On Local Features for GMM Based Face Verification

Sanderson, Conrad; Saban, M.; Gao, Yongsheng

doi:10.1109/icita.2005.194

Cited by 12 publications

(9 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A further study of this feature extraction technique is given in Ref. [45]. The degree of overlap (N O ) has two effects: the first is that as overlap is increased the spatial area used to derive one feature vector is decreased (see Fig.…”

Section: Dct-based Systemmentioning

confidence: 99%

On transforming statistical models for non-frontal face verification

Sanderson

Bengio

Gao

2006

Pattern Recognition

View full text Add to dashboard Cite

We address the pose mismatch problem which can occur in face verification systems that have only a single (frontal) face image available for training. In the framework of a Bayesian classifier based on mixtures of gaussians, the problem is tackled through extending each frontal face model with artificially synthesized models for non-frontal views. The synthesis methods are based on several implementations of maximum likelihood linear regression (MLLR), as well as standard multi-variate linear regression (LinReg). All synthesis techniques rely on prior information and learn how face models for the frontal view are related to face models for non-frontal views. The synthesis and extension approach is evaluated by applying it to two face verification systems: a holistic system (based on PCA-derived features) and a local feature system (based on DCT-derived features). Experiments on the FERET database suggest that for the holistic system, the LinReg-based technique is more suited than the MLLR-based techniques; for the local feature system, the results show that synthesis via a new MLLR implementation obtains better performance than synthesis based on traditional MLLR. The results further suggest that extending frontal models considerably reduces errors. It is also shown that the local feature system is less affected by view changes than the holistic system; this can be attributed to the parts based representation of the face, and, due to the classifier based on mixtures of gaussians, the lack of constraints on spatial relations between the face parts, allowing for deformations and movements of face areas.

show abstract

Section: Dct-based Systemmentioning

confidence: 99%

On transforming statistical models for non-frontal face verification

Sanderson

Bengio

Gao

2006

Pattern Recognition

View full text Add to dashboard Cite

show abstract

“…Once a face representation is chosen, a set of feature vectors needs to be extracted from the computed data representation and fed to the GMM construction procedure. A popular tool for this task is DCT, which has proven to be suitable for block-based feature extraction from both, 2D images [33, 34] as well as 3D range images [5]. While several variants of DCT-based feature extraction techniques were presented in the literature (see for example [5, 34], all of them have the same initial stage consisting of analysing facial data block-by-block, with a configurable amount of overlap between neighbouring blocks.…”

Section: Frameworkmentioning

confidence: 99%

“…A popular tool for this task is DCT, which has proven to be suitable for block-based feature extraction from both, 2D images [33, 34] as well as 3D range images [5]. While several variants of DCT-based feature extraction techniques were presented in the literature (see for example [5, 34], all of them have the same initial stage consisting of analysing facial data block-by-block, with a configurable amount of overlap between neighbouring blocks. In this paper we use the most common variant of DCT-based feature extraction, where each individual image block is decomposed in terms of 2D DCT basis functions and the feature vector x belonging to the currently analysed block is formed by considering the first d DCT coefficients, i.e., x = [ c i ] d i =0 , where c i is the i -th DCT coefficient.…”

Section: Frameworkmentioning

confidence: 99%

See 1 more Smart Citation

Towards Robust 3D Face Verification Using Gaussian Mixture Models

Krizaj

Dobrišek

2012

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

This paper focuses on the use of Gaussian Mixture models (GMM) for 3D face verification. A special interest is taken in practical aspects of 3D face verification systems, where all steps of the verification procedure need to be automated and no meta-data, such as preannotated eye/nose/mouth positions, is available to the system. In such settings the performance of the verification system correlates heavily with the performance of the employed alignment (i.e., geometric normalization) procedure. We show that popular holistic as well as local recognition techniques, such as principal component analysis (PCA), or Scale-invariant feature transform (SIFT)-based methods considerably deteriorate in their performance when an "imperfect" geometric normalization procedure is used to align the 3D face scans and that in these situations GMMs should be preferred. Moreover, several possibilities to improve the performance and robustness of the classical GMM framework are presented and evaluated: i) explicit inclusion of spatial information, during the GMM construction procedure, ii) implicit inclusion of spatial information during the GMM construction procedure and iii) on-line evaluation and possible rejection of local feature vectors based on their likelihood. We successfully demonstrate the feasibility of the proposed modifications on the Face Recognition Grand Challenge data set.

show abstract

“…The second approach involves obtaining illumination-robust features. A representative approach was proposed by Sanderson et al (2005) [19]. They applied discrete cosine transform (DCT) and added more delta coefficients to feature vectors: DCT-mod, DCT-mod-delta, and DCT-mod2.…”

Section: Introductionmentioning

confidence: 99%

Visual Observation Confidence based GMM Face Recognition robust to Illumination Impact in a Real-world Database

2016

KSII TIIS

View full text Add to dashboard Cite

The GMM is a conventional approach which has been recently applied in many face recognition studies. However, the question about how to deal with illumination changes while ensuring high performance is still a challenge, especially with real-world databases. In this paper, we propose a Visual Observation Confidence (VOC) measure for robust face recognition for illumination changes. Our VOC value is a combined confidence value of three measurements: Flatness Measure (FM), Centrality Measure (CM), and Illumination Normality Measure (IM). While FM measures the discrimination ability of one face, IM represents the degree of illumination impact on that face. In addition, we introduce CM as a centrality measure to help FM to reduce some of the errors from unnecessary areas such as the hair, neck or background. The VOC then accompanies the feature vectors in the EM process to estimate the optimal models by modified-GMM training. In the experiments, we introduce a real-world database, called KoFace, besides applying some public databases such as the Yale and the ORL database. The KoFace database is composed of 106 face subjects under diverse illumination effects including shadows and highlights. The results show that our proposed approach gives a higher Face Recognition Rate (FRR) than the GMM baseline for indoor and outdoor datasets in the real-world KoFace database (94% and 85%, respectively) and in ORL, Yale databases (97% and 100% respectively).

show abstract

On Local Features for GMM Based Face Verification

Cited by 12 publications

References 18 publications

On transforming statistical models for non-frontal face verification

On transforming statistical models for non-frontal face verification

Towards Robust 3D Face Verification Using Gaussian Mixture Models

Visual Observation Confidence based GMM Face Recognition robust to Illumination Impact in a Real-world Database

Contact Info

Product

Resources

About