Document Text Detection (OCR) with EasyOCR and Python

preview_player
Показать описание
How to extract and detect text in document images/PDF files? EasyOCR is an open-source project that allows you to do that automatically. We'll replace the Tesseract OCR engine and learn how to use EasyOCR for our document classification pipeline.

00:00 - Intro
00:58 - Update libraries
06:22 - Convert HTML files to images
16:00 - EasyOCR
33:20 - Conclusion

#pytorch #python #deeplearning #ocr #machinelearning #nlp
Рекомендации по теме
Комментарии
Автор

thanks man good shit, now they will treat me like a god amongst men

lifted
Автор

thankyou so much for the vids.... Amazing content... just one query Shouldnt top be max(ys)?? at 24:27??

radacror
Автор

Great videos. The little subscribe reminders are annoying though and make it hard to hear.

ThomasLPacker
Автор

Hello sir, can i use this model on a diffirent language? in my case is Mongolian

cmplxyz
Автор

How do you measure the quality of OCR extraction?? There is bouding box error and OCR text error too. What is the usual standard?

adityask