TU Berlin

Fachgebiet NachrichtenübertragungWiss. Veröffentlichungen

Inhalt des Dokuments

zur Navigation

Wissenschaftliche Veröffentlichungen

Restricted Boltzmann Machine Image Compression
Zitatschlüssel 1533Küchhold2018
Autor Markus Küchhold and Maik Simon and Thomas Sikora
Buchtitel Picture Coding Symposium (PCS 2018)
Jahr 2018
Adresse San Francisco, CA, USA
Monat jun
Notiz DOI: 10.1109/PCS.2018.8456279
Organisation IEEE
Zusammenfassung 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 zur Publikation Download Bibtex Eintrag



Schnellnavigation zur Seite über Nummerneingabe