A5025836373- Face recognition and analysis
- Biometric Identification and Security
- Digital Media Forensic Detection
- Generative Adversarial Networks and Image Synthesis
- Advanced Steganography and Watermarking Techniques
- User Authentication and Security Systems
- Adipokines, Inflammation, and Metabolic Diseases
- Image Processing Techniques and Applications
- Adversarial Robustness in Machine Learning
- Ovarian cancer diagnosis and treatment
- Advanced Neural Network Applications
- Anomaly Detection Techniques and Applications
- Remote Sensing and LiDAR Applications
- 3D Shape Modeling and Analysis
- Advanced Image Fusion Techniques
- Food Supply Chain Traceability
- Photoacoustic and Ultrasonic Imaging
- Innovation and Socioeconomic Development
- Brain Tumor Detection and Classification
- Hypothalamic control of reproductive hormones
- Facial Nerve Paralysis Treatment and Research
- Advanced Image and Video Retrieval Techniques
- Fire Detection and Safety Systems
- Intelligent Tutoring Systems and Adaptive Learning
- Hydrological Forecasting Using AI
Institute of Post Graduate Medical Education and Research
2023-2025
Symbiosis International University
2024-2025
Medical College and Hospital, Kolkata
2025
New York University
2023-2024
National Institute of Technology Durgapur
2024
Indian Institute of Technology Hyderabad
2022-2023
International Institute of Information Technology, Hyderabad
2023
Michigan State University
2017-2022
Maulana Abul Kalam Azad University of Technology, West Bengal
2021
University of Salzburg
2019
The need for reliably determining the identity of a person is critical in number different domains ranging from personal smartphones to border security; autonomous vehicles e-voting; tracking child vaccinations preventing human trafficking; crime scene investigation personalization customer service. Biometrics, which entails use biological attributes such as face, fingerprints and voice recognizing person, being increasingly used several applications. While biometric technology has made...
Importance The prevalence of polycystic ovary syndrome (PCOS) varies across the globe. Indian studies on PCOS are limited by poor design, small sizes, regional representations, and varying methods. Objectives To estimate nationwide in India, examine phenotypic spectrum, assess magnitude comorbidities associated with PCOS. Design, Setting, Participants This cross-sectional study recruited 9824 women aged 18 to 40 years from November 1, 2018, July 31, 2022, 5 zones country. A prevalidated...
Abstract Context Prader-Willi Syndrome is one of the commonest mono-chromosomal (15q11-13), polygenic syndromic childhood obesity. Objectives We primarily compares and correlate serum Lp(a), hs-CRP,and baseline clinical characteristics genetically confirmed children with PWS at their growth-hormone treatment-naïve stage to control groups. Secondary objectives were Lp(a) hs-CRP concentration MLPA subgroups,body composition indices,sleep apnea parameters,and hepatic shear-stress by...
Medical diagnosis involves the expert opinion of trained health care professionals based on causal inference from medical data. While data are typically collected using specialized medical-grade sensors, similar characteristics useful for sometimes present in biometric (e.g., face images, ocular and speech signals). In this paper, we explore biometrics literature to study following questions. 1) What kind cues embedded commonly utilized forms audio-visual data? 2) How can these be gleaned...
We present the task of differential face morph attack detection using a conditional generative network (cGAN). To determine whether image in an identification document, such as passport, is morphed or not, we propose algorithm that learns to implicitly disentangle identities from conditioned on trusted reference cGAN. Furthermore, proposed method can also recover some underlying information about second subject used generating morph. performed experiments AMSL morph, MorGAN, and EMorGAN...
A face morph is created by strategically combining two or more images corresponding to multiple identities. The intention for the morphed image match with Current attack detection strategies can detect morphs but cannot recover identities used in creating them. task of deducing individual from a known as demorphing. Existing work de-morphing assume availability reference pertaining one identity order accomplice - i.e., other identity. In this work, we propose novel method that both...
The principle of Photo Response Non Uniformity (PRNU) is often used to link a digital image with the sensor that produced it. In this regard, number schemes have been proposed in literature extract PRNU details from given input image. work, we study impact photometric transformations applied near-infrared ocular images, on PRNU-based iris identification accuracy. contributions work are as follows: (a) Firstly, evaluate 7 different 4 schemes; (b) Secondly, develop an explanatory model based...
The field of digital image forensics concerns itself with the task validating authenticity an or determining device that produced image. Device sensor identification can be accomplished by estimating sensor-specific pixel artifacts, such as Photo Response Non Uniformity (PRNU), leave imprint in resulting Research this has predominantly focused on images obtained using sensors operating visible spectrum. Iris recognition systems, other hand, utilize near-infrared (NIR) In work, we evaluate...
Social scientists have long been interested in the motives of hackers, particularly financially motivated attackers. This article analyzes web defacements, a less studied and more public form cyberattack, which content page is deliberately substituted with unwanted text graphics chosen by perpetrator. These attacks use variety strategies are performed for motives, including political ideological goals. The proliferation such has resulted vast amounts data that open new opportunities...
The performance of automated face recognition systems is inevitably impacted by the facial aging process. However, high quality datasets individuals collected over several years are typically small in scale. In this work, we propose, train, and validate use latent text-to-image diffusion models for synthetically de-aging images. Our succeed with few-shot training, have added benefit being controllable via intuitive textual prompting. We observe degrees visual realism generated images while...
This paper introduces a new technique for tracing the malicious nodes in mobile adhoc network (MANET) wireless communication. As hosts are free to move any where and can change topology frequently, each node of MANET much more vulnerable insider attacks specially under noise external due lack permanent infrastructure, limited resources, central administrator etc. Here this paper, we have done an investigation mathematical analysis based upon detection with modeling .We propose scanning...
The principle of Photo Response Non-Uniformity (PRNU) is used to link an image with its source, i.e., the sensor that produced it. In this work, we investigate if it possible modify iris acquired using one in order spoof PRNU noise pattern a different sensor. regard, develop perturbation routine iteratively modifies blocks pixels original such approaches target Experiments indicate efficacy proposed method spoofing patterns present whilst still retaining biometric content.
The principle of Photo Response Non Uniformity (PRNU) is often exploited to deduce the identity smartphone device whose camera or sensor was used acquire a certain image. In this work, we design an algorithm that perturbs face image acquired using such (a) sensor-specific details pertaining are suppressed (sensor anonymization); (b) pattern different incorporated spoofing); and (c) biometric matching perturbed not affected (biometric utility). We employ simple approach utilizing Discrete...