摘要
研究图像边缘检测问题,由于图像分割过程产生噪声和丢失边缘信息造成图像质量差。传统检测没有考虑到图像边缘局部结构信息,只是根据前像素点和相邻像素点之间关系来进行边缘检测,不能很好的抑制噪声,易获得断裂的边缘,导致边缘检测精度较低。为提高图像边缘检测精度,提出一种采用遗传算法的图像边缘检测算法。综合考虑局部结构信息和像素点之间关系的基础上,将边缘检测问题转成一种优化问题,然后采用遗传算法对该问题进行求解。仿真结果表明,相对于传统检测算法,遗传算法提高了图像边缘检测精度,克服传统算法存在的缺陷,稳定性更高,抗噪性能更优。
In order to improve the precision of image edge detection based on genetic algorithm, wht paper put for-ward an algorithm for image edge detection. Considering the local structural information and pixel based on the rela-tionship between, the edge detection was transformed into an optimization problem, and then the genetic algorithm was used to solve this problem. The simulation results show that, compared with the traditional detection algorithm, the genetic algorithm can improve the precision of image edge detection algorithms, and has higher stability and better anti-noise performance.
出处
《计算机仿真》
CSCD
北大核心
2012年第9期289-292,共4页
Computer Simulation
关键词
图像边缘
检测算法
遗传算法
费用函数
Image edge
Detection method
Genetic algorithm
Cost function
