Please wait a minute...
Journal of ZheJiang University (Engineering Science)  2020, Vol. 54 Issue (12): 2294-2300    DOI: 10.3785/j.issn.1008-973X.2020.12.003
    
Detection method for composite hole guided by texture boundary
Tai-heng ZHANG1(),Biao MEI2,Lei QIAO1,Hao-jie YANG1,Wei-dong ZHU1,*()
1. School of Mechanical Engineering, Zhejiang University, Hangzhou 310027, China
2. Institute of Advanced Technology, Zhejiang University, Hangzhou 310027, China
Download: HTML     PDF(1677KB) HTML
Export: BibTeX | EndNote (RIS)      

Abstract  

A novel hole detection method guided by texture boundary was proposed, aiming to solve the detection problem of composite circular reference holes. The texture contrast based on local ternary pattern (LTP) and gray-level co-occurrence matrix (GLCM) was extracted first to perform the fast segmentation of intra-hole texture and out-of-hole texture, which could obtain the texture boundaries closely matching the hole boundaries. Then, the position information of texture boundaries was used to remove most of the edge points that belong to non-hole boundaries. The connectivity information of texture boundaries was used to group the remaining edge points. Finally, the randomized circle detection method with circle-parameter statistics mechanism was applied to detect a single circle from each group of edge points, which completed the detection of multiple hole targets. Experimental results showed that this method had a detection rate of more than 94%, an error rate of less than 3%, a high detection speed and good detection robustness in the composite hole detection scene.



Key wordslocal binary pattern (LBP)      local ternary pattern (LTP)      gray-level co-occurrence matrix (GLCM)      texture segmentation      circle detection      robotic drilling     
Received: 29 October 2019      Published: 31 December 2020
CLC:  TP 391  
Corresponding Authors: Wei-dong ZHU     E-mail: thzhang@zju.edu.cn;wdzhu@zju.edu.cn
Cite this article:

Tai-heng ZHANG,Biao MEI,Lei QIAO,Hao-jie YANG,Wei-dong ZHU. Detection method for composite hole guided by texture boundary. Journal of ZheJiang University (Engineering Science), 2020, 54(12): 2294-2300.

URL:

http://www.zjujournals.com/eng/10.3785/j.issn.1008-973X.2020.12.003     OR     http://www.zjujournals.com/eng/Y2020/V54/I12/2294


纹理边界引导的复合材料圆孔检测方法

针对复合材料纹理背景下圆形基准孔检测困难的问题,提出一种纹理边界引导的圆孔检测方法.该方法将局部三进制模式(LTP)与灰度共生矩阵(GLCM)对比度融合为纹理对比度,通过提取纹理对比度特征实现孔内纹理和孔外纹理的快速分割,得到与圆孔边界近似吻合的纹理边界,利用纹理边界的位置信息去除绝大多数非圆孔边界的边缘点,利用纹理边界的连通信息对剩余边缘点进行分组,使用内嵌圆参数统计机制的随机圆检测算法从每组边缘点各检出1个圆孔目标,进而完成对多个圆孔目标的检测.实验结果表明,在复合材料圆孔检测场景中该方法有94%以上检出率,3%以下检错率和较高的检测速度,并表现出良好的检测鲁棒性.


关键词: 局部二进制模式(LBP),  局部三进制模式(LTP),  灰度共生矩阵(GLCM),  纹理分割,  圆检测,  机器人制孔 
Fig.1 Principle of local binary pattern
Fig.2 Circle detection guided by texture boundary
Fig.3 RCD on single group of edge points
Fig.4 Texture boundary results and algorithm efficiency of different texture segmentation methods
纹理量化方法 对比度差值 纹理量化方法 对比度差值
原图 36 LTP 104
LBP 79 VLTP 130
Tab.1 Contrast difference between two textures of different texture description methods
圆孔类别 待检孔数 检出圆孔数
RCD投票 统计机制
图2 56 7 48
图4 40 23 17
Tab.2 Hole detection results of RCD voting and statistical record
Fig.5 Visualization of some experimental results for VRSR, EDCircles and RCD
圆孔
类别
检测效率/ms 检出率 检错率
VGSR EDCircles VGSR EDCircles VGSR EDCircles
F1 39.8 6.8 30/30 30/30 0/30 0/30
F2 41.6 20.1 39/43 36/43 0/43 0/43
F3 45.6 14.4 68/71 60/71 3/71 3/71
F4 46.8 13.4 46/50 36/50 2/50 8/50
F5 45.7 17.5 41/44 22/44 0/44 4/44
F6 53.0 13.9 40/40 20/40 0/40 4/40
F7 44.1 14.9 32/35 15/35 3/35 9/35
F8 42.2 16.1 54/58 21/58 0/58 0/58
F9 48.6 17.6 18/21 3/21 2/21 0/21
F10 44.7 14.3 55/56 7/56 0/56 4/56
F11 42.0 16.5 26/28 2/28 1/28 1/28
总计 44.9 15.0 94.3% 52.9% 2.3% 6.9%
Tab.3 Comparison of VGSR and EDCircles on hole detection performance
[1]   韦红余, 陈文亮, 蒋红宇, 等 面向现代飞机装配的长寿命机械连接技术[J]. 航空制造技术, 2009, (17): 34- 37
WEI Hong-yu, CHEN Wen-liang, JIANG Hong-yu, et al Long-life mechanical connecting technology for modern aircaft assembly[J]. Aeronautical Manufacturing Technology, 2009, (17): 34- 37
doi: 10.3969/j.issn.1671-833X.2009.17.004
[2]   卜泳, 许国康, 肖庆东 飞机结构件的自动化精密制孔技术[J]. 航空制造技术, 2009, (24): 61- 64
BO Yong, XU Guo-kang, XIAO Qing-dong Automatic precision drilling technology of aircraft structural part[J]. Aeronautical Manufacturing Technology, 2009, (24): 61- 64
doi: 10.3969/j.issn.1671-833X.2009.24.011
[3]   ZHU W D, MEI B, YAN G R, et al Development of a monocular vision system for robotic drilling[J]. Journal of Zhejiang University-Science C: Computers and Electronics, 2014, 15 (8): 593- 606
doi: 10.1631/jzus.C1300379
[4]   FENG X, FANG C, DING X, et al. Iris localization with dual coarse-to-fine strategy [C] // International Conference on Pattern Recognition. Hong Kong: IEEE Computer Society, 2006.
[5]   FLEYEH H, DAVAMI E Eigen-based traffic sign recognition[J]. IET Intelligent Transport Systems, 2011, 5 (3): 190- 196
doi: 10.1049/iet-its.2010.0159
[6]   廖苗, 赵于前, 曾业战, 等 基于支持向量机和椭圆拟合的细胞图像自动分割[J]. 浙江大学学报: 工学版, 2017, 51 (4): 722- 728
LIAO Miao, ZHAO Yu-qian, ZENG Ye-zhan, et al Automatic segmentation for cell images based on support vector machine and ellipse fitting[J]. Journal of Zhejiang University: Engineering Science, 2017, 51 (4): 722- 728
[7]   LEO M, MAZZEO P L, NITTI M Accurate ball detection in soccer images using probabilistic analysis of salient regions[J]. Machine Vision and Applications, 2013, 24 (8): 1561- 1574
doi: 10.1007/s00138-013-0518-9
[8]   XIAO T, LI S, WANG B, et al. Joint detection and identification feature learning for person search [C] // 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017.
[9]   DAHYOT R Statistical Hough transform[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31 (8): 1502- 1509
doi: 10.1109/TPAMI.2008.288
[10]   MUKHOPADHYAY P, CHAUDHURI B B A survey of Hough transform[J]. Pattern Recognition, 2015, 48 (3): 993- 1010
doi: 10.1016/j.patcog.2014.08.027
[11]   DUDA R O Use of the Hough transformation to detect lines and curves in pictures[J]. Communications of the ACM, 1972, 15 (1): 11- 15
doi: 10.1145/361237.361242
[12]   CHEN T C, CHUNG K L An efficient randomized algorithm for detecting circles[J]. Computer Vision and Image Understanding, 2001, 83 (2): 172- 191
doi: 10.1006/cviu.2001.0923
[13]   AKINLAR C, TOPAL C EDCircles: a real-time circle detector with a false detection control[J]. Pattern Recognition, 2013, 46 (3): 725- 740
doi: 10.1016/j.patcog.2012.09.020
[14]   TAN X, TRIGGS B Enhanced local texture feature sets for face recognition under difficult lighting conditions[J]. IEEE Transactions on Image Processing, 2010, 19 (6): 1635- 1650
doi: 10.1109/TIP.2010.2042645
[15]   HARALICK R M Texture feature for image classification[J]. IEEE Transaction on Systems, Man, and Cybernetics, 1973, 3 (6): 610- 621
[16]   OJALA T, HARWOOD I A comparative study of texture measures with classification based on feature distributions[J]. Pattern Recognition, 1996, 29 (1): 51- 59
doi: 10.1016/0031-3203(95)00067-4
[17]   AKHLOUFI M A, BENDADA A. Locally adaptive texture features for multispectral face recognition [C] // 2010 IEEE International Conference on Systems Man and Cybernetics. Istanbul: IEEE, 2010.
[18]   LIAO W H, YOUNG T J. Texture classification using uniform extended local ternary patterns [C] // IEEE International Symposium on Multimedia. Taichung: IEEE, 2011.
[19]   侯群群, 王飞, 严丽 基于灰度共生矩阵的彩色遥感图像纹理特征提取[J]. 国土资源遥感, 2013, 25 (4): 26- 32
HOU Qun-qun, WANG Fei, YAN Li Extraction of color image texture feature based on gray-level co-occurrence matrix[J]. Remote Sensing for Land and Resources, 2013, 25 (4): 26- 32
[20]   ERSHAD S F. Texture classification approach based on combination of edge and co-occurrence and local binary pattern [C] // International Conference on Image Processing, Computer Vision, and Pattern Recognition. Harbin: [s.n.], 2011.
[21]   MALLAIAH S, DANTI A, NARASIMHAMURTHY S K Invariant of rotation and scaling for classification of arecanut based on local binary patterns[J]. International Journal of Computer Science and Software Engineering, 2013, 3 (10): 598
[22]   WANG G D, ZHANG P L, REN G Q, et al Texture feature extraction method fused with LBP and GLCM[J]. Computer Engineering, 2012, 38 (11): 199- 201
[23]   TANG Z, SU Y, ER M J, et al A local binary pattern based texture descriptors for classification of tea leaves[J]. Neurocomputing, 2015, 168: 1011- 1023
doi: 10.1016/j.neucom.2015.05.024
[1] CHEN Wei, ZHU Wei dong, ZHANG Ming, ZHAO Jian dong, MEI Biao. Clamping force prediction for robotic drilling of stacked structure[J]. Journal of ZheJiang University (Engineering Science), 2015, 49(12): 2282-2289.
[2] HE Zhi-xiang, DING Xiao-qing, FANG Chi, WEN Di. Multiview face detection based on LBP and CCS-AdaBoost[J]. Journal of ZheJiang University (Engineering Science), 2013, 47(4): 622-629.