From identity card image, this repo detect 4 corners, align by OpenCV, then detect word in image and recognize word by Transformer OCR.
Tutorial: Recognize Identity Card Tutorial
Final Result
{
"id": "38138424",
"name": "LÊ KIỀU DIỄM",
"birth": "1989",
"add": "Tân Hưng Tây Phú Tân Cà Mau",
"home": "Khóm 8 Phường 8 TP Cà Mau Cà Mau"
}
pip install -r requirement.txt
Download weight from here , then put into src/vietocr/config_text_recognition folder.
python main.py
Phiên bản này dành riêng cho cộng đồng. Mọi người nếu có mong muốn tìm giải pháp thương mại xin vui lòng liên hệ mình theo email [email protected]
Hi,
Thanks for sharing the great work. Does the model work on other types of identity cards? Like US driver license. Thanks.
Em dùng anacoda để install nhưng vẫn không thể chạy được
Hello Sir Hope you are doing well .After installing the dependencies and running the main.py I am not getting any output where we have to give path to images and path to weights i mean in which file we should give this path and which files we have to run along with main.py file
em bị lỗi này ạ và không biết sửa sao. Em xài windows
Hi bro,
Bài viết của bạn rất hữu ít vời mình, cám ơn bạn. Mình thấy bạn đang xài file pretrained của anh Quốc.
Thì nó chưa chính xác nên mình hỏi là cần phải train lại không? hay do mình làm sai nên kq chưa chính xác?
Cám ơn nhiều nhé
It works well with your image however, i uploaded other photos and it shows some errors
bạn có thể hướng dẫn code này gồm những file nào được không?
I tried to run server.py and got this error, please help
Many thanks
File "server.py", line 4, in <module> from serve_model import * File "/root/extract-information-from-identity-card/complete/serve_model.py", line 4, in <module> from merged_model import CompletedModel File "/root/extract-information-from-identity-card/complete/merged_model.py", line 94, in <module> model = CompletedModel() File "/root/extract-information-from-identity-card/complete/merged_model.py", line 17, in __init__ self.text_recognition_model = TextRecognition(path_to_checkpoint='./config_text_recognition/transformerocr.pth') File "/root/extract-information-from-identity-card/complete/recognition.py", line 11, in __init__ self.detector = Predictor(self.config) File "/root/extract-information-from-identity-card/complete/predictor.py", line 17, in __init__ model.load_state_dict(torch.load(weights, map_location=torch.device(device))) File "/root/idcard-ocr/lib/python3.6/site-packages/torch/nn/modules/module.py", line 1224, in load_state_dict self.__class__.__name__, "\n\t".join(error_msgs))) RuntimeError: Error(s) in loading state_dict for VietOCR: size mismatch for transformer.embed_tgt.weight: copying a param with shape torch.Size([232, 256]) from checkpoint, the shape in current model is torch.Size([233, 256]). size mismatch for transformer.fc.weight: copying a param with shape torch.Size([232, 256]) from checkpoint, the shape in current model is torch.Size([233, 256]). size mismatch for transformer.fc.bias: copying a param with shape torch.Size([232]) from checkpoint, the shape in current model is torch.Size([233]).
Hi bạn,
Cảm ơn bạn vì repo này và bài viết chia sẻ rất tuyệt vời.
Hiện khi chạy mình bị lỗi này:
INFO: 127.0.0.1:65113 - "POST /predict/image HTTP/1.1" 500 Internal Server Error
ERROR: Exception in ASGI application
Traceback (most recent call last):
File "/Users/tuanvc/identity-card/lib/python3.6/site-packages/uvicorn/protocols/http/h11_impl.py", line 394, in run_asgi
result = await app(self.scope, self.receive, self.send)
File "/Users/tuanvc/identity-card/lib/python3.6/site-packages/uvicorn/middleware/proxy_headers.py", line 45, in __call__
return await self.app(scope, receive, send)
File "/Users/tuanvc/identity-card/lib/python3.6/site-packages/uvicorn/middleware/debug.py", line 81, in __call__
raise exc from None
File "/Users/tuanvc/identity-card/lib/python3.6/site-packages/uvicorn/middleware/debug.py", line 78, in __call__
await self.app(scope, receive, inner_send)
File "/Users/tuanvc/identity-card/lib/python3.6/site-packages/fastapi/applications.py", line 201, in __call__
await super().__call__(scope, receive, send) # pragma: no cover
File "/Users/tuanvc/identity-card/lib/python3.6/site-packages/starlette/applications.py", line 111, in __call__
await self.middleware_stack(scope, receive, send)
File "/Users/tuanvc/identity-card/lib/python3.6/site-packages/starlette/middleware/errors.py", line 181, in __call__
raise exc from None
File "/Users/tuanvc/identity-card/lib/python3.6/site-packages/starlette/middleware/errors.py", line 159, in __call__
await self.app(scope, receive, _send)
File "/Users/tuanvc/identity-card/lib/python3.6/site-packages/starlette/exceptions.py", line 82, in __call__
raise exc from None
File "/Users/tuanvc/identity-card/lib/python3.6/site-packages/starlette/exceptions.py", line 71, in __call__
await self.app(scope, receive, sender)
File "/Users/tuanvc/identity-card/lib/python3.6/site-packages/starlette/routing.py", line 566, in __call__
await route.handle(scope, receive, send)
File "/Users/tuanvc/identity-card/lib/python3.6/site-packages/starlette/routing.py", line 227, in handle
await self.app(scope, receive, send)
File "/Users/tuanvc/identity-card/lib/python3.6/site-packages/starlette/routing.py", line 41, in app
response = await func(request)
File "/Users/tuanvc/identity-card/lib/python3.6/site-packages/fastapi/routing.py", line 202, in app
dependant=dependant, values=values, is_coroutine=is_coroutine
File "/Users/tuanvc/identity-card/lib/python3.6/site-packages/fastapi/routing.py", line 148, in run_endpoint_function
return await dependant.call(**values)
File "server.py", line 27, in predict_api
prediction = predict(image)
File "/Users/tuanvc/Projects/extract-information-from-identity-card/complete/serve_model.py", line 23, in predict
result = model.predict(img)
File "/Users/tuanvc/Projects/extract-information-from-identity-card/complete/merged_model.py", line 94, in predict
self.text_recognition(cropped_image)
File "/Users/tuanvc/Projects/extract-information-from-identity-card/complete/merged_model.py", line 78, in text_recognition
result = self.text_recognition_model.predict_on_batch(np.array(list_ans))
File "/Users/tuanvc/Projects/extract-information-from-identity-card/complete/recognition.py", line 63, in predict_on_batch
return self.detector.batch_predict(batch_images)
File "/Users/tuanvc/Projects/extract-information-from-identity-card/complete/predictor.py", line 58, in batch_predict
sent = translate(batch, self.model).tolist()
AttributeError: 'tuple' object has no attribute 'tolist'
Mình print cái translate(batch, self.model) ra thì nó như này:
(array([
[ 1, 139, 2, 2, 2],
[ 1, 194, 197, 2, 98],
[ 1, 143, 120, 2, 2],
[ 1, 145, 137, 2, 2],
[ 1, 145, 28, 98, 2],
[ 1, 77, 114, 2, 2],
[ 1, 43, 76, 86, 2]]),
array([0.58601838, 0.83988384, 0.89621916, 0.92887259, 0.9296508 ,0.71749118, 0.93631878]))
Bạn có thể gợi ý cho mình về kết quả của translate(batch, self.model) để mình fix lỗi này được không?
Cảm ơn bạn rất nhiều!
khi chạy mình gặp lỗi này. mong mng giúp đỡ
Chào anh, em đã chạy được project nhưng có vẻ nó không thể nhận dạng được căn cước công dân mới, anh có thể hướng dẫn train lại với ảnh căn cước công dân không ạ?
Hi,
Mình vừa thử download và chạy thử dự án của bạn. Có vẻ kết quả quả OCR trả ra không đúng với các phần dữ liệu có chữ lower case và ngày sinh (riêng phần tên thì đúng)
When I run last step: python3 server.py
It show error:
Traceback (most recent call last):
File "server.py", line 4, in <module>
from serve_model import *
File "/home/python/extract-information-from-identity-card/complete/serve_model.py", line 4, in <module>
from merged_model import CompletedModel
File "/home/python/extract-information-from-identity-card/complete/merged_model.py", line 1, in <module>
from complete.detector import Detector
ModuleNotFoundError: No module named 'complete'
I'm using python3, already install uvicorn and fastapi
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
Django
The Web framework for perfectionists with deadlines.
Laravel
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
Microsoft
Open source projects and samples from Microsoft.
Google
Google ❤️ Open Source for everyone.
Alibaba
Alibaba Open Source for everyone
D3
Data-Driven Documents codes.
Tencent
China tencent open source team.