Aguará: An Improved Face Recognition Algorithm through Gabor Filter Adaptation

Abstract

our work on the recognition stage, taking the detected face as the input to the algorithm. This stage can be separated We developed an EBGM-based algorithm that successin two steps: feature extraction, where important inforfully implements face recognition under constrained condimation for discrimination is saved, and the matching step, tions. A suitable adaptation of the Gaborfilters was foundwhere the recognition result is given with the aid of a face through a power spectral analisys (PSD) of the face imdatabase. ages. We outperformed the best-known implementations of Several face recognition methods have been proposed the EBGM algorithm in the FERET database. The results are during the last thirty years. In the vast literature on the topic comparable with those of the state of the art.(see [15] for a review), there are different classifications of the existing techniques. The following is one posible highlevel classification:

Face recognition using decimated redundant discrete wavelet transforms

“…For the FERET database, we compare DRDWT with HEC [7], aguar'a06NF [35], LGPDP [6], HGPP [37], Atan K-HLGPP [38], and MutualGabor-GDA [5]. The corresponding experimental results are presented in Table 5.…”

“…Until now, a large number of face recognition methods, such as appearance-based methods [1][2][3][4], Gabor wavelet methods [5][6][7]35,38], and machine learning-based methods [8,9], have been developed for still images. Zhao et al [10] provided a comprehensive survey of the studies of machine recognition of faces, categorized existing recognition techniques, and presented a detailed description of a number of representative methods.…”

A Review on Feature Extraction Techniques in Face Recognition

“…In the pattern recognition a descriptor is used to represent the features of the image. This method introduces a new technique using local descriptors for the feature extraction [7]. A block diagram of the used algorithm in this technique adopted from [18], has been shown in Figure 8.…”

“…In the second method local features are extracted, for example the location and local statistics of the eyes, nose and mouth are used in the recognition task. EBGM methods are included in this category [7].…”

“…In the third technique a face graph is represented to describe a face. The Gabor filter performs on nodes (coordinates of the nodes), at the end, the minimum average distance classifier corresponds each face graph with the faces in the data base and matching or not matching is decided upon [7]. In the fourth technique the face region is divided into small regions (blocks), and then a Local Binary Pattern (LBP) operator produces binary pattern histograms.…”