Title :
Subsampling Image Compression using Al-Alaoui Backpropagation Algorithm
Author :
Ferzli, Rony ; Al-Alaoui, Mohamad
Author_Institution :
Arizona State Univ., Tempe
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;
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
DOI :
10.1109/ICECS.2007.4511226
