Title :
Probability of error metrics for best-basis selection
Author :
McWhorter, Todd ; Clark, Michael
Author_Institution :
Mission Res. Corp., Monterey, CA, USA
fDate :
Oct. 29 2000-Nov. 1 2000
Abstract :
In this paper we derive a metric for selecting the best-basis of a wavelet packet used to compress a classifier database. The metric will choose a basis that minimizes the probability of error given that the database must be represented with a finite number of bits. We also solve the corresponding bit allocation problem.
Keywords :
data compression; error statistics; transform coding; wavelet transforms; best-basis selection; bit allocation problem; classifier database; data compression; error probability minimization; probability of error metrics; wavelet packet; Bit rate; Computer architecture; Databases; Degradation; Entropy; Information theory; Random variables; Rate-distortion; Wavelet packets; Wavelet transforms;
Conference_Titel :
Signals, Systems and Computers, 2000. Conference Record of the Thirty-Fourth Asilomar Conference on
Conference_Location :
Pacific Grove, CA, USA
Print_ISBN :
0-7803-6514-3
DOI :
10.1109/ACSSC.2000.910687
