Face Verification Using Multiple Localized Face Features
In this paper, we described face verification execution using different feature extraction methods on different regions of the face. We chose two feature extraction methods which are the Discrete Cosine Transform (DCT) and the Local Binary Pattern (LBP). Classification is done separately on for each region using Support Vector Machine. The final verification decision is calculated by combining the classification scores of the face region. The results show that generally, LBP gives better results than DCT on our dataset and parameter settings but both methods did not extract good discriminating features on the nose region.
KeywordsFace verification local binary pattern discrete cosine transform support vector machine
Unable to display preview. Download preview PDF.
- 3.King, I., Xu, L.: Localized principal component analysis learning for face feature extraction and recognition. In: Proceedings to the Workshop on 3D Computer Vision, pp. 124–128 (1997)Google Scholar
- 7.Chadha, A.R., Vaidya, P.P., Roja, M.M.: Face recognition using discrete cosine transform for global and local features. In: 2011 International Conference on Recent Advancements in Electrical, Electronics and Control Engineering (ICONRAEeCE), pp. 502–505. IEEE (2011)Google Scholar
- 8.Ojala, T., Pietikäinen, M., Harwood, D.: A comparative study of texture measures with classification based on feature distributions. Pattern Recognition 29 (1996)Google Scholar