| Item type |
SIG Technical Reports(1) |
| 公開日 |
2018-05-31 |
| タイトル |
|
|
タイトル |
Lossy Image Compression using Deep Convolutional AutoEncoder |
| タイトル |
|
|
言語 |
en |
|
タイトル |
Lossy Image Compression using Deep Convolutional AutoEncoder |
| 言語 |
|
|
言語 |
eng |
| キーワード |
|
|
主題Scheme |
Other |
|
主題 |
学生セッション |
| 資源タイプ |
|
|
資源タイプ識別子 |
http://purl.org/coar/resource_type/c_18gh |
|
資源タイプ |
technical report |
| 著者所属 |
|
|
|
Waseda University |
| 著者所属 |
|
|
|
Waseda University |
| 著者所属 |
|
|
|
Waseda University |
| 著者所属 |
|
|
|
Waseda University |
| 著者所属(英) |
|
|
|
en |
|
|
Waseda University |
| 著者所属(英) |
|
|
|
en |
|
|
Waseda University |
| 著者所属(英) |
|
|
|
en |
|
|
Waseda University |
| 著者所属(英) |
|
|
|
en |
|
|
Waseda University |
| 著者名 |
Zhengxue, Cheng
Heming, Sun
Masaru, Takeuchi
Jiro, Katto
|
| 著者名(英) |
Zhengxue, Cheng
Heming, Sun
Masaru, Takeuchi
Jiro, Katto
|
| 論文抄録 |
|
|
内容記述タイプ |
Other |
|
内容記述 |
Image compression has been investigated as a fundamental research topic for many decades. Recently, deep learning is gradually being used in image compression. In this paper, we present a lossy image compression architecture, which utilizes convolutional autoencoder (CAE) to achieve a high coding efficiency. First, we design a novel CAE structure to replace the conventional transforms and train this CAE using a rate-distortion loss function. Second, to generate a more energy-compact representation, we utilize the principal components analysis (PCA) to rotate the feature maps produced by the CAE, and then apply the quantization and entropy coder to generate the codes. Experimental results demonstrate that our method outperforms traditional image coding algorithms, by achieving a 13.7% BD-rate decrement on the Kodak database images compared to JPEG2000. Besides, our method maintains a moderate complexity similar to JPEG2000. |
| 論文抄録(英) |
|
|
内容記述タイプ |
Other |
|
内容記述 |
Image compression has been investigated as a fundamental research topic for many decades. Recently, deep learning is gradually being used in image compression. In this paper, we present a lossy image compression architecture, which utilizes convolutional autoencoder (CAE) to achieve a high coding efficiency. First, we design a novel CAE structure to replace the conventional transforms and train this CAE using a rate-distortion loss function. Second, to generate a more energy-compact representation, we utilize the principal components analysis (PCA) to rotate the feature maps produced by the CAE, and then apply the quantization and entropy coder to generate the codes. Experimental results demonstrate that our method outperforms traditional image coding algorithms, by achieving a 13.7% BD-rate decrement on the Kodak database images compared to JPEG2000. Besides, our method maintains a moderate complexity similar to JPEG2000. |
| 書誌レコードID |
|
|
収録物識別子タイプ |
NCID |
|
収録物識別子 |
AN10438399 |
| 書誌情報 |
研究報告オーディオビジュアル複合情報処理（AVM）
巻 2018-AVM-101,
号 4,
p. 1-6,
発行日 2018-05-31
|
| ISSN |
|
|
収録物識別子タイプ |
ISSN |
|
収録物識別子 |
2188-8582 |
| Notice |
|
|
|
SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc. |
| 出版者 |
|
|
言語 |
ja |
|
出版者 |
情報処理学会 |
IPSJ-AVM18101004.pdf (4.8 MB)
