An Automatic Multilevel Facial Expression Recognition System

Sönmez, Elena Battini

doi:10.19113/sdufbed.50007

Cited by 6 publications

(3 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Even novel techniques like Discrete Wavelet Transform (DWT) found their place in facial expression recognition, as demonstrated by [44], who employed a Single-hidden-layer Neural Network (NN) for classification and achieved a recognition rate of 89.49% ± 0.76%.…”

Section: Related Work Fermentioning

confidence: 99%

An In-Depth Review of Deep Facial Expression Recognition: Obstacles, Utilizations, and Prospective Directions

Khaleel Almsari,

Hussein Miry,

M. Salman

2023

IRJIET

View full text Add to dashboard Cite

Facial expression recognition (FER) is emerging as an emerging and multifaceted field of study. The use of FER in areas such as healthcare, security, and safe driving has not only enhanced the credibility of these technologies, but also their integration into human computer interaction to achieve intelligent outcomes. Computational FER seeks to replicate the skill of humans in decoding facial expressions, providing important cues that complement spoken language and aid listeners in understanding. Likewise, FER's deep learning (DL) and Artificial Intelligence (AI) methodologies are meticulously designed, incorporating advanced modules for efficiency and real time processing. In light of this background, many investigations have looked at different aspects of FER. Although current surveys focus primarily on traditional technologies and generic methodologies for on premises servers, they overlook the large field of deep learning inspired by edge vision and AI assisted FER technologies.To fill this gap, the current study conducts a comprehensive and thorough analysis of the prevailing FER literature. It carefully surveys the operational framework of FER technologies, highlighting their basic and intermediate phases, as well as the underlying pattern structures. Furthermore, the study addresses the limitations inherent in current FER surveys. The exploration extends to the FER datasets, subjecting them to thorough examination, thus revealing the attendant challenges and pitfalls. In addition, it provides a comprehensive discussion of the various metrics used to measure the effectiveness of FER methods.

show abstract

Section: Related Work Fermentioning

confidence: 99%

An In-Depth Review of Deep Facial Expression Recognition: Obstacles, Utilizations, and Prospective Directions

Khaleel Almsari,

Hussein Miry,

M. Salman

2023

IRJIET

View full text Add to dashboard Cite

show abstract

“…Nonetheless, bio-signal-based algorithms often have better accuracy than speech-based stress-detection systems. Despite this performance obstacle, improving neural network-based techniques by gathering a lot of data makes speech-based stress-detection systems more attractive [4]. Detecting stress in individuals is important for early intervention and prevention of long-term health problems.…”

Section: Introductionmentioning

confidence: 99%

Decoding Stress with Computer Vision-Based Approach Using Audio Signals for Psychological Event Identification during COVID-19

Ankit Kumar

2024

jes

View full text Add to dashboard Cite

Interpreting psychological events can be costly and quite complex. It is simple to translate such experiences into a person's spoken and nonverbal cues. The suggested model investigates a computer vision-based method for using an individual's audio signal to identify stressful psychological events. Different people's input speech signals are recorded and compared to the common questionnaire. A series of inquiries pertaining to the second stage of COVID-19 events are included in the questionnaire set. Through additional processing, these speech signals are converted into frequency components by means of the Fast Fourier transformation (FFT) method. A long short-term memory module processes each frequency component and produces temporal information from each frequency band. The features of speech signals are extracted into the temporal frames by this module. The VGG 16 algorithm is used to further classify each temporal frame into stress and un-stress classes. A classifier with 16 layers of architecture is called VGG 16. A feed-forward convolutional neural network called VGG 16 is used to divide the vast array of speech signal features into classes: stressed and unstressed. The proposed model attempts to recognize speech signals as stress indicators. A standard set of questionnaires with a series of interrogation-style questions has been used to develop the stress symptoms in an individual's mind. The audio signals generated by each person's responses are recorded and subsequently analyzed for stress and un-stress classes. The proposed model was able to identify stress in speech signals with 98% accuracy. The time and cost implications of the suggested model are relevant. Medical research is typically costly and time-consuming.LSTM; VGG 16; CNN model; data preprocessing; speech signal.

show abstract

“…The best accuracy for LBP+KNN was 87.44 % when cell size 32 was used, while the best accuracy for LBP+SVM was 90.23% when cell size 32 was used. The characterization experiment was conducted using the ADFES-BIV dataset [7]. They proposed a programmed framework that used a sparse-representation-based classifier and achieved an accuracy of up to 80% by considering the fleeting data inherent in video recordings.…”

Section: Introductionmentioning

confidence: 99%

Enhanced Emotion Recognition in Videos: A Convolutional Neural Network Strategy for Human Facial Expression Detection and Classification

Ashraf¹,

Gunawan

Arifin³

et al. 2023

IJEEI

View full text Add to dashboard Cite

The human face is essential in conveying emotions, as facial expressions serve as effective, natural, and universal indicators of emotional states. Automated emotion recognition has garnered increasing interest due to its potential applications in various fields, such as human-computer interaction, machine learning, robotic control, and driver emotional state monitoring. With artificial intelligence and computational power advancements, visual emotion recognition has become a prominent research area. Despite extensive research employing machine learning algorithms like convolutional neural networks (CNN), challenges remain concerning input data processing, emotion classification scope, data size, optimal CNN configurations, and performance evaluation. To address these issues, we propose a comprehensive CNN-based model for real-time detection and classification of five primary emotions: anger, happiness, neutrality, sadness, and surprise. We employ the Amsterdam Dynamic Facial Expression Set -Bath Intensity Variations (ADFES-BIV) video dataset, extracting image frames from the video samples. Image processing techniques such as histogram equalization, color conversion, cropping, and resizing are applied to the frames before labeling. The Viola-Jones algorithm is then used for face detection on the processed grayscale images. We develop and train a CNN on the processed image data, implementing dropout, batch normalization, and L2 regularization to reduce overfitting. The ideal hyperparameters are determined through trial and error, and the model's performance is evaluated. The proposed model achieves a recognition accuracy of 99.38%, with the confusion matrix, recall, precision, F1 score, and processing time further quantifying its performance characteristics. The model's generalization performance is assessed using images from the Warsaw Set of Emotional Facial Expression Pictures (WSEFEP) and Extended Cohn-Kanade Database (CK+) datasets. The results demonstrate the efficiency and usability of our proposed approach, contributing valuable insights into real-time visual emotion recognition.

show abstract

An Automatic Multilevel Facial Expression Recognition System

Cited by 6 publications

References 22 publications

An In-Depth Review of Deep Facial Expression Recognition: Obstacles, Utilizations, and Prospective Directions

An In-Depth Review of Deep Facial Expression Recognition: Obstacles, Utilizations, and Prospective Directions

Decoding Stress with Computer Vision-Based Approach Using Audio Signals for Psychological Event Identification during COVID-19

Enhanced Emotion Recognition in Videos: A Convolutional Neural Network Strategy for Human Facial Expression Detection and Classification

Contact Info

Product

Resources

About