Gabor feature based classification using the enhanced fisher linear discriminant model for face recognition

By Chengjun Liu, Harry Wechsler. IEEE Transactions on Image Processing, 2002

2,099 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/bbbd015155bbe5098aad6b49a548e9f3570e49ec

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Dacheng Tao
2. Xiaogang Wang
3. Luc Van Gool
4. Xiaoou Tang
5. Yu Qiao
6. Chen Change Loy
7. Ming-Hsuan Yang
8. Yi Yang

Citations in the corpus

• Age Synthesis and Estimation via Faces: A Survey (2010, methodology): “The Gabor feature [145] has also been tried on the age estimation task [146], which has been demonstrated to be more effective than LBP.”
• Gabor-Based Region Covariance Matrices for Face Recognition (2008, methodology): “Besides, two Gabor-feature-based methods, Gabor PCA and Gabor LDA are also considered [5].”
• Local Derivative Pattern Versus Local Binary Pattern: Face Recognition With High-Order Local Pattern Descriptor (2010, methodology): “ture descriptors extracted by a set of Gabor wavelets (kernels) which model the receptive field profiles of cortical simple cells [5], [6], [15], [28], [29].”
• Rotating your face using multi-task deep neural network (2015, methodology): “Face recognition Typically, for the past twenty years, hand-crafted features such as LBP [1], SIFT [15] or Gabor [14] have been used in the face recognition task.”
• Reliable Crowdsourcing and Deep Locality-Preserving Learning for Unconstrained Facial Expression Recognition (2019, background): “Again, to demonstrate the reliability of the compound emotion labels, we computed the baseline for the naive emotion detector, which decreased to 5.79% when using the Gabor features.”
• Multi-View Perceptron: a Deep Model for Learning Face Identity and View Representations (2014, background): “Substantial efforts have been dedicated to extract identity features by hand, such as LBP [1], Gabor [14], and SIFT [15].”
• A review on Gabor wavelets for face recognition (2006, methodology): “Analytical methods Elastic graph matching based methods DLA [29] Own 88 EBGM [30] FERET 98 Multiple facial features [34] Yale 96.4 Gabor + Bayesian [65] XM2VTS 97.1 AR 93.3 Facial feature detection based graph location [30] Own 93.3 ORL 94.5 Non-graph matching based methods Variable facial feature p”
• CloudID: Trustworthy cloud-based and cross-enterprise biometric identification (2015, background): “Since the adjacent pixels in an image are usually highly correlated, we can reduce this information redundancy by downsampling the feature images resulting from Gabor filters (Liu & Wechsler, 2002; Shen et al., 2007).”
• Histogram of Gabor Phase Patterns (HGPP): A Novel Object Representation Approach for Face Recognition (2007, methodology): “GFC is also trained on the FERET training database, and nearest-neighbor classifier based on the cosine similarity measurement is used to make a final classification [9].”
• Discriminant Correlation Analysis: Real-Time Feature Level Fusion for Multimodal Biometric Recognition (2016, background): “images that result from Gabor filters [35], [38].”
• Going deeper in facial expression recognition using deep neural networks (2015, background): “These features can be geometric features such as facial landmarks [19], appearance features such as pixel intensities [32], Gabor filters [23], Local Binary Patterns (LBP) [38], Local Phase Quantization (LPQ) [53], and Histogram of Oriented Gradients (HoG) [29], or motion features such as optical fl”
• Recent advances in visual and infrared face recognition - a review (2005, methodology): “of different realizations of LDA methods have also been recently proposed [84–87].”
• Age and gender classification using convolutional neural networks (2015, methodology): “Past approaches to estimating or classifying these attributes from face images have relied on differences in facial feature dimensions [29] or “tailored” face descriptors (e.g., [10, 15, 32]).”
• Demographic Estimation from Face Images: Human vs. Machine Performance (2015, methodology): “To compute S1 layer features, we build a family of Gabor filters similar to those in [61], but we use 8 orientations (u 2 1⁄20; 7 ) and 12 scales (v 2 1⁄21; 12 ) as suggested in [23].”
• Regularization studies of linear discriminant analysis in small sample size scenarios with application to face recognition (2005, methodology): “Of the appearance-based FR methods, those utilizing linear discriminant analysis (LDA) techniques have shown promising results as it is demonstrated in (Belhumeur et al., 1997; Zhao et al., 1999; Chen et al., 2000; Yu and Yang, 2001; Liu and Wechsler, 2002; Lu et al., 2003a,b; Ye and Li, 2004).”
• Learning Discriminant Face Descriptor (2014, background): “Gabor [17], [18] and local binary patterns (LBP) [19] are two representative features.”