|M.Sc Student||Rosenblum Kevin|
|Subject||Dictionary and Sensing Matrix Optimization for Block Sparse|
|Department||Department of Electrical Engineering||Supervisor||Professor Lihi Zelnik-Manor|
|Full Thesis text|
Recent work has demonstrated that using a carefully designed dictionary instead of a predefined one, can improve the sparsity in jointly representing a class of signals. This has motivated the derivation of learning methods for designing a dictionary which leads to the sparsest representation for a given set of signals. In addition, using a carefully designed sensing matrix rather than a random one, can improve the performance of compressed sensing. In particular, a well-designed sensing matrix can reduce the coherence between the atoms of the equivalent dictionary, and as a consequence, reduce the reconstruction error. In some applications, the signals of interest can be well approximated by a union of a small number of subspaces (e.g., face recognition and motion segmentation). This implies the existence of a dictionary which leads to block-sparse representations.
In this work, we propose an algorithm for learning a block-sparsifying dictionary of a given set of signals. We do not require prior knowledge on the association of signals into groups (subspaces). Instead, we develop a method that automatically detects the underlying block structure. This is achieved by iteratively alternating between updating the block structure of the dictionary and updating the dictionary atoms to better fit the data. Our experiments show that for block-sparse data the proposed algorithm significantly improves the dictionary recovery ability and lowers the representation error compared to dictionary learning methods that do not employ block structure. We further propose a framework for sensing matrix design that improves the ability of block-sparse approximation techniques to reconstruct and classify signals. This method is based on minimizing a weighted sum of the inter-block coherence and the sub-block coherence of the equivalent dictionary. Our experiments show that the proposed algorithm significantly improves signal recovery and classification ability of the Block-OMP algorithm compared to sensing matrix optimization methods that do not employ block structure.