Facial Expression Recognition with Contrastive Learning and Uncertainty-Guided Relabeling

We proposed a facial motion tracking and expression recognition system based on video data. By a 3D deformable facial model, the online statistical model (OSM) and cylinder head model (CHM) were combined to track 3D facial motion in the framework of particle filtering. For facial expression recognition, a fast and efficient algorithm and a robust and precise algorithm were developed. With the first, facial animation and facial expression were retrieved sequentially. After that facial animation was obtained, facial expression was recognized by static facial expression knowledge learned from anatomical analysis. With the second, facial animation and facial expression were simultaneously retrieved to increase the reliability and robustness with noisy input data. Facial expression was recognized by fusing static and dynamic facial expression knowledge, the latter of which was learned by training a multi-class expressional Markov process using a video database. The experiments showed that facial motion tracking by OSM+CHM is more pose robust than that by OSM, and the facial expression score of the robust and precise algorithm is higher than those of other state-of-the-art facial expression recognition methods.

With the work and study pressure on people increasing and the importance of mental health problems on the rise, facial expression analysis plays an important role in mental health auxiliary diagnosis and treatment (MHADT). This study proposes a facial expression localization and recognition model that integrates Main Directional Mean Optical Flow (MDMO) with the Transformer architecture. It addresses the problems of insufficient generalization ability and limited temporal modeling ability of traditional methods in facial expression recognition. The study is based on the authoritative Audio/Visual Emotion Challenge 2019 Depression Detection Sub-challenge (AVEC2019 DDS) dataset in the mental health field, which contains 163 training samples, 56 validation samples, and 56 test samples. With Explicit Shape Regression, Local Binary Patterns, Mnemonic Descent Method, Convolutional Neural Network, and benchmark models as comparison objects, it systematically evaluates the model's performance in error, accuracy, and processing speed. The results show that the model achieves the best performance in both facial expression localization and recognition tasks. The validation set errors are 7.26 and 6.85, the localization accuracy reaches 89.6%, and the recognition accuracy reaches 88.9%, which is significantly better than other methods. At the same time, its image processing time is 55 milliseconds (ms) and 44ms, balancing high precision and real-time performance. The study indicates that the fusion of MDMO and Transformer can effectively capture the spatial and temporal features of facial expressions. Thus, this fusion method provides an efficient, stable, and scalable technical solution for emotion recognition in MHADT. This improves both the FER and localization accuracy and effect. Besides, it provides a novel reference in both approaches and application level for the intelligent development of mental health evaluation.

Facial expression recognition is a practical application in the field of artificial intelligence. This article focuses on the introduction of the principles of each facial expression recognition method based on deep learning in chronological order, as well as the advantages and disadvantages of each method. The methods of facial expression recognition based on deep learning introduced in this article are as follows: Li Dunyu [1] proposed a method of LBP and BP neural network to realize facial expression recognition. And then the convolutional neural network is widely used, Zhou Benjun [2] merged LBP and convolutional neural network to realize facial expression recognition; Liu [3] establish a model that combines a recurrent neural network with a 3D convolutional neural network, and added a timeline so that the machine can extract and recognize facial expressions in a video; Jung [4] proposed to combine the convolutional neural network and the deep neural network to form a new neural network DTAGN, by using this new network he completes facial expression recognition; Shi Xugan [5] proposed a model of combining deep belief network with multi-layer perceptron (MLP), and successfully applied it to the research of facial expression recognition. By utilizing joint training of feature points and multiple networks Xia Tian [6] finish the research; Zhang Feifei [7] and other scholars proposed multi-pose facial expression recognition based on generating an adversarial network.

In order to solve the problems of low average gradient and long recognition time in traditional facial expression recognition method, a multi-scale detail enhancement method for facial dynamic expression recognition of sprint athletes is proposed. A principal component analysis method was used to establish the facial expression feature subspace of sprinters, to project and reduce the dimension of the facial dynamic expression feature vector of sprinters, and to obtain the low frequency information and high frequency information of the facial image of sprinters by bilateral filtering. The multi-scale details of expression are enhanced by using side suppression network model and improving image S curve. The feature vector of facial dynamic expression is input into support vector machine to recognise the facial dynamic expression of sprinter. Experimental results show that the average value of annoying gradient is about 98 and the shortest time s. is about 1.9.

Background: Individuals with child maltreatment (CM) experiences show alterations in emotion recognition (ER). However, previous research has mainly focused on populations with specific mental disorders, which makes it unclear whether alterations in the recognition of facial expressions are related to CM, to the presence of mental disorders or to the combination of CM and mental disorders, and on ER of emotional, rather than neutral facial expressions. Moreover, commonly, recognition of static stimulus material was researched. Objective: We assessed recognition of dynamic (closer to real life) negative, positive and neutral facial expressions in individuals characterised by CM, rather than a specific mental disorder. Moreover, we assessed whether they show a negativity bias for neutral facial expressions and whether the presence of one or more mental disorders affects recognition. Methods: Ninety-eight adults with CM experiences (CM+) and 60 non-maltreated (CM−) adult controls watched 200 non-manipulated coloured video sequences, showing 20 neutral and 180 emotional facial expressions, and indicated whether they interpreted each expression as neutral or as one of eight emotions. Results: The CM+ showed significantly lower scores in the recognition of positive, negative and neutral facial expressions than the CM− group (p < .050). Furthermore, the CM+ group showed a negativity bias for neutral facial expressions (p < .001). When accounting for mental disorders, significant effects stayed consistent, except for the recognition of positive facial expressions: individuals from the CM+ group with but not without mental disorder scored lower than controls without mental disorder. Conclusions: CM might have long-lasting influences on the ER abilities of those affected. Future research should explore possible effects of ER alterations on everyday life, including implications of the negativity bias for neutral facial expressions on emotional wellbeing and relationship satisfaction, providing a basis for interventions that improve social functioning.

Background/Objectives: There is only limited research work is going on in the field of facial expression recognition on low resolution images. Mostly, all the images in the real world will be in low resolution and might also contain noise, so this study is to design a novel convolutional neural network model (FERConvNet), which can perform better on low resolution images. Methods: We proposed a model and then compared with state-of-art models on FER2013 dataset. There is no publicly available dataset, which contains low resolution images for facial expression recognition (Anger, Sad, Disgust, Happy, Surprise, Neutral, Fear), so we created a Low Resolution Facial Expression (LRFE) dataset, which contains more than 6000 images of seven types of facial expressions. The existing FER2013 dataset and LRFE dataset were used. These datasets were divided in the ratio 80:20 for training and testing and validation purpose. A HDM is proposed, which is a combination of Gaussian Filter, Bilateral Filter and Non local means denoising Filter. This hybrid denoising method helps us to increase the performance of the convolutional neural network. The proposed model was then compared with VGG16 and VGG19 models. Findings: The experimental results show that the proposed FERConvNet_HDM approach is effective than VGG16 and VGG19 in facial expression recognition on both FER2013 and LRFE dataset. The proposed FERConvNet_HDM approach achieved 85% accuracy on Fer2013 dataset, outperforming the VGG16 and VGG19 models, whose accuracies are 60% and 53% on Fer2013 dataset respectively. The same FERConvNet_HDM approach when applied on LRFE dataset achieved 95% accuracy. After analyzing the results, our FERConvNet_HDM approach performs better than VGG16 and VGG19 on both Fer2013 and LRFE dataset. Novelty/Applications: HDM with convolutional neural networks, helps in increasing the performance of convolutional neural networks in Facial expression recognition. Keywords: Facial expression recognition; facial emotion; convolutional neural network; deep learning; computer vision

Facial expression recognition (FER) in the wild is a challenging task due to some uncontrolled factors such as occlusion, illumination, and pose variation. The current methods perform well in controlled conditions. However, there are still two issues with the in-the-wild FER task: (i) insufficient descriptions of long-range dependency of expression features in the facial information space and (ii) not finely refining subtle inter-classes distinction from multiple expressions in the wild. To overcome the above issues, an end-to-end model for FER, named attention-modulated contextual spatial information network (ACSI-Net), is presented in this paper, with the manner of embedding coordinate attention (CA) modules into a contextual convolutional residual network (CoResNet). Firstly, CoResNet is constituted by arranging contextual convolution (CoConv) blocks of different levels to integrate facial expression features with long-range dependency, which generates a holistic representation of spatial information on facial expression. Then, the CA modules are inserted into different stages of CoResNet, at each of which the subtle information about facial expression acquired from CoConv blocks is first modulated by the corresponding CA module across channels and spatial locations and then flows into the next layer. Finally, to highlight facial regions related to expression, a CA module located at the end of the whole network, which produces attentional masks to multiply by input feature maps, is utilized to focus on salient regions. Different from other models, the ACSI-Net is capable of exploring intrinsic dependencies between features and yielding a discriminative representation for facial expression classification. Extensive experimental results on AffectNet and RAF_DB datasets demonstrate its effectiveness and competitiveness compared to other FER methods.

Deep reinforcement learning for robust emotional classification in facial expression recognition

Facial expression recognition (FER) techniques can be widely used in human-computer interaction, intelligent robots, intelligent monitoring, and other domains. Currently, FER methods based on deep learning have become the mainstream schemes. However, these methods have some problems, such as a large number of parameters, difficulty in being applied to embedded processors, and the fact that recognition accuracy is affected by facial deflection. To solve the problem of a large number of parameters, we propose a DSC-DenseNet model, which improves the standard convolution in DenseNet to depthwise separable convolution (DSC). To solve the problem wherein face deflection affects the recognition effect, we propose a posture normalization model based on GAN: a GAN with two local discriminators (LD-GAN) that strengthen the discriminatory abilities of the expression-related local parts, such as the parts related to the eyes, eyebrows, mouth, and nose. These discriminators improve the model’s ability to retain facial expressions and evidently benefits FER. Quantitative and qualitative experimental results on the Fer2013 and KDEF datasets have consistently shown the superiority of our FER method when working with multi-pose face images.

Facial expressions recognition and synthesis are important research fields to study how human beings reflect to environments in affective computing. With the rapid development of mathematical theory on multivariate statistics and multi-media technology especially image processing, facial expressions recognition researchers have achieved many useful results. Recently studies show that approaches to facial modeling and expressions recognition and synthesis analysis could be adapted to control security or even real-time health monitoring in the real world. Similarity, how to achieve facial expressions recognition and synthesis for independent-free mechanism is a central design in general. Based on the cognitive analysis of independent user's affective facial recognition researches we proposed an emotions composition model to dope out what are the user's new affective facial expressions. At this point, principal component, cluster and discriminate analysis were applied to show and verify independent user's affective expressions can be composited for synthesis by basic facial expressions such as happy, neutral and unhappy. Experiments were conducted to prove our models to be very significant.

Training deep neural networks for image recognition often requires large-scale human annotated data. To reduce the reliance of deep neural solutions on labeled data, state-of-the-art semi-supervised methods have been proposed in the literature. Nonetheless, the use of such semi-supervised methods has been quite rare in the field of facial expression recognition (FER). In this paper, we present a comprehensive study on recently proposed state-of-the-art semi-supervised learning methods in the context of FER. We conduct comparative study on eight semi-supervised learning methods, namely Pi-Model, Pseudo-label, Mean-Teacher, VAT, MixMatch, ReMixMatch, UDA, and FixMatch, on three FER datasets (FER13, RAF-DB, and AffectNet), when various amounts of labeled samples are used. We also compare the performance of these methods against fully-supervised training. Our study shows that when training existing semi-supervised methods on as little as 250 labeled samples per class can yield comparable performances to that of fully-supervised methods trained on the full labeled datasets. To facilitate further research in this area, we make our code publicly available at: https://github.com/ShuvenduRoy/SSL_FER.

Extraction of discriminate features which could represent the facial expression accurately plays a vital role in effective Facial Expression Recognition (FER). Although much progress has been made, selecting the discriminate features is still a challenging and interesting problem in the FER system. In this paper, we propose a new FER method, which uses the active shape mode (ASM) algorithm to landmark the key points of face, then extracts local binary patterns (LBP) features around the key points and uses the Multi-Task Learning (MTL) algorithm to select the discriminate patches to represent facial expression accurately. Then we use uses support vector machine (SVM) classifier to predict the facial emotion. Experiments on the Extended Cohn-Kanada database show that the proposed method has a promising performance and realizes the recognition rate of 96.44%.

With the continuous development of facial expression technology, especially the development of deep learning, and the establishment of in-the-wild datesets in recent years, field face recognition has become a hot research field in the wild of facial expression recognition. Different from the traditional facial expression recognition(FER), in-the-wild facial facial expression recognition, the problem of recognition accuracy caused by illumination, occlusion or low image resolution. Therefore, in order to solve these problems, new methods have been put forward continuously in recent years. In this paper, we first continue to summarize the widely used datesets, and then summarize the paper methods of facial expression recognition in the field proposed in the past two years.

Introduction To date, most ways to perform facial expression recognition rely on two-dimensional images, advanced approaches with three-dimensional data exist. These however demand stationary apparatuses and thus lack portability and possibilities to scale deployment. As human emotions, intent and even diseases may condense in distinct facial expressions or changes therein, the need for a portable yet capable solution is signified. Due to the superior informative value of three-dimensional data on facial morphology and because certain syndromes find expression in specific facial dysmorphisms, a solution should allow portable acquisition of true three-dimensional facial scans in real time. In this study we present a novel solution for the three-dimensional acquisition of facial geometry data and the recognition of facial expressions from it. The new technology presented here only requires the use of a smartphone or tablet with an integrated TrueDepth camera and enables real-time acquisition of the geometry and its categorization into distinct facial expressions. Material and Methods Our approach consisted of two parts: First, training data was acquired by asking a collective of 226 medical students to adopt defined facial expressions while their current facial morphology was captured by our specially developed app running on iPads, placed in front of the students. In total, the list of the facial expressions to be shown by the participants consisted of “disappointed”, “stressed”, “happy”, “sad” and “surprised”. Second, the data were used to train a self-normalizing neural network. A set of all factors describing the current facial expression at a time is referred to as “snapshot”. Results In total, over half a million snapshots were recorded in the study. Ultimately, the network achieved an overall accuracy of 80.54% after 400 epochs of training. In test, an overall accuracy of 81.15% was determined. Recall values differed by the category of a snapshot and ranged from 74.79% for “stressed” to 87.61% for “happy”. Precision showed similar results, whereas “sad” achieved the lowest value at 77.48% and “surprised” the highest at 86.87%. Conclusions With the present work it can be demonstrated that respectable results can be achieved even when using data sets with some challenges. Through various measures, already incorporated into an optimized version of our app, it is to be expected that the training results can be significantly improved and made more precise in the future. Currently a follow-up study with the new version of our app that encompasses the suggested alterations and adaptions, is being conducted. We aim to build a large and open database of facial scans not only for facial expression recognition but to perform disease recognition and to monitor diseases’ treatment progresses.

Facial expression recognition (FER) is an important means for machines to perceive human emotions and interact with human beings. Most of the existing facial expression recognition methods only use a single convolutional neural network to extract the global features of the face. Some insignificant details and features with low frequency are easy to be ignored, and part of the facial features are lost. This paper proposes a facial expression recognition method based on multi branch structure, which extracts the global and detailed features of the face from the global and local aspects respectively, so as to make a more detailed representation of the facial expression and further improve the accuracy of facial expression recognition. Specifically, we first design a multi branch network, which takes Resnet-50 as the backbone network. The network structure after Conv Block3 is divided into three branches. The first branch is used to extract the global features of the face, and the second and third branches are used to cut the face into two parts and three parts after Conv Block5 to extract the detailed features of the face. Finally, the global features and detail features are fused in the full connection layer and input into the classifier for classification. The experimental results show that the accuracy of this method is 73.7%, which is 4% higher than that of traditional Resnet-50, which fully verifies the effectiveness of this method.