講演抄録/キーワード |
講演名 |
2020-03-16 16:45
Image compression by colorization ○Hiya Roy・Subhajit Chaudhury・Toshihiko Yamasaki・Tatsuaki Hashimoto(UTokyo) PRMU2019-86 |
抄録 |
(和) |
(まだ登録されていません) |
(英) |
Image compression techniques exploit the inherent psycho-visual limitations in human vision to reduce the number of bits required to store an image without degrading its perceptual quality. While most recent methods use an encoder-decoder based Convolutional Neural Networks (CNN) features, our approach focuses on limiting the size of the compressed representation by sampling and storing some color informative pixels of the chrominance channels. We propose a uniform sampler-based encoder, that chooses and stores only a few color informative pixels. During decoding, we use these color values from a few selected pixels along with the luminance channel to reconstruct the full-color image that looks perceptually similar to the original image. Experimental results prove the effectiveness of the proposed method by demonstrating comparable or better performance compared to the state-of-the-art methods in image compression. |
キーワード |
(和) |
/ / / / / / / |
(英) |
Lossy image compression / Colorization / Deep neural networks / / / / / |
文献情報 |
信学技報, vol. 119, no. 481, PRMU2019-86, pp. 107-108, 2020年3月. |
資料番号 |
PRMU2019-86 |
発行日 |
2020-03-09 (PRMU) |
ISSN |
Online edition: ISSN 2432-6380 |
著作権に ついて |
技術研究報告に掲載された論文の著作権は電子情報通信学会に帰属します.(許諾番号:10GA0019/12GB0052/13GB0056/17GB0034/18GB0034) |
PDFダウンロード |
PRMU2019-86 |