Intra-Class Variation Reduction Using Training Expression Images for Sparse Representation Based Facial Expression Recognition

Lee, Seol‐Hoon; Plataniotis, Konstantinos N.; Ro, Yong Man

doi:10.1109/taffc.2014.2346515

Cited by 112 publications

(38 citation statements)

References 44 publications

(126 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We believe that by assigning a single expression to a image can be ambiguous when there is transition between expressions or the given expression is not at its peak, and therefore the top-2 expression can result in a better classification performance when evaluating image sequences. [30], 84.4 [21], 88.5 [42], 92.0 [24] 92.4 [25], 93.6 [49] FER2013 66.4±0.6 81.7±0.3 69.3 [44] The proposed architecture was implemented using the Caffe toolbox [16] on a Tesla K40 GPU. It takes roughly 20 hours to train 175K samples for 200 epochs.…”

Section: Resultsmentioning

confidence: 99%

Going deeper in facial expression recognition using deep neural networks

Mollahosseini¹,

Chan

Mahoor³

2016

2016 IEEE Winter Conference on Applications of Computer Vision (WACV)

818

367

View full text Add to dashboard Cite

Automated Facial Expression Recognition (FER) has remained a challenging and interesting problem. Despite efforts made in developing various methods for FER, existing approaches traditionally lack generalizability when applied to unseen images or those that are captured in wild setting. Most of the existing approaches are based on engineered features (e.g. HOG, LBPH, and Gabor) where the classifier's hyperparameters are tuned to give best recognition accuracies across a single database, or a small collection of similar databases. Nevertheless, the results are not significant when they are applied to novel data. This paper proposes a deep neural network architecture to address the FER problem across multiple well-known standard face datasets. Specifically, our network consists of two convolutional layers each followed by max pooling and then four Inception layers. The network is a single component architecture that takes registered facial images as the input and classifies them into either of the six basic or the neutral expressions. We conducted comprehensive experiments on seven publically available facial expression databases, viz. MultiPIE, MMI, CK+, DISFA, FERA, SFEW, and FER2013. The results of proposed architecture are comparable to or better than the state-of-the-art methods and better than traditional convolutional neural networks and in both accuracy and training time.

show abstract

Section: Resultsmentioning

confidence: 99%

Going deeper in facial expression recognition using deep neural networks

Mollahosseini¹,

Chan

Mahoor³

2016

2016 IEEE Winter Conference on Applications of Computer Vision (WACV)

818

367

View full text Add to dashboard Cite

show abstract

“…the cross-database task is a much more challenging task than the subjectindependent one and the recognition rates are considerably lower than the ones in the subject-independent case. Table II shows the recognition rate achieved on each database in [33], 84.4 [34], 88.5 [35], 92.0 [36], 92.4 [37], 93.6 [38] MMI 78.68 55.83 63.4 [37], 75.12 [39], 74.7 [36], 79.8 [35], 86.7 [2], 78.51 [40] FERA 66.66 49.64 56.1 [37], 55.6 [41] [3] the cross-database case and it also compares the results with other state-of-the-art methods. Like before, in "Inception-ResNet without CRF" column, the CRF module is replaced with a softmax in our proposed network.…”

Section: B Resultsmentioning

confidence: 99%

Spatio-Temporal Facial Expression Recognition Using Convolutional Neural Networks and Conditional Random Fields

Hasani

Mahoor

2017

2017 12th IEEE International Conference on Automatic Face &Amp; Gesture Recognition (FG 2017)

View full text Add to dashboard Cite

Automated Facial Expression Recognition (FER) has been a challenging task for decades. Many of the existing works use hand-crafted features such as LBP, HOG, LPQ, and Histogram of Optical Flow (HOF) combined with classifiers such as Support Vector Machines for expression recognition. These methods often require rigorous hyperparameter tuning to achieve good results. Recently Deep Neural Networks (DNN) have shown to outperform traditional methods in visual object recognition. In this paper, we propose a two-part network consisting of a DNN-based architecture followed by a Conditional Random Field (CRF) module for facial expression recognition in videos. The first part captures the spatial relation within facial images using convolutional layers followed by three Inception-ResNet modules and two fully-connected layers. To capture the temporal relation between the image frames, we use linear chain CRF in the second part of our network. We evaluate our proposed network on three publicly available databases, viz. CK+, MMI, and FERA. Experiments are performed in subjectindependent and cross-database manners. Our experimental results show that cascading the deep network architecture with the CRF module considerably increases the recognition of facial expressions in videos and in particular it outperforms the stateof-the-art methods in the cross-database experiments and yields comparable results in the subject-independent experiments.

show abstract

“…Table 2 presents the comparative recognition rates on BU-3DFE database. Lee et al method depends on sparse representation [12]. Zheng's method is using group sparse reduced rank regression using GSRRR and ALM [13].…”

Section: Simulation Resultsmentioning

confidence: 99%

“…Average Recognition Rate (%) Lee et al [12] 87.85 Zheng [13] 78.9 Analyzed LBP Based 82.33 VI. CONCLUSION In this paper, we analyzed the performance of Local Binary Patterns for face recognition.…”

Section: Methodsmentioning

confidence: 99%

Analysis of Local Binary Patterns for face recognition under varying facial expressions

Khorsheed

Yurtkan

2016

2016 24th Signal Processing and Communication Application Conference (SIU)

View full text Add to dashboard Cite

Face recognition is one of the most popular biometric today. However, there are still challenges in the development of a robust, real-time face recognition system. Several challenges can be listed as poor illumination, rotations of the face and deformations on the face caused by factors like aging. The most frequent deformations on the face are due to facial expressions that indicate the emotional state of the person. A robust face recognition system should perform well under facial expression deformations. In this paper, we focus on this challenge of face recognition and analyzed the performance of the well known feature extractor Local Binary Patterns (LBPs) under varying facial expressions. The facial expressions considered are the six basic expressions which are anger, disgust, fear, happiness, sadness and surprise. The system is tested on BU-3DFE database. The simulation results show that the LBP features form a strong base for expression invariant face recognition and are open to further improvements.

show abstract

Intra-Class Variation Reduction Using Training Expression Images for Sparse Representation Based Facial Expression Recognition

Cited by 112 publications

References 44 publications

Going deeper in facial expression recognition using deep neural networks

Going deeper in facial expression recognition using deep neural networks

Spatio-Temporal Facial Expression Recognition Using Convolutional Neural Networks and Conditional Random Fields

Analysis of Local Binary Patterns for face recognition under varying facial expressions

Contact Info

Product

Resources

About