智能系统学报Issue(1)：68-74,7.DOI:10.3969/j.issn.1673-4785.201410008
回溯搜索优化算法辅助的多阈值图像分割
Backtracking search optimization algorithm assisted multilevel threshold for image segmentation
摘要
Abstract
The threshold method is a simple and effective image segmentation technique .However, the amount of calculation for solving threshold appears to be exponential amplification with the increase of threshold .This results in a huge challenge for multi-threshold image segmentation .This paper utilizes Otsu and Kapur methods as the tar-get function in order to deal with image segmentation .In this paper , image segmentation is considered as an optimi-zation problem whose objective function is formulated according to Otsu and Kapur methods , respectively .The backtracking search optimization algorithm is used to solve these two objective functions and to realize multi -thresh-old image segmentation .The proposed approach is applied to nature image segmentation and compared to other algo-rithms.The results showed that the multi-threshold image segmentation technique on the basis of backtracking search optimization algorithm is feasible and the segmentation effect is satisfactory.关键词
阈值法/回溯搜索优化算法/图像分割/Otsu/Kapur/PSNRKey words
threshold method/backtracking search optimization algorithm/image segmentation/Otsu/Kapur/PSNR分类
信息技术与安全科学引用本文复制引用
尹雨山,王李进,尹义龙,王冰清,赵文婷,徐云龙..回溯搜索优化算法辅助的多阈值图像分割[J].智能系统学报,2015,(1):68-74,7.基金项目
国家自然科学基金-广东联合基金重点资助项目（ U1201258）；山东省自然科学杰出青年基金资助项目（ JQ201316）． （）
