基于差异信息理论的彩色图像边缘检测算法

Algorithm of Color Image Edge Detection Based on Differential Information Theory

分析了彩色图像具有较大信息差异性的本质特征,结合灰色系统的差异信息理论,提出了采用差异信息理论进行彩色图像边缘检测处理的新方法。该算法首先分析彩色图像基元的结构特点,确定彩色图像差异信息序列,然后通过计算差异信息测度、信息熵相对测度、差异信息相对测度确定图像边缘点。实验表明,采用该方法进行彩色图像边缘检测具有一定的可行性和有效性。

The essential characteristics with greater information difference of color image are interpreted in detail. A new method to process edge detection of color image is put forward based on the differential information theory of grey system. At first, it analyses to the characteristic of pixels, and confirms differential information serial of color image. Then, it distinguishes between non-edge pixels and edge pixels through computing the differential information measure, the information entropy relative measure and the differential information relative measure. The experimental result indicates that the method of edge detection of color image has certain feasibility and validity.