Fame-a flexible appearance modeling environment

Stegmann, Mikkel Bille; Ersbøll, Bjarne Kjær; Larsen, Rasmus

doi:10.1109/tmi.2003.817780

Cited by 258 publications

(147 citation statements)

References 36 publications

Supporting

Mentioning

141

Contrasting

Order By: Relevance

“…The images for evaluating the proposed method are collected from multiple publicly available databases, including the FRGC v2.0 database [14], the FERET database [15], the IMM database [17], and the Labeled Faces in the Wild (LFW) database [9]. The collected images (see examples in Figure 3) are partitioned distinctively into four subsets.…”

Section: Methodsmentioning

confidence: 99%

Face Alignment Using a Ranking Model based on Regression Trees

Gao

Ekenel

Stiefelhagen

2012

Procedings of the British Machine Vision Conference 2012

View full text Add to dashboard Cite

In this work, we exploit the regression trees-based ranking model, which has been successfully applied in the domain of web-search ranking, to build appearance models for face alignment. The model is an ensemble of regression trees which is learned with gradient boosting. The MCT (Modified Census Transform) as well as its unbinarized version PCT (Pseudo Census Transform) are used as features due to their robustness to illumination changes. To avoid the overfitting problem in gradient boosting, we use random trees to initialize the boosting. The Nelder Mead's simplex method is applied for fitting the learned model. We compare the proposed regression trees-based pointwise ranking model to pairwise ranking model. Experiments show that the proposed model improves both robustness and accuracy for face alignment.

show abstract

Section: Methodsmentioning

confidence: 99%

Face Alignment Using a Ranking Model based on Regression Trees

Gao

Ekenel

Stiefelhagen

2012

Procedings of the British Machine Vision Conference 2012

View full text Add to dashboard Cite

show abstract

“…Given the high difference in attitude, it has been necessary to train a model for the upper camera and a model for the lower camera. The software implementation is provided by an Application Programming Interface dedicated to AAM provided by [38], [39].…”

Section: Biometric Algorithmmentioning

confidence: 99%

Metrological characterization of 3D biometric face recognition systems in actual operating conditions

et al. 2017

View full text Add to dashboard Cite

<p>Nowadays, face recognition systems are going to widespread in many fields of application, from automatic user login for financial activities and access to restricted areas, to surveillance for improving security in airports and railway stations, to cite a few.<br />In such scenarios, the architectures based on stereo vision and 3D reconstruction of the face are going to assume a predominant role because they can generally assure a better reliability than solutions based on a single camera (which make use of a single image instead of a couple of images). To realize such systems, different architectures can be considered by varying the positioning of the pair of cameras with respect to the face of the subject to be identified, as well as both kind and resolution of camera considered. These parameters can affect the correct decision rate of the system in classifying the input face, especially in presence of image uncertainty.<br />In this paper, several 3D architectures differing in camera specifications and geometrical positioning of the camera pair (with respect to the input face) are realized and compared. The detection of facial features in the images is made by adopting a popular method based on the Active Appearance Model (AAM) algorithm. 3D position of facial features is then obtained by means of stereo triangulation. The performance of the realized systems has been compared in terms of sensitivity to the quantities of influence and related uncertainty, and of typical indexes for the analysis of classification systems. Main results of such comparison show that the best performance can be reached by reducing the distance between cameras and subject to be identified and by minimizing the horizontal angle between the plane containing the camera pair axis and the face to be identified.</p>

show abstract

“…Hence, the line that connects both mouth corners is expected to be detected. Finally, these corners are taken as initialization points for a 15-point Active Appearance Model fitting process, that was previously trained with more than 350 manually-marked mouth images using the code provided by Stegmann et al [13] in conjunction with the OpenCV Library [2]. By using this technique, we were going to segment mouth regions, some of which are illustrated in Figure 2. …”

Section: Mouth Template Segmentationmentioning

confidence: 99%