Logarithmic r-θ map for hybrid optical neural network filter for object recognition within cluttered scenes

Kypraios, Ioannis, Young, Rupert C D and Chatwin, Chris R (2009) Logarithmic r-θ map for hybrid optical neural network filter for object recognition within cluttered scenes. Studies in Computational Intelligence, 231. pp. 91-120. ISSN 1860-949X

Full text not available from this repository.

Abstract

Space-variant imaging sensors can be designed to exhibit in-plane rotation and scale invariance to image data. We combine the complex logarithmic r-θ mapping of a space-variant imaging sensor with the hybrid optical neural network filter to achieve, with a single pass over the input data, simultaneous invariance to: out-of-plane rotation; in-plane rotation; scale; projection and shift invariance. The resulting filter we call a complex logarithmic r-θ mapping for the hybrid optical neural network filter. We include in the L-HONN filter's design a window based unit for registering the translation invariance of the input objects, initially lost by applying the logarithmic mapping. We test and record the results of the L-HONN filter for single and multiple input objects of the same class within cluttered still images and video frame sequences

Item Type: Article
Schools and Departments: School of Engineering and Informatics > Engineering and Design
Subjects: T Technology > TA Engineering (General). Civil engineering (General) > TA0329 Engineering mathematics. Engineering analysis
Depositing User: Rupert Young
Date Deposited: 28 Nov 2012 10:52
Last Modified: 28 Nov 2012 10:52
URI: http://sro.sussex.ac.uk/id/eprint/40784
📧 Request an update