1 October 2007 Improved performance of scale-invariant pattern recognition using a combined Mellin radial harmonic function and wavelet transform
Author Affiliations +
Abstract
By using a combination of the Mellin radial harmonic function and the Mexican-hat wavelet transform, scale- and shift-invariant pattern recognition is reported. Without preprocessing of the input object, this filter is capable of identifying over a wide allowable scale range of 0.25 to 1. The correlation peaks are sharp, and the peak intensity is fairly uniform, with a variance below 30%. Computer simulation is adopted to investigate the performance of the filter. Experimental results implemented using a photorefractive joint-transform correlator, including those obtained under white noise, are also presented.
© (2007) Society of Photo-Optical Instrumentation Engineers (SPIE)
Yih-Shyang Cheng, Yih-Shyang Cheng, Hui Chi Chen, Hui Chi Chen, } "Improved performance of scale-invariant pattern recognition using a combined Mellin radial harmonic function and wavelet transform," Optical Engineering 46(10), 107204 (1 October 2007). https://doi.org/10.1117/1.2799534 . Submission:
JOURNAL ARTICLE
8 PAGES


SHARE
RELATED CONTENT

Color pattern recognition based on projection preprocessing
Proceedings of SPIE (October 23 1997)
Optical wavelet matched filters
Proceedings of SPIE (October 29 1992)

Back to Top