摘要
皮革缺陷检测技术落后是影响皮革行业快速发展的众多原因之一,因此改进检测方法是皮革行业快速转型升级的重要手段之一。论文提出一种基于分块的PCA融合算法和迭代阈值分割算法相结合的皮革缺陷检测方法。该算法可以一次性检测出皮革中孔洞缺陷(穿透和未穿透)和表面划痕缺陷,经实验证明论文提出的算法相比其他方法,检测效果更好,分割出的缺陷轮廓更加清晰、完整,检测准确度高达83.9%。
The backward leather defect detection technology is one of the many reasons that affect the rapid development of the leather industry.Therefore,improving the detection method is one of the important means for the rapid transformation and up⁃grading of the leather industry.This paper proposes a leather defect detection method based on the combination of a block-based PCA fusion algorithm and an iterative threshold segmentation algorithm.This algorithm can detect hole defects(penetration and non-penetration)and surface scratches in leather at one time.Experiments show that the algorithm proposed in this paper has better detection effect than other methods,and the segmented defect contours are clearer,Complete,the detection accuracy is as high as 83.9%.
作者
张森
郑洲洲
ZHANG Sen;ZHENG Zhouzhou(College of Electromechanical Engineering,Qingdao University of Science and Technology,Qingdao 266061)
出处
《计算机与数字工程》
2022年第7期1510-1515,共6页
Computer & Digital Engineering
关键词
皮革
缺陷检测
PCA
红外热成像
阈值分割
leather
defect detection
PCA
infrared thermal imaging
threshold segmentation
