Facial expression recognition based on a weighted Local Binary Pattern
Mohammad Shoyaib, Mohammad Abdullah-Al-Wadud, Jo Moo Youl, Muhammad Mahbub Alam, Oksam Chae · 2010
We introduce a facial expression recognition method, which incorporates a weight to the Local Binary Pattern (LBP), and generates solid expression features. Furthermore, we use Adaboost to select a small set of prominent features, which is used by the Support Vector Machine (SVM) to classify facial expressions efficiently. Experimental results demonstrate that our method outperforms the state-of-the-art methods in terms of both accuracy and complexities.