18 September 1997 Three-dimensional multistage network applying for facial images decomposition
Author Affiliations +
Proceedings Volume 3205, Machine Vision Applications, Architectures, and Systems Integration VI; (1997) https://doi.org/10.1117/12.285563
Event: Intelligent Systems and Advanced Manufacturing, 1997, Pittsburgh, PA, United States
The paper presents a novel three-dimensional network and its application to pattern analysis. This is a multistage architecture which investigates partial correlations between structural image components. Initially the image is partitioned to be processed in parallel channels. In each channel, the structural components are transformed and subsequently separated depending on their informational activity, to be mixed with the components from other channels for further processing. An output result is represented as a pattern vector, whose components are computed one at a time to allow the quickest possible response. The paper presents an algorithm applied to facial images decomposition. The input gray-scale image is transformed so that each pixel contains information about the spatial structure of its neighborhood. A three-level representation of gray-scale image is used in order for each pixel to contain the maximum amount of structural information. The most correlated information is extracted first, making the algorithm tolerant to minor structural changes.
© (1997) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Leonid I. Timchenko, Serge V. Chepornyuk, Maxim A. Grudin, David Mark Harvey, Yuri F. Kutaev, Alexander A. Gertsiy, Lubov V. Zahoruiko, "Three-dimensional multistage network applying for facial images decomposition", Proc. SPIE 3205, Machine Vision Applications, Architectures, and Systems Integration VI, (18 September 1997); doi: 10.1117/12.285563; https://doi.org/10.1117/12.285563

Back to Top