DocumentCode :
3059201
Title :
Color Image Compression with Modified Forward-Only Counterpropagation Neural Network: Improvement of the Quality using Different Distance Measures
Author :
Mishra, Deepak ; Bose, Subhash Chandra N. ; Tolambiya, Arvind ; Dwivedi, Ashutosh ; Kandula, Prabhanjan ; Kumar, Ashiwani ; Kalra, Prem K.
Author_Institution :
Indian Inst. of Technol. Kanpur, Kanpur
fYear :
2006
fDate :
18-21 Dec. 2006
Firstpage :
139
Lastpage :
140
Abstract :
A modified forward-only counterpropagation neural network (MFO-CPN) for color image compression is proposed. It uses several higher-order distance measures for calculating winning node. It also incorporates nonlinear adjustment of learning rates in both the layers. Results with these distance functions are compared. Proposed modifications leads to improvement in the image quality and faster convergence of network.
Keywords :
data compression; image coding; image colour analysis; learning (artificial intelligence); neural nets; color image compression; distance measures; forward-only counterpropagation neural network; image quality; learning rate nonlinear adjustment; Backpropagation; Color; Convergence; Image coding; Image quality; Image reconstruction; Neural networks; Neurons; PSNR; Testing;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Information Technology, 2006. ICIT '06. 9th International Conference on
Conference_Location :
Bhubaneswar
Print_ISBN :
0-7695-2635-7
Type :
conf
DOI :
10.1109/ICIT.2006.37
Filename :
4273173
Link To Document :
بازگشت