الفهرس | Only 14 pages are availabe for public view |
Abstract Recently, there is a growing need for real–time facial expression system that can effectively deal with computer vision and pattern recognition. Computers become an increasing part of human social circle through human computer interaction (HCI). “Human-Computer Interaction in MIS is concerned with the ways humans interact with information, technologies, and tasks, especially in business, managerial, organizational, and cultural contexts”. HCI is a bidirectional process. Human face is the richest source of human emotions. A major challenge for real – time facial expression recognition is achieving optimal pre-processing, feature extraction or selection, and classification, particularly under conditions of input data variability. To attain successful recognition performance, most current expression recognition approaches require some control over the imaging conditions. This thesis proposes a real – time facial expression recognition framework to provide the following capabilities: (1) PCA method is used to solve the problem of space complexity resulted from high dimensionality, (2) The problem of dealing with abnormal faces without representatives in the database. This is solved by allowing the user to feed his or her facial expressions states as reference templates either form files or captured from cam. Implementation of the proposed real – time facial expressions recognition system shows that the performance is quite robust against changes in illumination, wardrobe, facial expressions and additive noise, blurred images (filters), resizing, shifting and even with some age changes. |