Deep Convolutional AutoEncoder-based Lossy Image Compression

Zhengxue Cheng, Heming Sun, Masaru Takeuchi, Jiro Katto

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

102 Citations (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 Sept 5
Event33rd Picture Coding Symposium, PCS 2018 - San Francisco, United States
Duration: 2018 Jun 242018 Jun 27

Publication series

Name2018 Picture Coding Symposium, PCS 2018 - Proceedings

Other

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

Keywords

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

ASJC Scopus subject areas

  • Signal Processing
  • Media Technology

Fingerprint

Dive into the research topics of 'Deep Convolutional AutoEncoder-based Lossy Image Compression'. Together they form a unique fingerprint.

Cite this