Fast Normalized Neural Processors for Pattern Detection Based on Cross Correlation Implementation in the Frequency Domain

Neural networks have shown good results for detecting a certain pattern in a given image. In this paper, fast neural networks for pattern detection are presented. Such neural processors are designed based on cross correlation in the frequency domain between the input image and the weights of neural networks. New general formulas for fast cross correlation as well as the speed up ratio are given. Also, commutative cross correlation is achieved. Furthermore, an approach to reduce the computation steps required by these fast neural networks for the searching process is presented. The principle of divide and conquer strategy is applied through image decomposition. Each image is divided into small in size sub-images and then each one is tested separately by using a single fast neural processor. Compared with conventional and fast neural networks, experimental results show that a speed up ratio is achieved when applying this technique to locate different patterns automatically in cluttered scenes. Furthermore, faster pattern detection is obtained by using parallel processing techniques to test the resulting sub-images at the same time using the same number of fast neural networks. In contrast to fast neural networks, the speed up ratio is increased with the size of the input image when using fast neural networks and image decomposition. Our previous work solved the problem of local sub-image normalization in the frequency domain. Here, the effect of image normalization on the speed up ratio of pattern detection is presented. Simulation results show that local sub-image normalization through weight normalization is faster than sub-image normalization in the spatial domain. Moreover, the overall speed up ratio of the detection process is increased as the normalization of weights is done off line.

[1]  H. El-Bakry.  Face detection using neural networks and image decomposition , 2002, Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290).

[2]  Hazem M. El-Bakry.  Comments on using MLP and FFT for fast object/face detection , 2003, Proceedings of the International Joint Conference on Neural Networks, 2003..

[3]  Qiangfu Zhao,et al.  Speeding-up normalized neural networks for face/object detection , 2005 .

[4]  B. Fasel.  Fast Multi-Scale Face Detection , 1998 .

[5]  H.M. El-Bakry.  Fast iris detection using neural nets , 2001, Canadian Conference on Electrical and Computer Engineering 2001. Conference Proceedings (Cat. No.01TH8555).

[6]  H. M. El-Bakry.  Fast Iris Detection Using Cooperative Modular Neural Nets , 2001 .

[7]  Hazem M. El-Bakry.  Fast Face Detection Using Neural Networks and Image Decomposition , 2001, Active Media Technology.

[8]  Souheil Ben-Yacoub,et al.  Fast Object Detection using MLP and FFT , 1997 .

[9]  Michael T. Orchard,et al.  Fast face detection using subspace discriminant wavelet features , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[10]  Hazem M. El-Bakry.  Face detection using fast neural networks and image decomposition , 2002, Neurocomputing.

[11]  Mohamed S. Kamel,et al.  Fast modular neural nets for face detection , 2000, 2000 IEEE International Symposium on Circuits and Systems. Emerging Technologies for the 21st Century. Proceedings (IEEE Cat No.00CH36353).

[12]  Herbert Stoyan,et al.  Fast neural networks for sub-matrix (object/face) detection , 2004, 2004 IEEE International Symposium on Circuits and Systems (IEEE Cat. No.04CH37512).

[13]  H.M. El-Bakry.  Human iris detection using fast cooperative modular neural nets , 2001, IJCNN'01. International Joint Conference on Neural Networks. Proceedings (Cat. No.01CH37222).

[14]  Takeo Kanade,et al.  Neural Network-Based Face Detection , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  Hazem M. El-Bakry.  Fast Iris Detection for Personal Verification Using Modular Neural Nets , 2001, Fuzzy Days.

[16]  Werasak Kurutach,et al.  A new robust face detection in color images , 2002, Proceedings of Fifth IEEE International Conference on Automatic Face Gesture Recognition.

[17]  Raphaël Féraud,et al.  A fast and accurate face detector for indexation of face images , 2000, Proceedings Fourth IEEE International Conference on Automatic Face and Gesture Recognition (Cat. No. PR00580).

[18]  Juergen Luettin,et al.  Fast Face Detection using MLP and FFT , 1999 .

[19]  Hazem M. El-Bakry.  Fast iris detection for personal identification using modular neural networks , 2001, ISCAS 2001. The 2001 IEEE International Symposium on Circuits and Systems (Cat. No.01CH37196).

[20]  Hazem M. El-Bakry.  Automatic human face recognition using modular neural networks , 2001 .

[21]  Hazem M. El-Bakry.  Fast cooperative modular neural nets for human face detection , 2001, Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205).

[22]  Qiangfu Zhao,et al.  Fast Pattern Detection Using Normalized Neural Networks and Cross-Correlation in the Frequency Domain , 2005, EURASIP J. Adv. Signal Process..