Robust Features for Frontal Face Authentication in Difficult Image Conditions
In this paper we extend the recently proposed DCT-mod2 feature extraction technique (which utilizes polynomial coefficients derived from 2D DCT coefficients obtained from horizontally & vertically neighbouring blocks) via the use of various windows and diagonally neighbouring blocks. We also propose enhanced PCA, where traditional PCA feature extraction is combined with DCT-mod2. Results using test images corrupted by a linear and a non-linear illumination change, white Gaussian noise and compression artefacts, show that use of diagonally neighbouring blocks and windowing is detrimental to robustness against illumination changes while being useful for increasing robustness against white noise and compression artefacts. We also show that the enhanced PCA technique retains all the positive aspects of traditional PCA (that is, robustness against white noise and compression artefacts) while also being robust to illumination changes; moreover, enhanced PCA outperforms PCA with histogram equalisation pre-processing.
KeywordsPrincipal Component Analysis Feature Extraction Discrete Cosine Transform Face Image Gaussian Mixture Model
Unable to display preview. Download preview PDF.
- Gonzales, R. C., Woods, R. E.: Digital Image Processing. Addison-Wesley, 1993.Google Scholar
- Lockie, M. (editor): Facial verification bureau launched by police IT group. Biometric Technology Today 10 (No. 3) (2002) 3–4.Google Scholar
- Samaria, F.: Face Recognition Using Hidden Markov Models. PhD Thesis, University of Cambridge, 1994.Google Scholar
- Sanderson, C., Paliwal, K.K.: Polynomial Features for Robust Face Authentication. Proc. Intern. Conf. on Image Processing, Rochester, New York, 2002, pp. 997–1000 (Vol. 3).Google Scholar
- Sanderson, C.: The VidTIMIT Database. IDIAP Communication 02-06, Martigny, Switzerland, 2002.Google Scholar