1 November 1992 Unsupervised orthogonalization neural network for image compression
Author Affiliations +
Proceedings Volume 1826, Intelligent Robots and Computer Vision XI: Biological, Neural Net, and 3D Methods; (1992) https://doi.org/10.1117/12.131602
Event: Applications in Optical Science and Engineering, 1992, Boston, MA, United States
In this paper, we present a unsupervised orthogonalization neural network, which, based on Principal Component (PC) analysis, acts as an orthonormal feature detector and decorrelation network. As in the PC analysis, this network involves extracting the most heavily information- loaded features that contained in the set of input training patterns. The network self-organizes its weight vectors so that they converge to a set of orthonormal weight vectors that span the eigenspace of the correlation matrix in the input patterns. Therefore, the network is applicable to practical image transmission problems for exploiting the natural redundancy that exists in most images and for preserving the quality of the compressed-decompressed image. We have applied the proposed neural model to the problem of image compression for visual communications. Simulation results have shown that the proposed neural model provides a high compression ratio and yields excellent perceptual visual quality of the reconstructed images, and a small mean square error. Generalization performance and convergence speed are also investigated.
© (1992) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Lurng-Kuo Liu, Lurng-Kuo Liu, Panos A. Ligomenides, Panos A. Ligomenides, } "Unsupervised orthogonalization neural network for image compression", Proc. SPIE 1826, Intelligent Robots and Computer Vision XI: Biological, Neural Net, and 3D Methods, (1 November 1992); doi: 10.1117/12.131602; https://doi.org/10.1117/12.131602


Univariant assessment of the visual quality of images
Proceedings of SPIE (June 01 2000)
On-Line Visual Data Compression Along A One-Dimensional Scan
Proceedings of SPIE (October 24 1988)
Visual pattern image sequence coding
Proceedings of SPIE (August 31 1990)
Edge-adaptive JPEG image compression
Proceedings of SPIE (February 26 1996)
New hybrid zerotree/DPCM image coder
Proceedings of SPIE (September 24 1998)

Back to Top