Foundations and Practical Applications of Cognitive Systems and Information Processing by Fuchun Sun Dewen Hu & Huaping Liu

Author:Fuchun Sun, Dewen Hu & Huaping Liu
Language: eng
Format: epub
Publisher: Springer Berlin Heidelberg, Berlin, Heidelberg

3 Improved PCNN Model

The PCNN is a biological inspired neural network based on the experimental observations of synchronous pulse bursts in cat and monkey visual cortex [3, 4]. Differing from traditional neural networks, the neurons of PCNN have the same parameter values and PCNN needs not to be trained, furthermore because of its biological foundation, it has original advantage in image processing, especially for image segmentation due to its synchronous pulse burst and dynamic threshold. However, the original PCNN suffers from a large number of feedback iterations, various parameter adjustments, and computational complexity, which are difficult to implement and time consuming [5], thus an improved PCNN model is proposed in this paper. The neuromime of the improved PCNN is shown in Fig. 3.

Fig. 3The neuromime of the improved PCNN

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.