标题：Application of soft mathematical morphology in image segmentation of IR ship image
作者：Dong, Yan-Zhi ;Zhou, Xiao-Dong ;Wang, Changjing ;Xie, Wei-Gang
作者机构：[Dong, Yan-Zhi ;Zhou, Xiao-Dong ] Dep. of Automat. Control Engineering, Nav. Aero. Engineering Institute, Yantai, 264001, China;[Xie, Wei-Gang ] Dep. 更多
会议名称：2004 7th International Conference on Signal Processing Proceedings (ICSP'04)
会议日期：31 August 2004 through 4 September 2004
来源：International Conference on Signal Processing Proceedings, ICSP
关键词：Image segmentation; Ship infrared image; Soft mathematical morphology; Threshold method
摘要：The image segmentation is the most important key in tracking processing of IR imaging precise guidance. Its effect determines the accuracy and result of following processing directly. The soft mathematical morphology can compress the noise effectively, get better processing results and complete processing in real time. So it is well adapted to infrared images processing. In this paper, we employed suitable structuring system based on the soft morphology theory and threshold theory to perform the image segmentation of actual ship infrared image. First, the soft erosion operation was used to eliminate the sea noise. Next, the soft dilation was used to remove the darker detail. Finally, the image segmentation was completed. We discussed the algorithm and listed some processing results. We also compared the algorithm with other traditional image segmentation operators such as Otsu method. The simulation results illustrate that the algorithm is better than the traditional methods and can get better image segmentation results. It can be used widely in IR tracking processing.