摘要
数学形态学广泛应用于图像处理和模式识别领域;针对形态学单结构元在边缘检测中边缘信息丢失的问题,提出了用不同方向的结构元素对图像进行多尺度检测的自适应边缘检测方法;首先利用形态学高低帽运算对原始图像进行平滑处理,采用差分最大值确定结构元素的方向,利用形态学运算调整结构元素尺度,改进了数学形态学边缘检测算法;实验结果表明,与传统边缘检测算法相比,该算法在保持图像边缘清晰的同时,有很强的去除噪声能力。
Mathematical morphology is applied widely in image processing and pattern recognition. The traditional method loses some edge information. In order to improve edge detection effective, this paper proposes a new algorithm that is a self--adaptive edge detection method based on morphology multi--structural elements and multi--scale. First, the original image is filtered using top--and--bottom hat operation. Second, the direction of morphology structuring elements confirmed by the maximum difference, the scale of structuring elements can be determined by morphology operation. This method can improve the traditional algorithm. Experimental result indicates that the new edge detection achieves better image proeessing effect than traditional method, has strong ability of eliminating noise as well as keeps clear image edge.
出处
《计算机测量与控制》
CSCD
北大核心
2009年第12期2538-2540,共3页
Computer Measurement &Control
基金
江苏省高校自然科学研究计划资助项目(08KJB140010)
关键词
形态学
边缘检测
多结构元
多尺度
morphology
edge detection
multi-structure elements
multi-scale
