Graph Algorithms and Computer Vision
Submitted by Sumod Mohan (@sumod) on Monday, 15 June 2015
Discover some of the interesting connections between various sub-areas of Machine Learning, Analytics and Computer Vision. Specifically how Random Walk on a Graph can give clustering of data, how clustering can help in Segmentation (image/video) of data and how many of these can boil down to eigen decomposition of a specially crafted matrix of graph data.
Graph based algorithms have found extensive applications in Computer Vision and have been in forefront for many vision applications. They have shown to have connections to other areas such as Natural Language Processing and Network Analysis. This talk aims to showcase some of the known connections between these areas with applications to data, big and small. This will be centered around applications in Computer Vision such as segmentation and face detection but will make forays into ranking and clustering. This would be a survey talk and will be aimed at showcasing the intuition behind some of these algorithms as opposed to enunciating the rigorous mathematics.