12 October 2010 An improved cortex-like neuromorphic system for target recognitions
Author Affiliations +
Abstract
This paper reports on the enhancement of biologically-inspired machine vision through a rotation invariance mechanism. Research over the years has suggested that rotation invariance is one of the fundamental generic elements of object constancy, a known generic visual ability of the human brain. Cortex-like vision unlike conventional pixel based machine vision is achieved by mimicking neuromorphic mechanisms of the primates' brain. In this preliminary study, rotation invariance is implemented through histograms from Gabor features of an object. The performance of rotation invariance in the neuromorphic algorithm is assessed by the classification accuracies of a test data set which consists of image objects in five different orientations. It is found that a much more consistent classification result over these five different oriented data sets has been achieved by the integrated rotation invariance neuromorphic algorithm compared to the one without. In addition, the issue of varying aspect ratios of input images to these models is also addressed, in an attempt to create a robust algorithm against a wider variability of input data. The extension of the present achievement is to improve the recognition accuracies while incorporating it to a series of different real-world scenarios which would challenge the approach accordingly.
© (2010) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Aristeidis Tsitiridis, Aristeidis Tsitiridis, Peter Yuen, Peter Yuen, Kan Hong, Kan Hong, Tong Chen, Tong Chen, Izzati Ibrahim, Izzati Ibrahim, James Jackman, James Jackman, David James, David James, Mark Richardson, Mark Richardson, } "An improved cortex-like neuromorphic system for target recognitions", Proc. SPIE 7838, Optics and Photonics for Counterterrorism and Crime Fighting VI and Optical Materials in Defence Systems Technology VII, 78380Q (12 October 2010); doi: 10.1117/12.864477; https://doi.org/10.1117/12.864477
PROCEEDINGS
12 PAGES


SHARE
Back to Top