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

In many applications such as law enforcement, attendance systems, and medical services, biometrics is utilized for identifying individuals. However, current systems, in general, do not enroll all possible age groups, particularly, toddlers and pre-school children. This research is the first of its kind attempt to prepare a multimodal biometric database for such potential users of biometric systems. In the proposed database, face, fingerprint, and iris modalities of over 100 children (age range of 18 months to 4 years) are captured in two different sessions, months apart. We also perform benchmarking evaluation of existing tools and algorithms to establish the baseline results for different unimodal and multimodal scenarios. Our experience and results suggest that while iris is highly accurate, it requires constant adult supervision to attain cooperation from children. On the other hand, face is the most easy-to-capture modality but yields very low verification performance. We assert that the availability of this database can instigate research in this important research problem. © 2017 IEEE.

World University root node

IEEE International Joint Conference on Biometrics, IJCB 2017

Multimodal biometric recognition for toddlers and pre-school children

Domestic violence is considered a major social problem worldwide. Different countries have enacted the law to contain and protect the victims of domestic violence. In order to understand the nature of domestic violence, medical professionals and researchers have performed manual analysis of facial injuries. The aim of these studies is to find commonly affected facial regions, to determine the types of maxillofacial trauma associated with domestic violence, and to distinguish the injuries of domestic violence from accidents. Analysis of these injuries assist the service providers in providing proper treatment to the victims as well as facilitate law enforcement investigation. This paper automates the process of analyzing the facial injuries to distinguish the victims of domestic abuse from others. For this purpose, Domestic Violence Face database of 450 subjects with two classes namely, Domestic Violence and Non-Domestic Violence, is prepared. The paper also presents a novel framework using activation maps of deep learning features for determining whether an image belongs to domestic violence class or not. The results on the proposed database show that deep learning based framework is effective in detecting domestic injuries. © 2018 IEEE.

IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops

On detecting domestic abuse via faces

The use of face as a biometric feature has been widely accepted and used in security and surveillance systems. Recent studies have made significant advancements to address various challenges in face recognition such as illumination, age, pose and disguise. Another important covariate is recognizing faces with pre-and-post facial plastic surgery. Facial plastic surgeries alter the geometry and texture of facial regions, the extent of which is dependent on both the number, and the type of surgeries performed. The increasing reach of plastic surgery and its expanding user base present an indispensable challenge that must be dealt with while devising robust face recognition systems. In this paper, we present Invariant Scattering transform based feature extraction to compute translation invariant representation at local and global levels that is stable against plastic surgery variations. The identification accuracy achieved by the proposed algorithm is over 97% at rank-10 on the IIITD plastic surgery face database. © 2018 IEEE.

Proceedings - International Conference on Pattern Recognition

Scattering Transform for Matching Surgically Altered Face Images

Unconstrained face recognition poses several challenges to existing algorithms and to address these variations, different methodologies are proposed, including utilizing video and 3D (depth) information. With the introduction of consumer level depth capturing devices such as Microsoft Kinect, research has been performed in utilizing low cost RGB-D depth data for characterizing and matching faces. Next generation of Kinect device, the Kinect version 2, has also been released which provides higher resolution color, depth and near infrared images at a comparable sensor cost. Such multiple information obtained from a single sensor can be extremely helpful in designing novel algorithms and systems for object and face recognition. This paper introduces the KaspAROV RGB-D video face database which contains face videos and images from both versions of the Kinect device for over 100 subjects which will be made available to the research community. The database captured in visible and NIR spectrum (along with depth) encompasses face images and videos with challenges such as pose, distance, and illumination. The database can be used to evaluate the performance of face recognition algorithms which utilize either uni-spectrum or multi-spectrum information. We provide standard experimental protocols for ease of comparative evaluation on the database and also include baseline results using several existing algorithms including a commercial face recognition system and deep learning algorithm. © 2017 Elsevier B.V.

Information Fusion

Unconstrained Kinect video face database

Development of low-cost robots with the capability to detect and avoid obstacles along their path is essential for autonomous navigation. These robots have limited computational resources and payload capacity. Further, existing direct range-finding methods have the trade-off of complexity against range. In this paper, we propose a vision-based system for obstacle detection which is lightweight and useful for low-cost robots. Currently, monocular vision approaches used in the literature suffer from various environmental constraints such as texture and color. To mitigate these limitations, a novel algorithm is proposed, termed as Pyramid Histogram of Oriented Optical Flow (p-HOOF), which distinctly captures motion vectors from local image patches and provides a robust descriptor capable of discriminating obstacles from nonobstacles. A support vector machine (SVM) classifier that uses p-HOOF for real-time obstacle classification is utilized. To avoid obstacles, a behavior-based collision avoidance mechanism is designed that updates the probability of encountering an obstacle while navigating. The proposed approach depends only on the relative motion of the robot with respect to its surroundings, and therefore is suitable for both indoor and outdoor applications and has been validated through simulated and hardware experiments. © 2018 World Scientific Publishing Company.

Unmanned Systems

A Low-Cost Monocular Vision-Based Obstacle Avoidance Using SVM and Optical Flow

Mobile biometric approaches provide the convenience of secure authentication with an omnipresent technology. However, this brings an additional challenge of recognizing biometric patterns in an unconstrained environment including variations in mobile camera sensors, illumination conditions, and capture distance. To address the heterogeneous challenge, this research presents a novel heterogeneity aware loss function within a deep learning framework. The effectiveness of the proposed loss function is evaluated for periocular biometrics using the CSIP, IMP and VISOB mobile periocular databases. The results show that the proposed algorithm yields state-of-the-art results in a heterogeneous environment and improves generalizability for cross-database experiments. © 2018 IEEE.

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

Heterogeneity aware deep embedding for mobile periocular recognition

Human skull identification is an arduous task, traditionally requiring the expertise of forensic artists and anthropologists. This paper is an effort to automate the process of matching skull images to digital face images, thereby establishing an identity of the skeletal remains. In order to achieve this, a novel Shared Transform Model is proposed for learning discriminative representations. The model learns robust features while reducing the intra-class variations between skulls and digital face images. Such a model can assist law enforcement agencies by speeding up the process of skull identification, and reducing the manual load. Experimental evaluation performed on two pre-defined protocols of the publicly available IdentifyMe dataset demonstrates the efficacy of the proposed model. © 2018 IEEE.

Learning a shared transform model for skull to digital face image matching

Face recognition research has benefited from the availability of challenging face databases and benchmark results on popular databases show very high performance on single-person per image/video databases. However, in real world surveillance scenarios, the environment is unconstrained and the videos are likely to record multiple subjects within the field of view. In such crowd surveillance videos, both face detection and recognition are still considered as onerous tasks. One of the key factors for limited research in this direction is unavailability of benchmark databases. This paper presents CrowdFaceDB video face database that fills the gap in unconstrained face recognition for crowd surveillance. The two fold contributions are: (1) developing an unconstrained crowd video face database of over 250 subjects, and (2) creating a benchmark protocol and performing baseline experiments for both face detection and verification. The experimental results showcase the exigent nature of crowd surveillance and limitations of existing algorithms/systems. © 2017

Pattern Recognition Letters

CrowdFaceDB: Database and benchmarking for face verification in crowd

Landslides are one of the severe natural catastrophes that affect thousands of lives and cause colossal damage to infrastructure from small to region scales. Detection of landslide is a prerequisite for damage assessment. We propose a novel method based on object-oriented image analysis using bi-temporal satellite images and DEM. The proposed methodology involves segmentation, followed by extraction of spatial and spectral features of landslides and classification based on supervised Bayesian classifier. The proposed framework is based on the change detection of spatial features which capture the spatial attributes of landslides. The proposed methodology has been applied for the detection and mapping of landslides of different sizes in selected study sites in Himachal Pradesh and Uttarakhand, India. For this, high-resolution multispectral images from the IRS, LISS-IV sensor and DEM from Cartosat-1 are used in this study. The resultant landslides are compared and validated with the inventory landslide maps. The results show that the proposed methodology can identify medium- and large-scale landslides efficiently. © Springer Nature Singapore Pte Ltd. 2018.

Advances in Intelligent Systems and Computing

Bayesian approach for landslide identification from high-resolution satellite images

Deep learning architectures use a set of layers to learn hierarchical features from the input. The learnt features are discriminative, and thus can be used for classification tasks. Convolutional neural networks (CNNs) are one of the widely used deep learning architectures. CNN extracts prominent features from the input by passing it through the layers of convolution and nonlinear activation. These features are invariant to scaling and small amount of distortions in the input image, but they offer rotation invariance only for smaller degrees of rotation. We propose an idea of using multiple instance of CNN to enhance the overall rotation invariant capabilities of the architecture even for higher degrees of rotation in the input image. The architecture is then applied to handwritten digit classification and captcha recognition. The proposed method requires less number of images for training, and therefore reduces the training time. Moreover, our method offers an additional advantage of finding the approximate orientation of the object in an image, without any additional computational complexity. © 2018, Springer Nature Singapore Pte Ltd.