MRES.B.02.01 Selected Topics in image Processing and Computer Vision (MRES.B.02.01)

This topic covers mainly the image representation problem by means of the popular Bag of Visual Words (BoW) and the dictionary learning "or codebook" problem. The BoW model converts vector-represented image patches to "codewords" , which in theor turn create a "codebook". A codeword can be considered as a representative of several similar patches. One simple method is performing k-means clustering over all the vectors. Codewords are then defined as the centers of the learned clusters. The number of the clusters is the codebook size.