Title :
Gradual training of cascaded shape regression for facial landmark localization and pose estimation
Author :
Wibowo, Moh Edi ; Tjondronegoro, Dian
Author_Institution :
Sci. & Eng. Fac., Queensland Univ. of Technol., Brisbane, QLD, Australia
Abstract :
Facial landmarks play an important role in face recognition. They serve different steps of the recognition such as pose estimation, face alignment, and local feature extraction. Recently, cascaded shape regression has been proposed to accurately locate facial landmarks. A large number of weak regressors are cascaded in a sequence to fit face shapes to the correct landmark locations. In this paper, we propose to improve the method by applying gradual training. With this training, the regressors are not directly aimed to the true locations. The sequence instead is divided into successive parts each of which is aimed to intermediate targets between the initial and the true locations. We also investigate the incorporation of pose information in the cascaded model. The aim is to find out whether the model can be directly used to estimate head pose. Experiments on the Annotated Facial Landmarks in the Wild database have shown that the proposed method is able to improve the localization and give accurate estimates of pose.
Keywords :
face recognition; feature extraction; image sequences; pose estimation; regression analysis; Wild database; cascaded shape regression; face alignment; face recognition; facial landmark localization; gradual training; landmark location correction; local feature extraction; pose estimation; Face; Feature extraction; Fitting; Shape; Training; Vectors; Facial landmark localization; cascaded shape regression; pose estimation;
Conference_Titel :
Multimedia and Expo (ICME), 2013 IEEE International Conference on
Conference_Location :
San Jose, CA
DOI :
10.1109/ICME.2013.6607601