Manuscript Number : IJSRSET195907
Movie Review Using Emotion Detection
Authors(3) :-Adars Manilal, Andrew Senson, Arathy Krishnan
Movie review is a general process taking place whenever a movie is released. The nature of movie is always a question for movie viewers. The release of movie makes viewers enthusiastic and they won’t be able to know the absolute nature of movie. Nowadays after the release of a movie a third person will be standing outside the theatre to know about people feelings. They will be holding a recording mic and another person will be taking video of the process. After the questioning is over, they release the video to internet or there private channels to show the nature of movie. Hence a live review of movie is not possible at the moment. This project presents a solution such that a live review is done at the time when movie is running in the screen. Emotion detection is the process of identifying human emotion. With the help of machine learning model we can have trained classifier and the nature of human emotion can be identified. A high definition camera inside the hall can detect faces of people and detect the emotions they are showing at each second. This system updates the review during each second and review about the movie will be updated at the present time thus getting a live review. By implementing this project the review about the movie can be seen at the present time through a web application. Facial expression recognition enables computers to understand human emotions and is the basis and prerequisite for quantitative analysis of human emotions. First, we look at different representations for faces in images and videos. The objective is to learn compact yet effective representations for describing faces. We first investigate the use of descriptors (of algorithm) for this task. Generally three important steps involving in the face recognition system are: (1) detection and rough normalization of faces, (2) feature extraction and accurate normalization of faces, (3) identification and/or verification. Having developed these representation, we propose a method for labeling faces in the challenging environment. The face feature tells clearly what is their opinion about the visual experience thus we can rate the movie according to their opinion. Through machine learning, sentiment analysis can be acheived with greater accuracy .There are many ways for facial emotion detection like Viola-Jones algorithm, convolution neural network method from deep learning. The efficient algorithmic method from above can be used to obtain a better output to know about an individuals facial emotion. In this project we deals with sentiment analysis through facial features and gives rating about the movies.
Adars Manilal
Sentimental Analysis, Machine Learning, Convolution Neural Network (CNN).
Publication Details
Published in :
Volume 5 | Issue 9 | May 2019 Article Preview
Department of Computer Science and Engineering, Younus College of Engineering and Technology, Pallimukku, Vadakkevila, Kollam, Kerala, India
Andrew Senson
Department of Computer Science and Engineering, Younus College of Engineering and Technology, Pallimukku, Vadakkevila, Kollam, Kerala, India
Arathy Krishnan
Department of Computer Science and Engineering, Younus College of Engineering and Technology, Pallimukku, Vadakkevila, Kollam, Kerala, India
Date of Publication :
2019-06-07
License: This work is licensed under a Creative Commons Attribution 4.0 International License.
Page(s) :
49-54
Manuscript Number :
IJSRSET195907
Publisher : Technoscience Academy
Journal URL :
https://ijsrset.com/IJSRSET195907