Class-adapted image compression using independent component analysis

A.J. Ferreira, M.A.T. Figueiredo
Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429)  
This paper exploits independent component analysis (ICA) to obtain transform-based compression schemes adapted to specific image classes. This adaptation results from the data-dependent nature of the ICA bases, learnt from training images. Several coder architectures are evaluated and compared, according to both standard (SNR) and perceptual (picture quality scale -PQS) criteria, on two classes of images: faces and fingerprints. For fingerprint images, our coders perform close to the well-known
more » ... e to the well-known special-purpose wavelet-based coder developed by the FBI. For face images, our ICA-based coders clearly outperform JPEG at the low bit-rates herein considered.
doi:10.1109/icip.2003.1247039 dblp:conf/icip/FerreiraF03 fatcat:f63clnzkqbh2laveqpg6zpbmru