Human iris detection using fast cooperative modular neural nets and image decomposition

• Autorzy: El-Bakry H. M.
• Języki publikacji: EN

Abstrakty

EN

In this paper, a combination of fast and cooperative modular neural nets to enhance the performance of the detection process is introduced. I have applied such approach successfully to detect human faces in cluttered scenes, [11]. Here, this technique is used to identify human irises automatically in a given image. Neural nets are used to test whether a window of 20x20 pixels contains an iris or not. The major difficulty in the learning process comes from the large database required for iris/non-iris images . A simple design for cooperative modular neural nets is presemted to solve this problem by dividing these data into three groups. Such division results in reduction of computational complexity and thus decreasing the time and memory needed during the test of an image. Simulation results for the proposed algorithm show a good performance. Moreover, a powerful system for personal identification using iris detection is presented. Futhermore, faster iris detection is obtained through image decomposition into many sub-images and applying cross correlation in the frequency domain between each sub-image and the weights of the hidden layer.

Słowa kluczowe

EN

personal identification; fast iris dection; and modular neural nets

• Wydawca: Institute of Information Technology of the Warsaw University of Life Sciences – SGGW
• Czasopismo: Machine Graphics and Vision
• Rocznik: 2002
• Tom: Vol. 11, No. 4
• Strony: 499--512
• Opis fizyczny: Bibliogr. 11 poz.

Twórcy

autor

El-Bakry H. M.

• Faculty of Computer Science & Information Systems Mansoura University - Egypt,

Bibliografia

• [1] Waibel A.: Modular construction of time delay neural networks for speech recognition. Neural Computing, 1, 39-46. 1989.
• [2] Joe K., Mori Y., Miyake S.: Construction of a large scale neural network: Simulation of handwritten japanese character recognition. NCUBE Concurrency, 2(2), 79-107. 1990.
• [3] Jacobs R., Jordan M., Barto A.: Task decomposition through competition in a modular connectionist architecture: the what and where vision tasks. Neural Computation, 3, 79-87. 1991.
• [4] Alpaydin E.: Multiple networks for function learning. Int. Conf. on NN, l CA, USA, 9-14. 1993.
• [5] Klette R., Zamperoni P.: Handbook of Image Processing Operators. John Wiley & Sons Ltd. 1996.
• [6] Ben-Yacoub S.: Fast Object Detection using MLP and FFT. IDIAP-RR 11, IDIAP. 1997.
• [7] Wildes R. P.: Iris recognition: an emerging biometrie technology. Proc. of IEEE, 85(9), 1347-1363. 1997.
• [8] Jain A., Bolle R., Pankanti S.: BIOMETRICS: Personal Identification in Networked Society. Kluwer Academic Publishers, Chap. 5, 103-122. 1998.
• [9] El-Bakry H. M.: Human iris detection using fast cooperative modular neural networks. Int . Joint Conf. on Neural Networks, Washington, De., USA, 14-19 July, 577-582. 2001.
• [10] El-Bakry H. M.: Fast face detection using neural networks and image decomposition. Sixth Int. Conf., Active Media Technology, Hongkong, 18-20 Dec., S-V, Berlin, Heidelberg, 205-215. 2001.
• [11] El-Bakry H. M.: Autornatic human face recognition using modular neural networks. MG & V, 10(1), 47-73. 2001.