Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Vietnamese License Plate #3

Open
hungpqz opened this issue Jun 7, 2017 · 4 comments
Open

Vietnamese License Plate #3

hungpqz opened this issue Jun 7, 2017 · 4 comments

Comments

@hungpqz
Copy link

hungpqz commented Jun 7, 2017

In Vietnam we have 2 type of license plate. One has 1 line and the other has 2 lines.

How to check if it is 1 line or 2 lines with this project? And some time I see the result is not correct. For example this image below (1 line license plate)

license

Correct one is : 51A13883 and this is 5JA3883

This is 2 lines license plate:

license

@hungthuanmk
Copy link

This problem might comes from restoration proccessing, what you need to do is improve detecting Plate algorithm.

@divya1md
Copy link

divya1md commented Feb 6, 2018

Hai, I am new to openCV and I wanna do number-plate recognition using opencv and python.
[(https://github.com/MicrocontrollersAndMore/OpenCV_3_License_Plate_Recognition_Python)]
I got this github link for my work and I couldn't get from where the classification.txt, flattenedimage.txt is from!
Can anyone help me with this?
Thanks in advance.

@bao-O
Copy link

bao-O commented Sep 13, 2019

@hungpqz I'm planning to train a model to detect vietnamese license plate and you likely have a exciting dataset. Can you send me that dataset for my study?
About your problem, maybe the original model was trained only on the dataset combined of 1 line plate dataset.

@IAM-P-LP
Copy link

@hungpqz Could you please send the dataset for vietnamese plate.Your dataset looks promising!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

5 participants