摘要
针对传统图像边缘检测速度慢和连续性差的缺点,通过构造图像信息测度特征属性,提出一种基于图像信息测度和ELM的图像边缘检测方法,采用度量F作为图像边缘检测的评价指标。研究结果表明,ELM图像边缘边缘检测效果优于LVQ、BP和Sobel算子,图像边缘更加清晰、纹理性较强、连续性好,并且具有较好地抗噪声性能。
In order to overcome the disadvantages of the traditional image edge detection,such as slow speed and poor continuity,a new image edge detection method based on image information measure and ELM is proposed.F measurement is used as the evaluation index of image edge detection,the results show that the edge of ELM image edge detection effect is better than those of LVQ,BP and Sobel operator,image edge is more clear and strong texture,good continuity,and has better anti noise performance.
引文
[1]吉玲,杨亚,付珊珊,等.一种改进的Canny边缘检测算法[J].微处理机,2015(1):40-43.
[2]Huang G B,Zhu Q Y,Siew C K.Extreme learning machine:Theory and applications[J].Neurocomputing,2006,70(1-3):489-501.
[3]Abdou I E,Pratt W.Quantitative design and evaluation of enhancement/thresholding edge detectors[J].Proceedings of the IEEE,1979,67(5):753-763.
[4]熊联欢,胡汉平,李德华,等.用BP网络进行彩色图像分割和边缘检测[J].华中科技大学学报自然科学版,1999,27(2):87-89.
[5]沈德海,鄂旭,张龙昌.基于Sobel算子的医学图像边缘检测研究[J].电子设计工程,2015,23(7):141-144.
[6]夏清,胡振琪,许立江,等.一种改进Sobel算子的热红外影像边缘检测方法[J].红外技术,2015(6):462-466.
[7]李琳琳,王纪奎,宋艳芳,等.基于蚁群优化算法的图像边缘检测[J].计算技术与自动化,2015(3):96-99.
[8]杨萍,张玉杰,李秦君.基于LS-SVM的contourletHMT变换的孔型测量图像边缘检测[J].计算机测量与控制,2015,23(10):3281-3282.
[9]Huang G B,Zhou H,Ding X,et al.Extreme learning machine for regression and multiclass classification.[J].IEEE Transactions on Systems Man&Cybernetics(Part B),2012,42(2):513.
[10]郑美珠,赵景秀.基于区域一致性测度的彩色图像边缘检测[J].计算机应用,2011,31(9):2485-2488.
[11]余瑞艳.基于方向信息测度的图像边缘检测[J].数学研究,2011,44(2):214-218.