基于方向空间的边缘检测

Edge detection based on direction space

提出了一种基于方向空间的边缘检测方法。首先建立方向差分级空间,沿方向差分级函数方向,通过逻辑判断的方法分别提取方向Ridge边缘像素和方向Valley边缘象素,构成方向Roof边缘映射图;然后再沿方向差分级函数方向,在所有相邻的方向Ridge边缘和方向Valley边缘之间提取方向Step边缘,构成方向Step边缘映射图;最后将几个不同方向获取的方向Ridge边缘映射图、方向Valley边缘映射图和方向Step边缘映射图,分别通过逻辑“或”的方法合成为相应的Ridge边缘映射图、Valley边缘映射图和Step边缘映射图。将该算法与经典算法、Marr-Hildreth算法和Canny算法进行的比较实验结果表明,提出的算法除了不需要复杂运算之外,在边缘定位准确度方面具有优势。

The directional differential space is set up, the ridge edge pixels and valley edge pixels are abstracted with the help of logical judgement along the direction of differential function to form directional roof edge map. Then step edge pixels are abstracted between the neighboring directional ridge edge and directional valley edge along the direction of differential function. The ridge edge map, valley edge map and step edge map gained along different directions are combined into corresponding ridge edge map, valley edge map and step edge map. The proposed method is compared with classical algorithm, Marr-Hildreth algorithm and Canny algorithm through experiments. The experimental results show that the proposed algorithm has higher precision on the location besides simple operation.