Title :
Reentrant pulse coupled neural networks (PCNNs)
Author :
Allen, Frank ; Caulfield, H. John
Author_Institution :
Dept. of Phys., Alabama A&M Univ., Normal, AL, USA
fDate :
27 Jun-2 Jul 1994
Abstract :
The PCNN developed by Johnson (1993) are syntactic pattern transformers. Hence their outputs are quite similar over a wide variety of “distortions”. We show that we can convert a PCNN into an attractor system which, away from boundaries, produces point attractor icons which are ideal inputs to statistical pattern processors
Keywords :
image processing; neural nets; statistical analysis; attractor system; point attractor icons; pulse coupled neural networks; statistical pattern processors; syntactic pattern transformers; Convergence; Data mining; Humans; Image converters; Image segmentation; Neural networks; Pattern recognition; Physics; Prototypes; Pulse transformers;
Conference_Titel :
Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-1901-X
DOI :
10.1109/ICNN.1994.374370
