World Scientific
  • Search
Skip main navigation

Cookies Notification

We use cookies on this site to enhance your user experience. By continuing to browse the site, you consent to the use of our cookies. Learn More
Our website is made possible by displaying certain online content using javascript.
In order to view the full content, please disable your ad blocker or whitelist our website

System Upgrade on Tue, Oct 25th, 2022 at 2am (EDT)

Existing users will be able to log into the site and access content. However, E-commerce and registration of new users may not be available for up to 12 hours.
For online purchase, please visit us again. Contact us at [email protected] for any enquiries.


    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.


    • P. D. Gaderet al., Neural Netw. 8(9), 1457 (1995). CrossrefGoogle Scholar
    • A. M. Waxmanet al., Neural Netw. 8(7/8), 1029 (1995). CrossrefGoogle Scholar
    • H. L. Roitblatet al., Neural Netw. 8(7/8), 1263 (1995). CrossrefGoogle Scholar
    • M. W. Roth, IEEE Trans. Neural Netw. 1(1), 28 (1990). CrossrefGoogle Scholar
    • D. H.   Ballard and C. M.   Brown , Computer Vision ( Prentice-Hall, Inc. , Englewood Cliffs, NJ , 1982 ) . Google Scholar
    • R. Brunelli and T. Poggio, Face recognition through geometrical features, ed. S. M. Ligure, in Proc. ECCV '92, 1992, pp. 792–800 . Google Scholar
    • R. Brunelli and T. Poggio, IEEE Trans. PAMI 15(10), 1042 (1993). CrossrefGoogle Scholar
    • M. V. Shirvaikar and M. M. Trivedi, IEEE Trans. Neural Netw. 6(1), 252 (1995). CrossrefGoogle Scholar
    • L. Spirkovska and M. B. Reid, Mach. Learning 15(2), 169 (1994). Google Scholar
    • D. P. Casasent and L. M. Neiberg, Neural Netw. 8(7/8), 1117 (1995). CrossrefGoogle Scholar
    • P. Winter, S. Sokhansanj, H. C. Wood and W. Crerar, Quality assessment and grading of lentils using machine vision, Agricultural Inst. Cana. Ann. Conf., Saskatoon, SK S7N 5A9, Canada, July 1996, Canadian Society of Agricultural Engineering, CASE Paper No. 96-310 . Google Scholar
    • V. Ciesielski and J. Zhu, A very reliable method for detecting bacterial growths using neural networks, in Proc. Int. Joint Conf. Neural Netw., Beijing, November 1992, pp. 62–67 . Google Scholar
    • J. S. N. Jean and J. Wang, IEEE Trans. Neural Netwo. 5(5), 752 (1994). CrossrefGoogle Scholar
    • S.-H. Lin, S.-Y. Kung and L.-J. Lin, IEEE Trans. Neural Netw. 8(1), 114 (1997). Google Scholar
    • A. Howard, C. Padgett and C. C. Liebe, A multi-stage neural network for automatic target detection, 1998 IEEE World Cong. Comput. Intell. — IJCNN'98, Anchorage, Alaska, 1998. pp. 231–236, 0-7803-4859-1/98 . Google Scholar
    • Y. C. Wong and M. K. Sundareshan, Data fusion and tracking of complex target maneuvers with a simplex-trained neural network-based architecture, 1998 IEEE World Comput. Intell. — IJCNN'98, Anchorage, Alaska, May 1998. pp. 1024–1029, 0-7803-4859-1/98 . Google Scholar
    • D. Valentin, H. Abdi and  O'Toole, J. Biol. Syst. 2(3), 413 (1994). LinkGoogle Scholar
    • P. Winter, W. Yang, S. Sokhansanj and H. Wood, Discrimination of hard-to-pop popcorn kernels by machine vision and neural network, ASAE/CSAE Meeting, Saskatoon, Canada, September 1996, Paper No. MANSASK 96-107 . Google Scholar
    • Y. LeCunet al., Intelligent Signal Processing (IEEE Press, 2001) pp. 306–351. Google Scholar
    • B. Verma, A neural network based technique to locate and classify microcalcifications in digital mammograms, 1998 IEEE World Cong. Comput. Intell. — IJCNN'98, Anchorage, Alaska, IEEE, 1998. pp. 1790–1793, 0-7803-4859-1/98 . Google Scholar
    • D. E.   Rumelhart , G. E.   Hinton and R. J.   Williams , Parallel Distributed Processing, Explorations in the Microstructure of Cognition: Foundations   1 , eds. D. E.   Rumelhart and J. L.   MeClelland ( The MIT Press , Cambridge, MA London , 1986 ) . CrossrefGoogle Scholar
    • T.   Kohonen , Self-Organization and Associative Memory , 3rd edn. ( Springer , Berlin Heidelberg New York , 1988 ) . CrossrefGoogle Scholar
    • G. L. Giles and T. Maxwell, Appl. Opt. 26(23), 4972 (1987). CrossrefGoogle Scholar
    • G. A. Carpenter and S. Grossberg, Comput. Vision Graphics Image Process. 37, 54 (1987). CrossrefGoogle Scholar
    • G. A. Carpenter and S. Grossberg, Appl. Opt. 26, 4919 (1987). CrossrefGoogle Scholar
    • P. G. Korning, Int. J. Neural Syst. 6(3), 299 (1995). LinkGoogle Scholar
    • D. J. Montana and L. Davis, Proce. 11th Int. Conf. Artif. Intell. (Morgan Kaufmann, San Mateo, CA, 1989) pp. 762–767. Google Scholar
    • D. Whitley and T. Hanson, Procce. 3rd Int. Conf. Genetic Algorithms and their Appl. (Morgan Kaufman, 1989) pp. 391–396. Google Scholar
    • V. Ciesielski and J. Riley, An evolutionary approach to training feed forward and recurrent neural networks, in Proc. 2nd Int. Conf. Knowledge Based Intell. Electronic Syst., eds. L. C. Jain and R. K. Jain, April 1998, Adelaide, pp. 596–602. . Google Scholar
    • R. Krishnan and V. Ciesielski, Proc. 5th Austral. Neural Netw. Conf., ed. A. C. Tsoi (University of Queensland, Brisbane, 1994) pp. 38–41, Google Scholar
    • M. A. Potter, Proc. Int. Workshop on Combinations of Genetic Algorithms and Neural Netw., eds.  Schaffer and  Whitley (Morgan Kaufmann, 1992) pp. 366–372. Google Scholar
    • X. Yao and Y. Liu, IEEE Trans. Neural Netw. 8(3), 694 (1997). CrossrefGoogle Scholar
    • X. Yao, Int. J. Intell. Syst. 8(4), 539 (1993). CrossrefGoogle Scholar
    • X. Yao, Proc. IEEE 87(9), 1423 (1999). Google Scholar
    • M. Zhang, A domain independent approach to 2D object detection based on the neural and genetic paradigms PhD thesis, Department of Computer Science, RMIT University, Melbourne, Australia, August (2001) . Google Scholar
    • Y. LeCunet al., Neural Comput. 1, 541 (1989). CrossrefGoogle Scholar
    • N. Rai, Pixel statistics in neural networks for domain independent object detection, Minor thesis, RMIT, Department of Computer Science (2000) . Google Scholar
    Remember to check out the Most Cited Articles!

    Check out these titles in artificial intelligence!