摘要
提出了一种将自适应正则化方法与非负支撑域递归逆滤波(NAS-RIF)算法相结合用于小波域的盲图像复原算法。该算法先对降质图像进行小波分解,得到了图像在不同子频段的信息。在各个子频段采用NAS-RIF算法进行复原。针对各个子频段内图像的频率和方向特性,分别引入了不同的正则化约束项。在各个子频段估计出噪声方差,提出了根据噪声方差和图像局部方差来选取正则化参数。分别对两幅模糊图像进行了仿真实验,复原结果取得的信噪比分别为19.66 dB和23.86 dB。实验结果表明,复原效果相对于空间自适应正则化方法有一定的提高。
An improved nonnegativity and support constraints recursive inverse filtering (NAS-RIF) algorithm based on wavelet transform is presented to restore blind images. The degraded image is decomposed to obtain its wavelet coefficients in wavelet domain. The image's different frequency sub-bands are also obtained. Then, NAS-RIF algorithm is used to restore degraded image in each sub-bands, different regularization terms are used in different sub-bands. By estimating the noise variance in each sub-bands, the adaptive regularization parameters can be calculated through the local properties of the observed image and the noise variance. The two simulating experiments are made and high signal to noise ratios (SNR) of 19.66 dB and 23.86 dB are obtained. The experimental results show that the method given by authors is more efficient than traditional space-adaptive regularization method.
出处
《光学学报》
EI
CAS
CSCD
北大核心
2009年第11期3000-3003,共4页
Acta Optica Sinica
基金
国家自然科学基金重点项目(90510020)
教育部科研重点项目(108174)资助课题