形态学高帽变换与低帽变换功能扩展及应用

摘要

数学形态学广泛应用于图像处理和模式识别领域.对形态学高帽变换与低帽变换功能进行扩展,提出了假高帽变换的概念和低帽变换的新方法.用形态学滤波对原始图像进行平滑处理,由形态学膨胀运算调整结构元素尺度,依据检测图像边缘熵确定权值进行融合.改进了传统形态学边缘检测算法,改善了亮背景上暗物体的边缘提取,对数字图像进行处理,满足了实际需求.实验结果表明,该算法能有效抑制噪声,且边缘清晰准确,效果优于经典的边缘检测算法.%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.