https://github.com/ikergarcia1996/handwritten-names-recognition

The goal of this project is to solve the task of name transcription from handwriting images implementing a NN approach.
https://github.com/ikergarcia1996/handwritten-names-recognition

character-recognition handwriting-recognition handwritten-character-recognition handwritten-text-recognition histogram-of-oriented-gradients multilayer-perceptron-network neural-networks neuralnetwork ocr principal-component-analysis restricted-boltzmann-machine

Last synced: 27 days ago
JSON representation

The goal of this project is to solve the task of name transcription from handwriting images implementing a NN approach.

• Host: GitHub
• URL: https://github.com/ikergarcia1996/handwritten-names-recognition
• Owner: ikergarcia1996
• License: mit
• Created: 2017-11-25T14:39:49.000Z (about 7 years ago)
• Default Branch: master
• Last Pushed: 2017-11-29T22:36:56.000Z (about 7 years ago)
• Last Synced: 2024-12-02T08:47:03.860Z (about 1 month ago)
• Topics: character-recognition, handwriting-recognition, handwritten-character-recognition, handwritten-text-recognition, histogram-of-oriented-gradients, multilayer-perceptron-network, neural-networks, neuralnetwork, ocr, principal-component-analysis, restricted-boltzmann-machine
• Language: Jupyter Notebook
• Homepage:
• Size: 158 MB
• Stars: 59
• Watchers: 6
• Forks: 30
• Open Issues: 2
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Handwritten Names Recognition

A program that solves the task of name transcription from handwriting images implementing a NN approach for Machine Learning and Neural Networks (MLNN) course.

![Objetive](https://github.com/ikergarcia1996/Handwritten-Names-Recognition/blob/master/DemoImages/objetive.png)

## Authors

```

Iker García Ferrero - ikergarcia1996

Eritz Yerga Gutierrez - eritzyg

```

## Dataset

For this project we used the [Transcriptions of names from handwriting](https://www.crowdflower.com/data-for-everyone/) dataset from [Data for Everyone](https://www.crowdflower.com/data-for-everyone/).

## How to run

To run this project you need [Python](https://www.python.org/) and [Jupyter Notebook](http://jupyter.org/).

Also you will need to install all the python libraries specified in the "README.md" inside the "Notebook" folder.

## Documentation

Documentation is available in the [releases section](https://github.com/ikergarcia1996/Handwritten-Names-Recognition/releases) with the corresponding release.

## Process for recognition

You can find a detailed explanation of this process in the [documentation](https://github.com/ikergarcia1996/Handwritten-Names-Recognition/releases).

![Process](https://github.com/ikergarcia1996/Handwritten-Names-Recognition/blob/master/DemoImages/Process.png)

## Results



  

  



## Pre downloaded dataset and Pre trained classifiers

To facilitate the usage of the program, a database with 10000 images and the pre trained classifiers are included. The documentation explains how to load them or how to generate new ones.