Replies: 1 comment 1 reply
-
YoloV8 has multiple pretrained models for following tasks:
None of these extracts text from image. In order to deal with that, if your input has standard size, you could crop your interesting parts from the image and extract text with python library "tesseract". Here is a python example code:
from PIL import Image
import pytesseract
# Open image
filename="03-RU-Account-Info.png"
img = Image.open(filename)
display(img)
# Crop a part
left, top, right, buttom = 50, 70, 50+300, 70+40
img_fullname = img.crop((left, top, right, buttom))
display(img_fullname)
full_name = pytesseract.image_to_string(img_fullname)
print(full_name) This will output Pavel Zeifart |
Beta Was this translation helpful? Give feedback.
1 reply
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
"Hello! I hope you're doing well. I've attached a sample screenshot with below link, and based on that screenshot, I'm looking to get the results in JSON format. The expected JSON structure is as follows:
https://drive.google.com/file/d/19KHUchuFa6zhHevaP0oxZebQhk0NeARl/view?usp=sharing
For Group1:
First Row: {"name": "First Name", "Type": "Input"}
Second Row: {"Day": "DropDown", "Month": "DropDown", "Year": "DropDown"}
For Group2:
Third Row: {"Id": "", "Social Security Number": "", "9 digit Number": ""}
Could you please help me convert the screenshot data into this JSON format?"
Beta Was this translation helpful? Give feedback.
All reactions