Facial action unit recognition using multi-class classification

Within the context of facial expression classification using the facial action coding system (FACS), we address the problem of detecting facial action units (AUs). Feature extraction is performed by generating a large number of multi-resolution local binary pattern (MLBP) features and then selecting from these using fast correlation-based filtering (FCBF). The need for a classifier per AU is avoided by training a single error-correcting output code (ECOC) multi-class classifier to generate occurrence scores for each of several AU groups. A novel weighted decoding scheme is proposed with the weights computed using first order Walsh coefficients. Platt scaling is used to calibrate the ECOC scores to probabilities and appropriate sums are taken to obtain separate probability estimates for each AU individually. The bias and variance properties of the classifier are measured and we show that both these sources of error can be reduced by enhancing ECOC through bootstrapping and weighted decoding.