A MINI PROJECT
On
EMOTION-BASED-MUSIC-PLAYER
BACHELOR OF TECHNOLOGY
IN
COMPUTER SCIENCE AND ENGINEERING
BY
Shamala Tejaswini (18VE1A05A8)
Marpaka Shivani Reddy (18VE1A0589)
Poddaturi Vishal (18VE1A05A0)
Gangula Bani Vishwas (18VE1A0575)
Under the Guidance of
M.Sudhakar, Asst.prof
ACADEMIC BATCH: 2018-2022
Abstract
Problem Statement
Literature Survey
Existing System
Drawbacks
Proposed System
Advantages
Implementation
Software and Hardware requirements
Design and Analysis
Architecture Diagram
Class Diagram
Use case Diagram
Sequence Diagram
Activity Diagram
Sample code
Test Case and Expected results
Testing and analysis
Results
Conclusion
A novel approach that provides, the user with an automatically
created playlist of songs based on the mood of the user.
Music plays a very important role in human’s daily life and in
the modern advanced technologies.
The difficulties in the creation of large playlists can overcome
here.
The music player itself the songs based on the current mood
of the user.
Existing methods for automating the playlist generation process
are computationally slow, less accurate and sometimes even
require use of additional hardware like sensors.
This proposed system based on extraction of facial expressions
that will generate a playlist automatically thereby reducing the
time and effort.
The accuracy of real time algorithm is 85-90% ,while for static
images it is 98-100%.
Cont………
Many factors contribute in conveying emotions of an individual.
Humans can recognize emotions with accuracy. If we can
effectively and efficiently utilize heretofore found knowledge in
computer science to find practical solutions for automatic
recognition of facial emotions.
Various techniques and approaches have been proposed
and developed to classify human emotional state of
behavior.
Facial features have been categorized into two major
categories such as Appearance-based feature extraction
and Geometric based feature extraction.
Current music players have features like play,
pause, shuffle, play next, play previous.
Detector is most effective only on frontal images of faces.
Sensitive to lighting conditions.
We might get multiple detections of the same face, due to
overlapping sub-windows.
Does not detect multiple images.
The foremost concept of this project is to automatically play
songs based on the emotions of the user.
It aims to provide user-preferred music with respect to the
emotions detected. In existing system user has to manually
select the songs, randomly played songs may not match to
the mood of the user, user has to classify the songs into
multiple emotions and then for playing the songs user has to
manually select a particular emotion.
• Hardware requirements:
Device enabled with internet
2 GB RAM
4 GB Internal storage memory.
• Software requirements:
OS : Windows 7 and above
Platform : OpenCV-Python
Our project detects the mood of the user and plays a song or
playlist according to his mood.
The project uses a web camera to capture the image of the
user, it then classifies the facial expression as happy, sad,
neutral, or angry and then plays the song according to the
input image.
This study proposes a music recommendation system which
extracts the image of the user, which is captured with the
help of a camera attached to the computing platform. Once
the picture has been captured, the captured frame of the
image from webcam feed is then being converted to a
grayscale image to improve the performance of the classifier
that is used to identify the face present in the picture. Once
the conversion is complete, the image is sent to the classifier
algorithm which, with the help of feature extraction
techniques is able to extract the face from the frame of the
web camera feed. Once the face is extracted individual
features from the face is extracted and is sent to the trained
network to detect the emotion expressed by the user.
Cont………
The overall idea behind making the system is to enhance
the experience of the user and ultimately relieve some
stress or lighten the mood of the user. The user does not
have to waste any time in searching or to look up for
songs and the best track matching the user’s mood is
detected and played automatically by the music player.
The image of the user is captured with the help of a
webcam. The user’s picture is taken and then as per the
mood/emotion of the user an appropriate song from the
playlist of the user is played matching the user’s
requirement.
For training we have used fisherface method
Train method to train the model
To save the model
For loading model
Prediction and confidence of result
Test case Result
Face Scanning Success
Feature Extraction Success
Emotion Recognition Success
Multiple Emotions Failure
Bad light Conditions Failure
The user carried out system testing once the completion of the
system development.
The purpose of this testing is to check the
functionalities system, whether if it is usable and well-functioned
Happy Sad Angry Neutral
If the face detected is – Angry If the face detected is - Sad
If the face detected is – Happy If the face detected is - Neutral
Which is very less thus helping in achieving a better
real time performance and efficiency.
MODULE TIME TAKEN (sec)
Face detection 0.8126
Facial Feature Extraction 0.9216
Emotion extraction Module 0.9994
Emotion – Audio Integration
Module
0.0006
Proposed System 1.0000
The future scope of the system would to design a
mechanism that would be helpful in music therapy
treatment and provide the music therapist the help need
to treat the patience suffering from disorders like mental
stress, anxiety, acute depression and trauma.
The proposed system also tends to avoid in the future the
unpredictable results produced in extreme bad light
conditions and very poor camera resolution.