Image segmentation by local morphological granulometries
Conference Paper
Overview
Additional Document Info
View All
Overview
abstract
Morphological granulometries are generated by successively opening a thresholded image by an increasing sequence of structuring elements. The result is a sequence of images, each of which is a subimage of the previous. By counting the number of pixels at each stage of the granulometry, a size distribution is generated that can be used as a signature of the image. An adaptation of the method that is appropriate to texture-based segmentation is described. Rather than construct a single size distribution based on the entire image, local size distribution are computed over windows within the image. These local size distributions lead to statistics at pixels within the image, and pixels are classified according to local statistics. If the image happens to be partitioned into regions of various texture the local statistics will tend to be homogeneous over any given region. Segmentation results from classifying the local statistics.