Subsampling Image Compression using Al-Alaoui Backpropagation Algorithm

Author

Ferzli, Rony ; Al-Alaoui, Mohamad

Author_Institution

Arizona State Univ., Tempe

fYear

2007

fDate

11-14 Dec. 2007

Firstpage

1260

Lastpage

1263

Abstract

With the advances in wireless communications and embedded systems, efficient storage and transmission of images and video over limited bandwidth is required. Novel image compression techniques need to be investigated; an artificial neural networks subsampling image compression method is presented using the Al - Alaoui backpropagation algorithm is used [1-5]. The Al-Alaoui algorithm is a weighted mean-square-error (MSE) approach to pattern recognition. It employs cloning of the erroneously classified samples to increase the population of their corresponding classes. Using the Al-Alaoui backpropagation, obtained simulation results show a faster convergence rate, zero misclassified pixels and an improvement in PSNR around 2 dB.

Keywords

backpropagation; data compression; image coding; image sampling; mean square error methods; neural nets; Al-Alaoui backpropagation; artificial neural networks; pattern recognition; subsampling image compression; weighted mean-square-error approach; Artificial neural networks; Backpropagation algorithms; Bandwidth; Cloning; Embedded system; Image coding; Image storage; Pattern recognition; Video compression; Wireless communication;

fLanguage

English

Publisher

ieee

Conference_Titel

Electronics, Circuits and Systems, 2007. ICECS 2007. 14th IEEE International Conference on

Conference_Location

Marrakech

Print_ISBN

978-1-4244-1377-5

Electronic_ISBN

978-1-4244-1378-2

Type

conf

DOI

10.1109/ICECS.2007.4511226

Filename

4511226