Scribd
Upload
5K views16 pages

Music Recommendation System Powerpoint Presentation

This project aims to develop a Song Recommender System (SRS) that recommends songs according to the emotion detected on a user's face from webcam footage. The methodology involves collecting data using Python libraries like mediapipe and numpy. This data is then trained using TensorFlow and other libraries to create trained models. These models are then implemented using Streamlit to build a web app that can capture a user's face, detect their emotion, and recommend songs on YouTube matching that emotion. The project presents screenshots of the testing and results, achieving its goal of emotion-based song recommendation. Future work could improve the models and expand the database of emotion-song mappings.

Uploaded by

A-Z
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
5K views16 pages

Music Recommendation System Powerpoint Presentation

This project aims to develop a Song Recommender System (SRS) that recommends songs according to the emotion detected on a user's face from webcam footage. The methodology involves collecting data using Python libraries like mediapipe and numpy. This data is then trained using TensorFlow and other libraries to create trained models. These models are then implemented using Streamlit to build a web app that can capture a user's face, detect their emotion, and recommend songs on YouTube matching that emotion. The project presents screenshots of the testing and results, achieving its goal of emotion-based song recommendation. Future work could improve the models and expand the database of emotion-song mappings.

Uploaded by

A-Z
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 16

ASHOKA INSTITUTE OF TECHNOLOGY AND MANAGEMENT,

VARANASI
PROJECT PRESENTATION ON SONG RECOMMENDER SYSTEM (SRS)
OF
BACHELOR OF TECHNOLOGY
IN
COMPUTER SCIENCE & ENGINEERING
BY
HARSHIT SRIVASTAVA
AYUSH KUMAR JAISWAL
DHANANJAY CHAUHAN
SOMESH SINGH
UNDER THE GUIDANCE OF
DR. PRITI kumari (HEAD OF DEPARTMENT)
CONTENTS
• Introduction
• Methodology
• Data Collection
• Data Training
• Final Implementation
• Testing and Screenshots
• Result
• Future Scope
INTRODUCTION

Rapid development of mobile devices and


internet has made possible for us to access Thus, there is a strong need of a good
different music resources freely. The recommendation system. Song
number of songs available exceeds the Recommender System (SRS) is a system
listening capacity of single individual. which learns from the data collection and
People sometimes feel difficult to choose after data training, it is ready to implement.
from millions of songs. Moreover, music SRS recommends the songs according to
service providers need an efficient way to the face emotion captured by web-cam of a
manage songs and help their costumers to system and it gives the result according to
discover music by giving quality the emotion of a face captured.
recommendation.
METHODOLOGY
 To implement the program we use Data Collection, Data Training for initial working of a
program. To collect the data we have to install the Python Library named mediapipe, numpy &
cv2.
 Data collection is the process of gathering quantitative and qualitative information on specific
variables with the aim of evaluating outcomes or gleaning actionable insights.
 Data Training is the initial dataset used to train machine learning algorithms. Models create
and refine their rules using this data. It's a set of data samples used to fit the parameters of a
machine learning model to training it by example.
 After that we run the final program with the help of streamlit PIP which is used to create a
custom webpage.
DATA COLLECTION
 Data collection or data gathering is the process of gathering and measuring information on
targeted variables in an established system, which then enables one to answer relevant
questions and evaluate outcomes. Data collection is a research component in all study fields,
including physical and social sciences, humanities, and business.
 For collecting the data we use various PIP’s (Package Management System for Python) but
mainly named mediapipe (It is a Framework for building machine learning pipelines for
processing time-series data like video, audio, etc. This cross-platform Framework works in
Desktop/Server, Android, iOS, and embedded devices like Raspberry Pi and Jetson Nano.)
DATA TRAINING
Data Training is the initial dataset used to train machine learning algorithms. Models create and refine their rules using
this data. It's a set of data samples used to fit the parameters of a machine learning model to training it by example.
Data Training is also known as training dataset, learning set, and training set.

To train the data we have use various PIP’s but mainly we used tensorflow (TensorFlow is a Python library for fast
numerical computing created and released by Google. It is a foundation library that can be used to create Deep
Learning models directly or by using wrapper libraries that simplify the process built on top of TensorFlow.
We have also used numpy, cv2, keras python libraries.

numpy python library is used for working with arrays numpy is short for “numerical python”.

cv2 python library which is used to loads an image from the specified file.

keras python library acts as an interface for the tensorflow library. It supports multiple backends, including
TensorFlow, Microsoft Cognitive Toolkit, Theano, and PlaidML
FINAL IMPLEMENTATION
 After Data Collection & Data Training we have created two files (labels.npy & model.h5) which will
mainly used for further process.

 Now in the final work we mainly use the streamlit & streamlit-webrtc python library for creating &
sharing web apps for data science and machine learning projects. It can help us to create and deploy
our data science solution in a few minutes with a few lines of code. It can seamlessly integrate with
other popular python libraries used in Data Science such as numpy, pandas, and many more.
TESTING AND SCREENSHOTS
RESULT
The work of this project is to recommend the song according to
the emotion of a user’s face. It captures the user’s face with the
help of a web-cam in the system and then recommends the song
on YouTube according to the User’s emotion captured at that time
by the system with the help of previously given data collected and
trained .
FUTURE SCOPE
THANKYOU!!
!

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy