A Comparative Study On Textures Descriptors In Facial Gender Classification

A Comparative Study On Textures Descriptors In Facial Gender Classification

An example of level 3 Multi-Block and Multi-Level

Authors:

Fares Bougourzi1, Salah Eddine Bekhouche2,Mohammed En-nadhir Zighem2, Azeddine Benlamoudi3, Abdelkrim Ouafi2 and Abdelmalik Taleb-Ahmed4,

  1. Laboratory of LTII, University of Béjaïa, Algeria
  2. Laboratory of LESIA, University of Biskra, Algeria
  3. Laboratory of LAGE, University of Ouargla, Algeria
  4. Laboratory of LAMIH, University of Valenciennes, France

Abstract:

The aim of this work is to investigate global and local image descriptors impact on facial gender classification by carrying out an independent comparative study among several texture descriptors algorithms.
In this paper, we consider three global descriptors namely, Gray-Level Co-Occurrence Matrix (GLCM), Gabor Wavelet Transform (GWT) and Autocorrelation Function (ACF). On the other hand, we consider four local image descriptors called, Local Binary Patterns (LBP), Local Directional Pattern (LDP), Local Phase Quantization (LPQ) and Binarized Statistical Image Features (BSIF).
The experimental comparison proofs that the local image descriptors are more efficient than the global ones in facial gender classification. All the experiments conducted on the Image of Groups (IoG) database.

Please cite as:

@InProceedings{CGE10GENDER,
Title = {A Comparative Study On Textures Descriptors In Facial Gender Classification},
Author = {Bougourzi, F. and Bekhouche, SE. and Zighem, ME and Benlamoudi, A. and Ouafi, A. and Taleb-Ahmed A.},
Booktitle = {10 ème Conférence sur le Génie Electrique},
Year = {2017},
month={Apr},
}

Downloads:

Paper: PDF
Database: IoG