Deep Convolutional AutoEncoder-based Lossy Image Compression

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Image compression has been investigated as a fundamental research topic for many decades. Recently, deep learning has achieved great success in many computer vision tasks, and is gradually being used in image compression. In this paper, we present a lossy image compression architecture, which utilizes the advantages of convolutional autoencoder (CAE) to achieve a high coding efficiency. First, we design a novel CAE architecture 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.

Original languageEnglish
Title of host publication2018 Picture Coding Symposium, PCS 2018 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages253-257
Number of pages5
ISBN (Print)9781538641606
DOIs
Publication statusPublished - 2018 Sep 5
Event33rd Picture Coding Symposium, PCS 2018 - San Francisco, United States
Duration: 2018 Jun 242018 Jun 27

Other

Other33rd Picture Coding Symposium, PCS 2018
CountryUnited States
CitySan Francisco
Period18/6/2418/6/27

Fingerprint

Image compression
Image coding
Principal component analysis
Computer vision
Entropy

Keywords

  • Convolutional autoencoder
  • Deep learning
  • Image compression
  • Principal component analysis

ASJC Scopus subject areas

  • Signal Processing
  • Media Technology

Cite this

Cheng, Z., Sun, H., Takeuchi, M., & Katto, J. (2018). Deep Convolutional AutoEncoder-based Lossy Image Compression. In 2018 Picture Coding Symposium, PCS 2018 - Proceedings (pp. 253-257). [8456308] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/PCS.2018.8456308

Deep Convolutional AutoEncoder-based Lossy Image Compression. / Cheng, Zhengxue; Sun, Heming; Takeuchi, Masaru; Katto, Jiro.

2018 Picture Coding Symposium, PCS 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2018. p. 253-257 8456308.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Cheng, Z, Sun, H, Takeuchi, M & Katto, J 2018, Deep Convolutional AutoEncoder-based Lossy Image Compression. in 2018 Picture Coding Symposium, PCS 2018 - Proceedings., 8456308, Institute of Electrical and Electronics Engineers Inc., pp. 253-257, 33rd Picture Coding Symposium, PCS 2018, San Francisco, United States, 18/6/24. https://doi.org/10.1109/PCS.2018.8456308
Cheng Z, Sun H, Takeuchi M, Katto J. Deep Convolutional AutoEncoder-based Lossy Image Compression. In 2018 Picture Coding Symposium, PCS 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2018. p. 253-257. 8456308 https://doi.org/10.1109/PCS.2018.8456308
Cheng, Zhengxue ; Sun, Heming ; Takeuchi, Masaru ; Katto, Jiro. / Deep Convolutional AutoEncoder-based Lossy Image Compression. 2018 Picture Coding Symposium, PCS 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 253-257
@inproceedings{2d35a297f22a4d529dee14e56e0628f0,
title = "Deep Convolutional AutoEncoder-based Lossy Image Compression",
abstract = "Image compression has been investigated as a fundamental research topic for many decades. Recently, deep learning has achieved great success in many computer vision tasks, and is gradually being used in image compression. In this paper, we present a lossy image compression architecture, which utilizes the advantages of convolutional autoencoder (CAE) to achieve a high coding efficiency. First, we design a novel CAE architecture 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.",
keywords = "Convolutional autoencoder, Deep learning, Image compression, Principal component analysis",
author = "Zhengxue Cheng and Heming Sun and Masaru Takeuchi and Jiro Katto",
year = "2018",
month = "9",
day = "5",
doi = "10.1109/PCS.2018.8456308",
language = "English",
isbn = "9781538641606",
pages = "253--257",
booktitle = "2018 Picture Coding Symposium, PCS 2018 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Deep Convolutional AutoEncoder-based Lossy Image Compression

AU - Cheng, Zhengxue

AU - Sun, Heming

AU - Takeuchi, Masaru

AU - Katto, Jiro

PY - 2018/9/5

Y1 - 2018/9/5

N2 - Image compression has been investigated as a fundamental research topic for many decades. Recently, deep learning has achieved great success in many computer vision tasks, and is gradually being used in image compression. In this paper, we present a lossy image compression architecture, which utilizes the advantages of convolutional autoencoder (CAE) to achieve a high coding efficiency. First, we design a novel CAE architecture 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.

AB - Image compression has been investigated as a fundamental research topic for many decades. Recently, deep learning has achieved great success in many computer vision tasks, and is gradually being used in image compression. In this paper, we present a lossy image compression architecture, which utilizes the advantages of convolutional autoencoder (CAE) to achieve a high coding efficiency. First, we design a novel CAE architecture 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.

KW - Convolutional autoencoder

KW - Deep learning

KW - Image compression

KW - Principal component analysis

UR - http://www.scopus.com/inward/record.url?scp=85053930037&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85053930037&partnerID=8YFLogxK

U2 - 10.1109/PCS.2018.8456308

DO - 10.1109/PCS.2018.8456308

M3 - Conference contribution

SN - 9781538641606

SP - 253

EP - 257

BT - 2018 Picture Coding Symposium, PCS 2018 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -