Machine Vision and Applications

, Volume 26, Issue 4, pp 519–531

Glasses detection on real images based on robust alignment

  • Alberto Fernández
  • Rodrigo García
  • Rubén Usamentiaga
  • Rubén Casado
Original Paper

DOI: 10.1007/s00138-015-0674-1

Cite this article as:
Fernández, A., García, R., Usamentiaga, R. et al. Machine Vision and Applications (2015) 26: 519. doi:10.1007/s00138-015-0674-1

Abstract

Automatic glasses detection on real face images is a challenging problem due to different appearance variations. Nevertheless, glasses detection on face images has not been thoroughly investigated. In this paper, an innovative algorithm for automatic glasses detection based on Robust Local Binary Pattern and robust alignment is proposed. Firstly, images are preprocessed and normalized in order to deal with scale and rotation. Secondly, eye glasses region is detected considering that the nosepiece of the glasses is usually placed at the same level as the center of the eyes in both height and width. Thirdly, Robust Local Binary Pattern is built to describe the eyes region, and finally, support vector machine is used to classify the LBP features. This algorithm can be applied as the first step of a glasses removal algorithm due to its robustness and speed. The proposed algorithm has been tested over the Labeled Faces in the Wild database showing a 98.65 % recognition rate. Influences of the resolution, the alignment of the normalized images and the number of divisions in the LBP operator are also investigated.

Keywords

Glasses detectionFace alignmentRobust Local Binary PatternFace image processing

Copyright information

© Springer-Verlag Berlin Heidelberg 2015

Authors and Affiliations

  • Alberto Fernández
    • 1
  • Rodrigo García
    • 1
  • Rubén Usamentiaga
    • 2
  • Rubén Casado
    • 3
  1. 1.Fundación CTIC (Technological Center)Technological Scientific Park of GijónGijónSpain
  2. 2.Department of Computer Science and EngineeringUniversity of OviedoGijónSpain
  3. 3.Treelogic, Technological Scientific Park of AsturiasLlaneraSpain