Gender recognition from face images with trainable COSFIRE filters

This MATLAB code allows you to perform gender recognition from face images for a given dataset.

Gender recognition from face images is an important application in the fields of security, retail advertising and marketing. We propose a novel descriptor based on COSFIRE filters for gender recognition. A COSFIRE filter is trainable, in that its selectivity is determined in an automatic configuration process that analyses a given prototype pattern of interest. We demonstrate the effectiveness of the proposed approach on a new dataset called GENDER-FERET with 474 training and 472 test samples and achieve an accuracy rate of 93.7%. It also outperforms an approach that relies on handcrafted features and an ensemble of classifiers. Furthermore, we perform another experiment by using the images of the Labeled Faces in the Wild (LFW) dataset to train our classifier and the test images of the GENDER-FERET dataset for evaluation. This experiment demonstrates the generalization ability of the proposed approach and it also outperforms two commercial libraries, namely Face++ and Luxand.
Due to the random selection of features, the recognition rate that you will obtain with this script may not be precisely the same as the reported one in the paper. It should, however, be very close. Please read the readme.txt file before running the code.
You are kindly invited to use this Matlab implementation and cite the following articles:
1. George Azzopardi, Antonio Greco, and Mario Vento. "Fusion of domain-specific and trainable features for gender recognition from face images." IEEE Access, 2018.
2. George Azzopardi, Antonio Greco, and Mario Vento. "Gender recognition from face images with trainable COSFIRE filters." Advanced Video and Signal Based Surveillance (AVSS), 2016 13th IEEE International Conference on. (pp. 235-241) IEEE, 2016.
3. George Azzopardi and Nicolai Petkov, "Trainable COSFIRE filters for keypoint detection and pattern recognition", IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 35(2), pp. 490-503, 2013.
Papers:
https://www.researchgate.net/publication/324250575_Fusion_of_domain-specific_and_trainable_features_for_gender_recognition_from_face_images
https://www.researchgate.net/publication/306315110_Gender_recognition_from_face_images_with_trainable_COSFIRE_filters