摘要
将视觉技术应用于轮胎帘布的疵点检测,通过预处理和二值化提高了以灰度共生矩阵法提取图像特征值的计算速度和准确率,并结合欧式距离特征匹配法实现了对待测图像的疵点判别。
The vision technology is applied for detecting defects in tire cord surface.We use both the pretreatment and threshold to improve the image extracting speed and accuracy of gray level co-occurrence matrix method,and combine the method with the Euclidean distance matching measurement to realize the defect detection.
出处
《长春工业大学学报》
CAS
2010年第6期669-673,共5页
Journal of Changchun University of Technology
关键词
图像处理
纹理
灰度共生矩阵
特征提取
image processing
texture
gray level co-occurrence matrix
feature extraction
