Currently, I am focusing on presentation attack detection in Iris biometrics. Earlier, I was involved in numerous projects of iris, fingerprint and face recognition. I have worked both in research and commercial projects.
|Presentation Attack Detection in Iris Biometrics|
|The project focuses on the problem of presentation attacks against iris recognition systems. Iris recognition systems recognize individuals based on their unique and complex iris patterns. A presentation attack (PA) occurs when an adversarial user presents a fake or altered biometric sample to the sensor in order to spoof another user’s identity, obfuscate their own identity, or create a virtual identity. Commonly used presentation attacks are printed iris images, plastic, glass, or doll eyes, cosmetic contact lenses, replaying a video of an individual’s eye, robotic eyes. To detect such attacks, we develop a deep convolutional neural network (CNN) that can determine if an input eye image corresponds to an attack or not.|
|Biometric Seafarer Identity Documents (B-SID)|
|The project was funded by the Directorate General of Shipping, Government of India. The aim of the project is to provide secure and hassle-free biometric based globally acceptable identity document called SID document (similar to e-Passport) to seafarer as per the ILO Convention 185(2003) for identification purpose across the world sea shores.|
|Passport Seva Project|
|Graduate Aptitude Test in Engineering (GATE) and Indian Institute of Technology Joint Entrance Examination (IIT-JEE) for IITs|
|OmniOutput Management Suite (O2MS) and OmniReports|
- Steven Hoffman, Renu Sharma, Arun Ross, Iris + Ocular: Generalized Iris Presentation Attack Detection Using Multiple Convolutional Neural Networks, 12th IAPR International Conference on Biometrics (ICB), Crete, Greece, 2019.
- Steven Hoffman, Renu Sharma, Arun Ross, Convolutional Neural Networks for Iris Presentation Attack Detection: Toward Cross-Dataset and Cross-Sensor Generalization, Computer Vision and Pattern Recognition Workshops (CVPRW), Salt Lake City, USA, 2018.[pdf]
- Renu Sharma, Sukhendu Das and Padmaja Joshi, Score Level Fusion using Generalized Extreme Value Distribution and Dezert-Smarandache Theory, for Multi-biometric Systems, IET-Biometrics, February, 2018, DOI: 10.1049/iet-bmt.2017.0076.[pdf]