This repository contains a project on Handwriting Classification using Machine Learning and Deep Learning techniques. The goal of this project is to accurately classify handwritten characters into their respective classes.
Handwriting recognition is a challenging task in the field of pattern recognition and machine learning. In this project, we explore two different approaches to tackle this problem: K-Nearest Neighbors (KNN) and Convolutional Neural Networks (CNN). Additionally, we combine these two models to create a hybrid/composite model for improved accuracy.
- Utilizes popular libraries such as pandas, numpy, opencv, matplotlib, sklearn, keras, tensorflow, imutils, seaborn, and more.
- Includes two main models: KNN and CNN, along with a hybrid model combining the strengths of both approaches.
- Provides a comprehensive training and testing pipeline for each model.
- Achieved an accuracy of 88.017% using the KNN algorithm, 94.6% using the CNN algorithm, and an impressive 94.83% with the hybrid model.
- Offers flexibility to experiment with hyperparameters and tweak the models for better performance.
- Clone the repository to your local machine:
git clone https://github.com/Piyush4455/Handwriting-Classification-Using-Deep-Learning-and-Machine-Leaning.git
- Install the required dependencies using pip:
pip install -r requirements.txt
- Ensure you have the necessary datasets in the correct directory.
I would like to acknowledge the following resources and references that helped me in creating this project: