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
Lens.org Logo
CITATIONS
Cited by 1 scholarly publication.
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Image compression

Computer programming

Quantization

Wavelets

Convolutional neural networks

Image quality

Network architectures

RELATED CONTENT


Back to Top