Recognition of expression variant faces using masked log-Gabor features and Principal Component Analysis

In this article we propose a method for the recognition of faces with different facial expressions. For recognition we extract feature vectors by using log-Gabor filters of multiple orientations and scales. Using sliding window algorithm and variances -based masking these features are extracted at image regions that are less affected by the changes of facial expressions. Extracted features are passed to the Principal Component Analysis (PCA) -based recognition method. The results of face recognition experiments using expression variant faces showed that the proposed method could achieve higher recognition accuracy than many other methods. For development and testing we used facial images from the AR and FERET databases. Using facial photographs of more than one thousand persons from the FERET database the proposed method achieved 96.6-98.9% first one recognition rate and 0.2-0.6% Equal Error Rate (EER).

Face Recognition using Principal Component Analysis and Log-Gabor Filters

In this article we propose a novel face recognition method based on Principal Component Analysis (PCA) and Log-Gabor filters. The main advantages of the proposed method are its simple implementation, training, and very high recognition accuracy. For recognition experiments we used 5151 face images of 1311 persons from different sets of the FERET and AR databases that allow to analyze how recognition accuracy is affected by the change of facial expressions, illumination, and aging. Recognition experiments with the FERET database (containing photographs of 1196 persons) showed that our method can achieve maximal 97-98% first one recognition rate and 0.3-0.4% Equal Error Rate. The experiments also showed that the accuracy of our method is less affected by eye location errors and used image normalization method than of traditional PCA -based recognition method.

Computerized Face Detection and Recognition

This publication presents methods for face detection, analysis and recognition: fast normalized cross-correlation (fast correlation coefficient) between multiple templates based face pre-detection method, method for detection of exact face contour based on snakes and Generalized Gradient Vector Flow field, method for combining recognition algorithms based on Cumulative Match Characteristics in order to increase recognition speed and accuracy, and face recognition method based on Principal Component Analysis of the Wavelet Packet Decomposition allowing to use PCA - based recognition method with large number of training images. For all the methods are presented experimental results and comparisons of speed and accuracy with large face databases.