Systems and Means of Informatics

November 2013, Volume 23, Issue 2, pp 50-61

PERSON CLASSIFICATION UPON FACE IMAGE BASED ON SIMILE CLASSIFIERS

  • V. S. Konushin
  • T. M. Lukina
  • A. I. Kuharenko
  • A.S. Konushin

Abstract

This paper presents a new approach to person classification from face images. It consists of two steps. First, similarity distances between a test face and faces from a known sample are computed. For this task special simile classifiers are trained. Similarity distances are estimated independently for each face fragment, e.g. nose, mouth, left or right eye, etc. Pixel colors, brightness, gradient norm and orientation are used as features both for each pixel and for whole fragment in form of a histogram or Gaussian distribution parameters. Person classification is performed based on these similarity distances. For classification SVM with RBF kernel is used. The proposed algorithm was tested on a gender classification task, using LFW and PubFig databases. The algorithm achieved 92.96% accuracy.

[+] References (21)

[+] About this article