摘要
通过对掌形图像采用小波模极大值算法去除噪声,建立了极大值矩阵及跟踪矩阵,分辨出小波系数的信噪属性,剔除了噪声部分对应的小波系数极大值,从而抑制了噪声污染。在阈值设置问题上,采用改进的自适应阈值,克服单一阈值不能在每级尺度上将信号与噪声作最大分离的缺点,该方法不仅有效去除噪声,同时保持了图像边缘细节,具有良好的消除噪声的效果。
Using on the algorithms of wavelet modulus maximum value to denoise the palm shape image, this paper builds up maximum matrix and trace matrix, resolves the S/N （signal/noise ratio） property of wavelet coefficient and eliminates the wavelet coefficient maximum of the noisy part, so that the noisy pollution is restrained. On the setting of the threshold value, the design adopted the improved adaptive threshold method. In order to overcome the disadvantage that single threshold value can＇t separate signal from noise on each scale. The method put forward in this paper not only cancels noise effectually but also keeps edge details of the image. It has good denoising effects.
出处
《信息技术》
2008年第5期48-51,共4页
Information Technology
关键词
掌形
图像去噪
小波模极大值
pahn shape image
image denoising
wavelet modulus maximum
