Neural networks and genetic algorithms for domain independent multiclass object detection

Zhang, M and Ciesielski, V 2004, 'Neural networks and genetic algorithms for domain independent multiclass object detection', International Journal of Computational Intelligence and Applications, vol. 4, no. 1, pp. 77-108.


Document type: Journal Article
Collection: Journal Articles

Title Neural networks and genetic algorithms for domain independent multiclass object detection
Author(s) Zhang, M
Ciesielski, V
Year 2004
Journal name International Journal of Computational Intelligence and Applications
Volume number 4
Issue number 1
Start page 77
End page 108
Total pages 31
Publisher Imperial College Press
Abstract This paper describes a domain independent approach to multiple class rotation invariant 2D object detection problems. The approach avoids preprocessing, segmentation and specific feature extraction. Instead, raw image pixel values are used as inputs to the learning systems. Five object detection methods have been developed and tested, the basic method and four variations which are expected to improve the accuracy of the basic method. In the basic method cutouts of the objects of interest are used to train multilayer feed forward networks using back propagation. The trained network is then used as a template to sweep the full image and find the objects of interest. The variations are (1) Use of a centred weight initialization method in network training, (2) Use of a genetic algorithm to train the network, (3) Use of a genetic algorithm, with fitness based on detection rate and false alarm rate, to refine the weights found in basic approach, and (4) Use of the same genetic algorithm to refine the weights found by method 2. These methods have been tested on three detection problems of increasing difficulty: an easy database of circles and squares, a medium difficulty database of coins and a very difficult database of retinal pathologies. For detecting the objects in all classes of interest in the easy and the medium difficulty problems, a 100% detection rate with no false alarms was achieved. However the results on the retinal pathologies were unsatisfactory. The centred weight initialization algorithm improved the detection performance over the basic approach on all three databases. In addition, refinement of weights with a genetic algorithm significantly improved detection performance on the three databases. The goal of domain independent object recognition was achieved for the detection of relatively small regular objects in larger images with relatively uncluttered backgrounds. Detection performance on irregular objects in complex, highly cluttered backgrounds such as the retina pictures, however, has not been achieved to an acceptable.
Subject Neural, Evolutionary and Fuzzy Computation
DOI - identifier 10.1142/S146902680400115X
Copyright notice © 2004 Imperial College Press
ISSN 1469-0268
Versions
Version Filter Type
Altmetric details:
Access Statistics: 132 Abstract Views  -  Detailed Statistics
Created: Mon, 04 Jan 2010, 08:03:25 EST by Catalyst Administrator
© 2014 RMIT Research Repository • Powered by Fez SoftwareContact us