Advanced Search
Wang Kejun, Zou Guofeng, Fu Guixia, Yuan Lei. An Approach to Fast Eye Location and Face Plane Rotation Correction[J]. Journal of Computer-Aided Design & Computer Graphics, 2013, 25(6): 865-872,879.
Citation: Wang Kejun, Zou Guofeng, Fu Guixia, Yuan Lei. An Approach to Fast Eye Location and Face Plane Rotation Correction[J]. Journal of Computer-Aided Design & Computer Graphics, 2013, 25(6): 865-872,879.

An Approach to Fast Eye Location and Face Plane Rotation Correction

  • In order to overcome the problem of bad effect of recognition due to the face plane rotation,an effective method of eye location and face plane rotation correction is proposed in this paper.First the eye classifier based on the AdaBoost algorithm is used to quickly detect the eye candidate region.Then according to the position and proportion of eyes in the candidate region,the candidate region is divided into three sub-regions with the same width,which are the left-eye sub-region,the intermediate sub-region and right-eye sub-region respectively.We calculate the integral projection for the left-eye sub-region and right-eye sub-region to accurately locate the eyes position.After eyes location,the calculation method of the rotation angle is proposed when the center of the image is used as the reference point,and the plane rotation correction of the face image is realized combined with image rotation formula.The experimental results show that the proposed method can prevent the emergence of pseudo feature points,and avoid the influences of the spectacle border and spectacle frame.The method improves the eyes location accuracy and realizes the face plane rotation correction;it has better real-time performance and practical value.
  • loading

Catalog

    Turn off MathJax
    Article Contents

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return