User:Saurabh

Research Interests

I’m working on the application of computer vision for the analysis of medical images and use of MRIs to improve the understanding of neurological disorders such as multiple sclerosis.

Education

University of British Columbia Vancouver, Canada Master of Applied Science (BMEG) (2011 - present) [Advisor: Prof. Roger Tam]

International Institute of Information Technology Hyderabad, India Bachelor of Technology (Honors) (ECE) (2003-2007) [Advisor: Prof. Jayanthi Sivaswamy]

Research and Professional Experience

Research Assistant, Center for Visual Information Technology, IIIT-Hyd

Drusen detection and analysis

Abstract: Drusen are tiny yellow or white deposits in the retina of the eye or on the optic nerve head. The presence of Drusen is one of the most common early signs of age-related macular degeneration. A new system has to be designed to detect the Drusen, which can be deployed in the hospital to assist doctors in their diagnosis. This project was done with LVPEI, Hyderabad.

Script Identification for Indian Languages

Abstract: Automatic identification of a script in a given document image facilitates many important applications such as automatic archiving of multilingual documents, searching online archives of document images and for the selection of script specific OCR in a multilingual environment. In this project, a new scheme was developed to identify different Indian scripts from a document image.

Segmenting and Visualizing Knee in 3D from MRI data

Abstract: Computer generated 3D models are helpful for better understanding of the human anatomy. These 3D models have the potential to enhance surgical training, to reduce patient risk by enabling pre-surgical planning on patient-specific models and can also be used in education and training. In this project a scheme was developed to segment different structures present in the knee and constructing a 3D model using the information extracted.

Iris based recognition system

Abstract: Accurate and automatic identification and authentication of users is a fundamental problem in network environments. Shared secrets such as PINs or passwords and key devices like smart cards just are not enough in some cases. Due to these reasons biometric identification systems have received more importance. In this project we implemented a method for iris based recognition system. The performance of the method was evaluated on CASIA database.

Teaching Assistant, International Institute of Information Technology, Hyderabad

• Electronics Workshop