遗传算法优化的形态学边缘检测算子

Morphological Edge Detector with Genetic Algorithm Optimizing

图像边缘检测通常是以类似于素描图的图像表达出物体的要素和特征,其任务是使图像边缘准确定位和抑制噪声。在传统形态学算子基础上提出一种遗传算法优化的形态学Top-Hat算子。实验表明,与传统的边缘检测算法相比,该算法不仅具有较强的边缘提取能力,而且通过合理选择结构元素能明显降低噪声对检测结果的影响,准确检测出图像边缘。

The aim of image edge detection is usually to use images to sketch pictures to express the features and outlines of objects. Its task is to locate image edges exactly and reduce its noise. A new morphological Top- hat operator with genetic algorithm is presented in this paper. The experimental results show that the detector proposed in this paper can considerably reduce noise in most remote sensing images and accurately extract the edge of images. Compared with the conventional detector, it is more feasible for noisy image processing.