DocumentCode :
2887256
Title :
A spectral multi-resolution image encoding network
Author :
Brause, Rüdiger W. ; Glitsch, Jügen
Author_Institution :
Dept. of Comput. Sci., J.W. Goethe Univ., Frankfurt, Germany
fYear :
1995
fDate :
5-8 Nov 1995
Firstpage :
138
Lastpage :
141
Abstract :
After a short introduction into traditional image transform coding, multirate systems and multiscale signal coding the paper focuses on the subject of image encoding by a neural network. Taking also noise into account a network model is proposed which not only learns the optimal localized basis functions for the transform but also learns to implement a whitening filter by multi-resolution encoding. A simulation showing the multi-resolution capabilities concludes the contribution
Keywords :
image coding; neural nets; transform coding; multi-resolution encoding; multirate systems; multiscale signal coding; network model; neural network; optimal localized basis functions; spectral multi-resolution image encoding network; whitening filter; Encoding; Filter bank; Frequency; Image coding; Low pass filters; Neural networks; Principal component analysis; Quantization; Sampling methods; Transform coding;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Tools with Artificial Intelligence, 1995. Proceedings., Seventh International Conference on
Conference_Location :
Herndon, VA
ISSN :
1082-3409
Print_ISBN :
0-8186-7312-5
Type :
conf
DOI :
10.1109/TAI.1995.479416
Filename :
479416
Link To Document :
بازگشت