Approximate Pattern Matching Using Hierarchical Graph Construction and Sparse Distributed Representation

With recent developments in deep networks, there have been significant advances in visual object detection and recognition. However, some of these networks are still easily fooled/hacked and have shown bag of features kinds of failures. Some of this is due to the fact that even deep networks make only marginal use of the complex structure that exists in real-world images. Primate visual systems appear to capture the structure in images, but how? In the research presented here, we are studying approaches for robust pattern matching using static, 2D Blocks World images based on graphical representations of the various components of an image. Such higher-order information represents the structure or shape of the visual object. This research led to a technique for representing an object\u27s structural information in a Sparse Distributed Representation (SDR) loosely based on the kinds of cortical circuits found in primate visual systems. We apply probabilistic graph isomorphism and subgraph isomorphism to our 2D Blocks World images and achieve O(1) and O(nk) complexity for an approximate match. The image labeled graph is created using OpenCV to find the object contours and objects\u27 labels and a fixed radius nearest neighbor algorithm to build the edges between the objects. Pattern matching is done using the properties of SDRs. Next, we use SVM to learn and distinguish images. SVM partitions the vector space where classification accuracy on noisy images gives us an assessment of how much information the SDR is capturing