基于局部处理的X射线图像裂纹缺陷自动检测
Automatic Detection of Crack Defects in X-ray Image Based on Local Processing
投稿时间:2019-09-01  修订日期:2019-09-01
DOI:
中文关键词: 裂纹缺陷自动检测  感兴趣区域  局部直方图增强  阈值技术  形态学处理
英文关键词: Crack defect automatic detection  Region of interest  Local histogram enhancement  Threshold technology  Morphological processing
基金项目:国家自然科学基金资助项目(60975011);中南民族大学中央高校基本科研业务费专项资金资助项
作者单位E-mail
娄联堂 中南民族大学 数学与统计学学院 louliantang@163.com 
何慧玲 中南民族大学 数学与统计学学院  
石胜平 中车长江车辆有限公司  
摘要点击次数: 300
全文下载次数: 0
中文摘要:
      该文研究了X射线图像裂纹缺陷自动检测问题. 首先利用局部预处理分割方法提取感兴趣区域,使检测到的缺陷区域准确地包含实际缺陷;然后把基于局部方差和局部直方图均衡化结合起来实现了图像的对比度增强,使裂纹缺陷肉眼可见;最后通过阈值技术和形态学分析方法将X射线图像中的裂纹缺陷有效的检测出来. 结果表明:相比于仅利用局部方差或局部直方图均衡化对图像做一次对比度增强,此方法能有效增强缺陷特征,更利于缺陷检测.
英文摘要:
      In this paper, the problem of automatic detection of crack defects in X-ray images is studied. Firstly, the region of interest is extracted by local preprocessing and segmentation method, so that the defect areas detected accurately contain the actual defects. Then, the image contrast is enhanced by combining the local variance and local histogram equalization, which can make the crack defectsSvisible to the naked eye. Finally, the crack defects in X-ray images are effectively detected by threshold technology and morphological analysis method. The results show that this method can effectively enhance the defect features and is more conducive to defect detection than only using local variance or local histogram equalization to enhance the image contrast once.
View Fulltext   查看/发表评论  下载PDF阅读器
关闭