A novel supervised dimensionality reduction algorithm: Graph-based Fisher analysis

Cui, Yan; Li, Fan

doi:10.1016/j.patcog.2011.10.006

Cited by 34 publications

(20 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A graph-based supervised DR method has been proposed in [30] for circumventing the problem of non-Gaussian distributed data. The degrees of importance of the same-class and not-sameclass vertices are encoded by the intrinsic and extrinsic graphs, respectively, based on a strictly monotonically decreasing function.…”

Section: Related Workmentioning

confidence: 99%

Subclass Graph Embedding and a Marginal Fisher Analysis paradigm

Maronidis

Tefas

Pitas

2015

Pattern Recognition

View full text Add to dashboard Cite

Section: Related Workmentioning

confidence: 99%

Subclass Graph Embedding and a Marginal Fisher Analysis paradigm

Maronidis

Tefas

Pitas

2015

Pattern Recognition

View full text Add to dashboard Cite

“…Shin et al [1], Dubey et al [2] and Wang et al [3] proposed some face feature description algorithms using singular value decomposition. Fàbregas et al brought linear discriminant analysis (LDA) into pattern recognition field when extracting the discriminant feature [4–14]. Some extension LDA algorithms have been studied and applied to face recognition such as the combined LDA with principal component analysis (PCA) and minimum distance classifier [5], gradient LDA [6], hash LDA [7], L P ‐norm LDA [8].…”

Section: Introductionmentioning

confidence: 99%

“…Some extension LDA algorithms have been studied and applied to face recognition such as the combined LDA with principal component analysis (PCA) and minimum distance classifier [5], gradient LDA [6], hash LDA [7], L P ‐norm LDA [8]. Shu et al present some improved algorithms based on basic LDA method [9–14]. Toutanova and Johnson [15] and Newman and Block [16] proposed a novel face feature extraction method using topic decomposition model.…”

Section: Introductionmentioning

confidence: 99%

Single sample description based on Gabor fusion

2019

View full text Add to dashboard Cite

Owing to lack of enough face image and invalidation of many traditional face recognition algorithms, face recognition with single training sample is really a great challenge. To solve the above problem, this study proposes a novel local weighted fusion Gabor (LWFG) algorithm. First, one single sample is segmented into a series of block sub‐images, and then, each of these sub‐images is decomposed into a series of multi‐resolution Gabor wavelets with multi‐orientation and multi‐scale. Second, different orientation Gabor wavelets with the same scale are fused. Next, different scale Gabor wavelets with the same orientation are fused according to the proposed fusion criterion. Third, the fusion Gabor feature histograms are calculated in each of the divided local regions. Meanwhile, every local region's information importance is measured by the proposed local image information content model. Finally, the fusion Gabor wavelet histograms are adaptively weighed by weighting map which calculated from information content model. This study conducted simulation experiments on different face databases under the different conditions including partial occlusion, expression change and illumination variation. The results indicated that the proposed LWFG algorithm is more effective with single training sample.

show abstract

“…A graph-based supervised DR method has been proposed in [11] for circumventing the problem of non-Gaussian distributed data. The importance degrees of the sameclass and not-same-class vertices are encoded by the intrinsic and extrinsic graphs, respectively, based on a strictly monotonically decreasing function.…”

Section: Introductionmentioning

confidence: 99%

Graph Embedding Exploiting Subclasses

Maronidis

Tefas

Pitas

2015

2015 IEEE Symposium Series on Computational Intelligence

View full text Add to dashboard Cite

Abstract-Recently, subspace learning methods for Dimensionality Reduction (DR), like Subclass Discriminant Analysis (SDA) and Clustering-based Discriminant Analysis (CDA), which use subclass information for the discrimination between the data classes, have attracted much attention. In parallel, important work has been accomplished on Graph Embedding (GE), which is a general framework unifying several subspace learning techniques. In this paper, GE has been extended in order to integrate subclass discriminant information resulting to the novel Subclass Graph Embedding (SGE) framework. The kernelization of SGE is also presented. It is shown that SGE comprises a generalization of the typical GE including subclass DR methods. In this vein, the theoretical link of SDA and CDA methods with SGE is established. The efficacy and power of the SGE has been substantiated by comparing subclass DR methods versus a diversity of unimodal methods all pertaining to the SGE framework via a series of experiments on various real-world data.

show abstract

A novel supervised dimensionality reduction algorithm: Graph-based Fisher analysis

Cited by 34 publications

References 24 publications

Subclass Graph Embedding and a Marginal Fisher Analysis paradigm

Subclass Graph Embedding and a Marginal Fisher Analysis paradigm

Single sample description based on Gabor fusion

Graph Embedding Exploiting Subclasses

Contact Info

Product

Resources

About