direkt zum Inhalt springen

direkt zum Hauptnavigationsmenü

Sie sind hier

TU Berlin

Page Content

Scientific Publications

Restricted Boltzmann Machine Image Compression
Citation key 1533Küchhold2018
Author Markus Küchhold and Maik Simon and Thomas Sikora
Title of Book Picture Coding Symposium (PCS 2018)
Year 2018
Address San Francisco, CA, USA
Month jun
Note DOI: 10.1109/PCS.2018.8456279
Organization IEEE
Abstract We propose a novel lossy block-based image compression approach. Our approach builds on non-linear autoencoders that can, when properly trained, explore non-linear statistical dependencies in the image blocks for redundancy reduction. In contrast the DCT employed in JPEG is inherently restricted to exploration of linear dependencies using a second-order statistics framework. The coder is based on pre-trained class-specific Restricted Boltzmann Machines (RBM). These machines are statistical variants of neural network autoencoders that directly map pixel values in image blocks into coded bits. Decoders can be implemented with low computational complexity in a codebook design. Experimental results show that our RBM-codec outperforms JPEG at high compression rates, both in terms of PSNR, SSIM and subjective results.
Link to publication Download Bibtex entry

Zusatzinformationen / Extras

Quick Access:

Schnellnavigation zur Seite über Nummerneingabe

Auxiliary Functions