Multispectral image analysis using pulsed coupled neural networks

Pulsed oscillatory neural networks are examined for application to analysis and segmentation of multispectral imagery from the Satelite Pour l’Observation de la Terre (SPOT). These networks demonstrate a capacity to segment images with better performance against many of the resolution uncertainty effects caused by local area adaptive filtering. To enhance synchronous behavior, a reset mechanism is added in the model. Previous work suggests that a reset activation pulse is generated by sacatic motor commands. Consequently, an algorithm is developed, which behaves similar to adaptive histogram techniques. These techniques appear both biologically plausible and more effective than conventional techniques. Using the pulse time-of-arrival as the information carrier, the image is reduced to a time signal which allows an intelligent filtering using feedback.