Title :
Threshold potential optimization in the Pulse Coupled Neural Network
Author :
R. Forgac;I. Mokris
Author_Institution :
Inst. of Inf., Slovak Acad. of Sci., Bratislava
Abstract :
The paper introduces an approach for threshold potential optimization in the Pulse Coupled Neural Network (PCNN) to solve the quality of generated features for image recognition tasks. Threshold potential plays very important role because it provides and controls pulse effect of PCNN. The suitable control of pulse effect can improve dimension reduction of image classification space by PCNN that is necessary for successful image recognition with high input image dimension.
Keywords :
"Neural networks","Neurons","Pixel","Brain modeling","Joining processes","Pulse generation","Image recognition","Image processing","Character generation","Pattern recognition"
Conference_Titel :
Intelligent Systems and Informatics, 2008. SISY 2008. 6th International Symposium on
Print_ISBN :
978-1-4244-2406-1
Electronic_ISBN :
1949-0488
DOI :
10.1109/SISY.2008.4664914
