摘要
提出了一种基于支持向量机进行图像去噪的方法。该方法利用支持向量回归技术构造图像去噪所需的滤波器,其中特征的提取和训练样本的设计旨在抑制不同类型的噪声。实验结果表明,该方法能够有效去除噪声,并能较好地保护边缘信息,适用于边缘检测等操作的预处理。
The paper presents a Support Vector Machine (SVM) based image denoising approach. The method proposed here employs the regression capability offered by SVM network to construct a filter for image denoising, where our feather selection and training data-set design enables the suppression of various kinds of noises. Our experimental results demonstrate that the proposed method works well for image denoising while edge information is substantially retained, thus it can be used as a promising image pre-processing tool.
出处
《微电子学与计算机》
CSCD
北大核心
2005年第4期96-99,共4页
Microelectronics & Computer
关键词
支持向量机
图像去噪
平滑滤波
边缘检测
Support Vector Machine(SVM), Image denoising, Smoothing filter, Edge detection
