当前位置: X-MOL 学术Pattern Recogn. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Joint Image Deblurring and Matching with Feature-based Sparse Representation Prior
Pattern Recognition ( IF 8 ) Pub Date : 2020-07-01 , DOI: 10.1016/j.patcog.2020.107300
Juncai Peng , Yuanjie Shao , Nong Sang , Changxin Gao

Abstract Image matching aims to find a similar area of the small image in the large image, which is one of the key steps in image fusion and vision-based navigation; however, most matching methods perform poorly when the images to be matched are blurred. Traditional approaches for blurred image matching usually follow a two-stage framework - first resorting to image deblurring and then performing image matching with the recovered image. However, the matching accuracy of these methods often suffers greatly from the deficiency of image deblurring. Recently, a joint image deblurring and matching method that utilizes the sparse representation prior to exploit the correlation between deblurring and matching was proposed to address this problem and found to obtain a higher matching accuracy. Yet, that technique is not efficient when the image is seriously blurred, and the method’s time complexity is excessive. In this paper, we propose a joint image deblurring and matching approach with a feature-based sparse representation prior. Our approach utilizes two-directional two-dimensional (2D)2PCA to extract feature vectors from images and obtains a sparse representation prior in a robust feature space rather than the original pixel space, thus mitigating the influence of image blur. Moreover, the reduction in the feature dimension can also increase the computational efficiency. Extensive experiments show that our approach significantly outperforms state-of-the-art approaches in terms of both accuracy and speed.

中文翻译:

基于特征的稀疏表示先验联合图像去模糊和匹配

摘要 图像匹配旨在在大图像中找到小图像的相似区域,是图像融合和基于视觉导航的关键步骤之一;然而,当要匹配的图像模糊时,大多数匹配方法表现不佳。传统的模糊图像匹配方法通常遵循两阶段框架 - 首先采用图像去模糊,然后与恢复的图像进行图像匹配。然而,这些方法的匹配精度往往受到图像去模糊不足的影响。最近,提出了一种在利用去模糊和匹配之间的相关性之前利用稀疏表示的联合图像去模糊和匹配方法来解决这个问题,并发现可以获得更高的匹配精度。然而,当图像严重模糊时,该技术效率不高,并且该方法的时间复杂度过高。在本文中,我们提出了一种基于特征的稀疏表示先验的联合图像去模糊和匹配方法。我们的方法利用二维二维 (2D)2PCA 从图像中提取特征向量,并在鲁棒的特征空间而不是原始像素空间中获得稀疏表示先验,从而减轻图像模糊的影响。此外,特征维数的减少也可以提高计算效率。大量实验表明,我们的方法在准确性和速度方面都明显优于最先进的方法。我们提出了一种联合图像去模糊和匹配方法,先验基于特征的稀疏表示。我们的方法利用二维二维 (2D)2PCA 从图像中提取特征向量,并在鲁棒的特征空间而不是原始像素空间中获得稀疏表示先验,从而减轻图像模糊的影响。此外,特征维数的减少也可以提高计算效率。大量实验表明,我们的方法在准确性和速度方面都明显优于最先进的方法。我们提出了一种联合图像去模糊和匹配方法,先验基于特征的稀疏表示。我们的方法利用二维二维 (2D)2PCA 从图像中提取特征向量,并在鲁棒的特征空间而不是原始像素空间中获得稀疏表示先验,从而减轻图像模糊的影响。此外,特征维数的减少也可以提高计算效率。大量实验表明,我们的方法在准确性和速度方面都明显优于最先进的方法。从而减轻图像模糊的影响。此外,特征维数的减少也可以提高计算效率。大量实验表明,我们的方法在准确性和速度方面都明显优于最先进的方法。从而减轻图像模糊的影响。此外,特征维数的减少也可以提高计算效率。大量实验表明,我们的方法在准确性和速度方面都明显优于最先进的方法。
更新日期:2020-07-01
down
wechat
bug