A Modified Cross Correlation in the Frequency Domain for Fast Pattern Detection Using Neural Networks

Recently, neural networks have shown good results for detection of a certain pattern in a given image. In our previous papers [1-5], a fast algorithm for pattern detection using neural networks was presented. Such algorithm was designed based on cross correlation in the frequency domain between the input image and the weights of neural networks. Image conversion into symmetric shape was established so that fast neural networks can give the same results as conventional neural networks. Another configuration of symmetry was suggested in [3,4] to improve the speed up ratio. In this paper, our previous algorithm for fast neural networks is developed. The frequency domain cross correlation is modified in order to compensate for the symmetric condition which is required by the input image. Two new ideas are introduced to modify the cross correlation algorithm. Both methods accelerate the speed of the fast neural networks as there is no need for converting the input image into symmetric one as previous. Theoretical and practical results show that both approaches provide faster speed up ratio than the previous algorithm.

Authors:

• Hazem M. El-Bakry
• Qiangfu Zhao

Keywords:

• Fast Pattern Detection
• Neural Networks
• Modified Cross Correlation

References:

[1] Hazem M. El-Bakry, and Qiangfu Zhao, "Fast Sub-Matrix
Detection Using Neural Networks and Cross Correlation in the
Frequency Domain," Second Workshop of Tohoku Branch,
IPSJ, (Information Processing Society of Japan), University of
Aizu, Aizuwakamatsu, Japan, Jan. 21, 2005.
[2] Hazem M. El-Bakry, and Qiangfu Zhao, "Fast Object/Face
Detection Using Neural Networks and Fast Fourier
Transform," the International Journal of Signal Processing,
vol.1, no.3, pp. 182-187, 2004.
[3] H. M. El-Bakry, and Qiangfu Zhao, "A New Symmetric Form
for Fast Sub-Matrix (Object/Face) Detection Using Neural
Networks and FFT," under publication in the International
Journal of Signal Processing.
[4] Hazem M. El-Bakry, and Qiangfu Zhao, "Fast Pattern
Detection Using Normalized Neural Networks and Cross
Correlation in the Frequency Domain," under publication in
the European Journal of Applied Signal Processing.
[5] Hazem M. El-Bakry, "Comments on Using MLP and FFT for
Fast Object/Face Detection," Proc. of IEEE IJCNN'03,
Portland, Oregon, July, 20-24, 2003, pp. 1284-1288.
[6] Hazem M. El-Bakry, "Human Iris Detection Using Fast
Cooperative Modular Neural Networks and Image
Decomposition," Machine Graphics & Vision Journal
(MG&V), vol. 11, no. 4, pp. 498-512, 2002.
[7] Hazem M. El-Bakry, "Face detection using fast neural
networks and image decomposition," Neurocomputing
Journal, vol. 48, pp. 1039-1046, 2002.
[8] S. Srisuk and W. Kurutach, "A New Robust Face Detection in
Color Images," Proc. of IEEE Computer Society International
Conference on Automatic Face and Gesture Recognition
(AFGR'02), Washington D.C., USA, May 20-21, 2002, pp.
306-311.
[9] Hazem M. El-Bakry, "Automatic Human Face Recognition
Using Modular Neural Networks," Machine Graphics &
Vision Journal (MG&V), vol. 10, no. 1, pp. 47-73, 2001.
[10] Ying Zhu, Stuart Schwartz, and Michael Orchard, "Fast Face
Detection Using Subspace Discriminate Wavelet Features,"
Proc. of IEEE Computer Society International Conference on
Computer Vision and Pattern Recognition (CVPR'00), South
Carolina, June 13 - 15, 2000, vol.1, pp. 1636-1643.
[11] R. Feraud, O. Bernier, J. E. Viallet, and M. Collobert, "A Fast
and Accurate Face Detector for Indexation of Face Images,"
Proc. of the Fourth IEEE International Conference on
Automatic Face and Gesture Recognition, Grenoble, France,
28-30 March, 2000.
[12] S. Baluja, H. A. Rowley, and T. Kanade, "Neural Network -
Based Face Detection," IEEE Trans. on Pattern Analysis and
Machine Intelligence, vol. 20, no. 1, pp. 23-38, 1998.