Facial Expression Recognition Using Enhanced Deep 3D Convolutional Neural Networks
01 Jul 2017-pp 2278-2288
TL;DR: In this article, a 3D Convolutional Neural Network (CNN) is proposed for facial expression recognition in videos, which consists of 3D Inception-ResNet layers followed by an LSTM unit that together extracts the spatial relations within facial images as well as the temporal relations between different frames in the video.
Abstract: Deep Neural Networks (DNNs) have shown to outperform traditional methods in various visual recognition tasks including Facial Expression Recognition (FER). In spite of efforts made to improve the accuracy of FER systems using DNN, existing methods still are not generalizable enough in practical applications. This paper proposes a 3D Convolutional Neural Network method for FER in videos. This new network architecture consists of 3D Inception-ResNet layers followed by an LSTM unit that together extracts the spatial relations within facial images as well as the temporal relations between different frames in the video. Facial landmark points are also used as inputs to our network which emphasize on the importance of facial components rather than the facial regions that may not contribute significantly to generating facial expressions. Our proposed method is evaluated using four publicly available databases in subject-independent and cross-database tasks and outperforms state-of-the-art methods.
Citations
More filters
TL;DR: A comprehensive survey on deep facial expression recognition (FER) can be found in this article, including datasets and algorithms that provide insights into the intrinsic problems of deep FER, including overfitting caused by lack of sufficient training data and expression-unrelated variations, such as illumination, head pose and identity bias.
Abstract: With the transition of facial expression recognition (FER) from laboratory-controlled to challenging in-the-wild conditions and the recent success of deep learning techniques in various fields, deep neural networks have increasingly been leveraged to learn discriminative representations for automatic FER. Recent deep FER systems generally focus on two important issues: overfitting caused by a lack of sufficient training data and expression-unrelated variations, such as illumination, head pose and identity bias. In this paper, we provide a comprehensive survey on deep FER, including datasets and algorithms that provide insights into these intrinsic problems. First, we describe the standard pipeline of a deep FER system with the related background knowledge and suggestions of applicable implementations for each stage. We then introduce the available datasets that are widely used in the literature and provide accepted data selection and evaluation principles for these datasets. For the state of the art in deep FER, we review existing novel deep neural networks and related training strategies that are designed for FER based on both static images and dynamic image sequences, and discuss their advantages and limitations. Competitive performances on widely used benchmarks are also summarized in this section. We then extend our survey to additional related issues and application scenarios. Finally, we review the remaining challenges and corresponding opportunities in this field as well as future directions for the design of robust deep FER systems.
712 citations
TL;DR: A brief review of researches in the field of FER conducted over the past decades, focusing on an up-to-date hybrid deep-learning approach combining a convolutional neural network for the spatial features of an individual frame and long short-term memory for temporal features of consecutive frames.
Abstract: Facial emotion recognition (FER) is an important topic in the fields of computer vision and artificial intelligence owing to its significant academic and commercial potential. Although FER can be conducted using multiple sensors, this review focuses on studies that exclusively use facial images, because visual expressions are one of the main information channels in interpersonal communication. This paper provides a brief review of researches in the field of FER conducted over the past decades. First, conventional FER approaches are described along with a summary of the representative categories of FER systems and their main algorithms. Deep-learning-based FER approaches using deep networks enabling “end-to-end” learning are then presented. This review also focuses on an up-to-date hybrid deep-learning approach combining a convolutional neural network (CNN) for the spatial features of an individual frame and long short-term memory (LSTM) for temporal features of consecutive frames. In the later part of this paper, a brief review of publicly available evaluation metrics is given, and a comparison with benchmark results, which are a standard for a quantitative comparison of FER researches, is described. This review can serve as a brief guidebook to newcomers in the field of FER, providing basic knowledge and a general understanding of the latest state-of-the-art studies, as well as to experienced researchers looking for productive directions for future work.
437 citations
16 May 2019
TL;DR: Zhang et al. as discussed by the authors proposed an approach that combines automatic features learned by convolutional neural networks (CNN) and handcrafted features computed by the bag-of-visual-words (BOVW) model in order to achieve the state of the art results in facial expression recognition (FER).
Abstract: We present an approach that combines automatic features learned by convolutional neural networks (CNN) and handcrafted features computed by the bag-of-visual-words (BOVW) model in order to achieve the state-of-the-art results in facial expression recognition (FER). To obtain automatic features, we experiment with multiple CNN architectures, pre-trained models, and training procedures, e.g., Dense–Sparse–Dense. After fusing the two types of features, we employ a local learning framework to predict the class label for each test image. The local learning framework is based on three steps. First, a k-nearest neighbors model is applied in order to select the nearest training samples for an input test image. Second, a one-versus-all support vector machines (SVM) classifier is trained on the selected training samples. Finally, the SVM classifier is used to predict the class label only for the test image it was trained for. Although we have used local learning in combination with handcrafted features in our previous work, to the best of our knowledge, local learning has never been employed in combination with deep features. The experiments on the 2013 FER Challenge data set, the FER+ data set, and the AffectNet data set demonstrate that our approach achieves the state-of-the-art results. With a top accuracy of 75.42% on the FER 2013, 87.76% on the FER+, 59.58% on the AffectNet eight-way classification, and 63.31% on the AffectNet seven-way classification, we surpass the state-of-the-art methods by more than 1% on all data sets.
223 citations
TL;DR: There is a need for state-of-the-art in neural networks application to PR to urgently address the above-highlights problems and the research focus on current models and the development of new models concurrently for more successes in the field.
Abstract: The era of artificial neural network (ANN) began with a simplified application in many fields and remarkable success in pattern recognition (PR) even in manufacturing industries. Although significant progress achieved and surveyed in addressing ANN application to PR challenges, nevertheless, some problems are yet to be resolved like whimsical orientation (the unknown path that cannot be accurately calculated due to its directional position). Other problem includes; object classification, location, scaling, neurons behavior analysis in hidden layers, rule, and template matching. Also, the lack of extant literature on the issues associated with ANN application to PR seems to slow down research focus and progress in the field. Hence, there is a need for state-of-the-art in neural networks application to PR to urgently address the above-highlights problems for more successes. The study furnishes readers with a clearer understanding of the current, and new trend in ANN models that effectively addresses PR challenges to enable research focus and topics. Similarly, the comprehensive review reveals the diverse areas of the success of ANN models and their application to PR. In evaluating the performance of ANN models, some statistical indicators for measuring the performance of the ANN model in many studies were adopted. Such as the use of mean absolute percentage error (MAPE), mean absolute error (MAE), root mean squared error (RMSE), and variance of absolute percentage error (VAPE). The result shows that the current ANN models such as GAN, SAE, DBN, RBM, RNN, RBFN, PNN, CNN, SLP, MLP, MLNN, Reservoir computing, and Transformer models are performing excellently in their application to PR tasks. Therefore, the study recommends the research focus on current models and the development of new models concurrently for more successes in the field.
217 citations
TL;DR: A comprehensive review of deep facial expression recognition (FER) including datasets and algorithms that provide insights into these intrinsic problems can be found in this article , where the authors introduce the available datasets that are widely used in the literature and provide accepted data selection and evaluation principles for these datasets.
Abstract: With the transition of facial expression recognition (FER) from laboratory-controlled to challenging in-the-wild conditions and the recent success of deep learning techniques in various fields, deep neural networks have increasingly been leveraged to learn discriminative representations for automatic FER. Recent deep FER systems generally focus on two important issues: overfitting caused by a lack of sufficient training data and expression-unrelated variations, such as illumination, head pose, and identity bias. In this survey, we provide a comprehensive review of deep FER, including datasets and algorithms that provide insights into these intrinsic problems. First, we introduce the available datasets that are widely used in the literature and provide accepted data selection and evaluation principles for these datasets. We then describe the standard pipeline of a deep FER system with the related background knowledge and suggestions for applicable implementations for each stage. For the state-of-the-art in deep FER, we introduce existing novel deep neural networks and related training strategies that are designed for FER based on both static images and dynamic image sequences and discuss their advantages and limitations. Competitive performances and experimental comparisons on widely used benchmarks are also summarized. We then extend our survey to additional related issues and application scenarios. Finally, we review the remaining challenges and corresponding opportunities in this field as well as future directions for the design of robust deep FER systems.
209 citations
References
More filters
27 Jun 2016
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Abstract: Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. On the ImageNet dataset we evaluate residual nets with a depth of up to 152 layers—8× deeper than VGG nets [40] but still having lower complexity. An ensemble of these residual nets achieves 3.57% error on the ImageNet test set. This result won the 1st place on the ILSVRC 2015 classification task. We also present analysis on CIFAR-10 with 100 and 1000 layers. The depth of representations is of central importance for many visual recognition tasks. Solely due to our extremely deep representations, we obtain a 28% relative improvement on the COCO object detection dataset. Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions1, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.
123,388 citations
Proceedings Article•
03 Dec 2012TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Abstract: We trained a large, deep convolutional neural network to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes. On the test data, we achieved top-1 and top-5 error rates of 37.5% and 17.0% which is considerably better than the previous state-of-the-art. The neural network, which has 60 million parameters and 650,000 neurons, consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax. To make training faster, we used non-saturating neurons and a very efficient GPU implementation of the convolution operation. To reduce overriding in the fully-connected layers we employed a recently-developed regularization method called "dropout" that proved to be very effective. We also entered a variant of this model in the ILSVRC-2012 competition and achieved a winning top-5 test error rate of 15.3%, compared to 26.2% achieved by the second-best entry.
73,978 citations
TL;DR: A novel, efficient, gradient based method called long short-term memory (LSTM) is introduced, which can learn to bridge minimal time lags in excess of 1000 discrete-time steps by enforcing constant error flow through constant error carousels within special units.
Abstract: Learning to store information over extended time intervals by recurrent backpropagation takes a very long time, mostly because of insufficient, decaying error backflow. We briefly review Hochreiter's (1991) analysis of this problem, then address it by introducing a novel, efficient, gradient based method called long short-term memory (LSTM). Truncating the gradient where this does not do harm, LSTM can learn to bridge minimal time lags in excess of 1000 discrete-time steps by enforcing constant error flow through constant error carousels within special units. Multiplicative gate units learn to open and close access to the constant error flow. LSTM is local in space and time; its computational complexity per time step and weight is O. 1. Our experiments with artificial data involve local, distributed, real-valued, and noisy pattern representations. In comparisons with real-time recurrent learning, back propagation through time, recurrent cascade correlation, Elman nets, and neural sequence chunking, LSTM leads to many more successful runs, and learns much faster. LSTM also solves complex, artificial long-time-lag tasks that have never been solved by previous recurrent network algorithms.
72,897 citations
07 Jun 2015
TL;DR: Inception as mentioned in this paper is a deep convolutional neural network architecture that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14).
Abstract: We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14). The main hallmark of this architecture is the improved utilization of the computing resources inside the network. By a carefully crafted design, we increased the depth and width of the network while keeping the computational budget constant. To optimize quality, the architectural decisions were based on the Hebbian principle and the intuition of multi-scale processing. One particular incarnation used in our submission for ILSVRC14 is called GoogLeNet, a 22 layers deep network, the quality of which is assessed in the context of classification and detection.
40,257 citations
20 Jun 2005
TL;DR: It is shown experimentally that grids of histograms of oriented gradient (HOG) descriptors significantly outperform existing feature sets for human detection, and the influence of each stage of the computation on performance is studied.
Abstract: We study the question of feature sets for robust visual object recognition; adopting linear SVM based human detection as a test case. After reviewing existing edge and gradient based descriptors, we show experimentally that grids of histograms of oriented gradient (HOG) descriptors significantly outperform existing feature sets for human detection. We study the influence of each stage of the computation on performance, concluding that fine-scale gradients, fine orientation binning, relatively coarse spatial binning, and high-quality local contrast normalization in overlapping descriptor blocks are all important for good results. The new approach gives near-perfect separation on the original MIT pedestrian database, so we introduce a more challenging dataset containing over 1800 annotated human images with a large range of pose variations and backgrounds.
31,952 citations