改进的动物精子图像分割算法  

Improved animal sperm image segmentation algorithm

作　　者：宋继清[1] 黄文明[1] 李寅威[1] 邓珍荣[1] 

机构地区：[1]桂林电子科技大学计算机科学与工程学院,广西桂林541004

出　　处：《计算机工程与设计》2012年第11期4259-4263,共5页Computer Engineering and Design

基　　金：国家自然科学基金项目(50805031);广西自然科学基金项目(桂科自0991240)

摘　　要：动物精子图像分割在计算机辅助精子质量分析系统(CASA)中有着非常重要的作用,直接关系到精子质量检测的精度和速度。在总结最大类间方差(Otsu)算法利弊的基础上,对传统二维Otsu算法原理以及在动物精子图像分割过程中存在处理时间过长的问题进行了研究,提出了一种改进的二维Otsu图像分割算法,通过改变二维直方图的分块方式将二维最优阈值搜索变为一维最优阈值搜索,从而缩短寻找最优阈值的处理时间。实验结果表明,改进的分割算法可以有效降低算法复杂度和噪声干扰,实现动物精子图像快速、准确的分割。Animal sperm image segmentation in the quality of computer-aided sperm analysis （CASA） system has a very important role, directly related to the accuracy and speed of sperm quality. Long processing time, the traditional two-dimensional Otsu algorithm principle, as well as in animal sperm image segmentation problem is studied on the basis of summing up the pros and cons of the Otsu Algorithm, which presents an improved image segmentation that transformed the one-dimensional optimal threshold search into the two-dimensional optimal threshold search by changing the block-division method of the two-dimensional histogram, thus reducing the processing time to find the optimal threshold. The experimental results show that the improved segmentation algorithm can effectively reduce the complexity of the algorithm and noise, animal sperm images fast, accurate segmentation.

关 键 词：二维最大类间方差算法 图像分割 二维最优阈值 精子图像 计算机辅助精子分析 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]