基于多层小波阈值函数的彩色图像边缘检测  

COLOR IMAGE EDGE DETECTION BASED ON MULTI-LAYER WAVELET THRESHOLD FUNCTION

作　　者：陈顺 李登峰 Chen Shun;Li Dengfeng(School of Mathematics and Computer,Wuhan Textile University,Wuhan 430200,Hubei,China)

机构地区：[1]武汉纺织大学数学与计算机学院,湖北武汉430200

出　　处：《计算机应用与软件》2022年第2期228-233,336,共7页Computer Applications and Software

基　　金：国家自然科学基金项目(61471410)。

摘　　要：针对彩色图像边缘检测中RGB颜色空间分量之间高的关联性会导致部分色彩信息未能被有效识别、检测及抗噪性低,提出一种多层小波阈值去噪函数的彩色图像边缘检测方法。采用改进的小波阈值去噪方法对彩色图像进行去噪预处理;运用四元数思想构建四方向特征矩阵求解Canny算子梯度幅值和幅角;进行非极大值抑制和自适应双阈值处理得到最终边缘检测图像。实验表明,该算法能够较好地获取彩色图像边缘信息,并有效降低漏检率和错检率,增强了自适应性,提高了边缘检测中边缘的连续性和抗噪性。Aiming at the problem that high correlation between RGB color space components in color image edge detection can cause partial color information not being effectively identified and detected,and low noise resistance,an edge detection method of color image based on multi-layer wavelet threshold denoising function is proposed.An improved wavelet threshold denoising method was used to denoise preprocessing of the color image;the quaternion idea was applied to construct a four-direction feature matrix to solve the gradient amplitude and angle of the Canny operator;the final edge detection image was obtained by non-maximum suppression and adaptive double-threshold processing.The experimental results show that our algorithm can obtain the edge information of color images well,effectively reduce the rate of missed detection and false detection,enhance the adaptability,and improve the continuity and noise immunity of edges in edge detection.

关 键 词：小波阈值函数 四元数 特征矩阵 CANNY算子 彩色图像 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]