Abstract

We describe a joint wavelet-transform correlator in which the wavelet function is combined with the input image as the input joint image to realize the wavelet transform of the objective image. The Haar wavelet and the Roberts filter are chosen as the wavelet functions to extract the features of the objective image. The relationship of the Haar wavelet and the Roberts filter is analyzed mathematically based on admissible condition of the wavelet. Computer simulations are provided to verify the theory and to illustrate the performance of this correlator.

© 1995 Optical Society of America

Improved feature extraction by use of a joint wavelet transform correlator

Boon Yi Soon, Mohammad S. Alam, and Mohammad A. Karim
Appl. Opt. 37(5) 821-827 (1998)

Joint wavelet representation correlator for pattern recognition

Sheng Zhong, Shutian Liu, Xueru Zhang, and Chunfei Li
Appl. Opt. 37(2) 374-379 (1998)

Feature-extracted joint transform correlation

Mohammad S. Alam
Appl. Opt. 34(35) 8148-8153 (1995)

Optical wavelet transform by the phase-only joint-transform correlator

Peter S. Erbach, Don A. Gregory, and Xiangyang Yang
Appl. Opt. 35(17) 3117-3126 (1996)

Detection performance of wavelet-based joint transform correlation

Joewono Widjaja
Appl. Opt. 46(34) 8278-8283 (2007)