CNN-Based Illumination Estimation with Semantic Information

被引:15
作者
Choi, Ho-Hyoung [1 ]
Kang, Hyun-Soo [2 ]
Yun, Byoung-Ju [3 ]
机构
[1] Kyungpook Natl Univ, Sch Dent, Adv Dent Device Dev Inst, 2177 Dalgubeol Daero, Daegu 41940, South Korea
[2] Chungbuk Natl Univ, Coll Elect & Comp Engn, Sch Informat & Commun Engn, 1 Chungdae Ro, Cheongju 28644, Chungcheongbuk, South Korea
[3] Kyungpook Natl Univ, Sch Elect Engn, IT Coll, 80 Daehak Ro, Daegu 41566, South Korea
来源
APPLIED SCIENCES-BASEL | 2020年 / 10卷 / 14期
基金
新加坡国家研究基金会;
关键词
human visual system (HVS); color constancy; residual neural network; semantic information; local and global information; image dataset; COLOR CONSTANCY; CHROMATICITY;
D O I
10.3390/app10144806
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
For more than a decade, both academia and industry have focused attention on the computer vision and in particular the computational color constancy (CVCC). The CVCC is used as a fundamental preprocessing task in a wide range of computer vision applications. While our human visual system (HVS) has the innate ability to perceive constant surface colors of objects under varying illumination spectra, the computer vision is facing the color constancy challenge in nature. Accordingly, this article proposes novel convolutional neural network (CNN) architecture based on the residual neural network which consists of pre-activation, atrous or dilated convolution and batch normalization. The proposed network can automatically decide what to learn from input image data and how to pool without supervision. When receiving input image data, the proposed network crops each image into image patches prior to training. Once the network begins learning, local semantic information is automatically extracted from the image patches and fed to its novel pooling layer. As a result of the semantic pooling, a weighted map or a mask is generated. Simultaneously, the extracted information is estimated and combined to form global information during training. The use of the novel pooling layer enables the proposed network to distinguish between useful data and noisy data, and thus efficiently remove noisy data during learning and evaluating. The main contribution of the proposed network is taking CVCC to higher accuracy and efficiency by adopting the novel pooling method. The experimental results demonstrate that the proposed network outperforms its conventional counterparts in estimation accuracy.
引用
收藏
页数:17
相关论文
共 40 条
[1]  
Abadi M., 2016, TENSORFLOW LARGE SCA
[2]   Colour Constancy Beyond the Classical Receptive Field [J].
Akbarinia, Arash ;
Parraga, C. Alejandro .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2018, 40 (09) :2081-2094
[3]  
[Anonymous], 2015, P IEEE INT C COMPUTE
[4]  
[Anonymous], 2015, BMVC
[5]  
[Anonymous], 2011, COLOR CONSTANCY RES
[6]  
[Anonymous], 2016, ARXIV 1606 00915 CS
[7]  
Bianco Simone, 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), P81, DOI 10.1109/CVPRW.2015.7301275
[8]   Automatic color constancy algorithm selection and combination [J].
Bianco, S. ;
Ciocca, G. ;
Cusano, C. ;
Schettini, R. .
PATTERN RECOGNITION, 2010, 43 (03) :695-705
[9]  
Bianco S., 2015, ARXIV15080099V2, DOI [10.1109/TIP.2017.2713044, DOI 10.1109/TIP.2017.2713044]
[10]   A SPATIAL PROCESSOR MODEL FOR OBJECT COLOR-PERCEPTION [J].
BUCHSBAUM, G .
JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS, 1980, 310 (01) :1-26