How to extract text box from a pdf?

0
votes

I am given a pdf which is a scanned answer sheet. And in that answer sheet I was to segment our answer boxes. I have looked into other answers as well but they are mainly for text pdfs, where as in my case, I have scanned images in pdf format.

Here is a sample pdf: https://drive.google.com/file/d/15EDEzT1_upy0EtMqD_vVUT5Z3xaiUokA/view?usp=sharing

image-processingimage-segmentationsemantic-segmentation
Convert the pdf document to images, and just use any handwritten OCR to extract the text. Consider the following tutorial here - Salman.S
Wowser what a mess google makes of that file Q1. Find x: 7,17,37,67,x ? A=12 2. Who was the first Prime Minister of India? A=awaunal Nehn 3. What is the capital of Lakshadweep? A=KavanU 4 Expand ATM. A=#utmid Tranttim Tunsken Lnu 5. 25% of 50 is? A=12-S read aloud and weep - K J
sorry it was Adobe Scan (mark it as 0 out of 10 for effort) not Google that caused the problem. As suggested above throw that sheet away and start again. Any answers should be audio correct - K J