Date Added: Apr 2011
This paper discuss about acquiring prior information of an image in order to represent it graphically. It involves two separate processes; detecting object parts of an image and integration of detected parts into several clusters. All these cluster centers form the visual words and over-segmenting the image into super-pixels using Novel Recursive Clustering Algorithm and formation of larger sub region using mid-level clustering algorithm, since it incorporates various information to decide the homogeneity of a sub region. The outcome of the two processes can be used as the input for the graph model.