14 October 1997 Neural method of spatiotemporal filter design
Author Affiliations +
Abstract
There is a lot of applications in medical imaging, computer vision, and the communications, where the video processing is critical. Although many techniques have been successfully developed for the filtering of the still-images, significantly fewer techniques have been proposed for the filtering of noisy image sequences. In this paper the novel approach to spatio- temporal filtering design is proposed. The multilayer perceptrons and functional-link nets are used for the 3D filtering. The spatio-temporal patterns are creating from real motion video images. The neural networks learn these patterns. The perceptrons with different number of layers and neurons in each layer are tested. Also, the different input functions in functional- link net are searched. The practical examples of the filtering are shown and compared with traditional (non-neural) spatio-temporal methods. The results are very interesting and the neural spatio-temporal filters seems to be very efficient tool for video noise reduction.
© (1997) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Jaroslaw Szostakowski, Jaroslaw Szostakowski, } "Neural method of spatiotemporal filter design", Proc. SPIE 3167, Statistical and Stochastic Methods in Image Processing II, (14 October 1997); doi: 10.1117/12.279648; https://doi.org/10.1117/12.279648
PROCEEDINGS
11 PAGES


SHARE
RELATED CONTENT

Learning deep similarity in fundus photography
Proceedings of SPIE (February 23 2017)
Motion Sensitive Cellular Automata
Proceedings of SPIE (April 19 1988)
Real Time Pyramid Transform Architecture
Proceedings of SPIE (December 10 1985)
Toward a pyramidal neural network system for stereo fusion
Proceedings of SPIE (February 29 1992)

Back to Top