Modified PCNN Model and Its Application to Mixed-Noise Removal

Author

Kai He ; Shao-Fa Li ; Cheng Wang

Author_Institution

Dept. of Comput. Sci. & Eng., South China Univ. of Technol., Guangzhou, China

fYear

2010

fDate

30-31 Jan. 2010

Firstpage

213

Lastpage

216

Abstract

Pulse coupled neural networks (PCNN) model is a bionic system. It emulates the behavior of visual cortical neurons of cats and has been extensively applied in image processing. We proposed an adaptive mixed-noise removal algorithm, in this paper, based on making further improvements to L&A-PCNN, and combined with theoretical analysis and experimental analysis to obtain the self-adaptive definition of the key parameters of the improved model. The simulation results show that the improved algorithm is not only better than L&A-PCNN method in the theoretical results, but also realized the automation of mixed-noise removal.

Keywords

biocybernetics; feature extraction; image denoising; neural nets; L&A-PCNN method; adaptive mixed noise removal algorithm; bionic system; image processing; pulse coupled neural network model; visual cortical neurons; Algorithm design and analysis; Cats; Computer science; Electromagnetic interference; Filters; Gaussian noise; Image processing; Marine technology; Neural networks; Neurons; L&A-PCNN; linear attenuated threshold; mixed-noise; pulse couple neural networks;

fLanguage

English

Publisher

ieee

Conference_Titel

Innovative Computing & Communication, 2010 Intl Conf on and Information Technology & Ocean Engineering, 2010 Asia-Pacific Conf on (CICC-ITOE)

Conference_Location

Macao

Print_ISBN

978-1-4244-5634-5

Electronic_ISBN

978-1-4244-5635-2

Type

conf

DOI

10.1109/CICC-ITOE.2010.61

Filename

5439256