Emotions based
music system
ABSTRACT
In this proposed system, we develop a prototype in
recommendation of dynamic music recommendation
system based on human emotions. Based on each
human listening pattern, the songs for each emotions
are trained. Integration of feature extraction and
machine learning techniques, from the real face the
emotion are detected and once the mood is derived
from the input image, respective songs for the specific
mood would be played to hold the users. In this
approach, the application gets connected with human
feelings thus giving a personal touch to the users.
EXISTING SYSTEM
Existing system is manual system in which one must
select songs by themselves.
Even though applications such as WYNK suggests
music they are not based on mood, they are based on
previous music history.
DISADVANTAGES OF EXISTING SYSTEM
Does’t consider persons state of mind I.E. Will
suggest same set of songs even though person is in
different mood.
In the existing system, there is no any system which
has both expression recognition and music
recommendation.
PROPOSED SYSTEM
The proposed system is divided into two parts front
end part which is the user interface and the back end
which performs all facial expression related operations.
All the application is implemented in python front end
is implemented using python module Tkinter and
backend is implemented using Keras module.
When the application is started it automatically triggers
the prediction module which is used for prediction of
facial expression. The prediction module calls the
system camera for retrieving image, then the image is
classified using the pre-trained model. This process is
repeated for N times to get N predictions, from N
predictions maximum counted value is taken and is
returned to the application.
Then the application suggests playlist based on
predicted value. Users can either start that playlist or
listen to his regular songs. Users can do operations
general music player operations such as play, pause,
next, previous. The application will suggest a playlist
based on mood for every K number of songs.
ADVANTAGES OF PROPOSED SYSTEM
The smart music player is an application that runs
based on the idea that we can detect a person's mood
based on the expression on his face.
The expression on the face is detected using
convoluted neural networks (CNN). The set of images
is taken from the camera of the device and these
images are given to a pre-trained CNN which returns
facial expression to application. Based on facial
expression a song playlist is suggested.
This is an additional feature of the existing feature of
a music player. Usually facial expression changes
within seconds and not consistent so it may lead to
wrong playlist suggestion to overcome this problem
application collects N number of images when the
application is started and takes facial expression
which has appeared the maximum number of times.
SYSTEM ARCHITECTURE
FUTURE SCOPE
Mood based music recommendations
Therapeutic Music Applications
Integrating with various music streaming platforms
Application for mental health and wellness
HARDWARE REQUIREMENTS
System : Pentium i3
Processor.
Hard Disk : 500 GB.
Monitor : 15’’ LED
Input Devices : Keyboard, Mouse
Ram : 4 GB
SOFTWARE REQUIREMENTS
Operating system : Windows 10.
Coding Language : Python
