Automatic local Gabor Features extraction for face recognition

TL;DR

This paper introduces a face recognition system that automatically detects facial features using a new algorithm, compares geometric and Gabor features, and demonstrates the superior performance of Gabor coefficients through experiments.

Contribution

A novel algorithm for automatic facial feature detection and a comparative analysis of geometric and Gabor features for face recognition.

Findings

Gabor coefficients outperform geometric distances in recognition accuracy.

The proposed system effectively detects and recognizes faces in color images.

Experimental results validate the importance of Gabor features for face recognition.

Abstract

We present in this paper a biometric system of face detection and recognition in color images. The face detection technique is based on skin color information and fuzzy classification. A new algorithm is proposed in order to detect automatically face features (eyes, mouth and nose) and extract their correspondent geometrical points. These fiducial points are described by sets of wavelet components which are used for recognition. To achieve the face recognition, we use neural networks and we study its performances for different inputs. We compare the two types of features used for recognition: geometric distances and Gabor coefficients which can be used either independently or jointly. This comparison shows that Gabor coefficients are more powerful than geometric distances. We show with experimental results how the importance recognition ratio makes our system an effective tool for automatic face detection and recognition.