A Genetic algorithm for creating a set of color spaces for ear authentication

[abstract]

An ensemble of 2D ear matchers is built by training each matcher using a set of Gabor filters and color spaces selected by a genetic algorithm (GA). First, using gray level images, we select the best Gabor filters by applying Sequential Forward Floating Selection. Second, using the RGB images, several color spaces are obtained as follows: a color model is defined as ?·R+?·G+?·B, where the parameters are selected using a GA. The optimization function is the equal error rate obtained considering the previously selected filter that was used. Finally, an ensemble of 1-nearest neighbor matchers use the color spaces and filters for classification. The performance of the proposed approach is measured using the well known Notre-Dame EAR dataset. To create the color spaces, the dataset is divided into training and testing sets using ear samples from different individuals. System parameters are selected using samples of individuals that belong to the training set. The method is then tested on the testing set. In this way, we can consider our protocol a reliable blind testing protocol. Our system obtains a rank-1 of ~81% and a rank-5 of ~92%.