SMART EYE Calculating Concentration Index of different Age Groups in Online class by Emotion Detection based on Facial Expressions and Speech

Abstract

Emotions play a vital role in life of human being. It is very important to know and newlinerecognize how others may react while interactions. Emotion recognition is one of the newlinehot topics these days in fields like medical, business, education, academic research newlineand many more. Many applications like cognitive computing, affective computing, newlinecomputer vision, entertainment is widely used with emotion recognition and are at newlinehigh demand. Affective computing recognizes a user s emotional status and respond newlineto the user in an effective way by intelligent human-machine interaction. There are newlinemany sources of emotion recognition like face expressions, hands, body language, newlinetext, speech etc. Applying any one of these techniques will not reflect much to find newlineemotions appropriately, as human emotions can change every single second or less newlinethan that. newlineModality is the word that refers to different modes of recognition. In early researches newlineit has been seen that single modality more over taken into considerations for emotion newlinerecognition which always not give better results due to insufficient information. newlineMulti-model functionality helps in overall recognition process for increasing newlinereliability. Fusing multiple feature sets and classifiers into one system will produce a newlinecomparably more accurate system. This research works includes combination of newlinespeech and facial expressions, as this hybrid mode will help in evaluating results newlineperfectly and as per desire. The proposed methodology used here consists of two main newlineparts; first is Facial Expression Recognizer (FER) and Speech Emotion Recognition newline(SER) is second part and for the final result hybrid mode will work that consider newlineoutput of both FER and SER. This is multi-sensory and multi-model emotion newlinerecognition system. newlineIt has been seen that this system gives better accuracy than any other existing systems newlineand results is more towards naturalness rather than traditional method. Hybrid system newlineuses the results of facial emotion and speech emotion recognition system. So, a final newlineresult will be conside