Ëàáîðàòîðèÿ êîìïüþòåðíîé ãðàôèêè è ìóëüòèìåäèà

We present a new approach to face classification using simile classifiers. Unlike other methods we explicitly estimate similarity distances to the known reference people and use these similarities as high-level features for the classification of the test face.
We test our algorithm on gender classification problem. Our algorithm shows classification accuracy of 92.96% on LFW dataset.