Effective recognition of facial emotions using dual transfer learned feature vectors and support vector machine

Subudhiray, Swapna; Palo, Hemanta Kumar; Das, Niva

doi:10.1007/s41870-022-01093-7

Cited by 8 publications

(8 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, pre-trained networks can be used for the following tasks: Classification, which can apply pre-trained networks directly to classification tasks [ 34 , 35 , 38 , 53 , 80 ]. Feature extraction, which is pre-trained network which can be used as a feature extractor using the activation layers as features, and these layers can be used to train other machine learning models, such as a support vector machine (SVM) [ 62 , 77 , 83 , 90 , 101 ]. Transfer learning, in which the layers of a neural network trained on one dataset are adjusted and reused to test a new dataset [ 54 , 73 , 102 , 103 , 104 ].…”

Section: New Trends In Using Neural Network For Fermentioning

confidence: 99%

“…Feature extraction, which is pre-trained network which can be used as a feature extractor using the activation layers as features, and these layers can be used to train other machine learning models, such as a support vector machine (SVM) [ 62 , 77 , 83 , 90 , 101 ].…”

Section: New Trends In Using Neural Network For Fermentioning

confidence: 99%

“…During its architecture evolution on each version, the main goal was to increase the computational efficiency and to decrease the number of parameters, and this optimization gained over each released version was also effective in terms of minimizing the error rate. Therefore, different versions of the Inception network are used for feature extraction in [ 30 ] or emotion recognition, transfer learning, and fine-tuning in [ 62 , 81 , 113 , 114 , 115 , 116 ].…”

Section: New Trends In Using Neural Network For Fermentioning

confidence: 99%

“…It was designed for low-resolution images, and because of time constraints in terms of computing power, it did not present significant results. In [ 81 , 124 ], both networks are used to evaluate the proposed method for facial emotion recognition and in [ 62 , 103 ] for transfer learning.…”

Section: New Trends In Using Neural Network For Fermentioning

confidence: 99%

“…Wide ResNet [121], a variant of ResNet, has decreased the depth and increased the width of residual networks. This type of architecture is used in [62] for effective analysis.…”

mentioning

confidence: 99%

See 4 more Smart Citations

New Trends in Emotion Recognition Using Image Analysis by Neural Networks, a Systematic Review

Cîrneanu,

Popescu,

Iordache

2023

Sensors

View full text Add to dashboard Cite

Facial emotion recognition (FER) is a computer vision process aimed at detecting and classifying human emotional expressions. FER systems are currently used in a vast range of applications from areas such as education, healthcare, or public safety; therefore, detection and recognition accuracies are very important. Similar to any computer vision task based on image analyses, FER solutions are also suitable for integration with artificial intelligence solutions represented by different neural network varieties, especially deep neural networks that have shown great potential in the last years due to their feature extraction capabilities and computational efficiency over large datasets. In this context, this paper reviews the latest developments in the FER area, with a focus on recent neural network models that implement specific facial image analysis algorithms to detect and recognize facial emotions. This paper’s scope is to present from historical and conceptual perspectives the evolution of the neural network architectures that proved significant results in the FER area. This paper endorses convolutional neural network (CNN)-based architectures against other neural network architectures, such as recurrent neural networks or generative adversarial networks, highlighting the key elements and performance of each architecture, and the advantages and limitations of the proposed models in the analyzed papers. Additionally, this paper presents the available datasets that are currently used for emotion recognition from facial expressions and micro-expressions. The usage of FER systems is also highlighted in various domains such as healthcare, education, security, or social IoT. Finally, open issues and future possible developments in the FER area are identified.

show abstract

Section: New Trends In Using Neural Network For Fermentioning

confidence: 99%

Section: New Trends In Using Neural Network For Fermentioning

confidence: 99%

Section: New Trends In Using Neural Network For Fermentioning

confidence: 99%

Section: New Trends In Using Neural Network For Fermentioning

confidence: 99%

“…Wide ResNet [121], a variant of ResNet, has decreased the depth and increased the width of residual networks. This type of architecture is used in [62] for effective analysis.…”

mentioning

confidence: 99%

See 3 more Smart Citations