Improvements to facial contour detection by hierarchical fitting and regression

There are many methods based on shape and texture models for detecting eye and mouth contour points from facial images. They reduce the false positive rate by utilizing a global model and adapting it for a given face. Changes to facial expressions are coupled with changes to the shapes of eyes and mouth, and a global facial model in itself cannot be adapted to all human facial expressions. Therefore, a hierarchical model fitting approach has been developed, whereby the global fitting captures the facial shape using the global model and the local fitting captures the each facial parts using these local models. This can detect facial contours with high accuracy for expressions to which the global model cannot be adapted.