Pre-trained Deep Learning Models for Facial Emotions Recognition

Atanassov, Atanas; Pilev, Dimitar

doi:10.1109/icai50593.2020.9311334

Cited by 10 publications

(6 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Separately, in work premises such as a bank or development office, even the emotional state of the persons present (visitors/workers) is relevant for security. There are developments using CNN that can determine the emotions of the detected visitors, and reporting this type of data would increase the security of both the workers and the data and equipment available [17,18].…”

Section: Resultsmentioning

confidence: 99%

Cyber-Physical Security Through Facial Recognition and Sensor Data Analysis

Atanasov,

Pilev

2024

JCTM

View full text Add to dashboard Cite

The digital age has brought tremendous opportunities for innovation and efficiency. However, it has also exposed businesses, governments, and individuals to a range of cyber threats, such as data breaches, network attacks, ransomware, malicious insiders, and identity theft. This requires the implementation of robust cybersecurity measures to safeguard sensitive information and ensure the uninterrupted operation of all critical IT systems. This paper aims to provide a facial recognition security system for cyber-physical security that incorporates a neural network and intelligent algorithms to assess the severity level of security breaches. The system also includes alarms with severity levels ranging from 1 (low severity) to 4 (critical), based on facial recognition and data from carbon dioxide and temperature sensors. In the event of a security breach, an incident response plan is presented. The proposed system is applicable to offices, workspaces, server rooms, data centers and other areas where information is stored, to enhance physical security and protect against cybersecurity threats.

show abstract

Section: Resultsmentioning

confidence: 99%

Cyber-Physical Security Through Facial Recognition and Sensor Data Analysis

Atanasov,

Pilev

2024

JCTM

View full text Add to dashboard Cite

show abstract

“…The selection of DNNs for facial emotion recognition is presented in our ICAI 2020 publication [8]. In it, we have analyzed many multiple neural networks such as DeepFace, OpenFace, VGG16, VGG19, Deepid, Resnet, Facenet, etc in order to select appropriate pre-trained neural network for FER.…”

Section: Choosing a Dnn For Facial Emotion Recognitionmentioning

confidence: 99%

“…Several DNN models presented in are based on ResNet18, ResNet15 or combination of ResNet50, EfficientNet-b0 and SqueezeNet models are used to recognize four weather conditions (cloudy, rainy, sunny, and sunrise) obtain up to 98.22 % accuracy [14 -16]. The accuracy of MeteCNN [17] which was designed to classify 11 weather conditions is 92.68 % and it is comparable to the results of ResNet50, MobileNet, and DenseNet given in Table I MeteCNN is a modified and optimized version of the convolutional neural network VGG16, which was discussed in [8] and was used by us for facial emotion recognition.…”

Section: Choosing a Dnn For Weather Recognitionmentioning

confidence: 99%

See 1 more Smart Citation

Multimodal System for Facial Emotion Recognition Based on Deep Learning

Atanassov,

Pilev,

Tomova

2024

JCTM

View full text Add to dashboard Cite

Emotions are one of the main ways of communication between people and of expressing attitudes towards objects, products, services, etc. They are divided to verbal and non-verbal classes. Human speech and intonation belong to the first class, and to the second (non-verbal) facial and body emotions, known as body language. The subject of this report is the development of multimodal deep learning system intended to recognize facial and body emotions and their relationship with the scene (weather) in which they occur. It is based on three deep learning neural networks (DNN) each one for recognition of facial emotion, body emotion and weather. Combining their results, we improve significantly the final facial emotion recognition (FER) results.

show abstract

“…Facial recognition systems have been beneficial in resolving a host of problems such as identity verification [1], [2], facial expression identification [3], facial emotions classification [4], crime resolution [5], vehicle security [6], [7] and host of others. The rate of kidnappings in Nigerian schools has increased owing to a lack of security frameworks.…”

Section: Introductionmentioning

confidence: 99%

A fast and non-trainable facial recognition system for schools

Oyebode

Ukaoha²

2022

IJEECS

View full text Add to dashboard Cite

Deep learning models have been at the forefront of facial recognition because they deliver improved classification accuracy over traditional ones. Regardless, deep learning models require an extensive dataset for training. To significantly cut down on its training time and dataset volume, pretrained models, have been used although, they are still required to undergo the usual training process for custom facial recognition tasks. This research focuses on an improved facial recognition system that lacks the training and retraining requirements. The system uses an existing deep learning feature extraction model. First, a user stands before a camera-enabled system. After that, the user supplies a unique identification number to fetch a corresponding face image from the database. This process generates two face feature vectors. One from the camera and that retrieved from the database. The cosine distance function determines the similarity value of these vectors. When the cosine distance value falls below a set threshold, the face is recognized and access granted. If the cosine distance of the two vectors gives a value above this threshold, access is denied. The proposed model performs satisfactorily on publicly available datasets.

show abstract

Pre-trained Deep Learning Models for Facial Emotions Recognition

Cited by 10 publications

References 2 publications

Cyber-Physical Security Through Facial Recognition and Sensor Data Analysis

Cyber-Physical Security Through Facial Recognition and Sensor Data Analysis

Multimodal System for Facial Emotion Recognition Based on Deep Learning

A fast and non-trainable facial recognition system for schools

Contact Info

Product

Resources

About