Modular Neural Network for Human Recognition from Ear Images Using Wavelets
This work is focused in the human recognition from ear images as biometric using modular neural networks with preprocessing ear images as network inputs. We proposed a modular neural network architecture composed of twelve modules, in order to simplify the problem making it smaller. Comparing with other biometrics, ear recognition has one of the best performances, even when it has not received much attention. To compare with other existing methods, we used the 2D Wavelet analysis with global thresholding method for compression, and Sugeno Measures and Winner-Takes-All as modular neural network integrator. Recognition results achieved was up to 97%.
Unable to display preview. Download preview PDF.
- 1.Xie, Z., Mu, Z.: Ear Recognition Using LLE and IDLLE Algorithm. Paper, University of Science and Technology Beijing, China (2008)Google Scholar
- 2.Lu, L., Zhang, X., Zhao, Y., Jia, Y.: Ear Recognition Based on Statistical Shape Model. Paper, University of Science and Technology Beijing, China (2008)Google Scholar
- 3.Ali, M., Javed, M.Y., Basit, A.: Ear Recognition Using Wavelets. Paper, National University of Sciences and Technology, Peshawar Road, Rawalpindi, Pakistan (2007)Google Scholar
- 4.Santos, J., Alexandre, L., Marques de Sa, J.: Modular Neural Network Task Decomposition Via Entropic Clustering. In: Sixth International Conference on Intelligent Systems Design and Applications, ISDA 2006 (2006)Google Scholar
- 5.Jain, A.K., Ross, A., Prabhakar, S.: An Introduction to Biometric Recognition. Paper, IEEE Transactions (2004)Google Scholar
- 6.Yan, P., Bowyer, K.W.: Empirical Evaluation of Advanced Ear Biometrics. Paper, University of Notre Dame (2005)Google Scholar
- 7.Lammi, H.K.: Ear Biometrics. Paper, Lappeenranta University of Technology, Finland (2003)Google Scholar
- 8.Salinas, R.: Neural Network Architecture Parametric Face Recognition. Paper, University of Santiago de Chile (2000)Google Scholar
- 9.Carreira-Perpinan, M.A.: Compression Neural Networks for Feature Extraction: Application to Human Recognition from Ear Images. Thesis, University Polytechnic of Madrid, Spain (1995)Google Scholar
- 10.Commonly used Biometrics Graphic: International Biometric Group, http://www.biometricgroup.com/ (Reviewed in April 2009)
- 11.Data Base: Ear Recognition Laboratory at USTB, http://www.ustb.edu.cn/resb/en/index (Reviewed in March 2009)