Facial expressions are the most visual method to convey emotions. Facial expressions of a person at different instances are not same. Automatic recognition of facial expressions is important for natural human-machine interfaces. Although human recognize facial expressions without delay, however expression reorganization by computer is still a challenge. In this proposed method Log Gabor filter bank of 5 scales and 8 different orientations is used. To reduce the dimensionality PCA (Principal Component Analysis) is then applied to Log- Gabor filtered images. The database used was JAFFE (Japanese female facial expression). The process involves detection of face, feature extraction using Log-Gabor filter, dimensionality reduction by PCA and classification of emotion using Euclidean distance metric. The work had been carried out in two stages. In stage I firstly, all the 7 emotions were detected using Log Gabor filter bank of 5 scales and 8 orientations. Secondly PCA was applied to compress 8 orientations and finally PCA was applied to compress 5 scales. In this stage the images of the training persons were included in the Test database. In stage II, 5 emotions angry, disgust, happy, neutral and surprise were detected by using Log Gabor filter bank of 5 scales and 8 orientations. In this stage images of training persons were not included in the Test database.
Read more