楚漆器内部不同尺度纵向裂痕视觉检测仿真  

Visual Inspection Simulation of Longitudinal Cracks at Different Scales in Chu Lacquerware

作　　者：郑祖芳 胡瑜琬 ZHENG Zu-fang;HU Yu-wan(School of Industrial Design,Hubei University of Technology,Hubei Wuhan 430068,China)

机构地区：[1]湖北工业大学工业设计学院,湖北武汉430068

出　　处：《计算机仿真》2022年第4期454-458,共5页Computer Simulation

基　　金：教育部人文社会科学研究项目(18YJC760147);湖北工业大学校基金(BSQD14050)。

摘　　要：针对传统漆器内部裂痕检测方法没有获取图像轮廓尺度,导致方法存在检测准确度差、效率低的问题,提出一种楚漆器内部不同尺度纵向裂痕视觉检测方法。对二元高斯函数的梯度灰度图像实施卷积运算,利用迟滞阈值实现二值化操作,得到漆器图像轮廓尺度,对漆器图像采取映射变换处理,通过邻域平均法完成漆器图像的平滑滤波操作,采用灰度阈值分割处理的方式,得到二值图像,引入灰度拉伸算法,实现对楚漆器内部不同尺度纵向裂痕的检测。实验结果表明,研究方法检测精度更高、检测速度更快,具有较好的高效性、准确性和可行性。Aiming at the problems of poor detection accuracy and low efficiency caused by the lack of image contour scale in the traditional internal crack detection method of lacquer ware, a visual detection method of longitudinal cracks with different scales in Chu lacquer ware is proposed. Based on the convolution computation for gradient gray image of binary gaussian function, hysteresis threshold was adopted for binarization, so that the contour scale of lacquer image was obtained. Then, the mapping transformation was performed on lacquer image. The neighborhood average method was used to smooth and filter the lacquer image. Moreover, gray threshold segmentation was used to obtain the binary image. Finally, the gray stretching algorithm was introduced to realize the visual inspection of longitudinal cracks of different scales in the interior of Chu lacquerware. Experimental results show that the proposed method has higher accuracy and faster detection. In addition, it has better efficiency, accuracy, and feasibility.

关 键 词：楚漆器内部 二元高斯函数 迟滞阈值 二值化操作 映射变换 

分 类 号：TP392[自动化与计算机技术—计算机应用技术]