Facial emotion recognition (FER) has been extensively researched over the past two decades due to its direct impact in the computer vision and affective robotics fields. However, the available datasets to train these models include often miss-labelled data due to the labellers bias that drives the model to learn incorrect features. In this paper, a facial emotion recognition system is proposed, addressing automatic face detection and facial expression recognition separately, the latter is performed by a set of only four deep convolutional neural network respect to an ensembling approach, while a label smoothing technique is applied to deal with the miss-labelled training data. The proposed system takes only 13.48 ms using a dedicated graphics processing unit (GPU) and 141.97 ms using a CPU to recognize facial emotions and reaches the current state-of-the-art performances regarding the challenging databases, FER2013, SFEW 2.0, and ExpW, giving recognition accuracies of 72.72%, 51.97%, and 71.82% respectively.
Face recognition has been very popular in recent years, for its advantages such as acceptance by the wide public and the price of cameras, which became more accessible. The majority of the current facial biometric systems use the visible spectrum, which suffers from some limitations, such as sensitivity to light changing, pose and facial expressions. The infrared spectrum is more relevant to facial biometric, for its advantages such as robustness to illumination change. In this paper, we propose two multispectral face recognition approaches that use both the visible and infrared spectra. We tested the new approaches with Uniform Local Binary Pattern (uLBP) as a local descriptor and Zernike Moments as a global descriptor on IRIS Thermal/Visible and CSIST Lab 2 databases. The experimental results clearly demonstrate the effectiveness of our multispectral face recognition system compared to a system that uses a single spectrum.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.