Supervised Descent Method Viola-Jones and Skin Color Based Face Detection and Tracking

  Satbir Kaur,  Aayushi Chadha

Real-time face detection and tracking is a demanding problem in many application circumstances such as faces and gesture recognition in image processing and robotics etc. The ongoing work implements a robust method using Supervised Descent Method (SDM) based Viola-Jones and Skin color based segmentation, which can locate various faces at the same time under the varying environment of illumination and complex background in online (real time) by using face detection and tracking in conjunction with depth data. To achieve robustness, the Kanade-Lucas-Tomasi point tracker is used and dedicated to work on facial features by inserting knowledge about the configuration and visual features of the face. The resulting detection and tracking method is designed to get better from the loss of points due to tracking drift or temporary occlusion. Performance calculation experiments will be carried out on a set of video sequences of several facial expressions. It has been shown that using the base methodologies, some of the points are lost, whereas new method has been proposed to overcome the drawback.

Keywords- KLT, SDM.

Unique Identification Number - IJEDR1702265
Page Number(s) - 1689-1695
Pubished in - Volume 5 | Issue 2 | June 2017
DOI (Digital Object Identifier) -   
Publisher - IJEDR (ISSN - 2321-9939)

  Satbir Kaur,  Aayushi Chadha,   "Supervised Descent Method Viola-Jones and Skin Color Based Face Detection and Tracking", International Journal of Engineering Development and Research (IJEDR), ISSN:2321-9939, Volume.5, Issue 2, pp.1689-1695, June 2017, Available at :http://www.ijedr.org/papers/IJEDR1702265.pdf