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

Modern urban areas constitute of rich mix of mobile devices with capability to be continuously connected to social networking infrastructure. This constitutes an ecosystem of urban pervasive devices that is large, decentralized and dynamic. Such an emerging urban pervasive computing scenario cannot be managed by traditional approaches of coordination and require innovative mechanisms such as nature-inspired approach of situated selforganization. In our previous work we had proposed a novel unified model of bio-inspired self-organization mechanism for coordination in urban pervasive environment. In this paper we propose a formal framework of bio-inspired model proposed earlier, including details of agent model, formal algorithm for distributed coordination and theoretical analysis of the algorithm. We also present simulation results to demonstrate adaptability, robustness and scalability of proposed algorithm. Copyright 2015 ACM.

World University root node

ACM International Conference Proceeding Series

Framework for analysis of bio-inspired self-organization in urban pervasive system

With the availability of large collection of document images in Indian languages, image based retrieval has gained popularity. The performance of such systems is effected by the presence of degraded and noisy images. Moreover, Optical character recognition systems for Indian scripts are not yet robust, leading to noisy OCR'ed text. Information retrieval system designed using inputs from both modalities (image features and OCR based recognition data) will lead to better retrieval performance in contrast to usage of individual modality. In this paper we present a indexing methodology that uses multiple kernel learning to combine features from different modalities by joint optimization of search time and accuracy. The evaluation of the proposed methodology is demonstrated on document images of Bangla and Devanagari script. © 2015 IEEE.

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

Document indexing framework for retrieval of degraded document images

The immune system in homo sapiens protects the body against diseases by identifying and attacking foreign pathogens. However, when the system misidentifies native cells as threats, it results in an auto-immune response. The auto-antibodies generated during this phenomenon may be identified through the indirect immunofluorescence test. An important constituent process of this test is the automated identification of antigen patterns in the cell images, which is the focus of this research. We perform a detailed literature review and present a framework to automate the identification of antigen patterns. The efficacy of the framework, demonstrated on the MIVIA ICPR 2012 HEp-2 Cell Contest and SNP HEp-2 Cell datasets, suggests that the algorithm is comparable with the state-of-the-art approaches. © 2013 IEEE.

Fulltext

IEEE Access

Revisiting HEp-2 Cell Image Classification

The approach of applying a cascaded network consisting of radial basis function nodes and least square error minimization block to Compressed Sensing for recovery of sparse signals is analyzed in this paper to improve the computation time and convergence of an existing ANN based recovery algorithm. The proposed radial basis function-least square error projection cascade network for sparse signal Recovery (RASR) utilizes the smoothed L0 norm optimization, L2 least square error projection and feedback network model to improve the signal recovery performance over the existing CSIANN algorithm. The use of ANN architecture in the recovery algorithm gives a marginal reduction in computational time compared to an existing L0 relaxation based algorithm SL0. The simulation results and experimental evaluation of the algorithm performance are presented here. © 2014 Elsevier Ltd.

Neural Networks

RBF-network based sparse signal recovery algorithm for compressed sensing reconstruction

Biometrics, the science of verifying the identity of individuals, is increasingly being used in several applications such as assisting law enforcement agencies to control crime and fraud. Existing techniques are unable to provide significant levels of accuracy in uncontrolled noisy environments. Further, scalability is another challenge due to variations in data distribution with changing conditions. This paper presents an adaptive context switching algorithm coupled with online learning to address both these challenges. The proposed framework, termed as QFuse, uses the quality of input images to dynamically select the best biometric matcher or fusion algorithm to verify the identity of an individual. The proposed algorithm continuously updates the selection process using online learning to address the scalability and accommodate the variations in data distribution. The results on the WVU multimodal database and a large real world multimodal database obtained from a law enforcement agency show the efficacy of the proposed framework. © 2015 Elsevier Ltd. All rights reserved.

Pattern Recognition

QFuse: Online learning framework for adaptive biometric system

Biometric Quality : From Assessment to Multibiometrics

This paper attempts to find an optimization algorithm to reduce number of iterations required for a node to be searched in a MultiCast Tee network. After effectively searching the node, it applies this technique in cloud computing, more exactly, cloud information security so that data is safely transferred from one user to another, without any hindrance. The basic idea to incorporate the concept of MultiCast Tree is because it always supports reliable transmission of information, if by any chance, there is a link failure, it does not reduce the availability of resources, nor does it increase any delay in transmission of information, and at the same time minimizes work load. Thus, we can effectively use it in cloud computing, which is nothing but provision of resources to a pool of users through some kind of an interface, for example, Internet. While monitoring the distributed foundation establishment of cloud computing, it becomes extremely important to take into consideration the security of the information provided by users. If we use a vast number of nodes or links, it becomes practically impossible to trace the reliability of transmission, and which might result in important information getting lost. Hence to avoid such a consequence, it becomes necessary to optimize the number of these links, so that it becomes easier to search them in a minimum amount of time. Our main attempt has been to optimize these links and effectively use it in a communication network which has characteristics of a MultiCast Tree incorporated in it. This not only helps in efficient use of cloud computing system, but also ensures users that their data is in safe hands. © 2015 IEEE.

International Conference on Electrical, Electronics, Signals, Communication and Optimization, EESCO 2015

Application of MultiCast Tree concept to cloud security with optimization algorithm for node search technique

Vehicular traffic monitoring and control using through road sensor network is challenging due to a continuous data streaming over the resource constrained sensor devices. The delay sensitivity and reliability of the large volume of application data as well as the scarcity of sensor resources demand efficient designing of data collection protocol. In this Chapter, a novel tree-based data gathering scheme has been proposed, exploiting the strip-like structure of the road network. An efficient scheduling mechanism is implemented to assure both the coverage and the critical power savings of the sensor nodes. The network connectivity is guaranteed throughout by the proposed tree maintenance module that handles the dynamics of the network as a result of sensor node joining and leaving events. An application message controller has been designed that works cooperatively with the tree management module, and handles continuous streaming of the application data to ensure no loss or redundancy in data delivery. The performance of the proposed scheme is evaluated using the simulation results and compared with other approaches for large data collection in sensor network. © 2015 Springer International Publishing Switzerland.

Modeling and Optimization in Science and Technologies

Sensory Data Gathering for Road Traffic Monitoring: Energy Efficiency, Reliability, and Fault Tolerance

This paper presents a novel flexible architecture for 3DTV based on multiple uncalibrated cameras. The proposed signal representation improves the interactivity of dense point-based methods, making them appropriate for modeling the scene semantics and free-viewpoint 3DTV applications. The main concern is to address the shortcomings of depth image-based 3D video systems for free-viewpoint visualization, and to provide an efficient implementation of the rendering part which is computationally intensive as well potentially determine the view quality. Novel rendering algorithms are added that specifically aim at solving the rendering artifacts, and sampling issues encountered in wide baseline extensions and arbitrary camera movements. To optimize the process, a "selective" warping technique is proposed that takes the advantage of temporal coherence to reduce the computational overhead. Performance is illustrated on challenging videos to prove the suitability and flexibility of the architecture for advanced 3DTV systems. © 2013 Elsevier Inc. All rights reserved.

Journal of Visual Communication and Image Representation

A flexible architecture for multi-view 3DTV based on uncalibrated cameras

This paper presents a novel low-cost hybrid Kinect-variety based content generation scheme for 3DTV displays. The integrated framework constructs an efficient consistent image-space parameterization of 3D scene structure using only sparse depth information of few reference scene points. Under full-perspective camera model, the enforced Euclidean constraints simplify the synthesis of high quality novel multiview content for distinct camera motions. The algorithm does not rely on complete precise scene geometry information, and are unaffected by scene complex geometric properties, unconstrained environmental variations and illumination conditions. It, therefore, performs fairly well under a wider set of operation condition where the 3D range sensors fail or reliability of depth-based algorithms are suspect. The robust integration of vision algorithm and visual sensing scheme complement each other's shortcomings. It opens new opportunities for envisioning vision-sensing applications in uncontrolled environments. We demonstrate that proposed robust integration provides guarantees on the completeness and consistency of the algorithm. This leads to improved reliability on an extensive set of experimental results. © 2014 IEEE.