OCR can not distinguish between zero and two of consolas font.

4 次查看（过去 30 天）
ISAAC DOUGHAN
ISAAC DOUGHAN 2020-8-9
回答： Rishik Ramena 2020-8-13
,,,,,,
I tried using OCR to train ocr to recognise numbers from 1 to 50
The font is consolas. However zero (0) and two (2) are always conflicting.
zero(0) always reads as 2 and sometimes as forward slash when using them in the matlab.
this is the onedrive link to a copy of data. I have also added the code to it
https://studentuef-my.sharepoint.com/:u:/g/personal/isaacd_uef_fi/EdC1xH4
Please what am i doing wrong?
Best regard,
Isaac
  2 个评论
Image Analyst
Image Analyst 2020-8-9
编辑：Image Analyst 2020-8-9
Attach an image where the 2 is determined to be a 0 and another image where it's determined to be a /. I mean here, not some third party site.
ISAAC DOUGHAN
ISAAC DOUGHAN 2020-8-9
Hi, I have attached the two situations to the question in addition to the Data files

请先登录，再进行评论。

请先登录，再回答此问题。

回答（1 个）

Rishik Ramena
Rishik Ramena 2020-8-13
To correctly identify the Zeros, you can change the value of the TextLayout parameter to ‘Block’ as OCR model is just trying to identify numbers which can be considered as a single block of text.
The documentation for OCR TextLayout parameter says: "If you get poor OCR results, try a different layout that matches the text in your image."

类别

在 Help Center 和 File Exchange 中查找有关 Text Detection and Recognition 的更多信息

标签

产品

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by