A systolic architecture for image segmentation by adaptive progressive thresholding

A special purpose VLSI architecture for the real time segmentation of endoscopic images is proposed in this paper. The architecture is based on a systolic implementation of a new algorithm named adaptive progressive thresholding (APT) that segments the darkest area of an endoscopic image representing the gastrointestinal lumen. This segmentation process is an extension of the Otsu´s (1978) method. The progressive approach of thresholding optimizes the threshold for an endoscopic image using an iterative procedure. A condition to converge the iterative procedure is suggested to make the segmentation automatic and adaptive. The APT algorithm is mapped onto a modified linear systolic array of simple processing elements with the elements of a particular segment communicating with its neighbors. The APT architecture is partitioned based on various sequential functions involved in the segmentation process and these functional modules are organized in a pipelined fashion according to their hardware feasibility. Currently, a prototype of the VLSI architecture for an image size of 256×256 is being designed and built. The functional simulation results obtained in the APT architecture are encouraging