Facial expression recognition (FER) is an essential part of effective human–computer interaction and serves as a helpful medium for children and patients who have problems with communication However, most of the previous studies focus on building a FER model based on supervised and unsupervised approaches This paper is focused on a semi-supervised deep belief network (DBN) approach to predict the facial expressions from the CK+, Oulu CASIA, MMI, and JAFFE datasets To achieve accurate classification of the facial expressions, a gravitational search algorithm (GSA) is applied to optimize some parameters in the DBN network The Histogram oriented gradients (HOG) and 2D-Discrete Wavelet Transform (2D-DWT) are used for feature extraction from the lip, cheek, brow, eye, and furrow patches The unwanted information present in the image is eliminated using a feature selection approach The feature extraction is done by the Kernel-principal component analysis to obtain higher-order correlations between input variables and detect non-linear components The HOG features extracted from the lip patch provides the best performance for accurate facial expression classification Finally, a comparative analysis to compare the proposed model with different machine learning techniques based on the evaluation criteria The results demonstrate that DBN-GSA based classifier is more accurate than the rest of the classifiers

Gravitational search algorithm based optimized deep learning model with diverse set of features for facial expression recognition

The analysis of human facial expressions from the thermal images captured by the Infrared Thermal Imaging (IRTI) cameras has recently gained importance compared to images captured by the standard cameras using light having a wavelength in the visible spectrum. It is because infrared cameras work well in low-light conditions and also infrared spectrum captures thermal distribution that is very useful for building systems like Robot interaction systems, quantifying the cognitive responses from facial expressions, disease control, etc. In this paper, a deep learning model called IRFacExNet (InfraRed Facial Expression Network) has been proposed for facial expression recognition (FER) from infrared images. It utilizes two building blocks namely Residual unit and Transformation unit which extract dominant features from the input images specific to the expressions. The extracted features help to detect the emotion of the subjects in consideration accurately. The Snapshot ensemble technique is adopted with a Cosine annealing learning rate scheduler to improve the overall performance. The performance of the proposed model has been evaluated on a publicly available dataset, namely IRDatabase developed by RWTH Aachen University. The facial expressions present in the dataset are Fear, Anger, Contempt, Disgust, Happy, Neutral, Sad, and Surprise. The proposed model produces 88.43% recognition accuracy, better than some state-of-the-art methods considered here for comparison. Our model provides a robust framework for the detection of accurate expression in the absence of visible light.

/pdf/a-deep-learning-model-for-classifying-human-facial-10e9ssn2w0.pdf

A deep learning model for classifying human facial expressions from infrared thermal images.

Facial emotion recognition finds a major role in affective computing. Recognizing emotion by facial expression is an extremely important activity to design control oriented and human computer interactive applications especially in cognitive science and neuroscience. For a precise and robust recognition, feature extraction is one of the major challenges in facial expression recognition system. Wavelet transform is one of the major key methods utilized for feature extraction in facial emotion recognition. In this paper, the statistical parameters from the proposed subband selective multilevel stationary wavelet gradient transform are calculated and are utilized as features for efficacious recognition of emotion. The features of the wavelet transform contain both spatial and spectral domain information which is best suited for identifying human emotions through facial expression. The introduction of gradient transform to find the gradient of subband avails to estimate the edges in images for the quality amelioration of subbands. The dimension reduction in the extracted features is done by using Pearson–kernel–principal component analysis method. The classification of emotion using the selected features is done by the proposed Gaussian membership function fuzzy SVM classifier. Experiments were performed on the well-known database for facial expression such as JAFEE database, CK + database and FG Net database and obtained promising emotion classification results.

G. Viswanatha Reddy

Papers

Facial expression recognition in the wild, by fusion of deep learnt and hand-crafted features