基于目标特征的织物疵点检测方法

Research on Fabric Defect Detection Algorithm

为了提高生产中织物疵点检测的准确率,本文运用了图像处理技术和基于目标特征参数的方法检测织物上的疵点。首先将织物的图像进行预处理,滤波去噪对目标图像的噪声进行抑制,织物图像增强使得图像上的疵点特征信息更加明显。然后利用最大熵阈值法把疵点分割出来。最后,跟据织物疵点图像的长宽比和归一化灰度值进行疵点分类识别。实验表明,表明该方法能提高织物疵点的识别准确率。

In order to improve the accuracy of fabric defect detection in production,this paper uses image processing technology and a method based on target feature parameters to detect fabric defects.Firstly,the fabric image is preprocessed,filtering and denoising suppress the noise of the target image,and the fabric image enhancement makes the defect feature information on the image more obvious.Then use the maximum entropy threshold method to segment the defects.Finally,according to the aspect ratio of the fabric defect image and the normalized gray value,the defects are classified and identified.Experiments show that this method can improve the accuracy of fabric defect recognition.