Facial emotion recognition under noisy environment using empirical mode decomposition

One of the challenges faced by automatic facial emotion recognition nowadays is the ability to deal with complicated environmental conditions such as noisy environments. In order to solve this problem, this paper aims to examine facial emotion recognition under noisy environment using empirical mode decomposition (EMD). EMD is a multiresolution technique which is adaptively decomposed nonstationary and nonlinear data into a small set of frequency component known as intrinsic mode functions (IMFs). First, the image is subjected to radon transform to convert into 1D projection signal followed by EMD algorithm. Then, the extracted IMFs features are subjected to a dimension reduction technique, namely Principle Component Analysis plus Linear Discriminant Analysis (PCA plus LDA). The reduced feature vector is used as input to Support Vector Machines (SVM) and k-Nearest Neighbor (k-NN) classifier for recognizing seven facial emotions. A series of experiments has been conducted on CK database. The experimental results show that facial emotion recognition under noisy environment using EMD technique enables to minimize the effect of the noise in classifying the facial emotion, thus demonstrates promising results.