Vedika Agarwal

Research interest: 
Digital Signal Processing
Computer Vision

I am a final year year undergraduate student at the Birla Institute of Technology and Science- Pilani, India; pursuing B.E. in Electrical and Electronics. I am currently doing my Bachelor Thesis on Multi Region Shape prior Segmentation for 3D Cardiac Images at Lab of Computational Computer Vision,Georgia Tech, USA. I am also working on Designing Overcomplete Dictionaries for Spare representation of signals using KSVD. Furthermore working on Correlation between Saliency Detection and Uncertainty Estimation has acquainted me with the existing state of the art algorithms for Saliency Detection and given me a deeper insight to vision related topics after my research project at School of Computer Engineering, NTU. Singapore. The idea, there, was to come up with a real time technique for estimating traffic density. We came up with a block based processing technique to detect vehicles with a speed one-twelfth of the existing state of the art algorithms and comparable accuracy. I have been co-authoring a paper for the same. My other relevant research projects include designing an Automatic Speaker Recognition module (using MFCCs, VQ, and LBG algorithm). Then Face Recognition module (using PCA, SVD), and detection of fricative consonants (using Zero crossings).