# Numeric Recognition Program Project

**URL:** <https://discourse.processing.org/t/numeric-recognition-program-project/41542>\
**Category:** Libraries\
**Created:** [March 31, 2023, 11:17am UTC](https://discourse.processing.org/t/numeric-recognition-program-project/41542 "2023-03-31T11:17:56Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![GWAK](https://avatars.discourse-cdn.com/v4/letter/g/13edae/32.png) [@GWAK](https://discourse.processing.org/u/GWAK)\
**Post date:** [March 31, 2023, 11:17am UTC](https://discourse.processing.org/t/numeric-recognition-program-project/41542/1 "2023-03-31T11:17:56Z")

</div>

Numeric Recognition Program Project

[![](https://img.youtube.com/vi/ENwRlHXfONU/maxresdefault.jpg "숫자인식 프로그램 개발(Numeric Recognition Program Development)") ](https://www.youtube.com/watch?v=ENwRlHXfONU)

1. Get camera data.
2. Remove as much external background as possible through a filter.
3. Recognize through OCR.

This is what we are doing now. However, now it is a form that works well only in one environment.

What method would be good to recognize this more accurately and in detail? I’m curious if you have any good ideas or techniques.  
help me.  
I’m curious about your opinion.