Share Email Print
cover

Proceedings Paper • new

A new end-to-end image compression system based on convolutional neural networks
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper 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.

Paper Details

Date Published: 6 September 2019
PDF: 14 pages
Proc. SPIE 11137, Applications of Digital Image Processing XLII, 111370M (6 September 2019); doi: 10.1117/12.2530195
Show Author Affiliations
Pinar Akyazi, Ecole Polytechnique Fédérale de Lausanne (Switzerland)
Touradj Ebrahimi, Ecole Polytechnique Fédérale de Lausanne (Switzerland)


Published in SPIE Proceedings Vol. 11137:
Applications of Digital Image Processing XLII
Andrew G. Tescher; Touradj Ebrahimi, Editor(s)

© SPIE. Terms of Use
Back to Top