双任务卷积神经网络的图像去模糊方法

陈清江; 胡倩楠; 李金阳

doi:10.37188/CJLCD.2021-0001

您当前的位置：

首页 >

文章列表页 >

双任务卷积神经网络的图像去模糊方法

图像增强与分割 | 更新时间：2021-11-08

- 双任务卷积神经网络的图像去模糊方法
- Image deblurring method based on dual task convolution neural network
- 液晶与显示 2021年36卷第11期页码：1486-1496
- 作者机构：
  
  西安建筑科技大学理学院, 陕西西安 710055
- 作者简介：
  
  [ "陈清江(1966-)，男，河南信阳人，博士，教授，2006年于西安交通大学获得博士学位，主要从事小波分析、图像处理与信号处理方面的研究。E-mail：qjchen66xytu@126.com" ]
  [ "胡倩楠(1996-), 女，陕西渭南人，硕士研究生，2019年于咸阳师范学院获得学士学位，主要从事小波分析、图像处理与信号处理方面的研究。Email：1227409677@qq.com" ]
- 基金信息：
  
  国家自然科学基金(61403298);陕西省自然科学基金(2015JM1024)
- DOI：10.37188/CJLCD.2021-0001
  中图分类号： TP391.41
- 收稿日期：2021-01-02，
  
  修回日期：2021-04-20，
  
  纸质出版日期：2021-11
- 稿件说明：
移动端阅览
陈清江, 胡倩楠, 李金阳. 双任务卷积神经网络的图像去模糊方法[J]. 液晶与显示, 2021,36(11):1486-1496.

Qing-jiang CHEN, Qian-nan HU, Jin-yang LI. Image deblurring method based on dual task convolution neural network[J]. Chinese journal of liquid crystals and displays, 2021, 36(11): 1486-1496.
陈清江, 胡倩楠, 李金阳. 双任务卷积神经网络的图像去模糊方法[J]. 液晶与显示, 2021,36(11):1486-1496. DOI： 10.37188/CJLCD.2021-0001.

Qing-jiang CHEN, Qian-nan HU, Jin-yang LI. Image deblurring method based on dual task convolution neural network[J]. Chinese journal of liquid crystals and displays, 2021, 36(11): 1486-1496. DOI： 10.37188/CJLCD.2021-0001.

摘要

针对现有图像去模糊卷积神经网络在图像复原过程中易出现纹理细节丢失、不加区分地对待所有通道和空间特征信息以及去模糊效果不佳等问题，本文提出了一种基于双任务卷积神经网络的图像去模糊方法。将图像去模糊任务分为去模糊子任务和高频细节恢复子任务来进行。其一，提出一种基于残差注意力模块和八度卷积残差块的编解码子网络模型，将此网络模型用于图像去模糊子任务；其二，提出一种基于双残差连接的高频细节恢复子网络模型，将此网络模型用于高频细节恢复子任务。将两个子网络采用并联方式组合起来，并使用平均绝对误差损失与结构损失来共同约束训练方向，实现图像去模糊。实验结果表明，本文方法具有较强的图像复原能力和较丰富的细节纹理，峰值信噪比(PSNR)为32.427 6 dB，结构相似度为0.947 0。与目前先进的去模糊算法相比能够有效提升图像去模糊效果。

Abstract

In order to solve the problems of texture details loss

indistinguishable treatment of all channel and spatial feature information and poor deblurring effect in the process of image restoration

an image deblurring method based on dual task convolutional neural network is proposed. The image deblurring task is divided into deblurring sub task and high frequency detail restoration sub task. Firstly

a coding and decoding sub network model based on Residual Attention Module and Octave Convolution Residual Block is proposed

which is used in image deblurring sub task. Secondly

a high frequency detail recovery sub network model based on Double Residual Connection is proposed

which is used in high frequency detail recovery sub task. The two subnetworks are combined in parallel

and the average absolute error loss and structure loss are used to constrain the training direction to achieve image deblurring. The experimental results show that the proposed method has strong image restoration ability and rich detail texture

the peak signal-to-noise ratio (PSNR) is 32.427 6 dB

and the structure similarity(SSIM) is 0.947 0. Compared with the current advanced deblurring algorithm

it can effectively improve the image deblurring effect.

关键词

Keywords

references

A KOUR , V K YADA , V MAHESHWARI , 等 . A review on image processing . International Journal of Electronics Communication and Computer Engineering , 2013 . 4 ( 1 ): 270 - 275 . http://www.researchgate.net/publication/271770488_a_review_on_image_processing http://www.researchgate.net/publication/271770488_a_review_on_image_processing .

MAIRAL J, BACH F, PONCE J, et al . Non-local sparse models for image restoration[C]//2009 IEEE 12 th International Conference on Computer Vision . Kyoto, Japan: IEEE, 2009: 2272-2279.

W S DONG , P Y WANG , W T YIN , 等 . Denoising prior driven deep neural network for image restoration . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2019 . 41 ( 10 ): 2305 - 2318 . DOI: 10.1109/TPAMI.2018.2873610 http://doi.org/10.1109/TPAMI.2018.2873610 .

NAH S, KIM T H, LEE K M. Deep multi-scale convolutional neural network for dynamic scene deblurring[C]// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition . Honolulu, HI, USA: IEEE, 2017: 257-265.

PAN J S, HU Z, SU Z X, et al . Deblurring text images via L 0 -regularized intensity and gradient prior[C]// Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition . Columbus, OH, USA: IEEE, 2014: 2901-2908.

A LEVIN , R FERGUS , F DURAND , 等 . Image and depth from a conventional camera with a coded aperture . ACM Transactions on Graphics , 2007 . 26 ( 3 ): 70 DOI: 10.1145/1276377.1276464 http://doi.org/10.1145/1276377.1276464 .

W Q REN , X C CAO , J S PAN , 等 . Image deblurring via enhanced low-rank prior . IEEE Transactions on Image Processing , 2016 . 25 ( 7 ): 3426 - 3437 . DOI: 10.1109/TIP.2016.2571062 http://doi.org/10.1109/TIP.2016.2571062 .

张万征 , 胡志坤 , 李小龙 . 基于LeNet-5的卷积神经图像识别算法 . 液晶与显示 , 2020 . 35 ( 5 ): 486 - 490 . http://cjlcd.lightpublishing.cn/thesisDetails#10.3788/YJYXS20203505.0486 http://cjlcd.lightpublishing.cn/thesisDetails#10.3788/YJYXS20203505.0486 .

W Z ZHANG , Z K HU , X L LI . Convolutional neural image recognition algorithm based on LeNet-5 . Chinese Journal of Liquid Crystals and Displays , 2020 . 35 ( 5 ): 486 - 490 . http://cjlcd.lightpublishing.cn/thesisDetails#10.3788/YJYXS20203505.0486 http://cjlcd.lightpublishing.cn/thesisDetails#10.3788/YJYXS20203505.0486 .

王旖旎 . 基于Inception V3的图像状态分类技术 . 液晶与显示 , 2020 . 35 ( 4 ): 389 - 394 . http://cjlcd.lightpublishing.cn/thesisDetails#10.3788/YJYXS20203504.0389 http://cjlcd.lightpublishing.cn/thesisDetails#10.3788/YJYXS20203504.0389 .

Y N WANG . Image classification technology based on Inception V3 . Chinese Journal of Liquid Crystals and Displays , 2020 . 35 ( 4 ): 389 - 394 . http://cjlcd.lightpublishing.cn/thesisDetails#10.3788/YJYXS20203504.0389 http://cjlcd.lightpublishing.cn/thesisDetails#10.3788/YJYXS20203504.0389 .

XU L, REN J S J, LIU C, et al . Deep convolutional neural network for image deconvolution[C]// Proceedings of the 27 th International Conference on Neural Information Processing Systems . Montreal, Canada: MIT Press, 2014: 1790-1798.

HRADIŠ M, KOTERA J, ZEMČÍK P, et al . Convolutional neural networks for direct text deblurring[C]// Proceedings of the British Machine Vision Conference . Swansea, UK: BMVA Press, 2015: 6.1-6.13.

SU S C, DELBRACIO M, WANG J, et al . Deep video deblurring for hand-held cameras[C]// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition . Honolulu, HI, USA: IEEE, 2017: 237-246.

ZHANG H G, DAI Y C, LI H D, et al . Deep stacked hierarchical multi-patch network for image deblurring[C]// Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Long Beach, CA, USA: IEEE, 2019: 5978-5986.

S B YIN , Y B WANG , Y H YANG . A novel image-dehazing network with a parallel attention block . Pattern Recognition , 2020 . 102 107255 DOI: 10.1016/j.patcog.2020.107255 http://doi.org/10.1016/j.patcog.2020.107255 .

CHEN Y P, FAN H Q, XU B, et al . Drop an octave: Reducing spatial redundancy in convolutional neural networks with octave convolution[C]// Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision . Seoul, Korea (South): IEEE, 2019: 3434-3443.

TAO X, GAO H Y, SHEN X Y, et al . Scale-recurrent network for deep image deblurring[C]// Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Salt Lake City, UT, USA: IEEE, 2018: 8174-8182.

陈清江 , 张雪 . 混合残差学习与导向滤波算法在图像去雾中的应用 . 光学精密工程 , 2019 . 27 ( 12 ): 2702 - 2712 . https://www.cnki.com.cn/Article/CJFDTOTAL-GXJM201912023.htm https://www.cnki.com.cn/Article/CJFDTOTAL-GXJM201912023.htm .

Q J CHEN , X ZHANG . Application of hybrid residual learning and guided filtering algorithm in image defogging . Optics and Precision Engineering , 2019 . 27 ( 12 ): 2702 - 2712 . https://www.cnki.com.cn/Article/CJFDTOTAL-GXJM201912023.htm https://www.cnki.com.cn/Article/CJFDTOTAL-GXJM201912023.htm .

LIU X, SUGANUMA M, SUN Z, et al . Dual residual networks leveraging the potential of paired operations for image restoration[C]// Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Long Beach, CA, USA: IEEE, 2019: 7000-7009.

WOO S, PARK J, LEE J Y, et al . CBAM: Convolutional block attention module[C]// Proceedings of the European Conference on Computer Vision . Munich, Germany: Springer, 2018: 3-19.

HE K M, ZHANG X Y, REN S Q, et al . Deep residual learning for image recognition[C]// Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition . Las Vegas, NV, USA: IEEE, 2016: 770-778.

SUN J, CAO W F, XU Z B, et al . Learning a convolutional neural network for non-uniform motion blur removal[C]// Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition . Boston, MA, USA: IEEE, 2015: 769-777.

M Y YE , D LYU , G S CHEN . Scale-iterative upscaling network for image deblurring . IEEE Access , 2020 . 8 18316 - 18325 . http://ieeexplore.ieee.org/document/8963625 http://ieeexplore.ieee.org/document/8963625 .

ZHOU S C, ZHANG J W, ZUO W M, et al . DAVANet: Stereo deblurring with view aggregation[C]// Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Long Beach, CA, USA: IEEE, 2019: 10988-10997.

浏览量

113

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于自适应遮挡恢复与拓扑姿态双向感知的三维手部重建方法

基于头部和整体信息联合的多尺度行人检测算法

基于改进YOLOv8n-Pose的疲劳驾驶检测

结合高效注意力机制的神经架构搜索高光谱图像分类