DocumentCode :
468295
Title :
A Novel Algorithm of Image Enhancement Based on Pulse Coupled Neural Network Time Matrix and Rough Set
Author :
Ma, Yide ; Lin, Dongmei ; Zhang, Beidou ; Xia, Chunshui
Author_Institution :
Lanzhou Univ., Lanzhou
Volume :
3
fYear :
2007
fDate :
24-27 Aug. 2007
Firstpage :
86
Lastpage :
90
Abstract :
This paper describes a novel algorithm of image enhancement based on pulse coupled neural network (PCNN) time matrix and rough set indiscernibility relation. Firstly, detect image noise using PCNN time matrix, and then partition the original image into three sub-images according to intensity attribute and noise attribute. Secondly, denoise using filtering methods based upon PCNN. Lastly, complete sub-images and enhance each of them by different methods. For the gray images with many object details in dark regions and badly corrupted by impulse noise, the computer simulations show excellent enhancement effect. Namely, noise can be reduced efficiently, object details can be enhanced better and the image would become clear after it is processed by this algorithm. Moreover, the effect of this algorithm is better than that of traditional image enhancement algorithm.
Keywords :
filtering theory; image enhancement; neural nets; rough set theory; filtering methods; image enhancement; pulse coupled neural network time matrix; rough set; Artificial neural networks; Brain modeling; Filtering; Image enhancement; Image processing; Neural networks; Neurons; Noise reduction; Partitioning algorithms; Set theory;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Fuzzy Systems and Knowledge Discovery, 2007. FSKD 2007. Fourth International Conference on
Conference_Location :
Haikou
Print_ISBN :
978-0-7695-2874-8
Type :
conf
DOI :
10.1109/FSKD.2007.93
Filename :
4406207
Link To Document :
بازگشت