Sub-Image Detection Using Fast Neural Processors and Image Decomposition
Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 32794
Sub-Image Detection Using Fast Neural Processors and Image Decomposition

Authors: Hazem M. El-Bakry, Qiangfu Zhao


In this paper, an approach to reduce the computation steps required by fast neural networksfor the searching process is presented. The principle ofdivide and conquer strategy is applied through imagedecomposition. Each image is divided into small in sizesub-images and then each one is tested separately usinga fast neural network. The operation of fast neuralnetworks based on applying cross correlation in thefrequency domain between the input image and theweights of the hidden neurons. Compared toconventional and fast neural networks, experimentalresults show that a speed up ratio is achieved whenapplying this technique to locate human facesautomatically in cluttered scenes. Furthermore, fasterface detection is obtained by using parallel processingtechniques to test the resulting sub-images at the sametime using the same number of fast neural networks. Incontrast to using only fast neural networks, the speed upratio is increased with the size of the input image whenusing fast neural networks and image decomposition.

Keywords: Fast Neural Networks, 2D-FFT, CrossCorrelation, Image decomposition, Parallel Processing.

Digital Object Identifier (DOI):

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2121


[1] Hazem M. El-Bakry, and Qiangfu Zhao, ?Comments on FastObject/Face Detection Using Neural Networks and Fast FourierTransform,? accepted for publication in the International Journalof Signal Processing.
[2] H. M. El-Bakry, ?Human Iris Detection Using Fast CooperativeModular Neural Networks and Image Decomposition,? MachineGraphics & Vision Journal (MG&V), vol. 11, no. 4, 2002, pp.498-512.
[3] H. M. El-Bakry, ?Automatic Human Face Recognition UsingModular Neural Networks,? The International Journal on MachineGraphics, Vol. 10, No. 1, 2001, pp. 47-73.
[4] H. M. El-Bakry, ?Comments on Using MLP and FFT for FastObject/Face Detection,? Proc. of IEEE IJCNN?03, Portland,Oregon, pp. 1284-1288, July, 20-24, 2003.
[5] R. Klette, and Zamperon, ?Handbook of image processingoperators,? John Wiley & Sons, Ltd, 1996.
[6] H. A. Rowley, S. Baluja, and T. Kanade, ?Neural Network - BasedFace Detection,? IEEE Trans. on Pattern Analysis and MachineIntelligence, Vol. 20, No. 1, pp. 23-38, 1998.
[7] H. Schneiderman and T. Kanade, ?Probabilistic modeling of localappearance and spatial relationships for object recognition,?Proceedings of IEEE Conference on Computer Vision and PatternRecognition (CVPR), pp. 45-51, SantaBarbara, CA, 1998.
[8] H. M. El-Bakry, ?Face detection using fast neural networks andimage decomposition,? Neurocomputing Journal, vol. 48, 2002,pp. 1039-1046.
[9] R. Feraud, O. Bernier, J. E. Viallet, and M. Collobert, ?A Fast andAccurate Face Detector for Indexation of Face Images,?Proceedings of Fourth IEEE International Conference onAutomatic Face and Gesture Recognition, Grenoble, France, 28-30 March, 2000.