0

Circular image converted to linear form.I am trying to extract the text present on circular rod using opencv function calls in python. I am able to convert the image to linear by following Read circular text using OCR When I pass this converted image to pytessaract image_to_string(), I am geeting output but it is not 100% accurate.

print(pytesseract.image_to_string(img,config='--psm 9 --oem 1 -c tessedit_char_whitelist=ABCDEFGHIJKLMNOPQRSTUVWXYabcdefghijklmnopqrstuvwxyzZ0123456789 ')) 
Expected Output - 6302 ART TURKIYE 02ZN1002F20 4 Actual Output - 3152 ART TURKiYE 021R 1 0025259 4

I am using pytesseract library and I don't want to use any paid tools to extract the data.

  • First of all, welcome to StackOverflow. Following the advices of the community, it is recommended to include source code formatted to better understand your issue and find the proper solution. Please check the documentation [on how to create a Minimal, Complete, and Verifiable example](https://stackoverflow.com/help/mcve) – Carlos Cavero Mar 15 '19 at 10:41
  • The link which I specified above contains the source code. In addition to that I have added the code which extracts the text from the image using tesseract module. print(pytesseract.image_to_string(img,config='--psm 9 --oem 1 -c tessedit_char_whitelist=ABCDEFGHIJKLMNOPQRSTUVWXYabcdefghijklmnopqrstuvwxyzZ0123456789 ')) where img is the input image which is converted to linear form from the circular ones. – mounika devineni Mar 18 '19 at 05:11

0 Answers0