基于双重阈值和张量投票的表面裂纹检测算法
|
摘要
针对裂纹与背景之间的低对比度及裂纹区域内灰度值不均匀所导致的裂纹提取困难问题,提出一种基于双边滤波和局部灰度差相结合的双重阈值裂纹片段提取法,并结合张量投票算法进行裂纹检测。该算法采用双重阈值法获取裂纹片段,并根据裂纹片段的接近度和连续性特征,通过张量投票算法得到裂纹的显著性图谱以及完整的裂纹曲线,利用裂纹曲线对裂纹片段进行连接并去除离散点,完成准确裂纹提取。实验结果表明,相比于根据裂纹片段首尾位置进行连接的方法,该算法处理类陶瓷元件表面裂纹图像时F-measure提高了约27%。
The double threshold method based on the combination of bilateral filter and local grayscale difference is proposed to extract crack segments,and tensor voting algorithm is adopted to solve the problem of crack extraction caused by low contrast between cracks and background,as well as unevenness of gray values within the crack region.The double threshold method is introduced to obtain crack segments,and then based on proximity and continuity of crack fragments,the significant map and complete center line are obtained with tensor voting.Accurate crack extraction is realized by connecting crack fragment and removing discrete points with center line.Experimental results show that,compared with the method based on the beginning and end of crack fragments to connect,the proposed algorithm can increase F-measure about 27% to process the surface image of ceramic elements with cracks.
The double threshold method based on the combination of bilateral filter and local grayscale difference is proposed to extract crack segments,and tensor voting algorithm is adopted to solve the problem of crack extraction caused by low contrast between cracks and background,as well as unevenness of gray values within the crack region.The double threshold method is introduced to obtain crack segments,and then based on proximity and continuity of crack fragments,the significant map and complete center line are obtained with tensor voting.Accurate crack extraction is realized by connecting crack fragment and removing discrete points with center line.Experimental results show that,compared with the method based on the beginning and end of crack fragments to connect,the proposed algorithm can increase F-measure about 27% to process the surface image of ceramic elements with cracks.
引文
[1]Liang S D,Zhang A F,Wang T,et al.Elimination of laser direct forming crack on DD4 parts by induction heating[J].Chinese Journal of Lasers,2017,44(2):0202003.梁少端,张安峰,王潭,等.感应加热消除激光直接成形DD4零件裂纹[J].中国激光,2017,44(2):0202003.
[2]Wang B,Wang X,Chen F,et al.Pavement crack recognition based on aerial image[J].Acta Optica Sinica,2017,37(8):0810004.王博,王霞,陈飞,等.航拍图像的路面裂缝识别[J].光学学报,2017,37(8):0810004.
[3]Chen J,Zhu Q B,Huang M,et al.Recognition of empoasca flavescens based on machine vision[J].Laser&Optoelectronics Progress,2018,55(1):011502.陈晶,朱启兵,黄敏,等.基于机器视觉的茶小绿叶蝉识别方法研究[J].激光与光电子学进展,2018,55(1):011502.
[4]Kirschke K R,Velinsky S A.Histogram-based approach for automated pavement-crack sensing[J].Journal of Transportation Engineering,1992,118(5):700-710.
[5]Li Q Q,Liu X L.Novel approach to pavement image segmentation based on neighboring difference histogram method[C]∥Proceedings of IEEEComputer Society,2008,2:792-796.
[6]Tsai Y,Kaul V,Mersereau R M.Critical assessment of pavement distress segmentation methods[J].Journal of Transportation Engineering,2010,136(1):11-19.
[7]Yan M D,Bo S B,Xu K,et al.Pavement crack detection and analysis for high-grade highway[C]∥Proceedings of International Conference on Electronic Measurement and Instruments,2007:548-552.
[8]Liu F F,Xu G A,Yang Y X,et al.Novel approach to pavement cracking automatic detection based on segment extending[C]∥Proceedings of International Symposium on Knowledge Acquisition and Modeling,2008:610-614.
[9]Hua C J,Xiong X M,Chen Y.Feature extraction of workpiece circular arc contour based on Sobel operator[J].Laser&Optoelectronics Progress,2018,55(2):021011.化春键,熊雪梅,陈莹.基于Sobel算子的工件圆弧轮廓特征提取[J].激光与光电子学进展,2018,55(2):021011.
[10]Subirats P,Dumoulin J,Legeay V,et al.Automation of pavement surface crack detection using the continuous wavelet transform[C]∥Proceedings of IEEE International Conference on Image Processing,2007:3037-3040.
[11]Medioni G,Lee M S,Tang C K.A Computational framework for segmentation and grouping[M].Amsterdam:Halland Elsevier,2000.
[12]Zou Q,Cao Y,Li Q Q,et al.Crackree:automatic crack detection from pavement images[J].Pattern Recognition Letters,2012,33(3):227-238.
[13]Guan H Y,Li J,Yu Y T,et al.Iterative tensor voting for pavement crack extraction using mobile laser scanning data[J].IEEE Transactions on Geoscience and Remote Sensing,2015,53(3):1527-1537.
[14]Shu J F,Chen X D,Huang J J.Research and application of tensor voting on wall crack detection[J].Journal of Geomatics,2017,42(2):80-84.束进芳,陈晓东,黄晶晶.墙体裂缝检测中张量投票算法的应用研究[J].测绘地理信息,2017,42(2):80-84.
[15]Tomasi C,Manduchi R.Bilateral filtering for gray and color images[C]∥Proceedings of 6thInternational Conference on Computer Vision,1998:839-846.
[16]Li J F,Yang F,Huang J.A fast implementation of improved bilateral filter based on ascending dimension[J].Journal of Circuits and Systems,2013,18(1):137-143.李俊峰,杨丰,黄靖.一种改进的增维型双边滤波的快速算法[J].电路与系统学报,2013,18(1):137-143.
[17]Paris S,Durand F.A fast approximation of the bilateral filter using a signal processing approach[J].International Journal of Computer Vision,2009,81(1):24-52.
[18]Mou L,Zhang X W,Zhang Z,et al.Saliency detection optimization method in natural scene[J].Laser&Optoelectronics Progress,2016,53(12):121501.牟丽,张学武,张卓,等.自然场景下的显著性检测优化方法[J].激光与光电子学进展,2016,53(12):121501.
[19]Guy G,Medioni G.Inferring global perceptual contours from local features[J].International Journal of Computer Vision,1996,20(1):113-133.
[20]Xu W,Tang Z M,LüJ Y,Pavement crack detection based on image saliency[J].Journal of Image and Graphics,2013,18(1):69-77.徐威,唐振民,吕建勇.基于图像显著性的路面裂缝检测[J].中国图象图形学报,2013,18(1):69-77.
[21]Xu W,Tang Z M,Xu D,et al.Integrating multifeatures fusion and gestalt principles for pavement crack detection[J].Journal of Computer-Aided Design&Computer Graphics,2015,27(1):147-156.徐威,唐振民,徐丹,等.融合多特征与格式塔理论的路面裂缝检测[J].计算机辅助设计与图形学学报,2015,27(1):147-156.
[22]Zhang G Q.Study on the concrete bridge bottom crack inspection method based on image processing[D].Beijing:Beijing Jiaotong University,2010.张国旗.基于图像处理的混凝土桥梁底面裂缝检测方法的研究[D].北京:北京交通大学,2010.
[2]Wang B,Wang X,Chen F,et al.Pavement crack recognition based on aerial image[J].Acta Optica Sinica,2017,37(8):0810004.王博,王霞,陈飞,等.航拍图像的路面裂缝识别[J].光学学报,2017,37(8):0810004.
[3]Chen J,Zhu Q B,Huang M,et al.Recognition of empoasca flavescens based on machine vision[J].Laser&Optoelectronics Progress,2018,55(1):011502.陈晶,朱启兵,黄敏,等.基于机器视觉的茶小绿叶蝉识别方法研究[J].激光与光电子学进展,2018,55(1):011502.
[4]Kirschke K R,Velinsky S A.Histogram-based approach for automated pavement-crack sensing[J].Journal of Transportation Engineering,1992,118(5):700-710.
[5]Li Q Q,Liu X L.Novel approach to pavement image segmentation based on neighboring difference histogram method[C]∥Proceedings of IEEEComputer Society,2008,2:792-796.
[6]Tsai Y,Kaul V,Mersereau R M.Critical assessment of pavement distress segmentation methods[J].Journal of Transportation Engineering,2010,136(1):11-19.
[7]Yan M D,Bo S B,Xu K,et al.Pavement crack detection and analysis for high-grade highway[C]∥Proceedings of International Conference on Electronic Measurement and Instruments,2007:548-552.
[8]Liu F F,Xu G A,Yang Y X,et al.Novel approach to pavement cracking automatic detection based on segment extending[C]∥Proceedings of International Symposium on Knowledge Acquisition and Modeling,2008:610-614.
[9]Hua C J,Xiong X M,Chen Y.Feature extraction of workpiece circular arc contour based on Sobel operator[J].Laser&Optoelectronics Progress,2018,55(2):021011.化春键,熊雪梅,陈莹.基于Sobel算子的工件圆弧轮廓特征提取[J].激光与光电子学进展,2018,55(2):021011.
[10]Subirats P,Dumoulin J,Legeay V,et al.Automation of pavement surface crack detection using the continuous wavelet transform[C]∥Proceedings of IEEE International Conference on Image Processing,2007:3037-3040.
[11]Medioni G,Lee M S,Tang C K.A Computational framework for segmentation and grouping[M].Amsterdam:Halland Elsevier,2000.
[12]Zou Q,Cao Y,Li Q Q,et al.Crackree:automatic crack detection from pavement images[J].Pattern Recognition Letters,2012,33(3):227-238.
[13]Guan H Y,Li J,Yu Y T,et al.Iterative tensor voting for pavement crack extraction using mobile laser scanning data[J].IEEE Transactions on Geoscience and Remote Sensing,2015,53(3):1527-1537.
[14]Shu J F,Chen X D,Huang J J.Research and application of tensor voting on wall crack detection[J].Journal of Geomatics,2017,42(2):80-84.束进芳,陈晓东,黄晶晶.墙体裂缝检测中张量投票算法的应用研究[J].测绘地理信息,2017,42(2):80-84.
[15]Tomasi C,Manduchi R.Bilateral filtering for gray and color images[C]∥Proceedings of 6thInternational Conference on Computer Vision,1998:839-846.
[16]Li J F,Yang F,Huang J.A fast implementation of improved bilateral filter based on ascending dimension[J].Journal of Circuits and Systems,2013,18(1):137-143.李俊峰,杨丰,黄靖.一种改进的增维型双边滤波的快速算法[J].电路与系统学报,2013,18(1):137-143.
[17]Paris S,Durand F.A fast approximation of the bilateral filter using a signal processing approach[J].International Journal of Computer Vision,2009,81(1):24-52.
[18]Mou L,Zhang X W,Zhang Z,et al.Saliency detection optimization method in natural scene[J].Laser&Optoelectronics Progress,2016,53(12):121501.牟丽,张学武,张卓,等.自然场景下的显著性检测优化方法[J].激光与光电子学进展,2016,53(12):121501.
[19]Guy G,Medioni G.Inferring global perceptual contours from local features[J].International Journal of Computer Vision,1996,20(1):113-133.
[20]Xu W,Tang Z M,LüJ Y,Pavement crack detection based on image saliency[J].Journal of Image and Graphics,2013,18(1):69-77.徐威,唐振民,吕建勇.基于图像显著性的路面裂缝检测[J].中国图象图形学报,2013,18(1):69-77.
[21]Xu W,Tang Z M,Xu D,et al.Integrating multifeatures fusion and gestalt principles for pavement crack detection[J].Journal of Computer-Aided Design&Computer Graphics,2015,27(1):147-156.徐威,唐振民,徐丹,等.融合多特征与格式塔理论的路面裂缝检测[J].计算机辅助设计与图形学学报,2015,27(1):147-156.
[22]Zhang G Q.Study on the concrete bridge bottom crack inspection method based on image processing[D].Beijing:Beijing Jiaotong University,2010.张国旗.基于图像处理的混凝土桥梁底面裂缝检测方法的研究[D].北京:北京交通大学,2010.