A Holistic Automatic Method for Grouping Facial Features Based on Their Appearance

Classification or typology systems used to categorize different human body parts exist for many years. Nevertheless, there are very few taxonomies of facial features. A reason for this might be that classifying isolated facial features is difficult for human observers. Previous works reported low inter-observer and intra-observer agreement in the evaluation of facial features. Therefore, this work presents a computer-based procedure to classify facial features based on their global appearance automatically. First, facial features are located, extracted and aligned using a facial landmark detector. Then, images are characterized using the eigenpictures approach. We then perform a clustering of each type of facial feature using as input the weights extracted from the eigenpictures approach. Finally, we validate the obtained clusterings with humans. This procedure deals with the difficulties associated with classifying features using judgments from human observers and facilitates the development of taxonomies of facial features. Taxonomies obtained with this procedure are presented for eyes, noses and mouths.