Face recognition via adaptive discriminant clustering

Kyperountas, Marios; Tefas, Anastasios; Pitas, Ioannis

doi:10.1109/icip.2008.4712362

Cited by 5 publications

(4 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [3] Marios Kyperountas, Anastasios Tefas, Ioannis Pitas has proposed a methodology in multiple steps. At each clustering step, the test and training faces are projected to a Discriminant face and the data that is projected onto space are partitioned into clusters using the k-means algorithm.…”

Section: Related Workmentioning

confidence: 99%

“…Face recognition has been a full of life analysis topic inside the Digital world. Various traditional approaches in the recognition such as are Correlation [3], Eigenfaces [4], and Sparse representation [13] since it is challenging to recognize face images with illumination and expression variations as well as corruptions due to occlusion or disguise. A typical solution is to collect a sufficient amount of training data in advance so that the above intraclass variations can be properly handled.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Survey on Face Recognition Techniques for Undersampled Data

2017

IJSR

View full text Add to dashboard Cite

With the increase of the Security threats around the world, it is very difficult to find a person whether he is an authorized one or not. Due to an increase of the Globalization and digitization around the world, the Face Recognition technology gains a lot of importance for identification purpose. These techniques are mainly focused on the authentication and authorization aspects and these methodologies will help us to locate any person by capturing and comparing those from the images that are present in the database, Even the disguised ones also. In this Survey paper, different types of Undersampled Face Recognition methods are analyzed.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Survey on Face Recognition Techniques for Undersampled Data

2017

IJSR

View full text Add to dashboard Cite

show abstract

“…In [19], training and tests are projected into the LDA space, improving the data separability. Yang and Zhang [46] adopted Gabor features, Chan and Kittler [8] used the LBP descriptor, and in [25] the authors adopted a multifeature representation combining Gabor, HOG and LBP.…”

Section: Related Workmentioning

confidence: 99%

Robust face recognition using sparse representation in LDA space

Adamo

Grossi

Lanzarotti

et al. 2015

Machine Vision and Applications

View full text Add to dashboard Cite

In this article, we address the problem of face recognition under uncontrolled conditions. The proposed solution is a numerical robust algorithm dealing with face images automatically registered and projected via the linear discriminant analysis (LDA) into a holistic low-dimensional feature space. At the heart of this discriminative system, there are suitable nonconvex parametric mappings based on which a fixed-point technique finds the sparse representation of test images allowing their classification. We theoretically argue that the success achieved in sparsity promoting is due to the sequence of values imposed on a characteristic parameter of the used mapping family. Experiments carried out on several databases (ORL, YaleB, BANCA, FRGC v2.0) show the robustness and the ability of the system for classification purpose. In particular, within the area of sparsity promotion, our recognition system shows very good performance with respect to those achieved by the stateof-the-art 1 norm-based sparse representation classifier (SRC), the recently proposed 2 norm-based collaborative representation classifier (CRC), the LASSO-based sparse decomposition technique, and the weighted sparse represen-B Raffaella Lanzarotti tation method (WSRC), which integrates sparsity and data locality structure.

show abstract

“…Given a test image, the method searches for the most similar cluster, and then within it, the identity of the probe image. In [9] the authors propose an iterative approach that subsequently reduces the search space. The method repeats a LDA-projection of both the training and test data, a k-means clustering to partition the search space into K clusters, and a nearest-neighbour classifier to select K ′ clusters closest to the probe image.…”

Section: Related Workmentioning

confidence: 99%

A Selection Module for Large-Scale Face Recognition Systems

Grossi

Lanzarotti

Lin

2015

Image Analysis and Processing — ICIAP 2015

View full text Add to dashboard Cite

Abstract. Face recognition systems aimed at working on large scale datasets are required to solve specific hurdles. In particular, due to the huge amount of data, it becomes mandatory to furnish a very fast and effective approach. Moreover the solution should be scalable, that is it should deal efficiently the growing of the gallery with new subjects. In literature, most of the works tackling this problem are composed of two stages, namely the selection and the classification. The former is aimed at significantly pruning the face image gallery, while the latter, often expensive but precise, determines the probe identity on this reduced domain. In this article a new selection method is presented, combining a multi-feature representation and the least squares method. Data are split into sub-galleries so as to make the system more efficient and scalable. Experiments on the union of four challenging datasets and comparisons with the state-of-the-art prove the effectiveness of our method.

show abstract

Face recognition via adaptive discriminant clustering

Cited by 5 publications

References 6 publications

A Survey on Face Recognition Techniques for Undersampled Data

A Survey on Face Recognition Techniques for Undersampled Data

Robust face recognition using sparse representation in LDA space

A Selection Module for Large-Scale Face Recognition Systems

Contact Info

Product

Resources

About