Head pose estimation based on fuzzy systems using facial geometric features
- 20 March 2017
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 777-782
Abstract
Head pose estimation has many applications in the field of computer vision and it is a useful part of pose-invariant face recognition. In this paper, we propose a novel method to estimate head pose (yaw and pitch rotations) based on fuzzy systems by facial geometric features. Firstly, seven certain points are selected on face. These points includes some main properties. They are all visible even for large pose variations. Since no point is selected on mouth region, obviously this method is insensitive to facial expression. By these points, some ratios and angles are computed as the inputs of two fuzzy systems. The output data of these systems are the corresponding yaw and pitch angles. After training them and determining some parameters, they are used for head yaw and pitch estimation. This method is evaluated on two databases and the experimental results demonstrate that our proposed method is strongly accurate, robust, and beneficial for head pose estimation.Keywords
This publication has 20 references indexed in Scilit:
- Hierarchical temporal graphical model for head pose estimation and subsequent attribute classification in real-world videosComputer Vision and Image Understanding, 2015
- Head Pose Estimation Based On Detecting Facial FeaturesInternational Journal of Multimedia and Ubiquitous Engineering, 2015
- CovGa: A novel descriptor based on symmetry of regions for head pose estimationNeurocomputing, 2014
- Face pose estimation with automatic 3D model creation in challenging scenariosImage and Vision Computing, 2012
- Head Pose Estimation in Computer Vision: A SurveyIEEE Transactions on Pattern Analysis and Machine Intelligence, 2008
- A two-stage head pose estimation framework and evaluationPattern Recognition, 2008
- The CAS-PEAL Large-Scale Chinese Face Database and Baseline EvaluationsIEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans, 2007
- Face pose estimation based on 3D detection of pupils and nostrils2006
- 3D Head Pose Estimation with Symmetry Based Illumination Model in Low Resolution VideoLecture Notes in Computer Science, 2004
- Fuzzy setsInformation and Control, 1965