Improvement of Active Net Model fo Region Detection in an Image

摘要

Processes in image recognition include target detection and shapeextraction. Active Net has been proposed as one of the methods forsuch processing. It treats the target detection in an image as anenergy optimization problem. In this paper, a problem of theconventional Active Net is presented and the new Active Net isproposed. The new net is improved the ability for detecting a target.Finally, the validity of the proposed net is confirmed byexperimental results.