Presentation 2017-06-23
Visibility Prediction of Color Scheme with the Model of Human Color Vision composed of Convolutional Neural Networks
Shodai Sasaki, Yoshihisa Shinozawa,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this research, we implement convolutional neural networks (CNN) and introduce a multi-stage color (MSC) model, which is a human color vision model, reproduce the appearance of human color on a computer and compare the image visibility of an unknown color scheme to perform prediction. By making the reaction values of multiple cell layers of the MSC model as input for the CNN, and learning the filters, it is possible to extract the features of two or more complicated colors. In addition, in order to extract the characteristics between images in the construction of the CNN, we propose a CNN that improves the structure. CNN learning was performed using the data of the pairwise comparison experiment. The results show that the accuracy of this method is higher than that of previous researchon the evaluation of visibility prediction.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Multi-Stage Color Model / color scheme / visibility prediction / convolutional neural networks
Paper # NC2017-11
Date of Issue 2017-06-16 (NC)

Conference Information
Committee NC / IPSJ-BIO / IBISML / IPSJ-MPS
Conference Date 2017/6/23(3days)
Place (in Japanese) (See Japanese page)
Place (in English) Okinawa Institute of Science and Technology
Topics (in Japanese) (See Japanese page)
Topics (in English) Machine Learning Approach to Biodata Mining, and General
Chair Masafumi Hagiwara(Keio Univ.) / / Kenji Fukumizu(ISM)
Vice Chair Yutaka Hirata(Chubu Univ.) / / Masashi Sugiyama(Univ. of Tokyo)
Secretary Yutaka Hirata(Tokyo Inst. of Tech.) / (Nagoya Univ.) / Masashi Sugiyama / (Kyoto Univ.)
Assistant Yoshihisa Shinozawa(Keio Univ.) / Keiichiro Inagaki(Chubu Univ.) / / Ichiro Takeuchi(Nagoya Inst. of Tech.) / Toshihiro Kamishima(AIST)

Paper Information
Registration To Technical Committee on Neurocomputing / Special Interest Group on Bioinformatics and Genomics / Technical Committee on Infomation-Based Induction Sciences and Machine Learning / Special Interest Group on Mathematical Modeling and Problem Solving
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Visibility Prediction of Color Scheme with the Model of Human Color Vision composed of Convolutional Neural Networks
Sub Title (in English)
Keyword(1) Multi-Stage Color Model
Keyword(2) color scheme
Keyword(3) visibility prediction
Keyword(4) convolutional neural networks
1st Author's Name Shodai Sasaki
1st Author's Affiliation Keio University(Keio Univ.)
2nd Author's Name Yoshihisa Shinozawa
2nd Author's Affiliation Keio University(Keio Univ.)
Date 2017-06-23
Paper # NC2017-11
Volume (vol) vol.117
Number (no) NC-109
Page pp.pp.39-44(NC),
#Pages 6
Date of Issue 2017-06-16 (NC)