关键词: 形态学, 边缘检测, 功能扩展, 信息熵, 图像融合

Abstract: Mathematical morphology is widely applied in image processing and pattern recognition.This paper proposes pseudo top-hat transformation and new bottom-hat transformation.The original image is filtered using open-and-close operation.The scale of structure elements can be determined by dilation operation.A new edge image with a better quality fused by their entropy can effectively be extracted using proposed ways.Experimental results indicate that the algorithm can effectively suppress noise and improve dim edge detection;the edges are clear and accurate.So the new edge detection method achieves better image processing effect than classical edge detection methods.

Key words: morphology, edge detection, function extension, information entropy, image fusion