Simultaneous image segmentation and edge detection

It is shown that the two tasks of region and edge segmentation can be achieved using a single, unified approach based upon the cooccurrence matrix. It is also shown that, when an image is composed of non-textured regions, then the cooccurrence matrix possesses a characteristic structure of peaks corresponding to regions and boundaries in the image. The cooccurrence matrix will be treated as a feature space and, by utilising the structure of the matrix, it will be split into several distinct parts corresponding to contributions from regions or boundaries in the image. A natural mapping between the labelled matrix and the image will be defined. Using the labelled cooccurrence matrix, this natural mapping will enable each pixel in the image to be classified as either a boundary pixel of a specific direction or as a pixel of a particular type of region. This natural mapping simultaneously defines a thresholded edge strength image and an image segmentation.<
>