Sohrab Ferdowsi

  • Citations Per Year
Learn More
We propose a scheme for multi-layer representation of images. The problem is first treated from an informationtheoretic viewpoint where we analyze the behavior of different sources of information under a multi-layer data compression framework and compare it with a single-stage (shallow) structure. We then consider the image data as the source of information(More)
We consider the problem of fast content identification in high-dimensional feature spaces where a sub-linear search complexity is required. By formulating the problem as sparse approximation of projected coefficients, a closed-form solution can be found which we approximate as a ternary representation. Hence, as opposed to dense binary codes, a framework of(More)
This paper addresses the problem of Approximate Nearest Neighbor (ANN) search in pattern recognition where feature vectors in a database are encoded as compact codes in order to speed-up the similarity search in large-scale databases. Considering the ANN problem from an information-theoretic perspective, we interpret it as an encoding, which maps the(More)
We analyze the privacy preservation capabilities of a previously introduced multi-stage image representation framework where blocks of images with similar statistics are decomposed into different codebooks (dictionaries). There it was shown that at very low rate regimes, the method is capable of compressing images that come from the same family with results(More)
In this paper, we investigate the problem of visual information encoding and decoding for face recognition. We propose a decomposition representation with vector quantization and constrained likelihood projection. The optimal solution is considered from the point of view of the best achievable classification accuracy by minimizing the probability of error(More)
Compressive Sensing (CS) has become one of the standard methods in face recognition due to the success of the family of Sparse Representation based Classification (SRC) algorithms. However it has been shown that in some cases, the locality of the dictionary codewords is more essential than the sparsity. Also sparse coding does not guarantee to be local(More)
Quantizing the residual errors from a previous level of quantization has been considered in signal processing for different applications, e.g., image coding. This problem was extensively studied in the 80’s and 90’s (e.g., see [1] and [4]). However, due to strong over-fitting, its efficiency was limited for more modern applications with larger scales. In(More)