Neural Networks And Genetic Algorithms For Domain Independent Multiclass Object Detection

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 level.

[1]  M. W. Roth.  Survey of neural network technology for automatic target recognition , 1990, IEEE Trans. Neural Networks.

[2]  Peter G. Korning,et al.  Training neural networks by means of genetic algorithms working on very long chromosomes , 1995, Int. J. Neural Syst..

[3]  Xin Yao,et al.  Evolving artificial neural networks , 1999, Proc. IEEE.

[4]  Alan N. Gove,et al.  Neural processing of targets in visible, multispectral IR and SAR imagery , 1995, Neural Networks.

[5]  Mohan M. Trivedi,et al.  A neural network filter to detect small targets in high clutter backgrounds , 1995, IEEE Trans. Neural Networks.

[6]  PAUL D. GADER,et al.  Segmentation free shared weight networks for automatic vehicle detection , 1995, Neural Networks.

[7]  X. Yao.  Evolving Artificial Neural Networks , 1999 .

[8]  Roberto Brunelli,et al.  Face Recognition: Features Versus Templates , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[10]  Shahab Sokhansanj,et al.  Discrimination of Hard-to-pop Popcorn Kernels by Machine Vision and Neural Networks , 2005 .

[11]  Ayanna M. Howard,et al.  A multi-stage neural network for automatic target detection , 1998, 1998 IEEE International Joint Conference on Neural Networks Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36227).

[12]  David P. Casasent,et al.  Classifier and shift-invariant automatic target recognition neural networks , 1995, Neural Networks.

[13]  Mengjie Zhang,et al.  A Domain Independent Approach to 2D Object Detection Based on the Neural and Genetic Paradigms , 2000 .

[14]  Jin Wang,et al.  Weight smoothing to improve network generalization , 1994, IEEE Trans. Neural Networks.

[15]  Lilly Spirkovska,et al.  Higher-order neural networks applied to 2D and 3D object recognition , 1994, Machine Learning.

[16]  Herbert L. Roitblat,et al.  Sonar recognition of targets embedded in sediment , 1995, Neural Networks.

[17]  Stephen Grossberg,et al.  A massively parallel architecture for a self-organizing neural pattern recognition machine , 1988, Comput. Vis. Graph. Image Process..

[18]  Simon Haykin,et al.  Intelligent Signal Processing , 2001 .

[19]  Xin Yao,et al.  A review of evolutionary artificial neural networks , 1993, Int. J. Intell. Syst..

[20]  Teuvo Kohonen,et al.  Self-Organization and Associative Memory, Second Edition , 1988, Springer Series in Information Sciences.

[21]  Victor Ciesielski,et al.  An evolutionary approach to training feedforward and recurrent neural networks , 1998, 1998 Second International Conference. Knowledge-Based Intelligent Electronic Systems. Proceedings KES'98 (Cat. No.98EX111).

[22]  Teuvo Kohonen,et al.  Self-Organization and Associative Memory , 1988 .

[23]  L. Darrell Whitley,et al.  Optimizing Neural Networks Using FasterMore Accurate Genetic Search , 1989, ICGA.

[24]  Colin Giles,et al.  Learning, invariance, and generalization in high-order neural networks. , 1987, Applied optics.

[25]  Lawrence D. Jackel,et al.  Backpropagation Applied to Handwritten Zip Code Recognition , 1989, Neural Computation.

[26]  Dana H. Ballard,et al.  Computer Vision , 1982 .

[27]  Brijesh Verma.  A neural network based technique to locate and classify microcalcifications in digital mammograms , 1998, 1998 IEEE International Joint Conference on Neural Networks Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36227).

[28]  Mitchell A. Potter,et al.  A genetic cascade-correlation learning algorithm , 1992, [Proceedings] COGANN-92: International Workshop on Combinations of Genetic Algorithms and Neural Networks.

[29]  Roberto Brunelli,et al.  Face Recognition through Geometrical Features , 1992, ECCV.

[30]  Alice J. O'Toole,et al.  CATEGORIZATION AND IDENTIFICATION OF HUMAN FACE IMAGES BY NEURAL NETWORKS: A REVIEW OF THE LINEAR AUTOASSOCIATIVE AND PRINCIPAL COMPONENT APPROACHES , 1994 .

[31]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[32]  Malur K. Sundareshan,et al.  Data fusion and tracking of complex target maneuvers with a simplex-trained neural network-based architecture , 1998, 1998 IEEE International Joint Conference on Neural Networks Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36227).

[33]  Sun-Yuan Kung,et al.  Face recognition/detection by probabilistic decision-based neural network , 1997, IEEE Trans. Neural Networks.

[34]  Xin Yao,et al.  A new evolutionary system for evolving artificial neural networks , 1997, IEEE Trans. Neural Networks.

[35]  Lilly Spirkovska,et al.  Higher-Order Neural Networks Applied to 2D and 3D Object Recognition , 1994, Machine Learning.

[36]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .