Studies on Magic Mirror Using Augmented Reality: Review

Dabhade, Ruchira Kurve (2021) Studies on Magic Mirror Using Augmented Reality: Review. In: New Approaches in Engineering Research Vol. 3. B P International, pp. 134-141. ISBN 978-93-91312-89-3

Full text not available from this repository.

Abstract

A magic mirror paradigm is an augmented reality (AR) system where a camera and display device act as a mirror where one can see a reflection of oneself and virtual objects together. The proposed system has a camera to capture the viewer’s facial expression. By analyzing the expressions, the system is able to determine the emotion of the viewer. If the viewer is in a negative emotion, the system then speaks positive sentences and plays the viewer’s favourite music to alleviate his/her emotion. The proposed system can serve as a calendar for event reminding. Hardware like USB Web Cam (8 MP or higher) & Computer System are used for this project. There are three modes in this system that is mirror mode, alleviation mode, silent mode, reminder mode.

Objective of this project is to recognize the mood of a person & to give them support as a digital friend. This project gives a reliable friend that will motivate you, keeps you always happy. Social signals reveal individual emotions toward of a person by facial expressions, vocal intonations and outbursts, body gestures and postures, etc. However, we only focus the research scope in the facial expression (Sad, angry, happy, surprise) for the purpose of simplifying the problem.

Facial expression is achieved through various methods such as optical flow, hidden Markov model, and neural network processing and active appearance model. For example, the Face Reader recognizes facial expressions by distinguishing six basic emotions (happy, angry, sad, surprised, scared, disgusted), plus neutral. Positive word inspiration, alleviating negative emotions, and affairs reminding is done through optical flow, hidden Markov model, neural network processing and active appearance model.

Item Type: Book Section
Subjects: Institute Archives > Engineering
Depositing User: Managing Editor
Date Deposited: 28 Oct 2023 05:24
Last Modified: 28 Oct 2023 05:24
URI: http://eprint.subtopublish.com/id/eprint/3301

Actions (login required)

View Item
View Item