Logarithmic r-[theta] mapping for hybrid optical neural network filter for multiple objects recognition within cluttered scenes

Kypraios, Ioannis, Young, Rupert C D, Chatwin, Chris R and Birch, Phil M (2009) Logarithmic r-[theta] mapping for hybrid optical neural network filter for multiple objects recognition within cluttered scenes. In: Optical Pattern Recognition XX; 16 April 2009 through 17 April 2009, Orlando, FL, USA.

Full text not available from this repository.

Abstract

The window unit in the design of the complex logarithmic r-¿ mapping for hybrid optical neural network filter can allow multiple objects of the same class to be detected within the input image. Additionally, the architecture of the neural network unit of the complex logarithmic r-¿ mapping for hybrid optical neural network filter becomes attractive for accommodating the recognition of multiple objects of different classes within the input image by modifying the output layer of the unit. We test the overall filter for multiple objects of the same and of different classes' recognition within cluttered input images and video sequences of cluttered scenes. Logarithmic r-¿ mapping for hybrid optical neural network filter is shown to exhibit with a single pass over the input data simultaneously in-plane rotation, out-of-plane rotation, scale, log r-¿ map translation and shift invariance, and good clutter tolerance by recognizing correctly the different objects within the cluttered scenes. We record in our results additional extracted information from the cluttered scenes about the objects' relative position, scale and in-plane rotation. © 2009 SPIE.

Item Type: Conference or Workshop Item (Paper)
Additional Information: Proceedings of SPIE - The International Society for Optical Engineering
Schools and Departments: School of Engineering and Informatics > Engineering and Design
Depositing User: Rupert Young
Date Deposited: 06 Feb 2012 21:13
Last Modified: 11 Apr 2012 08:20
URI: http://sro.sussex.ac.uk/id/eprint/30338
📧 Request an update