Gabor Orientation Histogram for Face Representation and Recognition
Recently the Gabor-based features have been successfully used for face representation and recognition. In these methods, the face image is filtered with the multiscale multiorientation Gabor filter bank to generate multiple Gabor magnitude images (GMIs),
- PDF / 303,576 Bytes
- 9 Pages / 439.37 x 666.142 pts Page_size
- 56 Downloads / 185 Views
Gabor Orientation Histogram for Face Representation and Recognition Jun Yi and Fei Su
Abstract Recently the Gabor-based features have been successfully used for face representation and recognition. In these methods, the face image is filtered with the multiscale multiorientation Gabor filter bank to generate multiple Gabor magnitude images (GMIs), and then the down-sampled GMIs or the LBP (local binary pattern) histograms of GMIs are stacked to form the feature. The stacking procedure makes the dimensions of these features very high, which causes extreme computing and storage load. In this paper, a novel Gabor-based feature termed Gabor orientation histogram (GOH) is proposed, which greatly reduces the feature dimension. Unlike stacking, GOH takes the structure underlying different GMIs into account by regarding the GMIs of different orientations at the same point as a whole, namely orientation vector, to represent the point. Moreover, GOH takes the structure of local region into account by calculating the orientation histogram based on the orientation vectors of points in the local region to describe the region, which is robust to local deformation and noises. The experimental results on the FERET and FRGC databases show that the proposed GOH reduces the feature extraction and recognition time significantly while retains the high recognition performance, which makes a progress toward the practical applications of Gaborbased features for face representation and recognition. Keywords Gabor filter
Gabor feature Face representation Face recognition
J. Yi (&) F. Su Beijing University of Posts and Telecommunications, Beijing, China e-mail: [email protected] F. Su e-mail: [email protected]
A. A. Farag et al. (eds.), Proceedings of the 3rd International Conference on Multimedia Technology (ICMT 2013), Lecture Notes in Electrical Engineering 278, DOI: 10.1007/978-3-642-41407-7_4, Springer-Verlag Berlin Heidelberg 2014
35
36
J. Yi and F. Su
4.1 Introduction One-dimensional (1D) Gabor function was proposed by Gabor in 1946 [4]. It achieves the theoretical lower limit for the uncertainty of time and frequency according to Gabor’s uncertainty principle of 1D temporal signal. Daugman generalized Gabor’s uncertainty principle from 1D temporal signal to two-dimensional (2D) spatial signal and proposed 2D Gabor function in 1985 [3]. Moreover, he showed that the 2D receptive-field profiles of simple cells in mammalian visual cortex were well described by the 2D Gabor function, which was further evaluated and verified by Jones and Palmer in 1987 [5]. Due to the nice mathematical property of Gabor function and its analogy to the biological mechanism, 2D Gabor filter has been widely used in image processing and analysis including face representation and recognition. Gabor-based features have achieved great success in the FERET evaluation [9] and excellent performance on the FERET database [10, 12]. However, Gabor-based features all treated the multiple outputs of different Gabor filters separately and just stacked t
Data Loading...
