Keras를 활용한 손글씨 교정 사이트 (‘20 제 14회 공개 SW 개발자 대회)
-
Updated
Jan 3, 2021 - Jupyter Notebook
Keras를 활용한 손글씨 교정 사이트 (‘20 제 14회 공개 SW 개발자 대회)
This is the code for my IB Extended Essay in Computer Science
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.
A deep learning model deployed as a web app to classify handwritten digits and letters using the EMNIST dataset
Teaching a neural network how to write letters and digits with reinforcement learning.
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.
User handwriting recognition app using a CNN trained on the EMNIST ByClass dataset
Machine learning models.
Digits Recognizer using correlation and similarity methods in MNIST Letters dataset.
# OCR with EAST Text Detection , contour and EMNIST Character Recognition
Dask-parallelized project, contrasting GaussianNB and LightGBM models for EMNIST handwritten character classification.
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.
Library to read the EMNIST and MNIST data sets
This project aims to implement AI-driven letter recognition using neural network libraries and the EMNIST dataset. By employing deep learning and data preprocessing, we seek to build a versatile system for accurately identifying letters in both handwritten and printed text, with applications in OCR and document digitization.
Evaluating the accuracy with different CNN kernel sizes for the EMNIST Balanced dataset
Add a description, image, and links to the emnist-dataset topic page so that developers can more easily learn about it.
To associate your repository with the emnist-dataset topic, visit your repo's landing page and select "manage topics."