摘要
LOG算子是图像边缘检测的重要算子,可以在不同尺度下检测图像的边缘特征。针对LOG算子存在的缺陷,并借助于LMS自适应算法获取最佳空间系数σ值,成功抑制了图像中的大部分噪声。并通过基于TMS320C6000专用信号处理器的图像处理系统实现了图像边缘检测的自动提取。实验结果表明,当σ值较小时,LOG算子对高反差像素比较敏感,能够检测出物体的精细边缘,并且与实际边缘的一致性较好,但同时高斯滤波不彻底,图像中出现大量的虚假边缘;当σ值较大时,算子能够检测出原图像的边缘,噪声情况明显减小,但是边缘间存在相互干扰,位移严重等情况;本算法检测出的图像边缘,不仅成功抑制了图像中大部分噪声和微小的灰度变化,还保证了较高的边缘定位精度。增强了LOG算子的实用性,并且该算法易于实现,可以较好的解决图像边缘检测问题。
LOG operator is important in detecting edges in images with different scales. In order to avoid the defects of LOG operator, a method to get the optimum value of a is proposed via LMS, a self-adaptable method, and successfully eliminated most of noise in image. Detection of edges can be achieved automatically through Digital Image Processing System based on TMS320C6000. The results of the experiments show that LOG operator is so sensitive to the variation of gray that it can detect edges precisely and cohere with real edges exactly with the lower value of σ. But there are lots of false edges because of residuary noise by Gause filter. With the higher value of σ, the operator can detect the edge of original images and noise is dramatically reduced while edges interfere with each other resulting in serious displacement. Edges detected by the operator not only reduce most noise and little variation of gray, but also locate edges accurately to improve the function of LOG operator. The method can be realized easily and resolve problems concerning edges of images.
出处
《青岛大学学报（工程技术版）》
CAS
2005年第4期65-68,共4页
Journal of Qingdao University(Engineering & Technology Edition)
