Facial Expression Recognition System

A wide range of applications exist for Facial Expression Recognition (FER) like neutral, sadness, surprise, happiness, fear, anger, contempt and disgust, which include Emotional / Mental state recognition, stress and anxiety detection in medial domain, security domain, human computer interaction etc. In computer vision field Facial Expression Recognition is very interesting and challenging area. In this paper, review some of the facial expression recognition methods are presented. The feature extraction techniques play a crucial role. In this paper a few Facial Feature Extraction techniques like Local Binary Pattern, Local Directional Pattern are discussed. Also recognition based on support vector machines and deep learning algorithms are discussed and compared.

The human face plays an important role for automatic recognition of emotion in the field of identification of human emotion and the interaction between human and computer for some real application like driver state surveillance, personalized learning, health monitoring, automatic music player, etc. In this article we have tried to design an automated framework for emotion detection using facial expression. Facial expression recognition system require to overcome the human face having multiple variability such as colour, orientation, expression, posture, texture and so on. Facial Expression Recognition is challenging problem up till now because of many reasons, moreover, it consists of three sub challenging tasks face detection, facial feature extraction and expression classification. PCA (Principal Component Analysis) analysis is used to detect the face from the captured image. Extended local binary pattern is used for feature extraction of the face. Emotion detection is done by calculating the Euclidian distance between the feature points. Emotions are classified into seven major categories viz. joy, sorrow, surprise, disgust, fear, anger, neutral.

The premise of this paper is to develop a system that detects human emotions through consecutive video frames. Emotions of a person can be detected using facial expressions because the most expressive way a human can show his emotions is through facial expressions. Emotion detection using facial expressions is widely used in various fields like computer science, medicine, and psychology. Automated facial expression recognition is also used in HCI system for better results. Human-computer-interaction can become more natural if computers are able to understand human emotions and their behavior. In this paper a new system for emotion detection using facial expression has been proposed. Input to the system is a sequence of video frames captured using a built-in webcam or external video device. A process of face extraction and cropping is carried out on the video frames captured and then emotions are detected by calculating the Euclidean distance of input image to the train images. The proposed system is implemented in MATLAB version 8.1.0.604 (R2013a).

2013

This paper proposes a emotion detector, applied for facial images, based on the analysis of facial segmentation. The parameterizations have been developed on spatial and transform domains, and the classification has been done by Support Vector Machines. A public database has been used in experiments, The Radboud Faces Database (RAFD), with eight possible emotions: anger, disgust, fear, happiness, sadness, surprise, neutral and contempt. Our best approach has been reached with decision fusion, using transform domains, reaching an accurate up to 96.62%.

publication descriptionJournal of Modern Science and Technology, 2018

Extracting and comprehension of emotion is of high significance for the collaboration among human and machine communication frameworks. The most expressive approach to show the human's emotion is through facial expression analysis. Facial Expression is an acknowledged, non-nosy additionally skillful technique for communication that has been well thoroughly considered as a plausible cooperation of such interface. This paper introduces and actualizes an extraction and acknowledgment technique for facial expression and emotion from still picture. The mean of this examination is making a Facial Expression Recognition (FER) conspire by utilizing Bezier curve and afterward checking the precision by utilizing diverse classifiers (Naïve Bayes, SVM and ANN). After taking a picture from dataset and sequentially applying skin color segmentation, largest connected component and binary image conversion, eyes and lips are isolated from the face. Subsequently Bezier curve for eyes and lips are recognized and are contrasted with those pictures that are stored in the database. Next it finds the nearest Bezier curve from the database. In this way by utilizing these technique emotions (Smile, Normal, Sad & Surprise) communicated by the human face can be distinguished effortlessly. Hence, a Bezier curve based solution together with image processing is used in classifying the emotions by using WEKA. Finally, ANN, Naïve Bayes and SVM classifiers are used to determine the accuracy of the system by training and testing the dataset.

2020

Received May 10, 2020 Revised Jun 1, 2020 Accepted Jul 24, 2020 Facial Expression is a significant role in affective computing and one of the non-verbal communication for human computer interaction. Automatic recognition of human affects has become more challenging and interesting problem in recent years. Facial Expression is the significant features to recognize the human emotion in human daily life. Facial expression recognition system (FERS) can be developed for the application of human affect analysis, health care assessment, distance learning, driver fatigue detection and human computer interaction. Basically, there are three main components to recognize the human facial expression. They are face or face’s components detection, feature extraction of face image, classification of expression. The study proposed the methods of feature extraction and classification for FER.

2013

In recent year facial expression recognition system has gained much popularity in the field of security because facial expression recognition system integrates with the face recognition system make entrenched and improve its strength. Automatic recognition of facial expression achieves greater attraction of researcher and human facial expressions have the ability to communicate emotion and play a major role in the study of psychological phenomena and the progress of nonverbal communication. This paper present facial expression detection method by first skin color segmentation for detecting face and then extract facial feature like eyes and lips after finding the interest point on these facial landmark. Then drawing Bezier curve of these facial points and on the basis of changes in muscles around the eyes, nose and mouths we recognize the three basic facial expressions and achieved expected results. Keywords— Facial expression recognition, Bezier curve, Haar like feature, corner poin...

Journal 4 Research - J4R Journal, 2016

Now days, the task of face recognition is widely used application of image analysis as well as pattern recognition. In biometric area of the research, automatically face & face expression recognition attracts researcher's interest. For classifying facial expressions into different categories, it is necessary to extract important facial features which contribute in identifying proper and particular expressions. Recognition and classification of human facial expression by computer is an important issue to develop automatic facial expression recognition system in vision community. In this paper the facial expression recognition system is proposed.

The automatic facial expression recognition (FER) system is an important concept in human computer interface (HCI), as human face is a part that gives information about the state of user's behavior through various expressions. This study of recognizing facial expression is one of the challenging research areas in image analysis and computer vision. Since last 2 decades many researchers are working to make HCI machines to operate with more reliability and efficiency even in the worst conditions. In this paper, we studied different FER methods such as face detection, feature extraction and expression classification where techniques like Knowledge-based, Feature-based, Principal Component Analysis (PCA), Independent Component Analysis (ICA), Gabor filters, Local Binary Patterns (LBP) with a range of classifiers like a SVM, Adaboost, HMM etc are been compared.

Extracting and comprehension of emotion is of high significance for the collaboration among human and machine communication frameworks. The most expressive approach to show the human's emotion is through facial expression analysis. Facial Expression is an acknowledged, non-nosy additionally skillful technique for communication that has been well thoroughly considered as a plausible cooperation of such interface. This paper introduces and actualizes an extraction and acknowledgment technique for facial expression and emotion from still picture. The mean of this examination is making a Facial Expression Recognition (FER) conspire by utilizing Bezier curve and afterward checking the precision by utilizing diverse classifiers (Naïve Bayes, SVM and ANN). After taking a picture from dataset and sequentially applying skin color segmentation, largest connected component and binary image conversion, eyes and lips are isolated from the face. Subsequently Bezier curve for eyes and lips are recognized and are contrasted with those pictures that are stored in the database. Next it finds the nearest Bezier curve from the database. In this way by utilizing these technique emotions (Smile, Normal, Sad & Surprise) communicated by the human face can be distinguished effortlessly. Hence, a Bezier curve based solution together with image processing is used in classifying the emotions by using WEKA. Finally, ANN, Naïve Bayes and SVM classifiers are used to determine the accuracy of the system by training and testing the dataset.