基于形态学运算和图像融合的疵病图像分割算法  

Faulty Image Segmentation Algorithm Based on Morphology Operation and Image Fusion

作　　者：侯劲尧 高爱华[1] 刘卫国[1] 闫丽荣[1] 李文瑾 HOU Jinyao;GAO Aihua;LIU Weiguo;YAN Lirong;LI Wenjin(College of Photoelectric Engineering, Xi'an University of Technology, Xi'an 710021, China)

机构地区：[1]西安工业大学,陕西西安710021

出　　处：《探测与控制学报》2021年第5期55-59,共5页Journal of Detection & Control

基　　金：陕西省科技厅重点研发项目资助(2019GY-063)。

摘　　要：针对疵病图像成像过程中因光照和灰尘影响造成图像分割过度的问题,提出基于形态学运算和图像融合的疵病图像分割算法。该算法采用形态学校正方法完善了疵病的表面特征,提取目标疵病图像,并与原图像融合,再利用Otsu算法完成疵病图像的分割。仿真实验结果表明,该算法能有效地将目标疵病和背景分割,对具有一定清晰度的疵病图像处理效果较好,且测量精确度能满足实际检测要求。In order to solve the problem of excessive image segmentation caused by illumination and dust in the imaging process of defectiv'e image,an image segmentation algorithm based on morphology operation and image fusion was proposed.The morphological correction method was used to improve the surface features of defects,extracts the target defects image,and fused it with the original image.Then,OTSU algorithm was used to complete the segmentation of defects image.Simulation results showed the target defects that could be effectively segmented from the background by the algorithm,the image processing effect of the defects with certain clarity was better,and the measurement accuracy could meet the requirements of the actual detection.

关 键 词：高反镜表面疵病 形态学处理 OTSU 图像融合 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置]