Facial Expression Recognition Based on Deep Learning Convolution Neural Network: A Review (original) (raw)

A Review on Facial Expression Recognition System using Deep Learning

2021

Human emotions are spontaneous and conscious mental states of feeling that are accompanied by physiological changes in the face muscles implying face expression. Some important emotions are happy, sad, anger, disgust, fear, surprise, neutral, etc. In non-verbal communication, facial expressions play a very important role because of the inner feelings of a person that reflect on faces. A lot of studies have been carried out for the computer modeling of human emotion. However, it's far behind the human vision system. In the area of computer vision, academic research in deep learning, specifically research into convolutional neural networks, received a lot of attention with the fast growth of computer hardware & the arrival of the Big Data era. Many researches & studies on emotion recognition & deep learning methods are carried out to identify emotions. This article presents a survey of Face Expression Recognition (FER) methods, including 3 key phases as pre-processing, extraction ...

Automated Facial Expression Recognition Using Deep Learning Techniques: An Overview

2020

Facial expression recognition (FER) plays a key role in conveying human emotions and feelings. Automated FER systems enable different machines to recognize emotions without the help of humans; this is considered as a very challenging problem in machine learning. Over the years there has been a considerable progress in this field. In this paper we present a state of the art overview on the different concepts of a FER system and the different used methods; plus we studied the efficiency of using deep learning architectures specifically convolutional neural networks architectures (CNN) as a new solution for FER problems by investigating the most recent and cited works.

Automatic Facial Expression Recognition Method Using Deep Convolutional Neural Network

2021

Facial expressions are part of human language and are often used to convey emotions. Since humans are very different in their emotional representation through various media, the recognition of facial expression becomes a challenging problem in machine learning methods. Emotion and sentiment analysis also have become new trends in social media. Deep Convolutional Neural Network (DCNN) is one of the newest learning methods in recent years that model a human's brain. DCNN achieves better accuracy with big data such as images. In this paper an automatic facial expression recognition (FER) method using the deep convolutional neural network is proposed. In this work, a way is provided to overcome the overfitting problem in training the deep convolutional neural network for FER, and also an effective pre-processing phase is proposed that is improved the accuracy of facial expression recognition. Here the results for recognition of seven emotional states (neutral, happiness, sadness, su...

Facial emotion recognition using convolutional neural networks (FERC)

SN Applied Sciences

Facial expression for emotion detection has always been an easy task for humans, but achieving the same task with a computer algorithm is quite challenging. With the recent advancement in computer vision and machine learning, it is possible to detect emotions from images. In this paper, we propose a novel technique called facial emotion recognition using convolutional neural networks (FERC). The FERC is based on two-part convolutional neural network (CNN): The firstpart removes the background from the picture, and the second part concentrates on the facial feature vector extraction. In FERC model, expressional vector (EV) is used to find the five different types of regular facial expression. Supervisory data were obtained from the stored database of 10,000 images (154 persons). It was possible to correctly highlight the emotion with 96% accuracy, using a EV of length 24 values. The two-level CNN works in series, and the last layer of perceptron adjusts the weights and exponent values with each iteration. FERC differs from generally followed strategies with single-level CNN, hence improving the accuracy. Furthermore, a novel background removal procedure applied, before the generation of EV, avoids dealing with multiple problems that may occur (for example distance from the camera). FERC was extensively tested with more than 750K images using extended Cohn-Kanade expression, Caltech faces, CMU and NIST datasets. We expect the FERC emotion detection to be useful in many applications such as predictive learning of students, lie detectors, etc.

A CNN based facial expression recognizer

Materials Today: Proceedings, 2021

Facial expression recognition [FER] has gained attraction among many researchers in the field of artificial intelligence. The existing models available for facial expression recognition are developed with the help of native machine learning models. But the accuracies and efficiency achieved by these models are still undergoing extensive research. The proposed research work uses Convolutional Neural Networks (CNN) deep learning models with sufficient Computational power to run the algorithms. This model is able to achieve good accuracy even on the new datasets. Our experimental results achieved an accuracy of 57% in a five-classification task.

Optimizing Deep Convolutional Neural Network for Facial Expression Recognition

European Journal of Engineering Research and Science

Facial expression recognition (FER) systems have attracted much research interest in the area of Machine Learning. We designed a large, deep convolutional neural network to classify 40,000 images in the data-set into one of seven categories (disgust, fear, happy, angry, sad, neutral, surprise). In this project, we have designed deep learning Convolution Neural Network (CNN) for facial expression recognition and developed model in Theano and Caffe for training process. The proposed architecture achieves 61% accuracy. This work presents results of accelerated implementation of the CNN with graphic processing units (GPUs). Optimizing Deep CNN is to reduce training time for system.

Optimizing Deep Convolutional Neural Network for Facial Expression Recognitions

Advances in intelligent systems and computing, 2018

Facial expression recognition (FER) systems have attracted much research interest in the area of Machine Learning. We designed a large, deep convolutional neural network to classify 40,000 images in the data-set into one of seven categories (disgust, fear, happy, angry, sad, neutral, surprise). In this project, we have designed deep learning Convolution Neural Network (CNN) for facial expression recognition and developed model in Theano and Caffe for training process. The proposed architecture achieves 61% accuracy. This work presents results of accelerated implementation of the CNN GPUs. Optimizing Deep CNN is to reduce training time for system.

Survey on Facial Emotion Recognition and Detection Using Deep Learning

International Journal of Innovative Research in Technology, 2021

In recent times, due to evolution of technologies and the role they play in our day to day lives along with human's interpersonal communication, human and machine or human computer interactions have become very basic. When human's interpersonal communication is concerned, humans are well trained in reading the emotions of others even when the other person is not communicating verbally. But this is not possible with human computer/machine interactions. To make this possible the use of Convolution neural network (CNN) in facial emotion recognition and detection technology plays a vital role.

CNN based Facial Expression Recognition System

Social Science Research Network, 2021

Training machines to think and behave like humans have fascinated many researchers around the world. Deep learning a subgroup of Machine Learning enables us to develop a system that can extract features, recognize distinct patterns, and classifies them just like a human brain. Facial Expression Recognition (FER) is one of the trending technology in the Human-Machine Interaction field. This paper contributes to a novel system that makes use of Convolutional Neural networks with fewer data samples and high accuracy. The main objective is to develop a system that can classify the different expressions from the human face and identifies them accurately. In our system, we had developed a 15 layer CNN architecture which plays an important role in classifying images and training the system. This existing system can classify 6 basics facial expressions such as happy, angry, fear, sad, disgust, and surprise with an accuracy of 98.1%.

Facial Expression Recognition Using Deep Convolution Neural Network With Tensorflow

International Journal of Advance Research and Innovative Ideas in Education, 2020

Facial expression recognition (FER) is an automatic system that manipulates the facial data and plays a vital role in human machine interfaces. Olden machine learning algorithms has attracted incrementing attention from researchers since the early nineties. It approaches often requires complex feature extraction process. In this paper we reflected recent advances in deep learning to Convolutional Neural Networks (CNN). It is an prominent field which uses nowadays applications such as in robots, games and neuromarketing. It is widely used technique uses facial expressions, eye movement and gestures which conveys the emotional status and feelings of persons. The proposed model made pivot on detecting the facial expressions of an individual from a single image. The number of parameters in our proposed networks concentrated by decreasing manner that accelerates the total performance speed and makes this well and make suitable for real time systems