基于Prewitt理论的自适应边缘检测算法

Adaptive edge-detection method based on Prewitt algorithm

利用Prewitt基本原理定义了新的算法模板,根据待检测像素周围的3×3邻域的像素平均灰度值,结合人眼的视觉特征自适应地生成动态阈值,不仅保留了原Prewitt算法可并行处理、能够抑制噪声等优点,还提高了运算速度。同时,针对Prewitt算法边缘检测相对粗糙、边缘细化算法效率较低的问题,分析和改进了原有边缘细化算法,改进算法先对含有噪声的图像进行边缘检测,过滤了伪边缘,再对图像边缘进行细化,从而得到单像素边缘。通过实验比较,所提算法能够自适应地生成动态阈值,并在保持Prewitt算法具有抑制噪声性能优点的基础上,提高了运算速度,而且可以获得更加细腻光滑的边缘。

For the slow calculation speed and given threshold of Prewitt algorithm, this paper proposed an adaptive of edge detection method. It used the basic principle of the Prewitt algorithm and defined the new template of algorithm. The algorithm got adaptively automatic threshold according to the mean value of the 3 × 3 area pixels around the detecting pixel and the pro- petty of people＇ s vision. It not only can keep the original advantages such as parallel process and restrain noise, but also can quick calculation speed. For the edge that Prewitt algorithm detected was comparatively thick, and the efficiency of original edge-thin algorithm was lower, analyzed and improved the original edge-thin algorithm. The improved algorithm firstly detected the edge of the image in which there existed noise and filters the fake edge, then thinned the edge of the image, and finally got the single pixel edge. By comparing the test result of the adaptive edge-detection algorithm with that of original Prewitt algorithm, the adaptive edge-detection method could get adaptively automatic threshold. Besides the original Prewitt algorithm property of restraining noise, it has quicked the calculation speed and gotten more smooth edge than original algorithm.