Improving a genetic algorithm segmentation by means of a fast edge detection technique

Thispaper presents a new hybrid range image segmentation approach. Two separate techniques are applied consecutively. First, iin edge based segmentation technique extracts the edge points-creases and jumps-contained in the given range image. Then, by using only the edge point position information, the boundaries are computed. Secondly, the points clustered into each region are approximated by single surfclces through a Genetic Algorirhm (CA). The CA takes advantage of previous edge representation finding the surface paramettw that best fit each region. It works in a local way, according to the boundary information, reducing considerably the required CPU time. Experimental results with diflerent range images are presented; moreover a comparison using either the edge detection stage or not is given.

• Type: Conference
• Year: 2001
• Where: ICIP
• Authors: Angel Domingo Sappa, Vitoantonio Bevilacqua, Michel Devy
• Keywords: Edge Based Segmentation, Edge Detection Stage, Edge Point Position, ICIP 2001, Image Processing