论文部分内容阅读
提出了一种基于Gabor滤波器的坯布表面缺陷检测方法。该方法基于Gabor滤波方案,分别将原始图像与滤波器进行卷积操作,然后采用大津法阈值分割来获得坯布表面缺陷。为了优化Gabor滤波器的检测效果,研究不同的参数设定对于检测结果的影响,通过不同类型的无纺布缺陷的实验结果证明了该方法的有效性。最后通过对比常用的检测算法,突出该算法的实用价值。
A new method to detect the surface defect of gray fabric based on Gabor filter is proposed. Based on the Gabor filter scheme, the proposed method convolutes the original image and the filter respectively, and then uses the Otsu method to obtain the surface defect of the fabric. In order to optimize the Gabor filter’s detection effect and study the influence of different parameter settings on the test results, the effectiveness of this method is proved by experimental results of different types of non-woven fabric defects. Finally, by comparing the commonly used detection algorithm, highlighting the practical value of the algorithm.