Facial Expression Analysis from Hand Drawn Sketches for Human Figure Drawing Psychological Test

Abstract

Human Figure Drawing Test (HFDT) is a popular instrument for the assessment of cognitive functioning of individuals. This and other similar brain functioning tests are used by psychologists to understand feelings, personality and reactions of individuals to different circumstances. Among different expressive behaviors, sketching is one of the simplest ways to study the feelings and personality of an individual. Not only subjects find he sketching activity interesting, it represents a good media for projection of psychological features of adults/children covering the literate as well as the illiterate population. Among different aspects of the HFDT, the focus of this study lies on the face of the drawn figure. A computerized system that analyzes the hand-drawn facial images to extract the expressions from the image is developed. Sketch of human face is drawn by the subject and then fed to the system, the image is then binarized and segmented into different facial components. Features (Gray level co-occurrence matrices, local binary patterns and histogram of oriented gradients) computed from the facial components are used to train an SVM classifier to learn to distinguish between four expression classes, happy, sad, angry and neutral. The system evaluated on a custom developed database of sketches realized promising results. The developed system could serve as a useful module toward development of a complete automated system to score human figure drawing test.