Optical_Character_Recognition

An Optical Character Recognition system using Pytesseract/Extracting data from Blood Pressure Reports.

As an IOT/Computer Visions Intern at the Graduate Rotational Internship program (GRIP) by The Sparks Foundation (TSF), the first task is to implement a character detector which extracts printed or handwritten text from an image/video.

For more learning purposes, I've utilized this feature in cleaning/extracting valuable information from Blood Pressure Reports as images.

Dependencies

tesseract-ocr package

pytesseract 0.3.8

Open-cv

Pandas

---

Using the pytesseract open source library to detect text on image/video.

Open-cv for Image Processing

Pandas for data manipulation