Extended local binary patterns for face recognition
Introduction
Face recognition, as one of the most successful applications of image analysis and understanding, has received considerable attention in the past decades due to its challenging nature and vast range of applications [18], [42]. In recent years this field progressed significantly and a number of face recognition and modeling systems have been developed [18]. Even though current face recognition systems have reached a certain level of maturity, the performance of these systems in uncontrolled environments is still far from the capability of the human vision system [18], [42]. In other words, there are still many challenges associated with accurate and robust face recognition in regards to computer vision and pattern recognition, especially under unconstrained environments. Therefore, this remains a stimulating field for further research.
As a classical pattern recognition problem, face recognition primarily consists of two critical subproblems: feature extraction and classifier designation, both of which have been the subject of significant study. Generally, facial feature description plays a relatively more important role if poor features are used, and even the best classifier will fail to achieve good recognition results. Numerous facial feature sets were presented with excellent surveys in reports by Zhao et al. [42] and Li and Jain [18]. Nevertheless, designing useful face descriptors remains a great challenge when faced with three competing goals: computational efficiency, effective discrimination, and robustness to intra-person variations (including changes in illumination, pose, expression, age, blur, and occlusion).
Most facial extraction approaches can be categorized as utilizing either holistic features or local features. The holistic approach uses the entire face region to construct a subspace representing a face image; Influential examples includes Principle Component Analysis (PCA) [36], Linear Discriminant Analysis (LDA) [3], Locally Linear Embedding (LLE) [33] and Locally Preserving Projections (LPP) [11]. In contrast, the local features approach involves local features first being extracted from a subregion of a face and then classified by combining and comparing with corresponding local statistics. Holistic features are unable to capture local variations in face appearance, and are more sensitive to variations in illumination, expression and occlusions [18]. Local feature based approaches are advantageous in that distributions of face images in local feature space are less affected by changes in facial appearance. As a result, local feature based face recognition approaches have been widely studied in recent years.
Among local feature approaches, local binary patterns (LBP) have emerged as one of the most prominent face analysis methods since the pioneering work by Ahonen et al. [1], and have attracted increasing attention due to their distinguished advantages: (1) ease of implementation; (2) invariance to monotonic illumination changes; and (3) low computational complexity. However, the original LBP method still has multiple limitations: (i) production of long histograms; (ii) capture of only very local texture structure and not long range information; (iii) limited discriminative capability based purely on local binarized differences; and (iv) limited noise robustness. On the basis of these issues, many LBP variants [12] have been proposed to improve face recognition performance.
Our research is motivated by recent work on texture classification in [24], where four LBP-like descriptors – Center Intensity based LBP (CI-LBP), Neighborhood Intensity based LBP (NI-LBP), Radial Difference based LBP (RD-LBP) and Angular Difference based LBP (AD-LBP) – were proposed, along with multiscale joint histogram features, which were found to be highly effective to rotation invariant texture classification. We expanded this research [24] to address the face identification problem by proposing a framework and more generalized formulation of the local intensities and differences features. Specifically, the major contributions of our work are summarized as follows:
- 1.
We proposed a new family of LBP-like descriptors based on local accumulated pixel differences: Angular Differences (AD) and Radial Differences (RD). The descriptors presented advantages of efficiency, complementarity to LBP, robustness, and the encoding of both microstructures and macrostructures, resulting in a more complete image representation. The extraction of the proposed descriptors did not require any training, and thus this approach showed better generalizability compared with popular learning methods, whose performance is degraded if the distribution of the testing sample varies significantly from that of the training set.
- 2.
Using the proposed descriptors, we found that the properties of the original uniform patterns introduced by Ojala et al. [30] did not hold true, and therefore we suggest the use of full patterns. We also proposed a labeled dominant pattern (LDP) scheme, which learns a set of dominant patterns (the most frequently occurring patterns from a set of training images) to capture discriminative textural information, but with lower dimensionality than the full pattern approach.
- 3.
Extensive experiments were conducted on the Extended Yale B, the FERET and the large-scale CAS-PEAL-R1 databases. Our approach proved to be highly robust to illumination changes, as evident by our recognition rate of 74.6% on the CAS-PEAL-R1 lighting probe set. This is, to the best of our knowledge, the highest score yet achieved on this data set.
A preliminary version of this work appeared in [22].
Section snippets
Related work
The primary motivation of this work is to design novel LBP-like descriptors and apply them to face recognition, thus the related literature focuses on LBP and its variants for face recognition.
Extended LBP descriptors
Guo et al. [9] proposed a complete LBP for texture classification, which included both the sign and the magnitude components between a given central pixel and its neighbors in order to improve the discriminative power of the original LBP operator. The operator derived from the sign component, denoted as LBP_S, is the same as the original LBP operator defined in (2): The operator computed from the magnitude component, denoted as LBP_M, performed a binary comparison between the
Face representation
With the proposed descriptors detailed in Section 3, our face feature representation pipeline is similar to the one proposed by Ahonen et al. [1], but incorporates a more sophisticated illumination normalization step as used by Tan and Triggs [35]. Fig. 4 illustrates the proposed extended set of features, and Fig. 7 summarizes the main operation for the face recognition pipeline. Histogram feature extraction from a face image involves the following steps:
- (1)
Crop the face region and align the face
Experiments
We conducted extensive experiments on three commonly-used databases: Extended Yale B, FERET and CAS-PEAL-R1. We used the standard evaluation protocol for each database in order to facilitate comparison with previous work. These databases incorporate several deviations from the ideal conditions, including illumination, expression, occlusion and pose alterations. We adopt several of the standard evaluation protocols reported in the face recognition literature, and we present a comprehensive
Conclusions
In this paper we proposed a novel extended set of LBP-like descriptors and developed a simplistic framework to fuse the proposed descriptors for face identification. The proposed set of descriptors consists of two intensity based descriptors LBP_S, and LBP_M, and four accumulated local differences based descriptors ADLBP_S, ADLBP_M, RDLBP_S, and RDLBP_M.
All of the proposed descriptors have desirable features of robustness to lighting, pose, and expression variations, computational efficiency
Acknowledgments
This work has been supported by the National Natural Science Foundation of China under contract number 61202336, by the Open Project Program of the National Laboratory of Pattern Recognition (201407354), and the National Basic Research Program of China (973 Program) (2013CB329401).
References (43)
- et al.
Discriminative features for texture description
Pattern Recognit.
(2012) - et al.
Extended local binary patterns for texture classification
Image Vis. Comput.
(2012) - et al.
A comparative study of texture measures with classification based on feature distributions
Pattern Recognit.
(1996) - et al.
Face decription with local binary patterns: application to face recognition
IEEE Trans. Pattern Anal. Mach. Intell.
(2006) - et al.
Soft histograms for local binary patterns
Proceedings of the 2007 Finnish Signal Processing Symposium
(2007) - et al.
Eigenfaces vs. fisherfaces: recognition using class specific linear projection
IEEE Trans. Pattern Anal. Mach. Intell.
(1997) - et al.
The CSU face identification evaluation system its purpose, features, and structure
Mach. Vis. Appl.
(2005) Multi-scale Local Binary Pattern Histograms for Face Recognition
(2008)- et al.
Multiscale local phase quantization for robust component-based face recognition using kernel fusion of multiple descriptors
IEEE Trans. Pattern Anal. Mach. Intell.
(2013) - et al.
Gabor-eigen-whiten-cosine: a robust scheme for face recognition
Analysis and Modelling of Faces and Gestures
(2005)
The CAS-PEAL large-scale Chinese face database and baseline evaluations
IEEE Trans. Syst. Man Cybern. A Syst. Hum.
A completed modeling of local binary pattern operator for texture classification
IEEE Trans. Image Process.
Face recognition using Laplacian faces
IEEE Trans. Pattern Anal. Mach. Intell.
Local binary patterns and its application to facial image analysis a survey
IEEE Trans. Syst. Man Cybern. C Appl. Rev.
A robust method for near infrared face recognition based on extended local binary pattern
Advances in Visual Computing
Face recognition using local quantized patterns
Proceedings of the British Machine Vision Conference
Heterogeneous face recognition using kernel prototype similarities
IEEE Trans. Pattern Anal. Mach. Intell.
Acquiring linear subspaces for face recognition under variable lighting
IEEE Trans. Pattern Anal. Mach. Intell.
Learning discriminant face descriptor
IEEE Trans. Pattern Anal. Mach. Intell.
Handbook of Face Recognition
Dominant local binary patterns for texture classification
IEEE Trans. Image Process.
Cited by (129)
Machine learning for weed–plant discrimination in agriculture 5.0: An in-depth review
2023, Artificial Intelligence in AgricultureM3SPCANet: A simple and effective ConvNets with unsupervised predefined filters for face recognition
2022, Engineering Applications of Artificial IntelligenceClassification of seven Iranian wheat varieties using texture features
2022, Expert Systems with ApplicationsTree trunk texture classification using multi-scale statistical macro binary patterns and CNN
2022, Applied Soft ComputingIllumination invariant face recognition using Fused Cross Lattice Pattern of Phase Congruency (FCLPPC)
2022, Information SciencesCitation Excerpt :LBP establishes a binary relationship between the center pixel and its neighbors using a threshold values [34]. In recent years, many adaptation of LBP has been made, namely Noise Resistant LBP (NRLBP) [35], Extended LBP (ELBP) [18], etc. However, owing to LBP’s single-orientation pixel difference approach, often it fails to encapsulate directional micro features.
An efficient cloud based face recognition system for e-health secured login using steerable pyramid transform and local directional pattern
2024, Journal of Ambient Intelligence and Humanized Computing