摘要
提出一种基于"分水岭"区域分割方法的图像识别算法。针对分水岭算法"过分割"的问题,进行小图像区域消解和有选择的输出关键区域,提出3种区域选择方法——均值方差法、主灰度法、双值法。实验表明,算法对于背景不太复杂的图像识别效果较好。
In this paper,an image recognition algorithm based on watershed regional segmentation method is proposed.To restrain the over-segmentation which results from watershed method,small regional degradation and selective output of the key regions are adopted.Three regional selection methods are used,which are named as Mean-Variance Method,Dominant-Gray Method and Two-Value Method.The simulation results demonstrate that the proposed method is efficient for the less complicated image recognition.
作者
张锏
ZHANG Jian(Suzhou University,Suzhou 234000,China)
出处
《电脑知识与技术（过刊）》
2010年第29期8284-8285,共2页
Computer Knowledge and Technology
关键词
图像识别
分水岭算法
区域选择
image recognition
watershed method
regional selection
