Mood Melody is a web application that recomends song based on the users emotion.
Basically, the user uploads an image that contains a facial expression of him.
After uploading the image, the image is beining analyzed and get the dominant emotion from it.
Since it can recognize seven emotion, to every emotions is assigned one or more music genres that are contained in CSV files.
After the music genre is deretmined, 10 random songs are being found in the CSV file and returned to the user.
The CSV files that contain the songs list have 28.372 records of songs from 1950 to 2019, and they are devided in 7 genres.
The App uses DeepFace for the image analysis and the emotion gathering from it, and Pandas for searching and getting data from a CSV file.
- Frameworks: Flask and React.js
- Languages: Python, HTML, CSS and JavaScript
- Other: DeepFace and Pandas
The app is easy to use and pretty much straight forward, as it hasn't to much options and functionalities jet.
- Image upload.
- Image analysis and emotion gathering.
- Song recommendation based on the found emotion from the image.
If you have any ideas on how to further expand this application, make it even more better, or if you find any errors/bugs in the code and the application itself, feel free to create a pull request with your changes, and you will be added to the list of contributors.
This project is licensed under the MIT License - see the LICENSE file for details.
You can contact me via email: kenan.kajtazovic.01@gmail.com.
Also, you can reach me on any platform listed in the description of my GitHub profile.
Comming soon...
The app is currently still in the process of development.
To see the code and current state of the project, checkout the develop branch.