Three Dimensional Face Recognition Using SVM Classifier

Mousavi, M.H.; Faez, Karim; Asghari, Abazar

doi:10.1109/icis.2008.77

Cited by 26 publications

(10 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…First, some methods, such as Moussavi et al [11], Mahoor et al [9] and Li et al [8], are interested in adopting low-level geometric features to face recognition for several reasons. They claim that they spend less effort in extracting features unlike the methods that are based on extracting high-level geometric features, e.g., shapes of facial curves [13], concave and convex facial regions [1], partial face regions [5] [10], or deformation distance metrics [7].…”

Section: Introduction and Related Workmentioning

confidence: 99%

Pose and Expression-Invariant 3D Face Recognition using Elastic Radial Curves

Drira¹,

Amor²,

Daoudi³

et al. 2010

Procedings of the British Machine Vision Conference 2010

View full text Add to dashboard Cite

In this paper we explore the use of shapes of elastic radial curves to model 3D facial deformations, caused by changes in facial expressions. We represent facial surfaces by indexed collections of radial curves on them, emanating from the nose tips, and compare the facial shapes by comparing the shapes of their corresponding curves. Using a past approach on elastic shape analysis of curves, we obtain an algorithm for comparing facial surfaces. We also introduce a quality control module which allows our approach to be robust to pose variation and missing data. Comparative evaluation using a common experimental setup on GAVAB dataset, considered as the most expression-rich and noise-prone 3D face dataset, shows that our approach outperforms other state-of-the-art approaches.

show abstract

Section: Introduction and Related Workmentioning

confidence: 99%

Pose and Expression-Invariant 3D Face Recognition using Elastic Radial Curves

Drira¹,

Amor²,

Daoudi³

et al. 2010

Procedings of the British Machine Vision Conference 2010

View full text Add to dashboard Cite

show abstract

“…However, especially in non cooperative scenarios, occlusion variations complicate the task of identifying subjects from their face images. In this paper, we have presented a fully automatic 3D face recognizer [13,14,15], which is robust to facial occlusions. For the alignment of occluded surfaces, we utilized a ICP registration scheme.…”

Section: Resultsmentioning

confidence: 99%

Robust 3D Face Recognition in Presence of Pose and Partial Occlusions or Missing Parts

Bagchi¹,

Bhattacharjee²,

Nasipuri³

2014

IJFCST

View full text Add to dashboard Cite

In this paper, we propose a robust 3D face recognition system which can handle pose as well as occlusions in real world. The system at first takes as input, a 3D range image, simultaneously registers it using ICP(Iterative Closest Point) algorithm. ICP used in this work, registers facial surfaces to a common model by minimizing distances between a probe model and a gallery model. However the performance of ICP relies heavily on the initial conditions. Hence, it is necessary to provide an initial registration, which will be improved iteratively and finally converge to the best alignment possible. Once the faces are registered, the occlusions are automatically extracted by thresholding the depth map values of the 3D image. After the occluded regions are detected, restoration is done by Principal Component Analysis (PCA). The restored images, after the removal of occlusions, are then fed to the recognition system for classification purpose. Features are extracted from the reconstructed non-occluded face images in the form of face normals. The experimental results which were obtained on the occluded facial images from the Bosphorus 3D face database, illustrate that our occlusion compensation scheme has attained a recognition accuracy of 91.30%.

show abstract

“…It is the sparse representation framework that facilitates the use of low-level features for robust face recognition in our approach. Note that methods based on range images [17,20] can also be viewed as imposing uniform sampling pattern onto 3D faces. However, the acquisition of range images involves an R 3 → R 2 projection, which is not pose-invariant.…”

Section: Background and Motivationmentioning

confidence: 99%

“…The marginal differences between these curves demonstrate the robustness of our proposed method to expressions. [17] 61 95% neutral 72.0% expressioned Berretti et al [3] 61 94% neutral 81% expression Mousavi et al [20] 61 91% overall…”

Section: Recognition Using All Feature Typesmentioning

confidence: 99%

“…For a fair comparison, we only compare the rates of recognizing the GavabDB portion of our dataset, whereas our search space is 120 individuals, larger than others. Note that in [19] and [20], the dataset includes the two faces "looking up" and "looking down", which are not included in our test. Compared with existing methods, our proposed method has better performance in handling expressions.…”

Section: Recognition Using All Feature Typesmentioning

confidence: 99%

See 1 more Smart Citation