基于Hessian矩阵的边缘检测方法

A Edge Detection Method Based on the Hessian Matrix

边缘是一幅图像最基本也最重要的特征,边缘检测是机器视觉和图像处理的关键环节和经典课题。本文结合人眼的视觉特性,利用彩色图像自身梯度方向信息,对彩色图像进行多通道边缘检测,得到图像的伪色彩边缘图。对边缘信息增强和去相关后提取亮度分量,用OTSU法二值化,最后利用Hessian矩阵提取边缘图像的中心路径,去除边缘毛糙和冗余的背景纹理,使图像边缘光滑连续。通过实验验证了本文算法的有效性,实验通过与两种经典算子Canny和Sobel以及基于小波的边缘检测方法做比较,结果表明,本文算法能够提高边缘检测的有效性和清晰度。

Edge is the most basic and important feature in an image, edge detection is the key link and classic topic in the machine vision and image processing. A new method is proposed combining with human visual characteristic. Firstly, to detect edges of a color image though multi-channel using the gradient direction information of the image then to get the pseudo-color edges. Then to extract the brightness after enhancing the edge information and removing the correlation, use the OTSU method to get the binarization image. Finally, the hessian matrix is utilized to make the edge smoothing and continuous with extracting the centerline in the image, removing the coarse edge and the redundancy of background texture. The effectiveness of the algorithm is verified by comparing with the canny operator, Sobel operator and the wavelet based detection method, and the experimental results show that the algorithm can improve the effectiveness,continuity and clarity of the edge detection.