基于改进Hough变换的刹车蹄块片安装孔定位检测法
|
摘要
针对刹车蹄块片质量无损检测系统中参考点建立需求,提出在复杂轮廓边缘中安装孔定位检测方法。该方法首先对刹车蹄块片侧面图像进行多方向Canny边缘提取,采用带辨向梯度Hough变换改进算法,实现对候选圆的粗定位;然后对候选圆边缘区域进行提取,采用最小平方误差拟合法进行候选圆精确定位和测量;最后依据圆完整度信息实现对安装孔的识别筛选。实验表明:该方法能够较准确地识别出安装孔,与其真实边缘之间误差小,取得良好的检测效果。
Aiming at the requirement of establishing reference points in the nondestructive quality inspection system for the brake pads,a method of locating detection for the installation holes was proposed in the complex contour edges. Firstly,the multi-directional Canny edge extraction of the brake pads image was carried out,the improved Hough transform algorithm with direction discrimination was used to realize the coarse positioning of the candidate circles; Secondly,the candidate circles edge regions were extracted and accurately located by the least square error fitting method; Finally,the installation holes were identified and screened according to the circular integrity information.The experiments show that this method can identify the installation holes accurately and have good detection effects while the error between the result and the real installation hole edge is small.
Aiming at the requirement of establishing reference points in the nondestructive quality inspection system for the brake pads,a method of locating detection for the installation holes was proposed in the complex contour edges. Firstly,the multi-directional Canny edge extraction of the brake pads image was carried out,the improved Hough transform algorithm with direction discrimination was used to realize the coarse positioning of the candidate circles; Secondly,the candidate circles edge regions were extracted and accurately located by the least square error fitting method; Finally,the installation holes were identified and screened according to the circular integrity information.The experiments show that this method can identify the installation holes accurately and have good detection effects while the error between the result and the real installation hole edge is small.
引文
[1]CHEN T C,CHUNG K L. An efficient randomized for detecting circle[J]. Computer Vision and Image Understanding,2001,83(2):172-191.
[2]CHEN K,WU J P. One dimensional voting scheme for circle and arc detection[J]. Journal of the Optical Society of America,A,2014,31(12):2593-2602.
[3]陈珂,吴建平,李金祥,等.一维概率Hough变换的实时鲁棒多圆检测方法[J].计算机辅助设计与图形学学报,2015,27(10):1832-1841.
[4]AKIHIKO T,ATSUSHI I. The randomized Hough transform based method for great circle detection on sphere[J]. Pattern Recognition Letters,2007,28(10):1186-1192.
[5]CHIU S H,LIAW J J,LIN K H. A fast randomized hough transform for circle/circular arc recognition[J]. International Journal of Pattern Recognition and Artificial Intelligence,2010,24(3):457-474.
[6]陈树越,李建森,黄萍,等.基于采样约束的随机Hough变换圆检测算法[J].计算机工程,2017,43(10):259-263.
[7]毛顺兵. Hough变换和轮廓匹配相结合的瞳孔精确检测算法[J].计算机应用,2016,36(5):1415-1420.
[8]叶峰,陈灿杰,赖乙宗,等.基于有序Hough变换的快速圆检测算法[J].光学精密工程,2014,22(4):1105-1111.
[9]陈小艳,王强,李柏林.改进的Hough变换检测圆方法[J].计算机系统应用,2015,24(8):197-201.
[10]YUAN B D,LIU M. Power histogram for circle detection on images[J]. Pattern Recognition,2015,48(10):3268-3280.
[11]张红霞,王灿,刘鑫,等.图像边缘检测算法研究新进展[J].2018,54(14):11-18.
[12]尼克松.特征提取与图像处理[M].北京:电子工业出版社,2010.
[13]蔡佳,黄攀峰,张彬.基于梯度的区域生长和距离直方图的快速圆检测方法[J].光学学报,2015,3(3):0315001:1-10.
[14]WANG Y F,CHEN G X. Application of gradient based hough transform to the detection of corrosion pits in optical images[J].Applied Surface Science.2016,366:9-18.
[15]YU H C,WANG T. Vision based technique for circle detection and measurement using lookup table and bitwise center accumulator[J]. Journal of the Optical Society of America,A,2017,34(3):415-423.
[2]CHEN K,WU J P. One dimensional voting scheme for circle and arc detection[J]. Journal of the Optical Society of America,A,2014,31(12):2593-2602.
[3]陈珂,吴建平,李金祥,等.一维概率Hough变换的实时鲁棒多圆检测方法[J].计算机辅助设计与图形学学报,2015,27(10):1832-1841.
[4]AKIHIKO T,ATSUSHI I. The randomized Hough transform based method for great circle detection on sphere[J]. Pattern Recognition Letters,2007,28(10):1186-1192.
[5]CHIU S H,LIAW J J,LIN K H. A fast randomized hough transform for circle/circular arc recognition[J]. International Journal of Pattern Recognition and Artificial Intelligence,2010,24(3):457-474.
[6]陈树越,李建森,黄萍,等.基于采样约束的随机Hough变换圆检测算法[J].计算机工程,2017,43(10):259-263.
[7]毛顺兵. Hough变换和轮廓匹配相结合的瞳孔精确检测算法[J].计算机应用,2016,36(5):1415-1420.
[8]叶峰,陈灿杰,赖乙宗,等.基于有序Hough变换的快速圆检测算法[J].光学精密工程,2014,22(4):1105-1111.
[9]陈小艳,王强,李柏林.改进的Hough变换检测圆方法[J].计算机系统应用,2015,24(8):197-201.
[10]YUAN B D,LIU M. Power histogram for circle detection on images[J]. Pattern Recognition,2015,48(10):3268-3280.
[11]张红霞,王灿,刘鑫,等.图像边缘检测算法研究新进展[J].2018,54(14):11-18.
[12]尼克松.特征提取与图像处理[M].北京:电子工业出版社,2010.
[13]蔡佳,黄攀峰,张彬.基于梯度的区域生长和距离直方图的快速圆检测方法[J].光学学报,2015,3(3):0315001:1-10.
[14]WANG Y F,CHEN G X. Application of gradient based hough transform to the detection of corrosion pits in optical images[J].Applied Surface Science.2016,366:9-18.
[15]YU H C,WANG T. Vision based technique for circle detection and measurement using lookup table and bitwise center accumulator[J]. Journal of the Optical Society of America,A,2017,34(3):415-423.