联合K-means和形态学算子的图像边缘检测
|
摘要
针对传统边缘检测算子边缘定位精度的不足,提出了一种联合K-means和形态学算子的图像边缘检测方法。首先通过K-means算法对图像进行分割,再对分割后的图像求反,然后利用形态学作腐蚀操作,挖去图像内部像素点,最后利用分割图像减去形态学腐蚀后的图像获得图像边缘。实验结果表明,该方法能有效获得精确的图像边缘,比其他几种传统方法具有更优的检测效果。
Aiming at the shortcoming of edge localization accuracy of traditional edge detection operator,an edge detection method based on K-means and morphological operator is proposed. Firstly,the image is segmented by K-means algorithm,and then the segmented image is inverted. Then,the internal pixel of the image is dug by using morphological corrosion. Finally,the edge image is obtained by subtracting the segmentation image and the image of morphological corrosion. The experimental results show that the proposed method can obtain the accurate edge of the image effectively,and has better detection effect than other traditional methods.
Aiming at the shortcoming of edge localization accuracy of traditional edge detection operator,an edge detection method based on K-means and morphological operator is proposed. Firstly,the image is segmented by K-means algorithm,and then the segmented image is inverted. Then,the internal pixel of the image is dug by using morphological corrosion. Finally,the edge image is obtained by subtracting the segmentation image and the image of morphological corrosion. The experimental results show that the proposed method can obtain the accurate edge of the image effectively,and has better detection effect than other traditional methods.
引文
[1]姚敏.数字图像处理(第二版)[M].北京:机械工业出版社,2012.
[2]Djemel D Z,Tabbone S. Edge detection techniques-an overview[J]. International Journal of Pattern Recognition and Image Analysis,1998(4):537-559.
[3] Basu M,Gaussian-based edge detection methods——a survey[J]. IEEE Trans Systems,Man,and Cybernetics:Part C,2002(3):252-260.
[4]林世毅,苏广川,陈东等.基于小波变换和数学形态学的边缘检测法[J].仪器仪表学报, 2004(4):685-687.
[5]张悦庭,尹忠科,王建英.一种新的图像边缘检测方法[J].电子与信息学报,2008(6):1295-1299.
[6]石跃祥,康蕴,刘海涛.基于数学形态学的彩色噪声图像边缘检测算法[J].计算机应用研究,2012(3):1172-1174.
[7] EVANS A N,LIU X U. A morphological gradient approach to color edge detection[J]. IEEE Trans on Image Processing,2006(6):1454-1463.
[8]LIU Ting,LUO Xiao-gang,PENG Cheng-lin,et al. Improved morphological edge detection algorithm for ultrasound heart ventricular wall image[C]//Proc of IEEE Bioinformatics and Biomedical Engineering Conference.2007:974-977.
[9]王益艳.鲁棒的形态学彩色图像边缘检测算法[J].计算机工程与应用,2013(6):12-15.
[10]李苏梅,韩国强.基于K-均值聚类算法的图像分割方法[J].计算机工程与应用,2008(16):163-167.
[11]赵小川. Matlab图像处理——能力提高与应用案例[M].北京:北京航空航天大学出版社,2014.
[12]王易偱,赵勋杰.基于K均值聚类分割彩色图像算法的改进[J].计算机应用与软件,2010(8):127-130.
[2]Djemel D Z,Tabbone S. Edge detection techniques-an overview[J]. International Journal of Pattern Recognition and Image Analysis,1998(4):537-559.
[3] Basu M,Gaussian-based edge detection methods——a survey[J]. IEEE Trans Systems,Man,and Cybernetics:Part C,2002(3):252-260.
[4]林世毅,苏广川,陈东等.基于小波变换和数学形态学的边缘检测法[J].仪器仪表学报, 2004(4):685-687.
[5]张悦庭,尹忠科,王建英.一种新的图像边缘检测方法[J].电子与信息学报,2008(6):1295-1299.
[6]石跃祥,康蕴,刘海涛.基于数学形态学的彩色噪声图像边缘检测算法[J].计算机应用研究,2012(3):1172-1174.
[7] EVANS A N,LIU X U. A morphological gradient approach to color edge detection[J]. IEEE Trans on Image Processing,2006(6):1454-1463.
[8]LIU Ting,LUO Xiao-gang,PENG Cheng-lin,et al. Improved morphological edge detection algorithm for ultrasound heart ventricular wall image[C]//Proc of IEEE Bioinformatics and Biomedical Engineering Conference.2007:974-977.
[9]王益艳.鲁棒的形态学彩色图像边缘检测算法[J].计算机工程与应用,2013(6):12-15.
[10]李苏梅,韩国强.基于K-均值聚类算法的图像分割方法[J].计算机工程与应用,2008(16):163-167.
[11]赵小川. Matlab图像处理——能力提高与应用案例[M].北京:北京航空航天大学出版社,2014.
[12]王易偱,赵勋杰.基于K均值聚类分割彩色图像算法的改进[J].计算机应用与软件,2010(8):127-130.