Email: shaydeut at usc dot edu
Office: 3737 Watt Way, PHE 233, USC, Los Angeles, CA, 90089
I am a PhD student in the Computer Science Department at the University of Southern California. My Advisor is Prof. Gerard Medioni and I am in the Computer Vision Lab of the Institute for Robotics and Intelligent Systems, at the Viterbi School of Engineering.
I completed my Masters in Applied Mathematics at Tel-Aviv University in 2010, under the supervision of Prof. Amir Averbuch and Dr. Shai Dekel. I also hold a B.Sc. in Mathematics from the Technion, Israel Institute of Technology. My M.Sc. research focused primarily on an alternative method for simultaneous image acquisition and compression called Adaptive Compressed Sensing. The Adaptive Compressed Sensing framework replaces the universal acquisition of incoherent measurements used in the 'classic Compressed Sensing' framework with a fast and direct method for adaptive wavelet tree acquisition. The main advantages of this adaptive approach are that the decoding time is significantly faster and that it allows greater control over the compressed images quality, in particular, the sharpness of edge.
My main research interests are in the areas of Computer Vision, Tensor Voting, Manifold Learning, Multi-Scale Representations, and Machine Learning algorithms.
S. Deutsch, A. Ortega, and G. Medioni. “Graph Manifold Based Frequency Analysis For Denoising", preprint.
S. Deutsch and G. Medioni. "Learning the Geometric Structure of Manifolds with Singularities Using the Tensor Voting Graph", To appear in Journal of Mathematical Imaging and Vision.
S. Deutsch, A. Ortega, and G. Medioni. “Manifold Denoising Based on Spectral Graph Wavelets", ICASSP 2016.
S. Deutsch and G. Medioni. “Intersecting Manifolds: Detection, Segmentation, and Labeling”, International Joint Conference on Artificial Intelligence, (IJCAI), 2015. [pdf]
S. Deutsch and G. Medioni. “Unsupervised Learning Using the Tensor Voting Graph”, Scale Space and Variational Methods in Computer Vision (SSVM), 2015. [pdf]