Abstract
This study demonstrates the application of one-dimensional discrete wavelet transforms in the classification of T-ray pulsed signals. Fast Fourier transforms (FFTs) are used as a feature extraction tool and a Mahalanobis distance classifier is employed for classification. Soft threshold wavelet shrinkage de-noising is used and plays an important role in de-noising and reconstruction of T-ray pulsed signals. An iterative algorithm is applied to obtain three optimal frequency components and to achieve preferred classification performance.
References
Donoho DL (1995) De-noising by soft thresholding. IEEE Trans Inf Theory 41(3):613–627
Ferguson B, Abbott D (2001) Wavelet de-noising of optical terahertz pulse imaging data. Fluct Noise Lett 1(2):L65–L70
Ferguson B, Wang S, Zhong H, Abbott D, Zhang XC (2003) Powder retection with T-ray imaging. Proc SPIE Terahertz Mil Secur Appl 5070:7–16
Fukunaga K, Hummels DM (1989) Leave-one-out procedures for nonparametric error estimates. IEEE Trans Pattern Anal Mach Intell II(4):421–423
Löffler T, Siebert K, Czasch S, Bauer H Tand Roskos (2002) Visualization and classification in biomedical terahertz pulsed imaging. Phys Med Biol 47(2002):3847–3852
Mallat SG (1999) A wavelet tour of signal processing. Academic, San Diego
Mittleman D, Gupta M, Neelamani R, Baraniuk G, Rudd V, Koch M (1999) Recent advances in terahertz imaging. Appl Phys B Lasers Opt 68:1085–1094
Qian S (2002) Time-frequency and wavelet transforms, 1st edn. Prentice Hall, Inc., New Jersey
Schürmann J (1996) Pattern classification: a unified view of statistical and neural approaches. Wiley, New York
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Yin, X.X., Kong, K.M., Lim, J.W. et al. Enhanced T-ray signal classification using wavelet preprocessing. Med Bio Eng Comput 45, 611–616 (2007). https://doi.org/10.1007/s11517-007-0185-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11517-007-0185-y