基于低尺度细节恢复的单幅图像阴影去除方法

doi:10.3969/j.issn.0372-2112.2020.07.007

电子学报 ›› 2020, Vol. 48 ›› Issue (7): 1293-1302.DOI: 10.3969/j.issn.0372-2112.2020.07.007

基于低尺度细节恢复的单幅图像阴影去除方法

吴文¹, 万毅²

1. 新疆理工学院信息工程系, 新疆阿克苏 843100;
2. 温州大学电气与电子工程学院, 浙江温州 325035

收稿日期:2019-06-12 修回日期:2020-01-03 出版日期:2020-07-25 发布日期:2020-07-25
通讯作者: 万毅
作者简介:吴文男,1994年5月出生,湖北武汉人.2019年毕业于湖北大学,获理学硕士学位,现为新疆理工学院信息工程系教员,主要研究方向为图像处理、深度学习等.E-mail:1119764335@qq.com
基金资助:
浙江省科技计划基础公益研究计划（No.LGG18F040002）；浙江省自然科学基金（No.LY19F020035）

Single Image Shadow Removal Using Low-Scale Detail Recovering

WU Wen¹, WAN Yi²

1. Department of Information Engineering, Xinjiang Institute of Technology, Aksu, Xinjiang 843100, China;
2. School of Electrical and Electronic Engineering, Wenzhou University, Wenzhou, Zhejiang 325035, China

Received:2019-06-12 Revised:2020-01-03 Online:2020-07-25 Published:2020-07-25

摘要/Abstract

摘要： 为了在光照复杂、纹理丰富的图像上获得更好的去阴影效果，基于生成对抗网络提出了一种新颖的阴影去除方法.首先，所提网络中的阴影检测子网为阴影图像生成阴影掩膜，基于该检测结果提出一种光照敏感的多尺度图像分解方法，在几乎不损失光照信息的同时提取图像纹理信息；然后，蒙版生成子网为分解后的低尺度图像生成相应的蒙版用于去除其中阴影；其次，边界复原子网修复阴影边界实现友好的过渡；最后，使用自适应衰减因子引导图像进行细节恢复以得到纹理丰富的结果.实验结果表明所提方法可以有效地提高阴影去除效果.

关键词: 图像处理, 阴影去除, 生成对抗网络, 光照敏感, 多尺度分解

Abstract: To obtain a better shadow removal result on images with complex illumination and texture,we proposed a novel approach based on generative adversarial networks.Firstly,shadow mask is generated by the shadow detection sub-net from input shadow image.Based on this detection result,we proposed an illumination sensitive multi-scale image decomposition method to extract the texture information with less or no illumination information loss.Secondly,shadow matte is generated by the matte generation sub-net for the low scale shadow image to remove shadows in it.Thirdly,the shadow boundary are naturally recovered by the boundary completion sub-net.Finally,the shadow removal result is obtained using a detail recovering method guided by adaptive attenuation factor.Experimental results show that the proposed method can improve the removal performance effectively.

Key words: image processing, shadow removal, generative adversarial networks, illumination sensitive, multi-scale decomposition

中图分类号:

TP391.41

吴文, 万毅. 基于低尺度细节恢复的单幅图像阴影去除方法[J]. 电子学报, 2020, 48(7): 1293-1302.

WU Wen, WAN Yi. Single Image Shadow Removal Using Low-Scale Detail Recovering[J]. Acta Electronica Sinica, 2020, 48(7): 1293-1302.

参考文献

[1] GUO Rui-qi,DAI Qie-yun,DEREK H.Paired regions for shadow detection and removal[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2013,35(12):2956-2967.
[2] KHAN S H,BENNAMOUN M,SOHEL F,et al.Automatic shadow detection and removal from a single image[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2016,38(3):431-446.
[3] VICENTE T F Y,HOAI M,SAMARAS D.Leave-one-out kernel optimization for shadow detection and removal[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2018,40(3):682-695.
[4] 舒坚,张学佩,等.基于深度卷积神经网络的多节点间链路预测方法[J].电子学报,2018,46(12):2970-2977. SHU Jian,ZHANG Xue-pei,et al.Multi-nodes link prediction method based on deep convolution neural networks[J].Acta Electronica Sinica,2018,46(12):2970-2977.(in Chinese)
[5] 李康,李亚敏,等.基于卷积神经网络的鲁棒高精度目标跟踪算法[J].电子学报,2018,46(9):2087-2093. LI Kang,LI Ya-min,et al.A robust and accurate object tracking algorithm based on convolutional neural network[J].Acta Electronica Sinica,2018,46(9):2087-2093.(in Chinese)
[6] 赵耀霞,吴桐,韩焱.基于卷积神经网络的复杂构件内部零件装配正确性识别[J].电子学报,2018,46(8):1983-1988. ZHAO Yao-xia,WU Tong,HAN Yan.Identifying the correctness of fit of internal components based on a convolutional neural network[J].Acta Electronica Sinica,2018,46(8):1983-1988.(in Chinese)
[7] LIU Feng,GLEICHER M.Texture-Consistent shadow removal[A].European Conference on Computer Vision[C].Berlin,Heidelberg:Springer,2008.437-450.
[8] FINLAYSON G D,HORDLEY S D,DREW M S.Removing shadows from images[A].European Conference on Computer Vision[C].Berlin,Heidelberg:Springer,2002.823-836.
[9] FINLAYSON G D,HORDLEY S D,et al.On the removal of shadows from images[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2006,28(1):59-68.
[10] MOHAN A,TUMBIN J,CHOUDHURY P.Editing soft shadows in a digital photograph[J].IEEE Computer Graphics and Applications,2007,27(2):23-31.
[11] XIAO C,XIAO D,ZHANG L,et al.Efficient shadow removal using subregion matching illumination transfer[J].Computer Graphics Forum,2013,32(7):421-430.
[12] ARBEL E,HELOR H.Shadow removal using intensity surfaces and texture anchor points[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,33(6):1202-1216.
[13] BARRON J T,MALIK J.Shape,illumination,and reflectance from shading[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,37(8):1670-1687.
[14] QU Liang-qiong,TIAN Jian-dong,HE Sheng-feng,et al.DeshadowNet:A multi-context embedding deep network for shadow removal[A].IEEE Conference on Computer Vision and Pattern Recognition[C].Honolulu,Hawaii,USA:IEEE,2017.4067-4075.
[15] WANG Ji-feng,LI Xiang,YANG Jian.Stacked conditional generative adversarial networks for iointly learning shadow detection and shadow removal[A].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition[C].USA:IEEE,2018.1788-1797.
[16] HU Xiao-wei,FU Chi-wing,ZHU Lei,et al.Direction-aware spatial context features for shadow detection and removal[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2018,arXiv:1712.04142.
[17] HU Xiao-wei,JIANG Yi-tong,FU Chi-Wing,et al.Mask-ShadowGAN:Learning to remove shadows from unpaired data[J].arXiv Preprint,2019,arXiv:1903:10683.
[18] FAN Hui,HAN Meng,LI Jin-jiang.Image shadow removal using end-to-end deep convolutional neural networks[J].Applied Sciences,2019,9(5):1009.
[19] GOODFELLOW I J,POUGET-ABADIE J,MIRZA M,et al.Generative adversarial nets[A].Advances in Neural Information Processing Systems[C].Montreal,Canada,2014.2672-2680.
[20] MIRZA M,OSINDERO S.Conditional generative adversarial nets[J].arXiv Preprint,2014,arXiv:1411.1784.
[21] ISOLA P,ZHU J Y,et al.Image-to-image translation with conditional adversarial networks[A].IEEE Conference on Computer Vision and Pattern Recognition[C].Honolulu,Hawaii,USA:IEEE,2017.1125-1134.
[22] LOFFE S,SZEGEDY C.Batch normalization:accelerating deep network training by reducing internal covariate shift[A].International Conference on Machine Learning[C].Lille,France:IEEE,2015.448-456.
[23] JOHNSON J,ALAHI A,LI Fei-fei.Perceptual losses for real-time style transfer and super-resolution[A].European Conference on Computer Vision[C].Amsterdam,The Nether Lands,2016.694-711.
[24] MAO Xu-dong,et al.Least squares generative adversarial networks[A].Proceedings of the IEEE International Conference On Computer Vision[C].Venice,Italy:IEEE,2017.2794-2802.
[25] WONGSUPHASAWAT K,SMILKOV D,WEXLER J,et al.Visualizing dataflow graphs of deep learning models in TensorFlow[J].IEEE Transactions on Visualization and Computer Graphics,2018,24(1):1-12.
[26] 杨学志,叶铭,等.采用混合特征相似性的极化SAR图像降噪算法[J].电子学报,2016,44(11):2583-2591. YANG Xue-zhi,YE Ming,et al.Speckle reduction for PolSAR images using hybrid features similarity[J].Acta Electronica Sinica,2016,44(11):2583-2591.(in Chinese)

基于低尺度细节恢复的单幅图像阴影去除方法

Single Image Shadow Removal Using Low-Scale Detail Recovering

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	李居朋, 王颖慧, 李刚. 医学图像关键点检测深度学习方法研究与挑战[J]. 电子学报, 2022, 50(1): 226-237.
[2]	李宝奇, 黄海宁, 刘纪元, 李宇. 基于改进CycleGAN的光学图像迁移生成水下小目标合成孔径声纳图像算法研究[J]. 电子学报, 2021, 49(9): 1746-1753.
[3]	席亮, 刘涵, 樊好义, 张凤斌. 基于深度对抗学习潜在表示分布的异常检测模型[J]. 电子学报, 2021, 49(7): 1257-1265.
[4]	陈星宇, 叶锋, 黄添强, 翁彬, 陈家祯, 林文忠. 融合小型深度生成模型的显著性检测[J]. 电子学报, 2021, 49(4): 768-774.
[5]	李峰, 詹邦成, 辛蕾, 刘洋, 刘志佳, 肖化超. 基于新型联合感知矩阵的压缩学习目标识别技术[J]. 电子学报, 2021, 49(11): 2108-2116.
[6]	唐艳秋, 潘泓, 朱亚平, 李新德. 图像超分辨率重建研究综述[J]. 电子学报, 2020, 48(7): 1407-1420.
[7]	朱克凡, 王杰贵, 刘有军. 小样本条件下基于数据增强和WACGAN的雷达目标识别算法[J]. 电子学报, 2020, 48(6): 1124-1131.
[8]	王格格, 郭涛, 余游, 苏菡. 基于生成对抗网络的无监督域适应分类模型[J]. 电子学报, 2020, 48(6): 1190-1197.
[9]	罗会兰, 陈鸿坤. 基于深度学习的目标检测研究综述[J]. 电子学报, 2020, 48(6): 1230-1239.
[10]	闻佳, 王宏君, 邓佳, 刘鹏飞. 基于深度学习的异常事件检测[J]. 电子学报, 2020, 48(2): 308-313.
[11]	江泽涛, 覃露露. 一种基于U-Net生成对抗网络的低照度图像增强方法[J]. 电子学报, 2020, 48(2): 258-264.
[12]	方晨, 郭渊博, 王娜, 甄帅辉, 唐国栋. 基于生成对抗网络的差分隐私数据发布方法[J]. 电子学报, 2020, 48(10): 1983-1992.
[13]	温立民, 巨永锋, 闫茂德. 基于自然统计特征分布的交通图像雾浓度检测[J]. 电子学报, 2017, 45(8): 1888-1895.
[14]	雷涛, 张艳宁, 樊养余, 王小鹏, 王履程. 矢量对偶形态学算子[J]. 电子学报, 2016, 44(6): 1285-1293.
[15]	姜珊, 胡贵军, 王海燕, 李莉. 基于彩色二维条码流的Display-to-Camera通信系统[J]. 电子学报, 2016, 44(4): 767-774.