| 引用本文: | 余孝源,谢巍.基于深度编码–解码器的图像模糊核估计[J].控制理论与应用,2020,37(4):731~738.[点击复制] |
| YU Xiao-yuan,XIE Wei.Blur kernel estimation method based on deep encoder-decoder network[J].Control Theory and Technology,2020,37(4):731~738.[点击复制] |
|
| 基于深度编码–解码器的图像模糊核估计 |
| Blur kernel estimation method based on deep encoder-decoder network |
| 摘要点击 1750 全文点击 623 投稿时间：2018-12-30 修订日期：2019-06-24 |
| 查看全文 查看/发表评论 下载PDF阅读器 |
| DOI编号 10.7641/CTA.2019.80999 |
| 2020,37(4):731-738 |
| 中文关键词 图像去模糊 编码-解码器 显著边缘 卷积核估计 |
| 英文关键词 Image Deblurring Encoder-decoder network Significant-edges estimation of blur kernel |
| 基金项目 广东省 |
|
| 中文摘要 |
| 在图像去模糊问题中，显著边缘结构对图像的模糊核估计具有重要的作用。本文提出一种基于深度编码-解码器的图像模糊核估计算法。首先，通过构建训练数据集对深度编码-解码器进行训练，进而自适应地获得模糊图像的显著边缘结构；接着，结合显著边缘结构和模糊图像，利用$L_2$范数正则化对模糊核进行估计；最后，利用超-拉普拉斯先验和所估计的模糊核对清晰图像进行估计。与传统的方法相比，所提出的方法不需要多尺度迭代框架。实验结果表明，所提出的算法在获得较好的显著边缘结构以及清晰图像的同时，能够减少算法计算的时间 |
| 英文摘要 |
| The significant edges-structure of blurry image plays an important role in estimation of blur kernel with the image deblurring problem. This paper proposes a method for estimating blur kernel based on deep encoder-decoder network. Firstly, after training by the constructing train dataset，the deep encoder-decoder network obtains the significant-edges of blurry image adaptively. And then, the blur kernel can be estimated by the $L_2$ norm regularization where combining the significant edge-structures and the blurry image. Finally, the latent image can be estimated by using the hyper-Laplacian priors after estimating blur kernel. Comparing with the traditional methods, the proposed method does not use the multi-scale iterative framework to estimate kernel. Experimental results show that the proposed method can reduce the computation time of the algorithm while obtaining better significant edge-structures and latent image. |