Title :
Application of Pulse Coupled Neural Network in Image Recognition
Author :
He, Shuiming ; Wang, Dianhong ; Nin, Yanbin
Author_Institution :
China Univ. of Geosci., Wuhan, China
Abstract :
Compared with other neural network, PCNN has congenital advantage. Johnson have proved that each input image has its own unique time signature series by lot´s of experiments, and additionally, most of the input images are also have their own unique image Entropy sequence, so according to these characteristics of the image, and combining the characteristics of PCNN itself in the field of image processing, as is shown in the experiments, PCNN could successfully recognize the image which was polluted by different noise.
Keywords :
entropy; image recognition; image sequences; neural nets; time series; image entropy sequence; image processing; image recognition; pulse coupled neural network; time signature series; Biological system modeling; Cells (biology); Entropy; Image processing; Image recognition; Joining processes; Neural networks; Neurons; Output feedback; Pulse modulation; Characteristic time series -component; Image recognition; Pulse coupled neural network;
Conference_Titel :
Computing, Control and Industrial Engineering (CCIE), 2010 International Conference on
Conference_Location :
Wuhan
Print_ISBN :
978-0-7695-4026-9
DOI :
10.1109/CCIE.2010.223