1 August 2004 Object recognition within cluttered scenes employing a hybrid optical neural network filter
Author Affiliations +
Abstract
We propose a hybrid filter, which we call the hybrid optical neural network (HONN) filter. This filter combines the optical implementation and shift invariance of correlator-type filters with the nonlinear superposition capabilities of artificial neural network methods. The filter demonstrates good performance in maintaining high-quality correlation responses and resistance to clutter to nontraining in-class images at orientations intermediate to the training set poses. We present the design and implementation of the HONN filter architecture and assess its object recognition performance in clutter.
© (2004) Society of Photo-Optical Instrumentation Engineers (SPIE)
Ioannis I. Kypraios, Ioannis I. Kypraios, Rupert C. D. Young, Rupert C. D. Young, Philip M. Birch, Philip M. Birch, Christopher R. Chatwin, Christopher R. Chatwin, } "Object recognition within cluttered scenes employing a hybrid optical neural network filter," Optical Engineering 43(8), (1 August 2004). https://doi.org/10.1117/1.1767194 . Submission:
JOURNAL ARTICLE
12 PAGES


SHARE
Back to Top