Eye Landmarks Detection Technology for Facial Micro-Expressions Analysis

In the paper the problem of the facial microexpressions analysis in the image sequence is considered. One of the important tasks of such analysis is the facial landmarks detection. The distinctive characteristics of the main categories of the modern methods to solve this task are indicated. The selection of the Spontaneous Actions and Micro-Movements (SAMM) dataset for experiments is proved. In this dataset the Facial Action Coding System (FACS) is used. The results of the landmarks detection in the areas of eyes obtained in two ways are represented, i.e. using the known Active Shape Model (ASM) and using the technology developed by the authors. The proposed technology makes it possible to detect the eye landmarks by the simple tools. The main stages of this technology are described. Its advantages in comparison with the ASM method are highlighted.