Title :
Image wavelet analysis with the Multimedia Video Processor
Author :
Brooks, Geoffrey
Author_Institution :
Coll. of Eng., Florida State Univ., Tallahassee, FL, USA
Abstract :
Images can be decomposed into wavelet components using quadrature mirror filtering (QMF) for significant signal entropy reduction and practically lossless subsequent reconstruction. The Multimedia Video Processor (MVP), a five-processor MIMD chip developed by Texas Instruments (TI), is considered for high speed image QMF. The image convolution operation is an integral part of QMF, as well as the basic computational workhorse for numerous other image processing functions. Computational and memory management techniques specific to image convolutions on this architecture are presented. The performance with these considerations is measured using the TI MVP software simulator
Keywords :
convolution; digital signal processing chips; entropy; filtering theory; image reconstruction; multimedia communication; quadrature mirror filters; storage management chips; video signal processing; wavelet transforms; Multimedia Video Processor; TI MVP software simulator; Texas Instruments; computational techniques; five-processor MIMD chip; high speed image QMF; image convolution; image processing functions; image wavelet analysis; lossless image reconstruction; memory management techniques; performance measurement; quadrature mirror filtering; signal entropy reduction; wavelet components; Convolution; Entropy; Filtering; Image analysis; Image processing; Image reconstruction; Instruments; Memory management; Mirrors; Wavelet analysis;
Conference_Titel :
Southeastcon '96. Bringing Together Education, Science and Technology., Proceedings of the IEEE
Conference_Location :
Tampa, FL
Print_ISBN :
0-7803-3088-9
DOI :
10.1109/SECON.1996.510039
