Face alignment using a ranking model based on regression trees

Hua Gao, Hazim Kemal Ekenel, Rainer Stiefelhagen

Research output: Contribution to conferencePaperpeer-review

5 Citations (Scopus)

Abstract

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.

Original languageEnglish
DOIs
Publication statusPublished - 2012
Event2012 23rd British Machine Vision Conference, BMVC 2012 - Guildford, Surrey, United Kingdom
Duration: 3 Sept 20127 Sept 2012

Conference

Conference2012 23rd British Machine Vision Conference, BMVC 2012
Country/TerritoryUnited Kingdom
CityGuildford, Surrey
Period3/09/127/09/12

Fingerprint

Dive into the research topics of 'Face alignment using a ranking model based on regression trees'. Together they form a unique fingerprint.

Cite this