aryashah2k / handwritten-multiple-digits-recognizer

An Intuitive Desktop GUI Application For Recognizing Multiple Handwritten Digits Drawn At The Same Time. Trained On MNIST Dataset and Built With Python, OpenCV and TKinter

Handwritten-Multiple-Digits-Recognizer

Introduction

Hello everyone👋, and welcome to this amazing repository which maintains all the code + documentation for the project Handwritten Multiple Digits Recognizer which was created during the third semester of my sophomore year at NMIMS University, Mukesh Patel School Of Technology Management And Engineering, Mumbai.

About

Table Of Contents

SRS Documentation	Software Requirements Specification
README Link	Click To View
View/Download As PDF	Click To View

Code Files For Project	2 Modules + 1 Model
GUI Module	View Code
Train_Digit_Recognizer	View Code
mnist.h5 Trained Model	Saved Model

Complete Code Explanation	Total Modules = 2
GUI Module	Click to view Explanation
Train_Digit_Recognizer Module	Click to view Explanation

How To Use The Project?/Project Installation Guide

Step 1: Clone the Repository to your local system

Step 2: Change the directory from current to the project folder location in your system

Step 3: Run the following command and wait till al the libraries and dependencies are loaded.

Step 4: If all goes well, you shall see the GUI Window loaded.

Step 5: You've sucessfully got the project running in your local system. Explore it and try all the functionalities!

You can view the live Demo GIFs in the section below.

Project Demonstration

The following GIF depicts how the project works covering all its functionalities!

Draw + Recognize Multiple Handwritten Digits

Clear Output

Feedback Button Functionality

For HD Video Demonstration, refer the following Google Drive Links:

Demo Video Name	View Link
Recognize Digits	Click To View
Clear Output	Click To View
Feedback Button Functionality	Click To View

How To Contribute?

Contributing

Contributions are what make the open source community such an amazing place to be learn, inspire, and create. Any contributions you make are greatly appreciated.

1. Fork the Project
2. Create your Feature Branch (git checkout -b feature/AmazingFeature)
3. Commit your Changes (git commit -m 'Add some AmazingFeature')
4. Push to the Branch (git push origin feature/AmazingFeature)
5. Open a Pull Request

Feel free to add new features and share it with me!

Feature Ideas I would Love To See Be Implemented:

• Add Text-To-Speech Functionality For Predictions
• Extend Recognition To Alphabets Using MNIST Alphabets Dataset
• Transform Into Web App!
• So much more,....

Donate/Support	View My Work(In Progress!)	Follow / Connect With Me	Follow / Connect With Me

Show Some ❤️, Give a ⭐ To This Repository!

handwritten-multiple-digits-recognizer's Issues

Add Project Guide To Installation

Need to add project installation guide in the form of code snippets and GIFs. Easy to use and well documented.

Add Project Demonstration Guide With All Functionalities

Add a GIF depicting the complete demonstration of project and showcasing its various functionalities. GIF could be all in one or individual for each functionality. Should be easy to follow and well documented.

Create an executable .exe file for the Project

Although the project seems complete, it is not readily usable since its usability is restricted to those who can run the project via cmd and have all the bindings installed. Aim of this issue is to resolve by creating a .exe executable of this project as a standalone application which performs the objective of "click and run" right from the user desktop.

Few ideas on how to achieve this?

Maybe look into any python package facilitating the creation of .exe files like "pyinstaller"