Going deeper in facial expression recognition using deep neural networks

Mollahosseini, Ali; Chan, David M.; Mahoor, Mohammad H.

doi:10.1109/wacv.2016.7477450

Cited by 787 publications

(378 citation statements)

References 47 publications

Supporting

Mentioning

371

Contrasting

Unclassified

Order By: Relevance

“…Inspired by the so-called GoogleLeNet network [85] a DCNN with "inception" layers was proposed in [62] for facial expression recognition. The idea of "inception" layers is that it is possible to approximate a sparse structure with spatially repeated dense components and using dimension reduction to keep the computational complexity in bounds, but only when required [85].…”

Section: Deep Learning Methodologies For Facial Expression Recognitiomentioning

confidence: 99%

“…The idea of "inception" layers is that it is possible to approximate a sparse structure with spatially repeated dense components and using dimension reduction to keep the computational complexity in bounds, but only when required [85]. The DCNN proposed in [62] consists of two convolutional layers each followed by max pooling and then four "Inception" layers. The paper presents comprehensive experiments on many publicly available facial expression databases including SFEW, and FER2013.…”

Section: Deep Learning Methodologies For Facial Expression Recognitiomentioning

confidence: 99%

See 1 more Smart Citation

Facial Affect “In-the-Wild”: A Survey and a New Database

Zafeiriou

Papaioannou

Kotsia

et al. 2016

2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

View full text Add to dashboard Cite

Well-established databases and benchmarks have been developed in the past 20 years for automatic facial behaviour analysis. Nevertheless, for some important problems regarding analysis of facial behaviour, such as (a) estimation of affect in a continuous dimensional space (e.g., valence and arousal) in videos displaying spontaneous facial behaviour and (b) detection of the activated facial muscles (i.e., facial action unit detection), to the best of our knowledge, well-established in-the-wild databases and benchmarks do not exist. That is, the majority of the publicly available corpora for the above tasks contain samples that have been captured in controlled recording conditions and/or captured under a very specific milieu. Arguably, in order to make further progress in automatic understanding of facial behaviour, datasets that have been captured in in-the-wild and in various milieus have to be developed. In this paper, we survey the progress that has been recently made on understanding facial behaviour inthe-wild, namely the datasets and methodologies that have been developed thus far, while paying particular attention to recently proposed deep learning techniques. Finally, we attempt a significant step further by proposing a novel, comprehensive benchmark that can be utilized for evaluating and training various methodologies for the problems of facial affect, behaviour analysis and understanding "inthe-wild". To the best of our knowledge, this is the first benchmark proposed for measuring continuous affect in the valence-arousal space "in-the-wild".

show abstract

Section: Deep Learning Methodologies For Facial Expression Recognitiomentioning

confidence: 99%

Section: Deep Learning Methodologies For Facial Expression Recognitiomentioning

confidence: 99%

Facial Affect “In-the-Wild”: A Survey and a New Database

Zafeiriou

Papaioannou

Kotsia

et al. 2016

2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

View full text Add to dashboard Cite

show abstract

“…So they use the deep learning and multilabel learning methods to build one model used to diagnose the chronic gastritis in traditional Chinese medicine. At the same time, deep convolution neural network is mainly used in image recognition and shows good results [20–23]. Hu et al [24] applied the convolution neural network to the pulse diagnosis.…”

Section: Introductionmentioning

confidence: 99%

Deep Convolutional Neural Networks for Classifying Body Constitution Based on Face Image

Huan

Wen

Zhang

et al. 2017

Computational and Mathematical Methods in Medicine

View full text Add to dashboard Cite

Body constitution classification is the basis and core content of traditional Chinese medicine constitution research. It is to extract the relevant laws from the complex constitution phenomenon and finally build the constitution classification system. Traditional identification methods have the disadvantages of inefficiency and low accuracy, for instance, questionnaires. This paper proposed a body constitution recognition algorithm based on deep convolutional neural network, which can classify individual constitution types according to face images. The proposed model first uses the convolutional neural network to extract the features of face image and then combines the extracted features with the color features. Finally, the fusion features are input to the Softmax classifier to get the classification result. Different comparison experiments show that the algorithm proposed in this paper can achieve the accuracy of 65.29% about the constitution classification. And its performance was accepted by Chinese medicine practitioners.

show abstract

“…The Machine learning approach is selected by the variety of a feature set. At last, database is used to store the training set [3].…”

Section: Introductionmentioning

confidence: 99%

Facial Expression Recognition Using Improved Artificial Bee Colony Algorithm

Saravanan¹

2017

ijetst

View full text Add to dashboard Cite

:In recent year, Emotion recognition can be done through different modalities, such as speech, facial expression, body gesture etc. Emotion recognition through facial expression has attracted a lot of interest. Generally the emotions are classified as anger, disgust, fear, happiness, sadness, and surprise. The accurate prediction of facial expression is difficult due to the illumination, pose facial occlusions and different shape. To solve this problem the previous system introduced salient facial patches based facial expression recognition. However it has lower true positive rate. In order to improve the face recognition accuracy, the proposed system introduced Improved Artificial Bee Colony algorithm (IABC) based facial expression recognition. In this proposed work, the face image is detected by Viola-Jones approach. By using low pass filter the noises in the images are removed. Then the active facial patches with respect to the position of eyes, eyebrows, nose, and lip corner are extracted from preprocessed images. In order to obtain salient patches, the active patches are further processed. After that an optimal features are selected by using IABC algorithm. Finally the different facial expression anger, disgust, fear, happiness, sadness, and surprise are classified by using multiclass Support Vector Machine (MSVM). The experimental results show that the proposed system achieves better performance compared with the existing system in terms of accuracy, precision and recall.

show abstract

Going deeper in facial expression recognition using deep neural networks

Cited by 787 publications

References 47 publications

Facial Affect “In-the-Wild”: A Survey and a New Database

Facial Affect “In-the-Wild”: A Survey and a New Database

Deep Convolutional Neural Networks for Classifying Body Constitution Based on Face Image

Facial Expression Recognition Using Improved Artificial Bee Colony Algorithm

Contact Info

Product

Resources

About