彩色图像边缘检测及其在图像融合中的应用

提出了一种新的基于小波变换的彩色图像边缘检测方法,运用噪声和微弱边缘的识别以及动态双域值的选取,使得检测出来的边缘定位精度高,抑制噪声性能好。利用基于区域特征的信息融合策略,比较待融合图像的边缘点的值和区域能量特征值,选择特征突出者对应的原始图像区域组成融合结果。实验结果表明,该算法可以良好地保留两幅图像的细节信息,得到高质量的融合图像。

Edge detection of color image and its application to image fusion

A new algorithm of edge detection to color image was improved with distinguishing noise from edge and using two dynamic threshold values. By means of multi_scale analysis,the image edge was described with more accuracy, higher signal_to_noise ratio and it also shows effective in detection the edges with weak contrast. A fusion method based on dynamic weighting of regional features was proposed. The result image is generated by comparison of fused images edge intensity and regional feature. The experiment results showed that the new method can reserve the image details, so the fusion image is good.