Handwritten Character Recognition is a web application built with Flask that enables users to draw handwritten letters and receive real-time predictions using a deep learning model.

A modular neural network implemented from scratch in Python. Includes customizable architecture, training with backpropagation, evaluation metrics, and visualizations using the EMNIST dataset.

Natural Language Processing Model that can recognise handwritten letters and convert them to typed text.

This is the code for my IB Extended Essay in Computer Science

Keras를 활용한 손글씨 교정 사이트 (‘20 제 14회 공개 SW 개발자 대회)

Simple parser of emnist letters

Digits Recognizer using correlation and similarity methods in MNIST Letters dataset.

A simple NN word recognizer based on the EMNIST dataset

This is a simple app to predict the alphabet that is written on the screen using an object of interest.

detecting hand written digits and letters from images (+camera) (EMNIST) (tensorflow)

Projekti rađeni u programskom jeziku Python. Svi projekti su vezani uz tematiku podatkovne analitike i podatkovne znanosti.

2020/2021 sem 2 - Neural Network Individual Assignment Project - EMNIST prediction - Predict and evaluate the output of model trained using multiple MLP model created by using the EMNIST datasets.

EMNIST Character Recognizer : Draw a character, and the app instantly predicts it using a PyTorch model trained on EMNIST—all in a simple Tkinter interface.

generate arbitrary handwritten letter/digits based on the inputs

Exploring advanced autoencoder architectures for efficient data compression on EMNIST dataset, focusing on high-fidelity image reconstruction with minimal information loss. This project tests various encoder-decoder configurations to optimize performance metrics like MSE, SSIM, and PSNR, aiming to achieve near-lossless data compression.

Classify the handwritten letters EMNIST

Library to read the EMNIST and MNIST data sets

Dask-parallelized project, contrasting GaussianNB and LightGBM models for EMNIST handwritten character classification.

# OCR with EAST Text Detection , contour and EMNIST Character Recognition