基于四元数和SOM神经网络的彩色图像边缘检测

Color image edge detection based on quaternion and self-organizing map neural network

针对传统边缘检测方法无法考虑到彩色图像各颜色分量的相关性,以及边缘提取效果受阈值影响的不足,提出一种四元数和自组织神经网络(SOM)相结合的彩色图像边缘检测算法。根据四元数柯西积分公式和四元数矢量积性质,构造图像的边缘特征向量对SOM神经网络进行训练,然后用训练好的SOM网络提取边缘。实验表明,该方法具有良好的边缘检测效果,并有较强的细节保持能力。

As the correlation between color components in color image is not considered in the traditional edge detection algorithms, and the detection results will be Mfeeted by the threshold value, a new kind of edge detection method for color image was proposed combining quaternion with Self-Organizing Map （SOM）. Based on the quatemionic Cauchy integral formula and vector product, the edge characteristic vector was constructed. Then the SOM was trained by the vector and used for edge detection. The experimental results show that the ProPosed method has stronger retention capacity of the details.