摘要
提出了一种基于相对熵的图象分割算法，该算法的主要思想是通过相对熵来选择阈值．现场颗粒物料图象作为一个应用实例，在本文中得到验证．实验结果表明。
In this paper, we present a relative entropy based algorithm to image segmentation. The main idea of this algorithm is to find a threshold by using relative entropy. Particle material image from plant scene is taken as example to show the practical application of the algorithm.Some experimental results are provided to show the proposed algorithm to be superior to the local entropy based algorithm of image segmentation.
出处
《信息与控制》
CSCD
北大核心
1997年第1期67-72,80,共7页
Information and Control
关键词
计算机视觉
图象处理
模式识别
图象分割
相对熵
computer vision, image processing, pattern recognition,Image segmentation, co occurrence matrix, relative entropy, local entropy
