Using Facial Symmetry to Handle Pose Variations in Real-World 3D Face Recognition

Passalis, G.; Perakis, Panagiotis; Theoharis, T.; Kakadiaris, Ioannis A.

doi:10.1109/tpami.2011.49

Cited by 151 publications

(123 citation statements)

References 40 publications

(52 reference statements)

Supporting

Mentioning

117

Contrasting

Unclassified

Order By: Relevance

“…The ridge regression and lasso regression were also explored to overcome the problem of subspace based face representation and Gabor features were used to improve recognition rates. Perakis [21] introduced the 3D face recognition method to handle pose variation. The face model is reconstructed from partial face model and it produces 83.7% recognition rate.…”

Section: Related Workmentioning

confidence: 99%

Recognizing Expression Variant and Occluded Face Images Based on Nested HMM and Fuzzy Rule Based Approach

Ramalingam¹,

Dhanushkodi²

2016

View full text Add to dashboard Cite

The face recognition with expression and occlusion variation becomes the greatest challenge in biometric applications to recognize people. The proposed work concentrates on recognizing occlusion and seven kinds of expression variations such as neutral, surprise, happy, sad, fear, disgust and angry. During enrollment process, principle component analysis (PCA) detects facial regions on the input image. The detected facial region is converted into fuzzy domain data to make decision during recognition process. The Haar wavelet transform extracts features from the detected facial regions. The Nested Hidden markov model is employed to train these features and each feature of face image is considered as states in a Markov chain to perform learning among the features. The maximum likelihood for the input image was estimated by using Baum Welch algorithm and these features were kept on database. During recognition process, the expression and occlusion varied face image is taken as the test image and maximum likelihood for test image is found by following same procedure done in enrollment process. The matching score between maximum likelihood of input image and test image is computed and it is utilized by fuzzy rule based method to decide whether the test image belongs to authorized or unauthorized. The proposed work was tested among several expression varied and occluded face images of JAFFE and AR datasets respectively.

show abstract

Section: Related Workmentioning

confidence: 99%

Recognizing Expression Variant and Occluded Face Images Based on Nested HMM and Fuzzy Rule Based Approach

Ramalingam¹,

Dhanushkodi²

2016

View full text Add to dashboard Cite

show abstract

“…However, in both cases a rigid shape is used, which is an important limitation for facial modeling. In contrast, Passalis et al [14] present an algorithm that allows non-rigid deformations by using a deformable shape model. They exploit facial symmetry to account for possible occlusions, but still require the full visibility (and detection) of the landmarks of the left or right side.…”

Section: Related Workmentioning

confidence: 99%

3D Facial Landmark Localization Using Combinatorial Search and Shape Regression

Sukno

Waddington

Whelan

2012

Computer Vision – ECCV 2012. Workshops and Demonstrations

View full text Add to dashboard Cite

Abstract. This paper presents a method for the automatic detection of facial landmarks. The algorithm receives a set of 3D candidate points for each landmark (e.g. from a feature detector) and performs combinatorial search constrained by a deformable shape model. A key assumption of our approach is that for some landmarks there might not be an accurate candidate in the input set. This is tackled by detecting partial subsets of landmarks and inferring those that are missing so that the probability of the deformable model is maximized. The ability of the model to work with incomplete information makes it possible to limit the number of candidates that need to be retained, substantially reducing the number of possible combinations to be tested with respect to the alternative of trying to always detect the complete set of landmarks. We demonstrate the accuracy of the proposed method in a set of 144 facial scans acquired by means of a hand-held laser scanner in the context of clinical craniofacial dysmorphology research. Using spin images to describe the geometry and targeting 11 facial landmarks, we obtain an average error below 3 mm, which compares favorably with other state of the art approaches based on geometric descriptors.

show abstract

“…In the context of facial biometrics, landmarks can be used either as the primary source of information [7] or merely as a detection and/or normalization step [14], but in both cases the accuracy of localization is an important factor that can condition the final performance of the whole system. Thus, localization of facial landmarks in 3D can be considered a relevant topic in itself and has attracted considerable attention, including the deployment of annotated datasets to benchmark different algorithms.…”

Section: Introductionmentioning

confidence: 99%

“…The results from automatic approaches indicate that the most prominent facial landmarks can be located with errors varying between 3 and 6 mm [14], [19], [22], [25], [26], with some advantage to algorithms incorporating texture over those based purely on geometric features. However, these errors seem still far from the localization accuracy that might be achieved by means of manual annotations.…”

Section: Introductionmentioning

confidence: 99%

Compensating inaccurate annotations to train 3D facial landmark localization models

Sukno

Waddington

Whelan

2013

2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG)

View full text Add to dashboard Cite

Abstract-In this paper we investigate the impact of inconsistency in manual annotations when they are used to train automatic models for 3D facial landmark localization. We start by showing that it is possible to objectively measure the consistency of annotations in a database, provided that it contains replicates (i.e. repeated scans from the same person). Applying such measure to the widely used FRGC database we find that manual annotations currently available are suboptimal and can strongly impair the accuracy of automatic models learnt therefrom. To address this issue, we present a simple algorithm to automatically correct a set of annotations and show that it can help to significantly improve the accuracy of the models in terms of landmark localization errors. This improvement is observed even when errors are measured with respect to the original (not corrected) annotations. However, we also show that if errors are computed against an alternative set of manual annotations with higher consistency, the accuracy of the models constructed using the corrections from the presented algorithm tends to converge to the one achieved by building the models on the alternative, more consistent set.

show abstract

Using Facial Symmetry to Handle Pose Variations in Real-World 3D Face Recognition

Cited by 151 publications

References 40 publications

Recognizing Expression Variant and Occluded Face Images Based on Nested HMM and Fuzzy Rule Based Approach

Recognizing Expression Variant and Occluded Face Images Based on Nested HMM and Fuzzy Rule Based Approach

3D Facial Landmark Localization Using Combinatorial Search and Shape Regression

Compensating inaccurate annotations to train 3D facial landmark localization models

Contact Info

Product

Resources

About