Extracting facial Feature is a key step in facial expression recognition (FER). Inaccurate feature extraction very often results in erroneous categorizing of facial expressions. Especially in robotic application, environmental factors such as illumination variation may cause FER system to extract feature inaccurately. In this paper, we propose a robust facial feature point extraction method to recognize facial expression in various lighting conditions. Before extracting facial features, a face is localized and segmented from a digitized image frame. Face preprocessing stage consists of face normalization and feature region localization steps to extract facial features efficiently. As regions of interest corresponding to relevant features are determined, Gabor jets are applied based on Gabor wavelet transformation to extract the facial points. Gabor jets are more invariable and reliable than gray-level values, which suffer from ambiguity as well as illumination variation while representing local features. Each feature point can be matched by a phase-sensitivity similarity function in the relevant regions of interest. Finally, the feature values are evaluated from the geometric displacement of facial points. After tested using the AR Face Database and the database built in our lab, average facial expression recognition rates of 84.1 % and 81.3% are obtained respectively.
The capability of robotic emotion recognition is an important factor for human-robot interaction. In order to facilitate a robot to function in daily live environments, a emotion recognition system needs to accommodate itself to various persons. In this paper, an emotion recognition system that can adapt to new facial data is proposed. The main idea of the proposed learning algorithm is to adjust parameters of SVM hyperplane for learning emotional expressions of a new face. After mapping the input space to Gaussian-kernel space, support vector pursuit learning (SVPL) is applied to retrain the hyperplane in the new feature space. To expedite the retraining procedure, only samples classified incorrectly in previous iteration are combined with critical historical sets to restrain a new SVM classifier. After adjusting hyperplane parameters, the new classifier will recognize previous erroneous facial data. Experimental results show that the proposed system recognize new facial data with high correction rates after fast retraining the hyperplane. Moreover, the proposed method also keeps satisfactory recognition rate of old facial samples.
'/%3e%3cuse xlink:href='%23a' transform='rotate(60)'/%3e%3ccircle r='17' fill='%23000095'/%3e%3ccircle r='15' fill='%23fff'/%3e%3c/svg%3e)
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)