K. J.

Somaiya Institute of Engineering & Information Technology, Mumbai

Department of Electronics and Telecommunication Engineering 

Academic Year 2020-21 

Pre synopsis Project Presentation

EMOTION BASED MUSIC

RECOMMENDATION AND PLAYER SYSTEM

JUGALKUMAR LAD LY B EXTC ROLL NO 7

NIYATI KARANI LY B EXTC ROLL NO 4
KINJAL VAGHASIYA LY B EXTC ROLL NO 66
Outline of Pre Synopsis Project Presentation
⮚ Introduction
⮚ Proposed Project/Model/Idea statement
⮚ Objective
⮚ Literature Survey
⮚ Social/Medical/Agricultural/Industry relevance
⮚ Software and Hardware requirements
⮚ System design idea
⮚ Future Scope
⮚ Applications
⮚ References
⮚ Introduction

➢ The human face plays an important role in knowing an individual's mood. The required
input are extracted from the human face directly using a camera.

➢ One of the applications of this input can be for extracting the information to deduce the
mood of an individual. This data can then be used to get a list of songs that comply
with the “mood” derived from the input.

➢ This eliminates the time-consuming and tedious task of manually segregating or

grouping songs into different lists and helps in generating an appropriate playlist based
on an individual's emotional features.

➢ Thus our project focus on detecting human emotions for developing emotion based
music player
⮚ Proposed Project/Model/Idea statement

⮚ 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.
⮚ Therefore our projected system concentrate on identifying the human feelings
for developing emotion based music player using computer vision and machine
learning techniques.
⮚ Objective

➢ The human emotions is an dynamic one and keep on changing on timely manner,
hence observing human emotion and storing values for classification is an
important factor.

➢ To provide an interface between the music system and also provide a very good
entertainment for the users.

➢ To implement the ideas of machine learning, it is programmed to search and

interpret the data and thus create a playlist based on the rules or the parameters
provided.

➢ To provide a new age platform for music lovers and to bridge gap between
growing technologies and music techniques.
 ⮚ Literature Survey
Active Bezier Curve Interactive Anthropometr
Appearance Fitting Model ic Model
Model
⮚ Emotion based music players are
the need of the hour and will Efficiency High in High as it is a Relatively low High Efficiency
favourable two step but real time
provide a boon to the fields of conditions. accurate process.
Emotion Intelligence, Medical Works process.
relatively poor
Science and Psychology. in blur images
or lowly lit
images.
⮚ In recent times, techniques such as
Neural Networks (NN), Support Advantages Based on Works for Study of real Most accurate
supervised detailed time accurate sophisticated
Vector Machines (SVM) have learning. images. data process
been used. We analyze these
Drawbacks Needs good Outliers can Limited data is High memory
techniques which are in quality images hamper the available and multiple
association with our application. accuracy softwares are
required

Keywords/ YCbCr Colour Bezier curve, Textual Meta SVM, ANN

Technology model, Action Feature map tags
used Units
⮚ Social/Medical/Agricultural/Industry relevance

⮚ As a music lover, we’ve always felt that music players should do far more
things than just playing songs and allowing users to create playlists. A music
player should be intelligent and act according to user’s preferences.
⮚ A music player should help users organize and play the songs automatically
without putting much effort into selection and re-organization of songs.
⮚ The Emotion-Based Music Player provides a better platform to all the music
listeners, and ensures automation of song selection and periodic updating of
playlists.
⮚ This helps users organize and play songs based on their moods. The player
should also give recommendation for users to change songs on-the-go.
⮚ This system minimizes the efforts of user to select music according to user’s
current emotional state.
⮚ We believe this sentiment-based music system will help user in enjoying
their music much more.
⮚ Social/Medical/Agricultural/Industry relevance

⮚ The application furthermore aims to provide a simpler, additional hardware-

free and reliable emotion-based music system to the Windows operating
system users. The Emotion-based music program would help people who
are searching for music driven on the emotion and emotional behavior.

⮚ It could help to reduce the search time for music and thus reduce the
unnecessary computational time and thus increase the overall accuracy and
efficiency of the system.

⮚ Not only will the tool relieve physical stress, it also acts as a aid for the
music therapy services and can also assist the music therapies in treating a
patient. It will also be a complete system for music lovers and listeners, with
its additional features discussed elsewhere here.
⮚ Hardware Requirements
➢ x86 64-bit CPU (Intel / AMD architecture)
➢ 4 GB RAM.
➢ 5 GB free disk space
➢ Camera
➢ Speaker

⮚ Software Requirements
➢ Modern Operating System:
➢ Windows 7 or 10
➢ Mac OS X 10.11 or higher, 64-bit
➢ Linux: RHEL 6/7, 64-bit (almost all libraries also work in Ubuntu)
➢ Supported Browsers (Desktop)
➢ Python 3.5 ➢ Pandastable 0.12.2.post1
➢ Keras 2.4.3 ➢ Numpy
➢ Spotipy 2.18.0 ➢ Pandas 1.2.0
➢ Opencv_python_headless 4.5.1.48 ➢ Pillow 8.2.0
➢ Flask 1.1.2 ➢ Tensorflow 2.3.0
⮚ Future Scope and Challenges

⮚ Since we intended this application to be used in any working

environment; accuracy and precision are highly desired to serve the
purpose.

⮚ The use of continues live video stream that is fed into the classifier
should be taken in a well-lit atmosphere for the classifier to give
accurate results.

⮚ There may also be genuinely raised concerns about privacy and

individual rights which can be addressed with some additional
measures such as prior consents for such working environments,
hiding a person’s identity in general, and maintaining transparency
about its fair uses within limited users.
 ⮚ Future Scope and Challenges

➢ The facial emotion recognition algorithms give optimized values of the Action Units
corresponding to eye, eyebrow and lip features. Then this gives input to the neural
network and we get emotions. The application developed will reduce the efforts of the
user in creating and managing playlists.

➢ The music player based on facial recognition system is highly essential for all the
person in modern day life ecology.

➢ This system is further enhanced with benefit able features for upgrading in future. The
methodology of enhancement in the automatic play of songs are done by detection of
the facial expression.

➢ The facial expression is detected by programming interface with the RPI camera. An
alternative method, based on additional emotions which is excluded in our system as
disgust and fear. On this emotion included to support the playing of music
automatically.
 ⮚ System design idea

➢ In the proposed system, we integrate computer

vision and machine learning techniques for
connecting facial emotion for music
recommendation.
➢ For experimental results we used PyCharm tool
for coding. In this we consider real face input of
human using webcam, then image processing
techniques are performed on the input acquired
image.
➢ The features from the input images are extracted
using point detection algorithm.
➢ The classification algorithm OpenCV is used for
training the input images for facial emotion
detection.
➢ Based on the emotions detected music would be
automatically played from the coding folder.
⮚ System design idea

➢ The human face plays an important role in knowing an individual's mood. Camera
is used to get the required input from the human face. One of the applications of
this input can be for extracting the information to deduce the mood of an
individual.

The “emotion” derived from the input provided earlier are used to get a list of
songs. This tedious task of manually Segregating or grouping songs into different
lists are reduced and helps in generating an appropriate playlist based on an
individual's emotional features.

Facial Expression Based Music Player aims at scanning and interpreting the data
and accordingly creating a playlist based on the parameters provided. Thus our
proposed system focuses on detecting human emotions for developing emotion
based music player, which are the approaches used by available music players to
detect emotions, which approach our music player follows to detect human
emotions and how it is better to use our system for emotion detection. A brief idea
about our systems working, playlist generation and emotion classification is also
given. In this project, we used pycharm tool for analysis.
 ⮚ Applications
⮚ The application solves the basic needs of music listeners without troubling them as existing
applications do: it uses technology to increase the interaction of the system with the user in many
ways. It eases the work of the end-user by capturing the image using a camera, determining their
emotion, and suggesting a customized playlist through a more advanced and interactive system.

⮚ The system allows users to create playlists, add songs to it and stream it.

⮚ This project system can be adapted by existing music streaming platforms for better and user-
friendly experience.

⮚ Some of the real time application using this are

➢ Apple Music: The well-known worldwide music streaming application. The advantage of this
application is the music suggestion by user favorite; however, the subscription cost is quite
high.
➢ Spotify: Another worldwide music streaming application. It also suggests songs based on the
user’s data collection. Moreover, the subscription cost is much cheaper than Apple Music.
➢ References

➢ International Research Journal of Engineering and Technology (IRJET):

https://www.irjet.net/archives/V6/i3/IRJET-V6I3403.pdf

➢ Music recommendation using facial emotion detection & classification:

http://www.jcreview.com/fulltext/197-1594987978.pdf

➢ Turkish Journal of Computer and Mathematics Education:

https://turcomat.org/index.php/turkbilmat/article/download/1101/882
Thank You