approachability analysis for the estimated pose. The work is novel in the sense that the objects to be picked are featureless and uniformly black in colour, hence existing approaches are not directly applicable. A key point involves optimal utilization of range data acquired from the laser scanner for 3-D segmentation using localized geometric information. This information guides segmentation of the image for better object pose estimation, used for pick-and-drop. We analytically assure the approachability of the object to avoid collision of the manipulator with the bin. Disturbance of objects caused during pick up has been modelled, which allows pickup of multiple pellets based on information from a single range scan. This eliminates the necessity of repeated scanning and data conditioning. The proposed method offers high object detection rate and pose estimation accuracy. The innovative techniques aimed at reducing the average pickup time makes it suitable for robust industrial operation. © 2016 IEEE.