Presentation | 2019-03-14 Quantization Adaptive Recurrent Neural Network for Image Compression Rige Su, Zhengxue Cheng, Jiro Katto, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Image compression is a means of applying data compression technology to digital images. The purpose is to reduce redundant information in image data, thereby improving the efficiency of format storage and transmission of data. The traditional image algorithm has performed well, such as JPEG and JPEG2000. Afterwards the BPG performed better than JPGE. In recent years, deep learning has engaged into the field of image compression. In this paper, we are going to proposal lossy image compression architecture based on LSTM network. And replace the binarization, which is used in currently architecture [1], and add the quantization layer to evaluate the quality, respectively. As the experiment results show that use the quantization can better than JPEG2000, that we test the network for using Kodak database. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Image compressionLSTMQuantization |
Paper # | IMQ2018-48,IE2018-132,MVE2018-79 |
Date of Issue | 2019-03-07 (IMQ, IE, MVE) |
Conference Information | |
Committee | IMQ / IE / MVE / CQ |
---|---|
Conference Date | 2019/3/14(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Kagoshima University |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | media of five senses, multimedia, media experience, picture codinge, image media quality, network,quality and reliability, etc |
Chair | Kenji Sugiyama(Seikei Univ.) / Takayuki Hamamoto(Tokyo Univ. of Science) / Kenji Mase(Nagoya Univ.) / Takanori Hayashi(Hiroshima Inst. of Tech.) |
Vice Chair | Toshiya Nakaguchi(Chiba Univ.) / Mitsuru Maeda(Canon) / Hideaki Kimata(NTT) / Kazuya Kodama(NII) / Masayuki Ihara(NTT) / Hideyuki Shimonishi(NEC) / Jun Okamoto(NTT) |
Secretary | Toshiya Nakaguchi(Nagoya Univ.) / Mitsuru Maeda(Sony) / Hideaki Kimata(KDDI Research) / Kazuya Kodama(Nagoya Univ.) / Masayuki Ihara(NTT) / Hideyuki Shimonishi(Kyushu Univ.) / Jun Okamoto(Nagoya Univ.) |
Assistant | Masaru Tsuchida(NTT) / Gosuke Ohashi(Shizuoka Univ.) / Kazuya Hayase(NTT) / Yasutaka Matsuo(NHK) / Satoshi Nishiguchi(Oosaka Inst. of Tech.) / Masanori Yokoyama(*) / Chikara Sasaki(KDDI Research) / Yoshiaki Nishikawa(NEC) / Ryo Yamamoto(UEC) |
Paper Information | |
Registration To | Technical Committee on Image Media Quality / Technical Committee on Image Engineering / Technical Committee on Media Experience and Virtual Environment / Technical Committee on Communication Quality |
---|---|
Language | ENG |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Quantization Adaptive Recurrent Neural Network for Image Compression |
Sub Title (in English) | |
Keyword(1) | Image compressionLSTMQuantization |
1st Author's Name | Rige Su |
1st Author's Affiliation | Waseda University(Waseda Univ.) |
2nd Author's Name | Zhengxue Cheng |
2nd Author's Affiliation | Waseda University(Waseda Univ.) |
3rd Author's Name | Jiro Katto |
3rd Author's Affiliation | Waseda University(Waseda Univ.) |
Date | 2019-03-14 |
Paper # | IMQ2018-48,IE2018-132,MVE2018-79 |
Volume (vol) | vol.118 |
Number (no) | IMQ-500,IE-501,MVE-502 |
Page | pp.pp.149-151(IMQ), pp.149-151(IE), pp.149-151(MVE), |
#Pages | 3 |
Date of Issue | 2019-03-07 (IMQ, IE, MVE) |