Facial Expression Recognition Using Convolutional Neural Network (original) (raw)

A Facial Expression Recognition System using Convolutional Neural Network

A Facial expression is the visible manifestation of the affective state, cognitive activity, intention, personality and psychopathology of a person and plays a communicative role in interpersonal relations. Automatic recognition of facial expressions can be an important component of natural human-machine interfaces; it may also be used in behavioral science and in clinical practice. An automatic Facial Expression Recognition system needs to perform detection and location of faces in a cluttered scene, facial feature extraction, and facial expression classification. Facial expression recognition system is implemented using Convolution Neural Network (CNN). CNN model of the project is based on LeNet Architecture. Kaggle facial expression dataset with seven facial expression labels as happy, sad, surprise, fear, anger, disgust, and neutral is used in this project. The system achieved 56.77 % accuracy and 0.57 precision on testing dataset.

Facial Expression Recognition Using Convolutional Network

International Journal for Research in Applied Science & Engineering Technology (IJRASET), 2022

This paper focuses on Emotion Recognition using facial expressions. It aims to detect facial expressions accurately and efficiently. Convolutional Neural Network has developed to help in recognizing emotions through facial expressions and classify them into seven basic categories which are: happy, sad, neutral, surprise, fear, disgust, and angry. So, Convolutional Neural Network is implemented to extract relevant features of the input images and classify them into seven labels. For evaluating the proposed model, Facial Emotion Recognition 2013 dataset is used so that the model achieves the best accuracy rate. Facial expression recognition has been an active area of research over the past few decades, and it is still challenging due to the high intra-class variation.

Facial Expression Classification Using Convolutional Neural Network and Support Vector Machine

—Perception of facial emotional expressions is an important element of human communication, supporting social interactions by means of their informative, evocative and incentive functions. Thus, computational approaches to automatically classify facial emotional expressions may contribute to improve human machine interfaces, among other applications. This work presents an algorithm for human emotional state classification from grayscale still images of faces. These images are from the Extended Cohn-Kanade public dataset and represent three emotional states: Aversion, Happiness and Fear. Preprocessing applied to the images are restricted to cropping the region around the eyes and mouth, image resizing, and intensity mean pixel to pixel subtraction. Images characteristics extraction are handled by a previously trained Alexnet Convolutional Neural Network. The classification system is a Support Vector Machine and has achieved an average accuracy of 98.52% on the aforementioned classes.

Emotion Recognition of Facial Expression Using Convolutional Neural Network

Innovative Data Communication Technologies and Application

Recognition of emotion using facial information is an interesting field for computer science, medicine, and psychology. Various researches are working with automated facial expression recognition system. Convolutional neural network (CNN) for facial emotion recognition method is basically used to recognize different-different human facial landmarks, geometrical poses, and emotions of faces. Human facial expression gives very important information to understand the emotions of a person for an interpersonal relationship. Since it is a classification problem, so the performance of any classifier is dependent on features extracted from the region of interest of the sample. In this paper, we are going to train the machine to recognize different types of emotions through human facial expressions using the Convolutional Neural Network (CNN). We have used sequential forward selection algorithms and softmax activation function.

Real Time Facial Expression Recognition using Convolution Neural Network Algorithm

International Journal for Research in Applied Science and Engineering Technology IJRASET, 2020

The most expressive way human beings display emotions is through facial expressions. The task of detecting facial expression of a human being via a computer is a very complex process due to its variability present across human faces including color, expression, position, and orientation. The aim of this paper is to presents a Convolution Neural Network (CNN) architecture for real-time facial expression recognition. We have used ICML 2013 Facial Expression Recognition Challenge dataset for this study and then trained our neural network for emotion state classification. In this study, we achieved accuracy of 84.18% and validation accuracy of 67.56% for classification of seven different emotions through facial expressions.

Hybrid Approach for Facial Expression Recognition Using Convolutional Neural Networks and SVM

Applied Sciences

Facial expression recognition is very useful for effective human–computer interaction, robot interfaces, and emotion-aware smart agent systems. This paper presents a new framework for facial expression recognition by using a hybrid model: a combination of convolutional neural networks (CNNs) and a support vector machine (SVM) classifier using dynamic facial expression data. In order to extract facial motion characteristics, dense facial motion flows and geometry landmark flows of facial expression sequences were used as inputs to the CNN and SVM classifier, respectively. CNN architectures for facial expression recognition from dense facial motion flows were proposed. The optimal weighting combination of the hybrid classifiers provides better facial expression recognition results than individual classifiers. The system has successfully classified seven facial expressions signalling anger, contempt, disgust, fear, happiness, sadness and surprise classes for the CK+ database, and facia...

FACIAL EMOTION RECOGNITION USING CONVOLUTIONAL NEURAL NETWORK

ICTACT JOURNAL ON IMAGE AND VIDEO PROCESSING , 2021

Facial expressions play a significant role in social communication since they convey a lot of information about people, such as moods, emotions, and other things. Many researchers gained an optimal accuracy in most of the popular facial recognition datasets: CK+, JAFFE, IEV, but in FER2013 the best model accuracy is about 74%. This article purpose deep learning-based models to mitigate this issue. Three models based on AlexNet, VGG19, and ResNet50 are used to train with the dataset, and the very best model among them is further analyzed. The best model is trained using various optimizers and evaluated based on its training and testing accuracy, confusion matrix, ROC Curve. The finest model gained an accuracy of 91.89504% which is better than past state of art models by at least 17% accuracy.

FACIAL EMOTION RECOGNITION USING CONVOLUTION NEURAL NETWORK

Facial expression recognition is a very active research topic due to its potential applications in the many fields such as human-robot interaction, human-machine interfaces, driving safety, and health-care. Despite of the significant improvements, facial expression recognition is still a challenging problem that wait for more and more accurate algorithms. This article presents a new model that is capable of recognizing facial expression by using deep Convolutional Neural Network (CNN). The CNN model is generated by using Caffe in Digits environment. Moreover, it is trained and tested on NVIDIA Tegra TX1 embedded development platform including a 250 Graphics Processing Unit (GPU) CUDA cores and Quadcore ARM Cortex A57 processor. The proposed model is applied to address the facial expression problem on the publicly available two expression databases, the JAFFE database and the Cohn-Kanade database.

Automatic Facial Expression Recognition using Convolutional Neural Network (CNN

Facial Expression Recognition is has been widely used in Artificial Intelligence, Human-Computer Interaction, and Security Monitoring. Convolution neural network (CNN) works as a depth learning architecture and it can extract the essential features of the image. In the case of large changes in shooting conditions, CNN's effect is better than the methods of Support Vector Machines (SVM) and Principal Component Analysis (PCA). Therefore, we are proposing a method based on CNN. The purpose is to classify each facial image as one of the seven facial expressions considered here. A new convolution neural network structure has been designed according to the characteristics of facial expression recognition. To extract implicit features convolution kernel is being used and max-pooling is being used to reduce the dimensions of the extracted implicit features. In comparison to AlexNet network, we can improve the recognition accuracy about on the FER and CK+ facial expression database with the help of Batch Normalization (BN) layer to our network. A facial expression recognition system is constructed for the convenience of application, and all the experimental results show that the system can reach the real-time needs.

Facial Expression Recognition Using AI

2021

The emotions evolved in face have an excellent influence on decisions and arguments about various subjects. In psychological theory, emotional states of an individual are often classified into six main categories: surprise, fear, disgust, anger, happiness and sadness. Automatic extraction of those emotions from the face images can help in human computer interaction also as many other applications. Machine learning algorithms and particularly deep neural network can learn complex features and classify the extracted patterns. In this paper, a deep learning based framework is used for human emotion recognition. The proposed framework uses the feature extraction then a Convolutional Neural Network (CNN) for classification. The experimental results show that the proposed methodology increases both of the speed training process of CNN and therefore the recognition accuracy.