1. Background of creating Python OCR System

Students use various documents such as books and the Internet when writing graduation studies and reports.

I think that creating a report is a heavy burden for students because there are occasions when they are quoted.

So, take a picture or take a screenshot and take a text from the image

I think that if I can wake it up, it will lead to work efficiency, so this time I will use the OCR System for PC

I decided to create it.

2. _ development environment _

File is released in rtInamoriRyusei / RT-Inamori.

We want many people to use it, so we will publish it for free.

I will put up a link below so please take advantage of it.

https://github.com/rtInamoriRyusei/RT-Inamori/releases/tag/v1.0

① From the above link

・dist.zip ・Tesseract-OCR.zip

Please download the two files and unzip both of them.

(2) Save the Tesseract-OCR File in C: \ Program Files.

③ After that, you can use it by double-clicking main.exe in distFile to start it.

④ From here, I will show you the actual screen and explain it. When you start it, you will see this screen. 　　

⑤ Next, drag and drop the image (.png / .jpg) you want to transcribe into the box above. Then it looks like this. 　　

⑥ Then press the Start Button to wake up the characters. 　　

⑦ All you have to do is copy and paste the characters in the box below.

When using the text, the text that cannot be copied is protected by the copyright law, so please be careful when using it in compliance with the copyright law.

How was that.

This time it was a short sentence, so it has good accuracy, but it depends on the size of the long sentence and the photo.

It is impossible to make characters with 100% accuracy due to character differences.

However, I think it would be nice if you could devise it while using the cutting method and size of the image.

There are still many parts that are not practical, but I hope it will lead to more efficient work.

If you like it, feel free to use it.