Occlusion invariant face recognition using selective local non-negative matrix factorization basis images

Oh, Hyukjun; Lee, Kyoung Mu; Lee, Sang Uk

doi:10.1016/j.imavis.2008.04.016

Cited by 93 publications

(45 citation statements)

References 14 publications

(26 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While several papers have dealt with occlusion [17,24,14,16], they still require well aligned face images to compensate for the occlusion effect. Ekenel and Stiefelhagen showed that face alignment plays a key role in recognition performance in case of occlusion [10].…”

Section: Introductionmentioning

confidence: 99%

Partial Face Recognition: Alignment-Free Approach

Liao

Jain

2013

IEEE Trans. Pattern Anal. Mach. Intell.

265

View full text Add to dashboard Cite

Many approaches have been developed for holistic face recognition with impressive performance. However, few studies have addressed the question of how to recognize an arbitrary image patch of a holistic face. In this paper we address this problem of partial face recognition. Partial faces frequently appear in unconstrained image capture environments, particularly when faces are captured by surveillance cameras or handheld devices (e.g. mobile phones). The proposed approach adopts a variable-size description which represents each face with a set of keypoint descriptors. In this way, we argue that a probe face image, holistic or partial, can be sparsely represented by a large dictionary of gallery descriptors. The proposed method is alignment free and we address large-scale face recognition problems by a fast filtering strategy. Experimental results on three public domain face databases (FRGCv2.0, AR, and LFW) show that the proposed method achieves promising results in recognizing both holistic and partial faces.

show abstract

Section: Introductionmentioning

confidence: 99%

Partial Face Recognition: Alignment-Free Approach

Liao

Jain

2013

IEEE Trans. Pattern Anal. Mach. Intell.

265

View full text Add to dashboard Cite

show abstract

“…Examples of several different methods for modeling the appearance of local face areas, and of performing classification, exist in the literature. For example, local nonnegative matrix factorization is adopted by [37] to model the local areas of a face, and a nearest-neighbor classifier is then used to classify each local area as belonging to the target class or to the occlusion class. Similarly, in [38] and [39], examples of occluded images patches are used to train an SVM classifier to detect occluded areas of a testing face image.…”

Section: A Literature Reviewmentioning

confidence: 99%

Largest Matching Areas for Illumination and Occlusion Robust Face Recognition

McLaughlin

Crookes

2017

IEEE Trans. Cybern.

View full text Add to dashboard Cite

“…Then, new feature vectors y i ∈ ℜ f are defined by y i = W T x i where x i ∈ ℜ d . This method has been widely used in face recognition [4,5,28] leading to good recognition accuracies. Those results have encouraged some researchers to classify gender in the transformed PCA space [29] where very good performances are reported.…”

Section: Principal Component Analysismentioning

confidence: 99%

Face gender classification: A statistical study when neutral and distorted faces are combined for training and testing purposes

Andreu

García-Sevilla

Mollineda

2014

Image and Vision Computing

View full text Add to dashboard Cite

This paper presents a thorough study of gender classification methodologies performing on neutral, expressive and partially occluded faces, when they are used in all possible arrangements of training and testing roles. A comprehensive comparison of two representation approaches (global and local), three types of features (grey levels, PCA and LBP), three classifiers (1-NN, PCA+LDA and SVM) and two performance measures (CCR and d ′ ) is provided over single-and cross-database experiments. Experiments revealed some interesting findings, which were supported by three non-parametric statistical tests: when training and test sets contain different types of faces, local models using the 1-NN rule outperform global approaches, even those using SVM classifiers; however, with the same type of faces, even if the acquisition conditions are diverse, the statistical tests could not reject the null hypothesis of equal performance of global SVMs and local 1-NNs.

show abstract

Occlusion invariant face recognition using selective local non-negative matrix factorization basis images

Cited by 93 publications

References 14 publications

Partial Face Recognition: Alignment-Free Approach

Partial Face Recognition: Alignment-Free Approach

Largest Matching Areas for Illumination and Occlusion Robust Face Recognition

Face gender classification: A statistical study when neutral and distorted faces are combined for training and testing purposes

Contact Info

Product

Resources

About