陕西科技大学学报（自然科学版）Issue(2)：152-155,163,5.
结合全局和随机局部频率调谐的复杂纹理表面缺陷检测
The defect detection for random texture surface combined with the whole and randomly partial frequency tuned
摘要
Abstract
This paper proposes a new defect detection method ,which combines the whole fre-quency tuned with the randomly partial frequency tuned ,to solve the problem of the different defect size ,the strong interference by its own texture arising in the course of defect detec-tion .By taking the frequency tuned of the whole image and the random partial blocks ,we ob-tained the combination of the global significant map and the partial significant map ,named integrated saliency map .Segmenting threshold of this map can achieve the detection for de-fect areas .Experiment show s that this method has the better real-time .Not only can it re-strain the texture ,but it is able to protrude defect targets as well .Compared with the tradi-tional methods ,it has certain superiority .关键词
机器视觉/缺陷检测/频率调谐/显著图Key words
machine vision/defects detection/frequency tuned/saliency map分类
信息技术与安全科学引用本文复制引用
李健,陈海丰,吴华..结合全局和随机局部频率调谐的复杂纹理表面缺陷检测[J].陕西科技大学学报（自然科学版）,2014,(2):152-155,163,5.基金项目
陕西省教育厅专项科研计划项目（11JK1065）；温州市科技合作项目 （）
