Facial Feature Detection using Conditional Regression Forests


Vural G., Gokmen M.

23nd Signal Processing and Communications Applications Conference (SIU), Malatya, Turkey, 16 - 19 May 2015, pp.1309-1312 identifier

  • Publication Type: Conference Paper / Full Text
  • City: Malatya
  • Country: Turkey
  • Page Numbers: pp.1309-1312

Abstract

Even though there are many studies on facial feature detection from two dimensional still images, real-time facial feature detection is one of fresh fields. In this paper, a structure including Conditional Regression Forest and Local Zernike Moments is introduced to solve this problem. In this study, regression forests learn the relations between facial image patches and location of facial feature points conditional to head pose. This method is evaluated on Labeled Faces in the Wild (LFW) [2] database and promising results are obtained.