噪声模糊图像盲目反降晰的模糊核准确估计

摘要

Most state-of-the-art single image blind deblurring techniques can't still handle perfectly the problem that the quality of blur kernel estimate can be degraded dramatically when the input image noise can't be ignored. In this work, we present a new method for estimating an accurate blur kernel from a blurry and noisy image using salient image structure. First, we use denoising as a preprocess to remove the input image noise, and then compute salient structure of the denoised result based on the total variation (TV) model. We also apply a gradient selection method to remove those salient edges that have a possible adverse effect on blur kernel estimation, thus improving the robustness of blur kernel estimation. Next, we adopt a two-phase blur kernel estimation strategy to achieve an accurate kernel estimation by taking advantage of the blur kernel estimation method from salient structure and iterative support detection (ISD) technique. Finally, we choose to use the non-blind deconvolution method with sparse prior knowledge to attain the final latent image restoration. Experiment results on synthetic and real world data show that our method produces more accurate blur kernels and higher quality latent images than previous approaches on noisy and blurry images. It handles effectively the truth that image deblurring techniques are very sensitive to noise, and estimates an accurate blur kernel from a noisy and blurry image.%针对大多数先进的单幅图像盲目反降晰技术在噪声无法忽略时,仍不能很好地处理模糊核估计质量退化严重的问题,提出一种利用图像显著结构从单幅噪声模糊图像中准确估计模糊核的方法.首先通过降噪预处理对图像噪声进行抑制,利用基于全总变分模型的方法提取模糊图像的显著结构,进而运用梯度选择方法移除不利于模糊核估计的显著边缘,提高模糊核估计的鲁棒性;然后采取两阶段模糊核估计策略,运用基于图像显著结构模糊核估计方法和迭代支持域检测技术实现模糊核的准确估计;最后通过稀疏先验约束的非盲目图像解卷积方法完成最终的图像恢复.实验结果表明,与已有方法相比,该方法在合成和真实图像上都能更准确地估计出噪声模糊图像的模糊核,获得更好的复原图像质量,可有效地处理图像反降晰对图像噪声敏感问题,实现了噪声模糊图像模糊核的准确估计.