[1]蔡坤琪.快速图像超分辨率方法研究[J].红外技术,2018,40(3):269-274.[doi:10.11846/j.issn.1001_8891.201803012]
 CAI Kunqi.A Study on Rapid Image Super-resolution[J].Infrared Technology,2018,40(3):269-274.[doi:10.11846/j.issn.1001_8891.201803012]
点击复制

快速图像超分辨率方法研究
分享到:

《红外技术》[ISSN:1001-8891/CN:CN 53-1053/TN]

卷:
40
期数:
2018年第3期
页码:
269-274
栏目:
出版日期:
2018-03-20

文章信息/Info

Title:
A Study on Rapid Image Super-resolution
文章编号:
1001-8891(2018)03-0269-06
作者:
蔡坤琪
琼台师范学院
Author(s):
CAI Kunqi
Qiongtai Nomal University
关键词:
超分辨率卷积神经网络深度学习图像处理峰值信噪比
Keywords:
super resolutionconvolutional neural networkdeep learningimage processingpeak signal to noise ratio
分类号:
TP751
DOI:
10.11846/j.issn.1001_8891.201803012
文献标志码:
A
摘要:
针对现有的基于样本学习的图像超分辨率方法参数较多、运算速度较慢等问题,结合基于卷积神经网络的超分辨率方法,提出一种快速图像超分辨率方法。设计一学习网络,以低分辨率图像作为网络的输入,从根本上减少网络的运算负担,加速网络运算;减小卷积核尺寸使得网络训练参数减少,提高运算速度;最后以亚像素卷积层同时实现网络的映射和图像融合过程。将所提方法在通用测试集上进行测试,并与其他方法的测试结果进行了对比,所提方法生成的图像具有更高的峰值信噪比,且具有更好的主观视觉效果。实验结果表明所提方法不仅运算速度能够得到大幅提升,而且能够生成更高质量的超分辨率图像,具有更佳的超分辨率性能。
Abstract:
Existing image super-resolution methods that are based on sample-learning involve a large number of associated parameters and protracted calculation time. Hence, a method for rapid image super-resolution has been proposed that incorporates convolutional neural networks. The proposed method directly processes low-resolution images as network inputs so that the networking computational cost can be reduced and the associated calculation speed can thereby be accelerated. The size of the convolutional kernel was decreased for reducing the number of network training parameters and for improving the computation speed. Furthermore, nonlinear mapping and image fusion were simultaneously achieved through the sub-pixel convolution layer. The proposed method was applied to images of universal test datasets and then compared with other methods for evaluation. The evaluation results obtained from the proposed method indicate a higher peak signal-to-noise ratio and better subjective visual effects. The experimental results confirm that the proposed method can improve the calculation speed by a large margin and can also produce super-resolution images of superior quality.

参考文献/References:

[1]? 苏衡, 周杰, 张志浩. 超分辨率图像重建方法综述[J]. 自动化学报, 2013, 39(8): 1202-1213.
SU Heng, ZHOU Jie, ZHANG Zhihao. Survey of super-resolution image reconstruction methods[J]. Acta Automatica Sinica, 2013, 39(8): 1202-1213.
[2]? CHANG H, YEUNG D Y, XIONG Y. Super-resolution through neighbor embedding[C]//Computer Vision and Pattern Recognition (CVPR). Proceedings of the 2004 IEEE Computer Society Conference on, IEEE Xplore, 2004: 275-282.
[3]? Timofte R, De Smet V, Van Gool L. Anchored neighborhood regression for fast example-based super-resolution [C]//IEEE International Conference on Computer Vision (ICCV), 2013: 1920-1927.
[4]? Timofte R, De Smet V, Van Gool L. A+: Adjusted anchored neighborhood regression for fast super-resolution[C]//Asian Conference on Computer Vision (ACCV), 2014: 111-126.
[5]? YANG Jianchao, Wright J, HUANG T, et al. Image super resolution via sparse representation[J]. IEEE Transactions on Image Processing, 2010, 19(11): 2861-2873.?
[6]? YANG Jianchao, HUANG T, Wright J, et al. Image super-resolution as sparse representation of raw image patches[C]//IEEE Computer Society Conference on Computer Vision and Pattern Recognition. DBLP, 2008: 1-8.
[7]? DONG Chao, Loy C C, HE Kaiming, et al. Image super-resolution using deep convolutional networks[J]. IEEE Transaction on Pattern Analysis & Machine Intelligence, 2016, 38(2): 295-307.
[8]? Jiwon Kim, Jung Kwon Lee, Kyoung Mu Lee. Accurate image super-resolution using very deep convolutional networks[C]//IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016: 1646-1654.
[9]? Jiwon Kim, Jung Kwon Lee, Kyoung Mu Lee. Deeply-recursive convolutional network for image super-resolution[C]//Proceeding of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, 2016: 1637-1645
[10]? Martin D, Fowlkes C, Tal D, et al. A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics[C]//IEEE International Conference on Computer Vision (ICCV), 2001: 416-423.
[11]? DONG C, CHEN C L, TANG X. Accelerating the Super-Resolution Convolutional Neural Network[C]//European Conference on Computer Vision, 2016: 391-407.
[12]? DONG Chao, Loy C C, HE Kaiming, et al. Learning a deep convolutional network for image super-resolution [C]//European Conference on Computer Vision (ECCV), 2014: 184-199.
?[13]? Schulter S, Leistner C, Bischof H. Fast and accurate image upscaling with super-resolution forests[C]//Computer Vision and Pattern Recognition. IEEE, 2015: 3791-3799.
[14]? HUANG J B, Singh A, Ahuja N. Single image super-resolution from transformed self-exemplars[C]//Computer Vision and Pattern Recognition. IEEE, 2015: 5197-5206.

相似文献/References:

[1]聂笃宪,陈一梅,陈鹤峰.去混合噪声的超分辨率图像重建算法[J].红外技术,2010,32(10):604.
 NIE Du-xian,CHEN Yi-mei,CHEN He-feng.Super-resolution Image Reconstruction Algorithm for mixed Noises Removal[J].Infrared Technology,2010,32(3):604.
[2]樊超,孙宁宁,夏旭.基于序列图像的超分辨率重建[J].红外技术,2010,32(5):279.
 FAN Chao,SUN Ning-ning,XIA Xu.Super-resolution Reconstruction Based on Image Sequences[J].Infrared Technology,2010,32(3):279.
[3]陈博洋,陈桂林,孙胜利.亚像元技术在图像采集系统中的应用[J].红外技术,2007,29(4):226.
 CHEN Bo-Yang,CHEN Gui-Lin,SUN Sheng-Li.Application of Subpixel Technology for Image Collection System[J].Infrared Technology,2007,29(3):226.
[4]浦利,金伟其,刘玉树,等.基于小波双立方配比插值的图像插值放大算法研究[J].红外技术,2006,28(8):453.
 PU Li,JIN Wei-qi,LIU Yu-shu,et al.A Study of Wavelet Bi-cubic Ratio Interpolation Algorithm[J].Infrared Technology,2006,28(3):453.
[5]徐宏财,向健勇,潘皓.一种改进的POCS算法的超分辨率图像重建[J].红外技术,2005,27(6):477.
 XU Hong-cai,XIANG Jian-yong,PAN Hao.An Improved POCS Algorithm for Super-resolution Image Reconstruction[J].Infrared Technology,2005,27(3):477.
[6]姚 敏,周 勤.一种低匹配误差敏感度的红外图像超分辨率算法[J].红外技术,2016,38(10):864.[doi:10.11846/j.issn.1001_8891.201610010]
 YAO Min,ZHOU Qin.An Infrared Images Super-resolution Algorithm with Low Registration Error Sensitivity [J].Infrared Technology,2016,38(3):864.[doi:10.11846/j.issn.1001_8891.201610010]
[7]刘 哲,黄世奇,姜 杰.基于引导滤波和多尺度局部自相似单幅红外图像超分辨率方法[J].红外技术,2017,39(4):345.[doi:10.11846/j.issn.1001_8891.201704009]
 LIU Zhe,HUANG Shiqi,JIANG Jie.Single Image Super Resolution Method Based on Multi-scale Self-similarity and Non Local Means [J].Infrared Technology,2017,39(3):345.[doi:10.11846/j.issn.1001_8891.201704009]
[8]王 晨,汤心溢,高思莉.基于深度卷积神经网络的红外场景理解算法[J].红外技术,2017,39(8):728.[doi:10.11846/j.issn.1001_8891.201708010]
 WANG Chen,TANG Xinyi,GAO Sili.Infrared Scene Understanding Algorithm Based on Deep Convolutional Neural Network [J].Infrared Technology,2017,39(3):728.[doi:10.11846/j.issn.1001_8891.201708010]
[9]闵召阳,赵文杰.卷积神经网络与时空上下文结合的目标跟踪算法[J].红外技术,2017,39(8):740.[doi:10.11846/j.issn.1001_8891.201708012]
 MIN Zhaoyang,ZHAO Wenjie.A Target Tracking Algorithm Combining Convolution Neural Network with Spatio Temporal Context [J].Infrared Technology,2017,39(3):740.[doi:10.11846/j.issn.1001_8891.201708012]
[10]刘 哲,韩九强,黄世奇.基于多引导滤波器的单幅图像超分辨率技术[J].红外技术,2017,39(10):920.[doi:10.11846/j.issn.1001_8891.201710009]
 LIU Zhe,HAN jiuqiang,HUANG Shiqi.Single Image Super-Resolution Based on Multi-Guided Filtering[J].Infrared Technology,2017,39(3):920.[doi:10.11846/j.issn.1001_8891.201710009]

备注/Memo

备注/Memo:
收稿日期:2017-07-06;修订日期:2018-03-05.
作者简介:蔡坤琪(1974-),男,讲师,研究方向为图像处理。
基金项目:国家自然科学基金(61471013)。

更新日期/Last Update: 2018-03-19