Translator Disclaimer
Presentation + Paper
6 September 2019 A new end-to-end image compression system based on convolutional neural networks
Author Affiliations +
Abstract
In this paper, two new end-to-end image compression architectures based on convolutional neural networks are presented. The proposed networks employ 2D wavelet decomposition as a preprocessing step before training and extract features for compression from wavelet coefficients. Training is performed end-to-end and multiple models operating at di↵erent rate points are generated by using a regularizer in the loss function. Results show that the proposed methods outperform JPEG compression, reduce blocking and blurring artifacts, and preserve more details in the images especially at low bitrates.
Conference Presentation
© (2019) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Pinar Akyazi and Touradj Ebrahimi "A new end-to-end image compression system based on convolutional neural networks", Proc. SPIE 11137, Applications of Digital Image Processing XLII, 111370M (6 September 2019); https://doi.org/10.1117/12.2530195
PROCEEDINGS
14 PAGES + PRESENTATION

SHARE
Advertisement
Advertisement
RELATED CONTENT

Wavelet-based fractal image compression
Proceedings of SPIE (September 25 2003)
Interactive wavelet-based 2D and 3D image compression
Proceedings of SPIE (June 30 1993)
Summary of technology and testbed for JPEG 2000
Proceedings of SPIE (December 28 2000)

Back to Top