COMPUTER VISION - OCR BOOSTING ACCURACY

Welcome to episode 5 of our OCR series! In this video we are going to focus on how to improve our results by boosting accuracy, handling noisy photos, and theoretical information related to improving the output of OCR. It’s
an essential element since image quality can play a key role on the results, or in a practical scenario we might receive PDF files that require OCR, but are not in the best condition. What can we do to help in this situation? Come join us to find out and please feel free to ask any questions that you may have!

[riptorforever]

i respect your goals in that leasson... Thx and Congratz!

[facundobertuarios]

I wish you can continue with this, you are saving my internship project XD

[anburenganathan]

Hello

Am trying to covert gif image into text file using opencv and pytesseract.... i can able to convert but accuracy is very poor.. (font is recursive type )

[BuntyUttarakhand]

How can i boost accuracy when text is not recognized after gray and GaussianBlur?I am converting a pdf to image then pre processing it before feeding to tesseract .i dont see much good result though, should i train tesseract with my font specifically ?

[Ankurkumar]

Hi, thanks a lot for sharing very informative videos. Need a help, I want to read the radio buttons/ check boxes from .jpg files, for example whether somebody as clicked on right option in answer sheet. Pls suggest

[devnath]

Is this OCR series part of your any udemy series ?