Title :
Feature generation improving by optimized PCNN
Author :
R. Forgac;I. Mokris
Author_Institution :
Institute of Informatics, Slovak Academy of Sciences, Bratislava, Slovakia
Abstract :
The paper analyses disadvantages of standard feature generation and their standardization for image recognition by pulse coupled neural network (PCNN). The aim of research was to propose a new form of feature value calculation that improves significantly the quality of generated features. It is part of algorithm for feature generation by optimized PCNN.
Keywords :
"Neurons","Joining processes","Mathematical model","Convolution","Neural networks","Equations","Pulse generation","Informatics","Image recognition","Biological system modeling"
Conference_Titel :
Applied Machine Intelligence and Informatics, 2008. SAMI 2008. 6th International Symposium on
Print_ISBN :
978-1-4244-2105-3
DOI :
10.1109/SAMI.2008.4469166
