High Performance and Efficient Facial Recognition Using Norm of ICA/Multiwavelet Features
In this paper, a supervised facial recognition system is proposed. For feature extraction, a Two-Dimensional Discrete Multiwavelet Transform (2D DMWT) is applied to the training databases to compress the data and extract useful information from the face images. Then, a Two-Dimensional Fast Independent Component Analysis (2D FastICA) is applied to different combinations of poses corresponding to the subimages of the low-low frequency subband of the MWT, and the \(\ell _2\)-norm of the resulting features are computed to obtain discriminating and independent features, while achieving significant dimensionality reduction. The compact features are fed to a Neural Network (NNT) based classifier to identify the unknown images. The proposed techniques are evaluated using three different databases, namely, ORL, YALE, and FERET. The recognition rates are measured using K-fold Cross Validation. The proposed approach is shown to yield significant improvement in storage requirements, computational complexity, as well as recognition rates over existing approaches.
This work was supported in part by NSF grant (CCF - 1320547) and by the Iraqi government scholarship (HCED).
- 1.Kinage, K., Bhirud, S.: Face recognition based on independent component analysis on wavelet subband. In: 3rd IEEE International Conference on Computer Science and Information Technology (ICCSIT). vol. 9, pp. 436–440 (2010)Google Scholar
- 2.AlEnzi, V., Alfiras, M., Alsaqre, F.: Face recognition algorithm using two dimensional principal component analysis based on discrete wavelet transform. In: Snasel, V., Platos, J., El-Qawasmeh, E. (eds.) ICDIPC 2011, Part I. CCIS, vol. 188, pp. 426–438. Springer, Heidelberg (2011) CrossRefGoogle Scholar
- 3.Hongtao, Y., Jiaqing, Q., Ping, F.: Face recognition with discrete cosine transform. In: Second International Conference on Instrumentation, Measurement, Computer, Communication and Control (IMCCC), pp. 802–805 (2012)Google Scholar
- 4.Satone, M., Kharate, G.: Face recognition based on pca on wavelet subband. In: IEEE Students’ Conference on Electrical, Electronics and Computer Science (SCEECS), pp. 1–4 (2012)Google Scholar
- 5.Ismaeel, T.Z., Kamil, A.A., Naji, A.K.: Article: human face recognition using stationary multiwavelet transform. Int. J. Comput. Appl. (IJCA) 72, 23–32 (2013)Google Scholar
- 6.Zhihua, X., Guodong, L.: Weighted infrared face recognition in multiwavelet domain. In: IEEE International Conference on Imaging Systems and Techniques (IST), pp. 70–74 (2013)Google Scholar
- 7.Reddy, P.V.N., Prasad, K.: Article: Multiwavelet based texture features for content based image retrieval. Int. J. Comput. Appl. 17, 39–44 (2011)Google Scholar
- 12.Lihong, Z., Ye, W., Hongfeng, T.: Face recognition based on independent component analysis. In: Control and Decision Conference (CCDC), Chinese, pp. 426–429 (2011)Google Scholar