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 focuses on decoding the process of face verification in the human brain using fMRI responses. 2400 fMRI responses are collected from different participants while they perform face verification on genuine and imposter stimuli face pairs. The first part of the paper analyzes the responses covering both cognitive and fMRI neuro-imaging results. With an average verification accuracy of 64.79% by human participants, the results of the cognitive analysis depict that the performance of female participants is significantly higher than the male participants with respect to imposter pairs. The results of the neuro-imaging analysis identifies regions of the brain such as the left fusiform gyrus, caudate nucleus, and superior frontal gyrus that are activated when participants perform face verification tasks. The second part of the paper proposes a novel two-level fMRI dictionary learning approach to predict if the stimuli observed is genuine or imposter using the brain activation data for selected regions. A comparative analysis with existing machine learning techniques illustrates that the proposed approach yields at least 4.5% higher classification accuracy than other algorithms. It is envisioned that the result of this study is the first step in designing brain-inspired automatic face verification algorithms. © 2017 IEEE.

World University root node

Proceedings of the International Joint Conference on Neural Networks

Region-specific fMRI dictionary for decoding face verification in humans

The growth of online services has resulted in a great need for tools to secure systems from would-be attackers without compromising the user experience. CAPTCHAs (Completely Automated Public Turing Tests to Tell Computers and Humans Apart) are one tool for this purpose, but their popular text-based form has been rendered insecure by improvements in character recognition technology. In this paper, we propose a novel imagebased CAPTCHA which employs object recognition as its test. Inspired by the negative selection approach in biological immune systems, an innovative two-phase filtering algorithm is proposed which ensures that the CAPTCHA is resilient to automated attack while remaining easy for human users to solve. In extensive testing involving over 3,000 participants, the proposed aiCAPTCHA achieved a 92.0% human success rate. © 2017 IEEE.

Proceedings - 2017 IEEE Symposium on Security and Privacy Workshops, SPW 2017

Attack-resistant aiCAPTCHA using a negative selection artificial immune System

Matching facial sketches to digital face images has widespread application in law enforcement scenarios. Recent advancements in technology have led to the availability of sketch generation tools, minimizing the requirement of a sketch artist. While these sketches have helped in manual authentication, matching composite sketches with digital mugshot photos automatically show high modality gap. This research aims to address the task of matching a composite face sketch image to digital images by proposing a transfer learning based evolutionary algorithm. A new feature descriptor, Histogram of Image Moments, has also been presented for encoding features across modalities. Moreover, IIITD Composite Face Sketch Database of 150 subjects is presented to fill the gap due to limited availability of databases in this problem domain. Experimental evaluation and analysis on the proposed dataset show the effectiveness of the transfer learning approach for performing cross-modality recognition. © 2017 IEEE.

IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops

Transfer Learning Based Evolutionary Algorithm for Composite Face Sketch Recognition

Classification is an important pattern recognition paradigm with a multitude of applications in popular research problems. Utilizing multiple data representations to improve the accuracy of classification has been explored in literature. However, approaches such as combining classifiers using majority voting and score level fusion do not utilize the underlying structure of the data which is available at the representation stage itself. In this paper, we propose a kernelization based extension to the group sparse representation classifier which can utilize multiple representations of input data to improve classification performance. By using a kernel, these representations are processed in a higher dimensional space where they are more separable, without substantially increasing computational costs. The proposed algorithm selects the ideal kernel to use along with its parameters automatically as part of the training process. We evaluate the proposed algorithm on three challenging biometric problems namely, cross distance face recognition, RGB-D face recognition, and multimodal biometrics to showcase its efficacy. Experimentally, we observe that the proposed algorithm can efficiently combine multiple data representations to further improve classification performance. © 2017 IEEE.

Kernel group sparse representation based classifier for multimodal biometrics

Face sketch to digital image matching is an important challenge of face recognition that involves matching across different domains. Current research efforts have primarily focused on extracting domain invariant representations or learning a mapping from one domain to the other. In this research, we propose a novel transform learning based approach termed as DeepTransformer, which learns a transformation and mapping function between the features of two domains. The proposed formulation is independent of the input information and can be applied with any existing learned or hand-crafted feature. Since the mapping function is directional in nature, we propose two variants of DeepTransformer: (i) semi-coupled and (ii) symmetrically-coupled deep transform learning. This research also uses a novel IIIT-D Composite Sketch with Age (CSA) variations database which contains sketch images of 150 subjects along with age-separated digital photos. The performance of the proposed models is evaluated on a novel application of sketch-to-sketch matching, along with sketch-to-digital photo matching. Experimental results demonstrate the robustness of the proposed models in comparison to existing state-of-the-art sketch matching algorithms and a commercial face recognition system. © 2017 IEEE.

Proceedings of the IEEE International Conference on Computer Vision

Face Sketch Matching via Coupled Deep Transform Learning

Latent fingerprints are important evidences used by law enforcement agencies. However, current state-of-the-art for automatic latent fingerprint recognition is not as reliable as live-scan fingerprints and advancements are required in every step of the recognition pipeline. This research focuses on automatically segmenting latent fingerprints to distinguish between ridge and non-ridge patterns. There are three major contributions of this research: (i) a machine learning algorithm for combining five different categories of features for automatic latent fingerprint segmentation, (ii) a feature selection technique using modified RELIEF formulation for analyzing the influence of multiple category features on latent fingerprint segmentation, and (iii) a novel SIVV based metric to measure the effect of the segmentation algorithm without the requirement to perform the entire matching process. The image is tessellated into local patches and saliency based features along with image, gradient, ridge, and quality based features are extracted. Feature selection is performed to study the contribution of the various category features towards foreground ridge pattern representation. Using these selected features, a trained Random Decision Forest based algorithm classifies the local patches as background or foreground. The results on three publicly available databases demonstrate the efficacy of the proposed algorithm. © 2016 Elsevier B.V. All rights reserved.

Information Fusion

Adaptive latent fingerprint segmentation using feature selection and random decision forest classification

Existing techniques of watermarking make use of transform domain to have better robustness towards attacks. Here, we propose a novel learning based auto-encoder Convolutional Neural Network (CNN) for non-blind watermarking which outperforms the existing frequency domain techniques in terms of imperceptibility and robustness adding new dimension of usage of CNNs towards security. As these CNNs efficiently learn the features and represent the input at the output, they find applications in all the fields of science. Code book images of different size are generated using the proposed architecture and subjected to different attacks. Results of the proposed method are compared with state of the art methods at different noises and attacks such as Gaussian, speckle, compression effects, cropping, filtering, etc. The proposed scheme is validated against various possible attacks and its out-performance with state of the art methods is presented. Further, transfer learning capabilities of auto-encoder CNN for efficient way of learning new code book is presented. The inability of intruder towards retrieval of data without the knowledge of architecture and keys employed is also discussed. © 2016

Computers and Security

Exploring the learning capabilities of convolutional neural networks for robust image watermarking

Cytopathologic testing is one of the most critical steps in the diagnosis of diseases, including cancer. However, the task is laborious and demands skill. Associated high cost and low throughput drew considerable interest in automating the testing process. Several neural network architectures were designed to provide human expertise to machines. In this paper, we explore and propose the feasibility of using deep-learning networks for cytopathologic analysis by performing the classification of three important unlabeled, unstained leukemia cell lines (K562, MOLT, and HL60). The cell images used in the classification are captured using a low-cost, high-throughput cell imaging technique: microfluidics-based imaging flow cytometry. We demonstrate that without any conventional fine segmentation followed by explicit feature extraction, the proposed deep-learning algorithms effectively classify the coarsely localized cell lines. We show that the designed deep belief network as well as the deeply pretrained convolutional neural network outperform the conventionally used decision systems and are important in the medical domain, where the availability of labeled data is limited for training. We hope that our work enables the development of a clinically significant high-throughput microfluidic microscopy-based tool for disease screening/triaging, especially in resource-limited settings. © 2016 Optical Society of America.

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

Cytopathological image analysis using deep-learning networks in microfluidic microscopy

Background Determination of effective connectivity (EC) among brain regions using fMRI is helpful in understanding the underlying neural mechanisms. Dynamic Bayesian Networks (DBNs) are an appropriate class of probabilistic graphical temporal-models that have been used in past to model EC from fMRI, specifically order-one. New-method High-order DBNs (HO-DBNs) have still not been explored for fMRI data. A fundamental problem faced in the structure-learning of HO-DBN is high computational-burden and low accuracy by the existing heuristic search techniques used for EC detection from fMRI. In this paper, we propose using dynamic programming (DP) principle along with integration of properties of scoring-function in a way to reduce search space for structure-learning of HO-DBNs and finally, for identifying EC from fMRI which has not been done yet to the best of our knowledge. The proposed exact search-&amp;-score learning approach HO-DBN-DP is an extension of the technique which was originally devised for learning a BN's structure from static data (Singh and Moore, 2005). Results The effectiveness in structure-learning is shown on synthetic fMRI dataset. The algorithm reaches globally-optimal solution in appreciably reduced time-complexity than the static counterpart due to integration of properties. The proof of optimality is provided. Comparison The results demonstrate that HO-DBN-DP is comparably more accurate and faster than currently used structure-learning algorithms used for identifying EC from fMRI. The real data EC from HO-DBN-DP shows consistency with previous literature than the classical Granger Causality method. Conclusion Hence, the DP algorithm can be employed for reliable EC estimates from experimental fMRI data. © 2017 Elsevier B.V.

School of Artificial Intelligence and Data Science (AIDE)

Journal of Neuroscience Methods

The dynamic programming high-order Dynamic Bayesian Networks learning for identifying effective connectivity in human brain from fMRI

Social networks are becoming an integral part of the modern society. Popular social network applications like Facebook, Twitter produces data in huge scale. These data shows all the characteristic of Big data. Accordingly, it leads to a deep change in the way social networks were being analyzed. The chapter describes a model of social network and its applications within the purview of information diffusion and community structure in network analysis.Here fuzzy granulation theory is used to model uncertainties in social networks. This provides a new knowledge representation scheme of relational data by taking care of the indiscernibility among the actors as well as the fuzziness in their relations. Various measures of network are defined on this new model. Within the context of this knowledge framework of social network, algorithms for target set selection and community detection are developed. Here the target sets are determined using the newmeasure granular degree, whereas it is granular embeddedness, together with granular degree, which is used for detecting various overlapping communities. The resulting community structures have a fuzzy-rough set theoretic description which allows a node to be a member of multiple communities with different memberships of association only if it falls in the (rough upper - rough lower) approximate region. A new index, called normalized fuzzy mutual information is introduced which can be used to quantify the similarity between two fuzzy partition matrices, and hence the quality of the communities detected. Comparative studies demonstrating the superiority of the model over graph theoretic model is shown through extensive experimental results. © Springer International Publishing AG 2017. All rights reserved.