Article: Viewpoint invariant model for face detection Journal: International Journal of Computational Vision and Robotics (IJCVR) 2013 Vol.3 No.3 pp.182 - 196 Abstract: In this work, we have developed a face invariant model for accurate face detection in images where faces can present viewpoint changes. The face model is based on learning a relation between local features and a face invariant. A probabilistic model learned from a training set captures the relationship between the appearance of facial features and the geometry of face invariant. It is then used to infer a face instance in new image. We use the local invariant features which have the high performances to distinguish objects appearance. The facial features are recognised by an appearance classifier which combines an EM classification and a probabilistic matching. Then, the geometrical parameters are predicted to locate face invariants and a hierarchical clustering method corrects the geometric error of the position of invariants. The geometric classification uses an aggregate value to construct clusters of invariants. The probabilities of facial appearance features are computed to select the best cluster and thus to locate face with arbitrary viewpoint in image. We evaluate our generic invariant by testing it in face detection experiments on different databases. The experimental results show that our face invariant model gives highly accurate face localisation. Inderscience Publishers - linking academia, business and industry through research

Title: Viewpoint invariant model for face detection

Authors: Mokhtar Taffar; Serge Miguet; Mohammed Benmohammed

Addresses: Computer Science Department, Faculty of Sciences and Technology, University of Jijel, BP 98, Campus Ouled Aissa, 18000, Jijel, Algeria ' LIRIS, CNRS UMR 5205, Université Lyon 2, 5, av. Pierre Mendes-France, Bât. C, Bur. 123, 69676, Bron, France ' LIRE Lab., University of Constantine, BP 325, Route Ain El-Bey, 25017, Constantine, Algeria

Abstract: In this work, we have developed a face invariant model for accurate face detection in images where faces can present viewpoint changes. The face model is based on learning a relation between local features and a face invariant. A probabilistic model learned from a training set captures the relationship between the appearance of facial features and the geometry of face invariant. It is then used to infer a face instance in new image. We use the local invariant features which have the high performances to distinguish objects appearance. The facial features are recognised by an appearance classifier which combines an EM classification and a probabilistic matching. Then, the geometrical parameters are predicted to locate face invariants and a hierarchical clustering method corrects the geometric error of the position of invariants. The geometric classification uses an aggregate value to construct clusters of invariants. The probabilities of facial appearance features are computed to select the best cluster and thus to locate face with arbitrary viewpoint in image. We evaluate our generic invariant by testing it in face detection experiments on different databases. The experimental results show that our face invariant model gives highly accurate face localisation.

Keywords: local invariant features; probabilistic matching; learning models; object class recognition; object appearance modelling; face detection; facial invariant models; biometrics; facial features; face localisation; feature recognition.

DOI: 10.1504/IJCVR.2013.056039

International Journal of Computational Vision and Robotics, 2013 Vol.3 No.3, pp.182 - 196

Accepted: 29 Jan 2013
Published online: 18 Jul 2014 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: Viewpoint invariant model for face detection

Keep up-to-date