一种光照不均图像的超分辨率重建算法研究Super-resolution reconstruction algorithm for images with uneven illumination
刘南艳;许新宇;高光普;
摘要(Abstract)：
针对传统的超分辨率重建算法在处理光照不均图像时会出现图像失真、边缘模糊等问题,在原有的极深超分辨率(VDSR)重建方法基础上提出一种光照不均图像的超分辨率重建方法。首先,采用自门控Swish激活函数代替常用的ReLU激活函数,解决了随着网络层数加深出现的过拟合问题,可以更好地学习映射关系;然后,在网络结构中提出一种简洁紧凑型的局部残差网络,在保证网络层数的同时能学习更多的图像细节信息,很好地解决了VDSR中由于图像多次传输出现的信息丢失问题;最后,在网络末端使用反卷积获得高分辨率图像。通过实验证明该方法对光照不均图像重建可以获得更高的峰值信噪比(PSNR)和结构相似度(SSIM)。
关键词(KeyWords)： 光照不均图像;超分辨率重建;激活函数;局部残差网络;特征提取;PSNR;SSIM
基金项目(Foundation): 国家自然科学基金(61702408)
作者(Author): 刘南艳;许新宇;高光普;
Email:
DOI: 10.16652/j.issn.1004-373x.2021.01.008
参考文献(References)：
- [1]李素梅，雷国庆，范如.基于卷积神经网络的深度图超分辨率重建[J].光学学报，2017,37(12):132-140.
- [2]张子龙，李庆武，何敏，等.一种基于多尺度结构自相似性的图像超分辨率重建算法[J].科学技术与工程，2016,16(33):92-97.
- [3] YANG W M,TIAN Y P,ZHOU F,et al. Consistent coding scheme for single-image super-resolution via independent dictionaries[J]. IEEE transaction on multimedia,2016,18(3):313-325.
- [4] ZHANG Y B,ZHANG Y L,ZHANG J,et al. CCR:clustering and collaborative representation for fast single image super-resolution[J]. IEEE transactions on multimedia,2015,18(3):405-417.
- [5] YANG M C,WANG Y C F. A self-learning approach to single image super-resolution[J]. IEEE transactions on multimedia,2013,15(3):498-508.
- [6]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.
- [7] REN C,HE X H,NGUYEN T Q. Single image super-resolution via adaptive high-dimensional non-local total variation and adaptive geometric feature[J]. IEEE transactions on image processing,2017,26(1):90-106.
- [8] PARK S C,PARK M K,KANG M G. Super-resolution image reconstruction:a technical overview[J]. Signal processing magazine,2003,20(3):21-36.
- [9] WANG Z Z,DELLER J R. Multi-frame super-resolution based on spare representation and matrix completion[C]//2013 IEEE China Summit&International Conference. New York:IEEE,2013:538-542.
- [10] DONG C,LOY C C,HE K M,et al. Learning a deep convolutional network for image super-resolution[C]//European Conference on Computer Vision. Berlin:Springer Verlag,2014:184-199.
- [11] DONG C,LOY C C,TANG X O. Accelerating the super-resolution convolutional neural network[C]//2016 Proceedings of European Conference on Computer Vision(ECCV). Berlin:Springer Verlag,2016:391-407.
- [12] KIM J,LEE J K,LEE K M. Accurate image super-resolution using very deep convolutional networks[C]//Processing of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas:IEEE,2016:1646-1654.
- [13] SIMONYAN K,ZISSERMAN A. Very deep convolution networks for large-scale image recognition[EB/OL].[2014-09-10]. https：//www.researchgate.net/publication/265385906.
- [14]付燕，李瑶，严斌斌.一种煤矿井下视频图像增强算法[J].工矿自动化，2018,44(7):80-83.
- [15]周登文，赵丽娟，段然，等.基于递归残差网络的图像超分辨率重建[J].自动化学报，2019,45(6):1157-1165.