基于改进的标记分水岭方法的棒材识别
|
摘要
针对图像中棒材识别问题,提出了一种新的标记分水岭的棒材分割识别方法,该方法结合距离变换与梯度重构对标记点进行限定,使用分水岭变换完成棒材识别。首先利用棒材图像低频部分进行阈值的自动提取,对区域对应的距离图中的局部极值点进行筛选。提取棒材图像中低频成份对应的局部极值区域,结合局部极值点得到前景标记。然后基于前景标记进行距离分水岭变换,将分水岭变换得到的脊线作为背景标记。最后对梯度重构以后的棒材图像基于标记进行梯度分水岭变换,得到棒材分割识别结果。本文方法一方面结合距离图进行标记点筛选及补充得到准确的棒材数目,有效解决了分水岭算法目标识别的过分割问题。另一方面保留了梯度图像分水岭变换后边缘定位准确的优点,得到完整的棒材轮廓。实验结果表明,该方法满足图像识别的实时性、鲁棒性、准确性要求,可将其应用于类圆目标识别及相关领域。
Aiming at the problem of bar identification in image,A new method of bar segmentation and identification for marking watershed is proposed.This method combines the distance transformation and gradient reconstruction to define the marking points,and uses watershed transformation to complete bar identification.Firstly,the low-frequency part of the bar image is used to automatically extract the threshold,and the local extreme points in the distance map corresponding to the area are screened.Extract the local extremum region corresponding to the low-frequency component in the bar image and combine the local extremum to obtain the foreground mark.Then the watershed is transformed based on the foreground marker,and the ridge line obtained by the watershed transformation is used as the background marker.Finally,after the gradient reconstruction,the bar image is the gradient-based watershed based on the marker to obtain the bar segmentation recognition result.In this paper,we combine the distance graph to select the marker point and add the exact number of bars,and solve the over-segmentation problem in the target recognition of watershed algorithm effectively.On the other hand,the advantages of accurate edge location after watershed transformation of gradient image are preserved,and the complete bar profile is obtained.Experimental results show that this method satisfies the real-time,robustness and accuracy requirements of image recognition,and can be applied to the recognition of quasi circle target and related fields.
Aiming at the problem of bar identification in image,A new method of bar segmentation and identification for marking watershed is proposed.This method combines the distance transformation and gradient reconstruction to define the marking points,and uses watershed transformation to complete bar identification.Firstly,the low-frequency part of the bar image is used to automatically extract the threshold,and the local extreme points in the distance map corresponding to the area are screened.Extract the local extremum region corresponding to the low-frequency component in the bar image and combine the local extremum to obtain the foreground mark.Then the watershed is transformed based on the foreground marker,and the ridge line obtained by the watershed transformation is used as the background marker.Finally,after the gradient reconstruction,the bar image is the gradient-based watershed based on the marker to obtain the bar segmentation recognition result.In this paper,we combine the distance graph to select the marker point and add the exact number of bars,and solve the over-segmentation problem in the target recognition of watershed algorithm effectively.On the other hand,the advantages of accurate edge location after watershed transformation of gradient image are preserved,and the complete bar profile is obtained.Experimental results show that this method satisfies the real-time,robustness and accuracy requirements of image recognition,and can be applied to the recognition of quasi circle target and related fields.
引文
[1] WANG Gang,SUN Xiao-liang,SHANG Yang,et al.A robust template matching algorithm based on best-buddies similarity[J].Acta Optica Sinica,2017,37(3):281-287.王刚,孙晓亮,尚洋,等.一种基于最佳相似点对的稳健模板匹配算法[J].光学学报,2017,37(3):281-287.
[2] Zhao C,Zhao H,Yao W.Fuzzy C-means clustering based on improved marked watershed transformation[J].2016,14(3):981-986.
[3] Ning Z,Shen W,Cheng X.Adhesion ore image separation method based on concave points matching[M].Information Technology and Intelligent Transportation Systems.Springer International Publishing,2017.
[4] Yang Y,Wang Y,Qian J.Building identification from SAR image based on the modified marker-controlled watershed algorithm[C].Geoscience and Remote Sensing Symposium.IEEE,2015,2481-2484.
[5] Tian X,Yu W.Color image segmentation based on watershed transform and feature clustering[C].Advanced Information Management,Communicates,Electronic and Automation Control Conference.IEEE,2017,1830-1833.
[6] Cai Q,Liu Y Q,Cao J,et al.A watershed image segmentation algorithm based on self-adaptive marking and interregional affinity propagation clustering[J].Acta Electronica Sinica,2017,45(8):1911-1918.
[7] Gonzalez R C,Woods R E.Digital image processing[M].3rd ed.Beijing:Publishing House of Electronics Industry,2010,468-471.
[8] Figliuzzi B,Chang K,Faessel M.Hierarchical segmentation based upon multi-resolution approximations and the watershed transform[C].International Symposium on Mathematical Morphology and Its Applications to Signal and Image Processing.Springer,Cham,2017,185-195.
[9] GAO Li,YANG Shu-yuan,LI Hai-qiang.New unsupervised image segmentation via Marker-based watershed[J].Joumal of Image Graphics,2007,(6):1025-1032.高丽,杨树元,李海强.一种基于标记的分水岭图像分割新算法[J].中国图象图形学报,2007(6):1025-1032.
[10] WEN Kai-feng,YE Shi-tong,WAN Zhi-ping.Infrared target segmentation algorithm based on maximum entropy threshold in complex background[J].Laser & Infrared,2016,46(1):103-108.温凯峰,叶仕通,万智萍.复杂背景下的最大熵阈值红外目标分割算法[J].激光与红外,2016,46(1):103-108.
[11] MIAO Hui-si,LIANG Guang-ming,LIU Ren-ren,et al.Watershed algorithm using edge gradient combined with distance transformation for segmentation of blood cells[J].Journal of Image and Graphics,2016,21(2):192-198.缪慧司,梁光明,刘任任,等.结合距离变换与边缘梯度的分水岭血细胞分割[J].中国图象图形学报,2016,21(2):192-198.
[12] WANG Ya.Adaptive marked watershed segmentation algorithm for red blood cell images[J].Journal of Image and Graphics,2017,22(12):1779-1787.王娅.血液红细胞图像自适应标记分水岭分割算法[J].中国图象图形学报,2017,22(12):1779-1787.
[13] Xu L,Lu H,Zhang M.Automatic segmentation of clustered quantum dots based on improved watershed transformation[J].Digital Signal Processing,2014,34(1):108-115.
[14] FANG Hong-ping,FANG Kang-ling,LIU Xin-hai.Clustered cells segmentation using modified watershed method based on adaptive H-minima[J].Application Research of Computers,2016,33(5):1587-1590.方红萍,方康玲,刘新海.自适应H-minima的改进分水岭堆叠细胞分割方法[J].计算机应用研究,2016,33(5):1587-1590.
[15] Koyuncu C F,Akhan E,Ersahin T,et al.Iterative h-minima-based marker-controlled watershed for cell nucleus segmentation[J].Cytometry Part A,2016,89(4):338-349.
[16] ZHANG Gui-mei,ZHOU Ming-ming,MA Ke.Image segmentation algorithm for reconstruction labeling watershed in color space[J].Journal of Image and Graphics,2012,17(5):641-647.张桂梅,周明明,马珂.基于彩色模型的重构标记分水岭分割算法[J].中国图象图形学报,2012,17(5):641-647.
[17] Qiang C,Liu Y Q,Jian C,et al.A watershed image segmentation algorithm based on self-adaptive marking and interregional affinity propagation clustering[J].Acta Electronica Sinica,2017,45(8):1911-1918.
[18] Zhang J,Zhang L,Academy N A.A watershed algorithm combining spectral and texture information for high resolution remote sensing image segmentation[J].Geomatics & Information Science of Wuhan University,2017,42(4):449-455,467.
[19] ZHANG Hai-tao, LI Ya-nan. Watershed algorithm with threshold mark for color image segmentation[J].Journal of Image and Graphics,2015,20(12):1602-1611.张海涛,李雅男.阈值标记的分水岭彩色图像分割[J].中国图象图形学报,2015,20(12):1602-1611.
[20] WANG Yu,CHEN Dian-ren,SHEN Mei-li,et al.Watershed segmentation based on morphological gradient reconstruction and marker extraction[J].Journal of Image and Graphics,2008,13(11):2176-2180.王宇,陈殿仁,沈美丽,等.基于形态学梯度重构和标记提取的分水岭图像分割[J].中国图象图形学报,2008,13(11):2176-2180.
[2] Zhao C,Zhao H,Yao W.Fuzzy C-means clustering based on improved marked watershed transformation[J].2016,14(3):981-986.
[3] Ning Z,Shen W,Cheng X.Adhesion ore image separation method based on concave points matching[M].Information Technology and Intelligent Transportation Systems.Springer International Publishing,2017.
[4] Yang Y,Wang Y,Qian J.Building identification from SAR image based on the modified marker-controlled watershed algorithm[C].Geoscience and Remote Sensing Symposium.IEEE,2015,2481-2484.
[5] Tian X,Yu W.Color image segmentation based on watershed transform and feature clustering[C].Advanced Information Management,Communicates,Electronic and Automation Control Conference.IEEE,2017,1830-1833.
[6] Cai Q,Liu Y Q,Cao J,et al.A watershed image segmentation algorithm based on self-adaptive marking and interregional affinity propagation clustering[J].Acta Electronica Sinica,2017,45(8):1911-1918.
[7] Gonzalez R C,Woods R E.Digital image processing[M].3rd ed.Beijing:Publishing House of Electronics Industry,2010,468-471.
[8] Figliuzzi B,Chang K,Faessel M.Hierarchical segmentation based upon multi-resolution approximations and the watershed transform[C].International Symposium on Mathematical Morphology and Its Applications to Signal and Image Processing.Springer,Cham,2017,185-195.
[9] GAO Li,YANG Shu-yuan,LI Hai-qiang.New unsupervised image segmentation via Marker-based watershed[J].Joumal of Image Graphics,2007,(6):1025-1032.高丽,杨树元,李海强.一种基于标记的分水岭图像分割新算法[J].中国图象图形学报,2007(6):1025-1032.
[10] WEN Kai-feng,YE Shi-tong,WAN Zhi-ping.Infrared target segmentation algorithm based on maximum entropy threshold in complex background[J].Laser & Infrared,2016,46(1):103-108.温凯峰,叶仕通,万智萍.复杂背景下的最大熵阈值红外目标分割算法[J].激光与红外,2016,46(1):103-108.
[11] MIAO Hui-si,LIANG Guang-ming,LIU Ren-ren,et al.Watershed algorithm using edge gradient combined with distance transformation for segmentation of blood cells[J].Journal of Image and Graphics,2016,21(2):192-198.缪慧司,梁光明,刘任任,等.结合距离变换与边缘梯度的分水岭血细胞分割[J].中国图象图形学报,2016,21(2):192-198.
[12] WANG Ya.Adaptive marked watershed segmentation algorithm for red blood cell images[J].Journal of Image and Graphics,2017,22(12):1779-1787.王娅.血液红细胞图像自适应标记分水岭分割算法[J].中国图象图形学报,2017,22(12):1779-1787.
[13] Xu L,Lu H,Zhang M.Automatic segmentation of clustered quantum dots based on improved watershed transformation[J].Digital Signal Processing,2014,34(1):108-115.
[14] FANG Hong-ping,FANG Kang-ling,LIU Xin-hai.Clustered cells segmentation using modified watershed method based on adaptive H-minima[J].Application Research of Computers,2016,33(5):1587-1590.方红萍,方康玲,刘新海.自适应H-minima的改进分水岭堆叠细胞分割方法[J].计算机应用研究,2016,33(5):1587-1590.
[15] Koyuncu C F,Akhan E,Ersahin T,et al.Iterative h-minima-based marker-controlled watershed for cell nucleus segmentation[J].Cytometry Part A,2016,89(4):338-349.
[16] ZHANG Gui-mei,ZHOU Ming-ming,MA Ke.Image segmentation algorithm for reconstruction labeling watershed in color space[J].Journal of Image and Graphics,2012,17(5):641-647.张桂梅,周明明,马珂.基于彩色模型的重构标记分水岭分割算法[J].中国图象图形学报,2012,17(5):641-647.
[17] Qiang C,Liu Y Q,Jian C,et al.A watershed image segmentation algorithm based on self-adaptive marking and interregional affinity propagation clustering[J].Acta Electronica Sinica,2017,45(8):1911-1918.
[18] Zhang J,Zhang L,Academy N A.A watershed algorithm combining spectral and texture information for high resolution remote sensing image segmentation[J].Geomatics & Information Science of Wuhan University,2017,42(4):449-455,467.
[19] ZHANG Hai-tao, LI Ya-nan. Watershed algorithm with threshold mark for color image segmentation[J].Journal of Image and Graphics,2015,20(12):1602-1611.张海涛,李雅男.阈值标记的分水岭彩色图像分割[J].中国图象图形学报,2015,20(12):1602-1611.
[20] WANG Yu,CHEN Dian-ren,SHEN Mei-li,et al.Watershed segmentation based on morphological gradient reconstruction and marker extraction[J].Journal of Image and Graphics,2008,13(11):2176-2180.王宇,陈殿仁,沈美丽,等.基于形态学梯度重构和标记提取的分水岭图像分割[J].中国图象图形学报,2008,13(11):2176-2180.