Taimori, Ali, Behrad, Alireza, Ghassemian, Hassan (2010). Automatic Human Face Detection and Tracking using Cascaded Classifiers and Deformable Meshes. , 10(1), 126-109.
Ali Taimori; Alireza Behrad; Hassan Ghassemian. "Automatic Human Face Detection and Tracking using Cascaded Classifiers and Deformable Meshes". , 10, 1, 2010, 126-109.
Taimori, Ali, Behrad, Alireza, Ghassemian, Hassan (2010). 'Automatic Human Face Detection and Tracking using Cascaded Classifiers and Deformable Meshes', , 10(1), pp. 126-109.
Taimori, Ali, Behrad, Alireza, Ghassemian, Hassan Automatic Human Face Detection and Tracking using Cascaded Classifiers and Deformable Meshes. , 2010; 10(1): 126-109.

Automatic Human Face Detection and Tracking using Cascaded Classifiers and Deformable Meshes

The Modares Journal of Electrical Engineering
Article 7, Volume 10, Issue 1, 2010, Pages 126-109    PDF (1.15 M)
Authors
Ali Taimori1; Alireza Behrad1; Hassan Ghassemian* 2
1Shahed Univ
2Tarbiat Modares Univ
Abstract
In this paper, we propose a novel method for fully automatic detection and tracking of human heads and faces in video sequences. The proposed algorithm consists of two modules: a face detection module and a face tracking module. The Detection module, detects the face region and approximates it with an ellipse at the first frame using a modified version of AdaBoost cascaded classifier. The detection module is capable of considering the 2-D head pose rotation. The tracking module utiliyes a combination of deformable mesh energy minimization and feature matching approaches. In order to track a face, features are extracted in the face region to tessellate the human face with triangular unstructured meshes. For tracking a mesh, it is necessary to define mesh energies including internal and external energies. We have used new energy definitions for both the internal and the external energies which can accurately track rigid and non-rigid motions of a face and facial features at subsequent frames. We tested the proposed method with different video samples like cluttered backgrounds, partial illumination variations, put on glasses, and 2-D and/or 3-D rotating and translating heads. The experimental results showed that the algorithm is rotation insensitive and has high accuracy, stability and also has convergence for face detection and tracking.
Keywords
Face Detection and Tracking; Head Pose Estimation; AdaBoost Learning; Face Features; Feature Matching; Deformable Meshes
Statistics
Article View: 134
PDF Download: 82
Statistics
Number of Journals45
Number of Issues2,196
Number of Articles24,877
Article View28,771,540
PDF Download18,603,454