Small experiment on optical character recognition with neural networks.
Alternatives To Optical_character_recognition
Project NameStarsDownloadsRepos Using ThisPackages Using ThisMost Recent CommitTotal ReleasesLatest ReleaseOpen IssuesLicenseLanguage
5 months ago13apache-2.0Lua
Face recognition with deep neural networks.
The Incredible Pytorch9,479
20 days ago1mit
The Incredible PyTorch: a curated list of tutorials, papers, projects, communities and more relating to PyTorch.
8 days ago232Python
People tracker on the Internet: OSINT analysis and research tool by Jose Pino
Deep Learning Roadmap3,139
3 months ago2mitPython
:satellite: Organized Resources for Deep Learning Researchers and Developers
Deep Learning Papers Translation2,807
3 years ago1
Awesome Speech Recognition Speech Synthesis Papers2,488
19 days ago1mit
Automatic Speech Recognition (ASR), Speaker Verification, Speech Synthesis, Text-to-Speech (TTS), Language Modelling, Singing Voice Synthesis (SVS), Voice Conversion (VC)
2 months ago2July 10, 201950otherC++
Submanifold sparse convolutional networks
Deep Anpr1,702
3 years ago98mitPython
Using neural networks to build an automatic number plate recognition system
Awesome Scene Text Recognition1,561
5 years ago4
A curated list of resources dedicated to scene text localization and recognition
Image Text Localization Recognition883
8 months ago
A general list of resources to image text localization and recognition 场景文本位置感知与识别的论文资源与实现合集 シーンテキストの位置認識と識別のための論文リソースの要約
Alternatives To Optical_character_recognition
Select To Compare

Alternative Project Comparisons

Optical character recognition

This program illustrates the pattern recognition capabilities of the multi-layer perceptron with an optical character recognition application. The program has a learning database which contains the matrix representations of the digits from 0-9. After learning the user can draw digits in the application and the program will try to recognize that digit.

##The controls

  1. ###Network initialization. Initialisation of the network can be done with the following panel.


In this panel we can set the number of the neurons on the hidden layers. For example in this case we set the network with one hidden layer which contains 10 neurons.

  1. ###Loading samples and teaching network.

Learning graph

We can load samples to the network by pressing the load button. After loading samples we can set the parameters like momentum, learning rate and the number of iterations. The learn button will starts the network to learn and as a result we can see the error on the graph, in the function of iterations. We can press the learn button more times and we can see the results of the learning iterations on the graph.

  1. ###Testing the knowledge.

Character drawer

To test the knowledge of the network first we need to draw a number in the square with the mouse. After we draw a number we should press the Test button and we will see the results of the recognition. As a result we can see a percent estimation to each character, and the number with the highest probability is marked with red color.

Popular Network Projects
Popular Recognition Projects
Popular Networking Categories

Get A Weekly Email With Trending Projects For These Categories
No Spam. Unsubscribe easily at any time.