- I'm currently working on a project to extract text from document- images (like passport and license) and storing the passport number and driving license number along with the name of the person in a database.
- I have used Pytesseract for the same.
- Does Pytesseract use any of the Neural Network Algorithms?
- The code with the sample image and output IS ATTACHTED BELOW.
from PIL import Image import pytesseract pytesseract.pytesseract.tesseract_cmd = r'C:\Program Files (x86)\Tesseract-OCR\tesseract.exe' im = Image.open('C:/Users/Kiran Lalwani/Desktop/dss/56db21ec-8d4d-4128-889a-948e81eb7127.jpg') text = pytesseract.image_to_string(im, lang='eng')
- Is there any other more efficient method?
- What about Tesseract-OCR or OpenCV or CNN or MATLAB for text extraction?
Have you ever tried using OpenCV + OCR?
https://www.pyimagesearch.com/2018/09/17/opencv-ocr-and-text-recognition-with-tesseract/
- Oscar Julian Perdomo Charry Not yet. I have only tried the code mentioned in my question. I will try to implement OpenCV+OCR as you mentioned within the next 2 days.
- Also I just wanted to clarify how is this efficient from the code in my question?
- Thank you for the suggestion.
Sonia Lalwani The best way to optimize the code is using bounding-box in passport or driving license in order to focus the whole problem in local problems.
The link above contains a couple of examples with this approach!
Oscar Julian Perdomo Charry I will try to do the same :) Thank you so much for your suggestion!
Sonia Lalwani Adobe Acrobat professional have in-built OCR (Optical Content Reader) option to read text from scanned images. You can also use other OCR tools to read text from your target scanned images.
I hope it will serve the purpose.
- Badges
- Science topic