15 March 1994 Composite wavelet features for image recognition
Author Affiliations +
Abstract
A detection technique based on a synergistic composition of wavelet feature detectors is demonstrated on sonar imaging data. The wavelets are used to preprocess the imagery for enhancing highlights and shadows. A neural network is trained on the preprocessed imagery to weight the output of two filters for underwater object detection. This approach is demonstrated on multiple scales. Results indicate this composite approach is highly effective.
© (1994) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Joseph P. Garcia, Joseph P. Garcia, Brian A. Telfer, Brian A. Telfer, Hanseok Ko, Hanseok Ko, Harold H. Szu, Harold H. Szu, } "Composite wavelet features for image recognition", Proc. SPIE 2242, Wavelet Applications, (15 March 1994); doi: 10.1117/12.170094; https://doi.org/10.1117/12.170094
PROCEEDINGS
14 PAGES


SHARE
RELATED CONTENT

Neural network-based watermark embedding and identification
Proceedings of SPIE (September 02 2008)
Object isolation using a pulse-coupled neural network
Proceedings of SPIE (November 10 1996)
WaveNet compressed-image restoration brassboard design
Proceedings of SPIE (April 02 1997)
Template basis techniques for pattern recognition
Proceedings of SPIE (October 22 1996)
Aided target recognition processing of MUDSS sonar data
Proceedings of SPIE (September 03 1998)

Back to Top