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

Variations in pose, expression, illumination, aging and disguise are considered as major challenges in face recognition and several techniques have been proposed to address these challenges. Plastic surgery, on the other hand, is considered as an arduous research issue; however, it has not yet been studied either theoretically or experimentally. This paper focuses on analyzing the effect of plastic surgery in face recognition algorithms. The preliminary study provides an experimental and analytical comparison of face recognition algorithms on a plastic surgery database of 506 individuals. The experimental results indicate that existing face recognition algorithms perform poorly when matching pre and post surgery face images. The results also suggest that it is imperative for future face recognition systems to be able to address this important issue and hence there is a need for more research in this important area. © 2009 IEEE.

World University root node

2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009

Effect of plastic surgery on face recognition: a preliminary study

Medical image fusion has revolutionized medical analysis by improving the precision and performance of computer assisted diagnosis. In this research, a fusion algorithm is proposed to combine pairs of multispectral magnetic resonance imaging such as T1, T2 and Proton Density brain images. The proposed algorithm utilizes different features of Redundant Discrete Wavelet Transform, mutual information based non-linear registration and entropy information\ to improve performance. Experiments on the BrainWeb database show that the proposed fusion algorithm preserves both edge and component information, and provides improved performance compared to existing Discrete Wavelet Transform based fusion algorithms. © 2009 IEEE.

Proceedings of the 7th International Conference on Advances in Pattern Recognition, ICAPR 2009

Multimodal medical image fusion using Redundant Discrete Wavelet Transform

Field experiments were conducted during 2003-04 to monitor the soil organic carbon and the nutrient uptake by pearl millet (Pennisetum glaucum L) under different combinations of irrigation water and nitrogenous fertilizer treatments In both the years, days of maturity increased with increase in nitrogen doses in irrigated plots Application of nitrogen induced higher leaf area index, but the difference in 80 and 120 kg N/ha levels were found to be significant The increase in biomass accumulation was faster in irrigated plots than the rainfed and it increased with N treatment The 1000-grain weight increased significantly with successive N levels, but the increment was pronounced only up to 40 kg N/ha in rainfed and up to 120 kg N/ha in irrigated treatment Grain yield varied significantly with nitrogen application rates as compared to those plots that received no N Mean yield in irrigated plots was also significantly higher than the unirrigatd plots Nitrogen content in pearl millet grain was more in irrigated plots' and also increased with N doses but no such relations could be established with irrigation as well as nitrogen doses for P and K, while N, P and K content in straw did not show any statistical relationship with either irrigation or fertilizer treatments During both the rainy (kharif) seasons 2003 and 2004, the soil organic carbon increased at harvest in comparison to that at sowing of the crop, in surface (0-15 cm) and subsurface (15-30 cm) layers; whereas no change or reduction in soil organic carbon content was found in the deeper (30-45 and 45-60 cm) layers The increments were more in irrigated plots (I 1), as compared to rainfed plots (I 0), possibly due to more use efficiency of the fertilizers.

Indian Journal of Agricultural Sciences

Soil organic carbon and nutrient uptake vis-a-vis growth and yield of pearl millet (Pennisetum glaucum) as influenced by water and nitrogen in Typic Haplustept soil

We propose an efficient skin region segmentation methodology using low complexity fuzzy decision tree constructed over B, G, R colour space. Skin and nonskin training dataset has been generated by using various skin textures obtained from face images of diversity of age, gender, and race people and nonskin pixels obtained from arbitrary thousands of random sampling of nonskin textures. Compact fuzzy model with very few numbers of rules allow to raster scan consumer photographs and classify each pixel as skin or nonskin for various face and human detection applications for embedded platforms.

Proceedings of INDICON 2009 - An IEEE India Council Conference

Efficient skin region segmentation using low complexity fuzzy decision tree model

This paper presents a 3-level RDWT biometric watermarking algorithm to embed the voice biometric MFC coefficients in a color face image of the same individual for increased robustness, security and accuracy. Phase congruency model is used to compute the embedding locations which preserves the facial features from being watermarked and ensures that the face recognition accuracy is not compromised. The proposed watermarking algorithm uses adaptive user-specific watermarking parameters for improved performance. Using face, voice and multimodal recognition algorithms, and statistical evaluation, we show that the proposed RDWT watermarking algorithm is robust to different frequency and geometric attacks, and provides the multimodal biometric verification accuracy of 94%. © 2007 Elsevier B.V. All rights reserved.

Image and Vision Computing

Feature based RDWT watermarking for multimodal biometric system

In law enforcement applications such as surveillance and forensics, video is often presented as evidence. It is therefore of paramount importance to establish the authenticity and reliability of the video data. This paper presents an intelligent video authentication algorithm which integrates learning based Support Vector Machine classification with Singular Value Decomposition watermarking. During video capture and storage, intrinsic local correlation information is extracted from the frames and embedded in the frames at local levels. Tamper detection and classification is performed using the inherent video information and embedded correlation information. The proposed algorithm is independent of the choice of watermark and does not require any key to store. Further, it is robust to global tampering such as frame addition and removal, local attacks such as object alteration and can differentiate between acceptable operations and malicious tampering. Experiments are performed on an extensive database which contains non-tampered videos and videos with several types of tampering. The results show that the proposed algorithm outperforms existing video authentication algorithms. © 2008 Springer Science+Business Media, LLC.

Telecommunication Systems

Integrating SVM classification with SVD watermarking for intelligent video authentication

Encyclopedia of Biometrics Springer Science+ Business Media, LLC 2009

In this work, we study several properties of the SHA-2 design which have been utilized in recent collision attacks against reduced round SHA-2. Small modifications to the SHA-2 design are suggested to thwart these attacks. The modified round function provides the same resistance to linearization attacks as the original SHA-2 round function, but, provides better resistance to non-linear attacks. Our next contribution is to introduce the general idea of "multiple feed-forward" for the construction of cryptographic hash functions. This can provide increased resistance to the Chabaud-Joux type "perturbation-correction" collision attacks. The idea of feed-forward is taken further by introducing the idea of feed-forward across message blocks leading to resistance against generic multi-collision attacks. The net effect of the suggested changes to the SHA-2 design has insignificant impact on the efficiency of computing the digest. Copyright 2009 ACM.

Proceedings of the 4th International Symposium on ACM Symposium on Information, Computer and Communications Security, ASIACCS'09

A new hash family obtained by modifying the SHA-2 family

In this paper we propose a novel method for object tracking in video images. The method is based on image segmentation and pattern matching. All moving and still objects in video images can be detected accurately with the help of efficient image segmentation techniques. We propose a hybrid algorithm for image segmentation using the notion of Particle Swarm Optimization (PSO) and Fuzzy-C-Means (FCM) clustering techniques. The results obtained using segmentation of successive frames are exploited for pattern matching in a simple feature space. As a consequence, multiple moving and still objects in video images are tracked simultaneously. We perform simulation experiments on object tracking to validate the efficiency of our proposed algorithm. The algorithm outperforms the existing algorithm in context of accuracy and time complexity.

Object tracking in video images using hybrid segmentation method and pattern matching

We present a model-guided segmentation and document layout extraction scheme based on hierarchical Conditional Random Fields (CRFs, hereafter). Common methods to classify a pixel of a document image into classes - text, background and image - are often noisy, and error-prone, often requiring post-processing through heuristic methods. The input to the system is a pixel-wise classification based on the output of a Fisher classifier based on the output of a set of Globally Matched Wavelet (GMW) Filters. The system extracts features which encode contextual information and spatial configurations of a given document image, and learns relations between these layout entities using hierarchical CRFs. The hierarchical CRF enables learning at various levels - 1. local features for text, background and image areas; 2. contextual features for further classifying region blocks - title, author block, heading, paragraph, etc.; and 3. probabilistic layout model for encoding global relations between the above blocks for a particular class of documents. Although the work has been motivated for an automated layout analyser and machine translator for technical papers, it can also be used for other applications such as search, indexing and information retrieval. © 2009 Springer-Verlag Berlin Heidelberg.