Facial Expression Recognition Utilizing Local Direction-Based Robust Features and Deep Belief Network

Abstract

Emotional health plays very vital role to improve people's quality of lives, especially for the elderly. Negative emotional states can lead to social or mental health problems. To cope with emotional health problems caused by negative emotions in daily life, we propose efficient facial expression recognition system to contribute in emotional healthcare system. Thus, facial expressions play a key role in our daily communications, and recent years have witnessed a great amount of research works for reliable facial expressions recognition (FER) systems. Therefore, facial expression evaluation or analysis from video information is very challenging and its accuracy depends on the extraction of robust features. In this paper, a unique feature extraction method is presented to extract distinguished features from the human face. For person independent expression recognition, depth video data is used as input to the system where in each frame, pixel intensities are distributed based on the distances to the camera. A novel robust feature extraction process is applied in this work which is named as local directional position pattern (LDPP). In LDPP, after extracting local directional strengths for each pixel such as applied in typical local directional pattern (LDP), top directional strength positions are considered in binary along with their strength sign bits. Considering top directional strength positions with strength signs in LDPP can differentiate edge pixels with bright as well as dark regions on their opposite sides by generating different patterns whereas typical LDP only considers directions representing the top strengths irrespective of their signs as well as position orders (i.e., directions with top strengths represent 1 and rest of them 0), which can generate the same patterns in this regard sometimes. Hence, LDP fails to distinguish edge pixels with opposite bright and dark regions in some cases which can be overcome by LDPP. Moreover, the LDPP capabilities are extended through principal component analysis (PCA) and generalized discriminant analysis (GDA) for better face characteristic illustration in expression. The proposed features are finally applied with deep belief network (DBN) for expression training and recognition.