Automatic blur-kernel-size estimation for motion deblurring
Automatic blur-kernel-size estimation for motion deblurring
复制标题
DOI：
10.1007/s00371-014-0998-2
复制
发表时间：
2014-06
期刊：
影响因子：
--
通讯作者：
Shaoguo Liu;Haibo Wang;Jue Wang;Sunghyun Cho;Chunhong Pan
中科院分区：
文献类型：
--
作者：
Shaoguo Liu;Haibo Wang;Jue Wang;Sunghyun Cho;Chunhong Pan
现有的图像去模糊方法往往把模糊核大小作为一个重要的人工参数。当设置不当时，该参数可能导致估计的模糊核中的显著误差。然而，手动为输入图像指定适当的内核大小通常是一个繁琐的试错过程。在本文中，我们提出了一种新的方法来自动估计潜在的模糊核大小值，可以导致良好的核估计。我们的方法利用图像梯度的自相关映射（自动映射），这是已知的反映运动模糊信息。我们发现，标准的自动映射遭受图像中的结构边缘，不能直接用于核大小估计。为了缓解这个问题，我们开发了一种改进的自动映射方法，其中包含一个方向衰减组件，它可以有效地减少结构边缘的影响，从而更准确和可靠的核大小估计。实验结果表明，该方法可以帮助国家的最先进的去模糊算法实现准确的核估计，而不依赖于手动参数调整。
Existing image deblurring approaches often take the blur-kernel-size as an important manual parameter. When set improperly, this parameter can lead to significant errors in the estimated blur kernels. However, manually specifying a proper kernel size for an input image is usually a tedious trial-and-error process. In this paper, we propose a new approach for automatically estimating the underlying blur-kernel-size value that can lead to good kernel estimation. Our approach takes advantage of the autocorrelation map (automap) of image gradients that is known to reflect the motion blur information. We show that the standard automap suffers from structural edges in the image and cannot be directly used for kernel size estimation. To alleviate this problem, we develop a modified automap method that contains a directional attenuation component, which can effectively reduce the influence of structural edges, leading to more accurate and reliable kernel size estimation. Experimental results suggest that the proposed approach can help state-of-the-art deblurring algorithms achieve accurate kernel estimation without relying on manual parameter tweaking.