Skip to content

A Java-based implementation of Convolutional Neural Networks (CNN) for character recognition. This repository includes the necessary code, datasets, and documentation to train and evaluate a CNN model for recognizing handwritten or printed characters.

License

Notifications You must be signed in to change notification settings

senurah/java-cnn-char-recog

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

21 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Character Recognition Convolutional Neural Network (CNN) using Java

This project implements a Convolutional Neural Network (CNN) for character recognition in Java. It was developed to practice and gain an understanding of CNNs.

How to use

  1. Download the MNIST data set using the provided link below.

  2. Change the "example_path" paths in the Main.class

    List<Image> imagesTest = new DataReader().readData("example_path/mnist_test.csv");

    List<Image> imagesTrain = new DataReader().readData("example_path/mnist_train.csv");

Dataset

This project uses the MNIST dataset for handwritten digits by default. You can download it from here. Place the dataset in the data directory.

Acknowledgements

This project was inspired by the YouTube video series "Character Recognition with CNN in Java" by Rae is Online. Special thanks to the channel for the valuable tutorials that helped in understanding CNN concepts.

License

This project is licensed under the MIT License. See the LICENSE file for more details.

Contact

For any questions or suggestions, feel free to open an issue or contact me at email.

About

A Java-based implementation of Convolutional Neural Networks (CNN) for character recognition. This repository includes the necessary code, datasets, and documentation to train and evaluate a CNN model for recognizing handwritten or printed characters.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages