基于最优识别区间的变步长产品表面缺陷检测研究

徐青; 韩跃平; 杨志刚; 孙宝华

doi:doi:10.3788/lop50.101001

激光与光电子学进展, 2013, 50 (10): 101001, 网络出版: 2013-09-04

基于最优识别区间的变步长产品表面缺陷检测研究

Variable Step Detection of Product Surface Defect Based on Optimal Identification Interval

论文大纲

徐青 ^*韩跃平杨志刚孙宝华

作者单位

中北大学信息与通信工程学院, 山西太原 030051

摘要

为实现对产品表面多个待检区域准确快速的检测，在最优识别区间内采用变步长机制快速获取待测产品的周向方位图像序列，实现在有限方位下利用不完全数据对多个待识别区域的快速检测。首先通过相关度计算及投影法确定各待检区域的最优识别区间和旋转步长，其次采用尺度不变特征变换（SIFT）算法与折半查找法确定随机摆放的待检产品在标准库中的最优位置信息，最后通过相关度计算判别各区域有无缺陷。实验表明在保证检测准确率的前提下，基于最优识别区间的变步长方法比传统全周向固定步长检测平均可节省6.37 s。

Abstract

In order to achieve the detection of multiple regions in the product surface rapidly and accurately, we select variable step mechanism to obtain the circumferential image sequence of the products to be tested in the optimal recognition interval quickly so that some incomplete data could be utilized to realize the rapid detection of multiple areas in the limited orientation. First of all, we need to determine the optimal identification range of the area and the rotation step through relativity calculation and projection method. Secondly, the scale invariant feature transform (SIFT) algorithm and binary search method are selected to find the optimal location information of product in the standard image library. Finally, we distinguish there are some defects or not by relativity calculation. The experiment results demonstrate that the variable step size method based on optimal identification interval can save an average time of 6.37 s than the traditional full-circumferential fixed step method while ensuring the detection accuracy.

参考文献

[1] 徐浪, 曾忠, 刘金赞, 等. 机器视觉在印刷缺陷在线检测中的应用与研究[J]. 计算机系统应用, 2013, 22(3): 186-190.

Xu Lang, Zeng Zhong, Liu Jinzan, et al.. Application and research of machine vision on on-line inspection for printed defect[J]. Computer Systems & Applications, 2013, 22(3): 186-190.

[2] 张学武, 丁燕琼, 闫萍. 一种基于红外成像的强反射金属表面缺陷视觉检测方法[J]. 光学学报, 2011, 31(3): 0312004.

Zhang Xuewu, Ding Yanqiong, Yan Ping. Vision inspection of metal surface defects based on infrared imaging[J]. Acta Optica Sinica, 2011, 31(3): 0312004.

[3] 李亚萍, 张广军, 李庆波. 基于O2-PLS方法的血糖无损检测实验研究[J]. 光学学报, 2010, 30(3): 854-860.

Li Yaping, Zhang Guangjun, Li Qingbo. Application of O2-PLS in experimental study on non-invasive measurement of blood glucose[J]. Acta Optica Sinica, 2010, 30(3): 854-860.

[4] 吴一全, 尹丹艳. 基于FLS-SVM背景预测的红外弱小目标检测[J]. 光学学报, 2010, 30(10): 2806-2811.

Wu Yiquan, Yin Danyan. Detection of small target in infrared image based on background predication by FLS-SVM[J]. Acta Optica Sinica, 2010, 30(10): 2806-2811.

[5] 龚芳, 张学武, 孙浩. 基于独立分量分析和粒子群算法的太阳能电池表面缺陷红外热成像检测[J]. 光学学报, 2012, 32(4): 0415002.

Gong Fang, Zhang Xuewu, Sun Hao. Detection system for module surface defects based on constrained ICA model and PSO method[J]. Acta Optica Sinica, 2012, 32(4): 0415002.

[6] 沈峘, 李舜酩, 柏方超, 等. 路面车辆实时检测与跟踪的视觉方法[J]. 光学学报, 2010, 30(4): 1076-1083.

Shen Huan, Li Shunming, Bo Fangchao, et al.. On road vehicles real-time detection and tracking using vision based approach[J]. Acta Optica Sinica, 2010, 30(4): 1076-1083.

[7] 韩芳芳. 表面缺陷视觉在线检测关键技术研究[D]. 天津: 天津大学, 2011. 3-7.

Han Fangfang. Key Techniques for Surface Defects Online Detection Based on Ma chine Vision[D]. Tianjin: Tianjin University, 2011. 3-7.

[8] 王文成, 常发亮. 一种基于区域投影的人眼精确定位方法[J]. 光电子·激光, 2011, 22(4): 618-622.

Wang Wencheng, Chang Faliang. A precise eye localization method based on region projection[J]. J Optoelectronics Laser, 2011, 22(4): 618-622.

[9] Matas J, Chum O, Urban M, et al.. Robust wide-baseline stereo from maximally stable extremal regions[J]. Image and Vision Computing, 2004, 22(10): 761-767.

[10] Mikolajczyk K, Schmid C. Scale & affine invariant interest point detectors[J]. International J Computer Vision, 2004, 60(1): 63-86.

[11] Lakemond Ruan, Sridharan Sridha, Fookes Clinton. Hessian-based affine adaptation of salient local image features[J]. J Mathematical Imaging and Vision, 2012, 44(2): 150-167.

[12] Tuytelaars T, Van Gool L. Matching widely separated views based on affine invariant regions[J]. International J Computer Vision, 2004, 59(1): 61-85.

[13] Yu Guoshen, Morel J M. ASIFT: a new framework for fully affine invariant image comparison[J]. SIAM J Imaging Sciences, 2009, 2(2): 438-469.

[14] 及莹, 陆月明. 一种基于SIFT算法的图像镜像变换识别方法[J]. 计算机应用研究, 2013, 30(3): 924-926.

Ji Ying, Lu Yueming. Method based on SIFT for recognition of flip images[J]. Application Research of Computers, 2013, 30(3): 924-926.

[15] Lowe D G. Distinctive image features from scale-invariant keypoints[J]. International J Computer Vision, 2004, 60(2): 91-110.

徐青, 韩跃平, 杨志刚, 孙宝华. 基于最优识别区间的变步长产品表面缺陷检测研究[J]. 激光与光电子学进展, 2013, 50(10): 101001. Xu Qing, Han Yueping, Yang Zhigang, Sun Baohua. Variable Step Detection of Product Surface Defect Based on Optimal Identification Interval[J]. Laser & Optoelectronics Progress, 2013, 50(10): 101001.

基于最优识别区间的变步长产品表面缺陷检测研究

关于本站 Cookie 的使用提示

全站搜索

基于最优识别区间的变步长产品表面缺陷检测研究

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索