摘要
文中基于图像稀疏分解,根据图像与噪声的稀疏分解不同,提出一种基于非对称原子模型的原子库,通过算法优化,实现对采集的布坯图像进行有效去噪分析,提高去噪图像的PSNR值,且具有更好的视觉效果。将所采集到的布坯数字图像去噪后将背景和缺陷进行分离,才能更有效地将缺陷进行界定,以利后续的相关特征提取。通过实验,与小波类去噪方法对比,文中的学习算法能更好地去除图像噪声,保留图像细节信息,获得更高PSNR值。
Base on the image sparse decomposition, according to the different characters of image and noise in sparse decomposition, proposed a model based on asymmetric atomic atoms library ,by algorithm the acquisition of effective de-noising analysis of gray images. Denoising to improve image PSNR values, and has a better visual effect. Will be collected by digital image denoising cloth blank background and the defects after separation in order to more effectively define the defects in order to facilitate the follow-up of the relevant characteristics of extraction. Experimental results show that in comparison with the wavelet based denoising methods, our learning based algorithm has better denoising ability, keep more detail image information and improve the peak signal to noise ratio.
出处
《计算机技术与发展》
2011年第3期113-116,共4页
Computer Technology and Development
基金
贵州省自然科学基金(黔科合J字[2009]2130号)
贵州大学自然科学基金(贵大自青基合字(2009)026号)
