2010
DOI: 10.1109/tpami.2010.128
|View full text |Cite
|
Sign up to set email alerts
|

Linear Regression for Face Recognition

Abstract: In this paper, we present a novel approach of face identification by formulating the pattern recognition problem in terms of linear regression. Using a fundamental concept that patterns from a single-object class lie on a linear subspace, we develop a linear model representing a probe image as a linear combination of class-specific galleries. The inverse problem is solved using the least-squares method and the decision is ruled in favor of the class with the minimum reconstruction error. The proposed Linear Re… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

3
510
0
6

Year Published

2013
2013
2018
2018

Publication Types

Select...
4
4
1

Relationship

0
9

Authors

Journals

citations
Cited by 933 publications
(519 citation statements)
references
References 24 publications
3
510
0
6
Order By: Relevance
“…The performance of the proposed method has been compared with other advanced methods already reported in the literature. Some of the state-of-the-art methods reported in the literature are Linear Regression for Face Recognition [30], local derivative pattern (LDP) versus LBP [31], Ageinvariant face recognition [32] and local texture feature (LTF) [33]. From the comparative analysis, it has been found that our proposed method gives better recognition and rejection rate compared to other advanced methods.…”
Section: Database Methodsmentioning
confidence: 99%
“…The performance of the proposed method has been compared with other advanced methods already reported in the literature. Some of the state-of-the-art methods reported in the literature are Linear Regression for Face Recognition [30], local derivative pattern (LDP) versus LBP [31], Ageinvariant face recognition [32] and local texture feature (LTF) [33]. From the comparative analysis, it has been found that our proposed method gives better recognition and rejection rate compared to other advanced methods.…”
Section: Database Methodsmentioning
confidence: 99%
“…It is observed from results that ČTROIKA and ŘTROIKA based classifier always performs better than their MLP counterparts. The authors in [23] addressed the facial expression variations and contiguous occlusion whereas the pose and illumination variations were not considered. The proposed work copes well with pose and illumination variations.…”
Section: Performance With Feret Face Datasetmentioning
confidence: 99%
“…We compare GRRC with SRC [10], CRC [32], Linear Regression for Classification (LRC) [37], linear Support Vector Machine (SVM) and Nearest Neighbor (NN) methods. If no specific instruction, for all the competing methods we use PCA to reduce the feature dimension.…”
Section: Face Recognition With Little Deformationmentioning
confidence: 99%
“…The manifold learning methods were proposed to overcome this limitation [5][6], and the representative manifold learning methods include locality preserving projection (LPP) [7], local discriminant embedding (LDE) [8], unsupervised discriminant projection (UDP) [9], etc. Besides, in order to better exploit the prior knowledge that face images from a single subject could construct a subspace, nearest subspace (NS) classifiers [19] [35][36] [37] are developed, which are usually superior to the simple nearest neighbor (NN) classifier.…”
Section: Introductionmentioning
confidence: 99%