Data Science Stack Exchange is a question and answer site for Data science professionals, Machine Learning specialists, and those interested in learning more about the field. Join them; it only takes a minute:

Sign up
Here's how it works:
  1. Anybody can ask a question
  2. Anybody can answer
  3. The best answers are voted up and rise to the top

Most vehicle license/number plate extractors I've found involve reading a plate from an image (OCR) but I'm interested in something that could tag instances of license plates in a body of text. Are there any such annotators out there?

share|improve this question
Any particular country? Different countries have different license plate formats. Its a big world out there. – Spacedman Jul 24 '14 at 11:48
@Spacedman Any country is fine :) – howdyjessie Jul 24 '14 at 17:38

There are a lot of pretty decent tools out there for text annotation in general, and given the broad nature of the task you're approaching (license plates are about as general as words), the annotation tools you are looking at should probably come from the more classical tools for annotation.

There was actually a pretty good discussion about annotation tools on this question, which should actually apply to this problem. The most relied-upon thing in annotation right now is probably brat. You can learn more about brat here.

Hope that helps! Let me know if you've got any more questions.

share|improve this answer
Never seen brat before; thanks for the tip! – howdyjessie Jul 24 '14 at 17:52

This can be done using regular expressions.

2 letters followed by a number (\d denotes digits) would be

[A-Z]{2} \d*

2 or 3 letters followed by a number is

[A-Z]{2,3} \d*
share|improve this answer
I don't mean to be negative, but regular expressions are an extremely poor choice for this problem. Between state-by-state variation, vanity plates, and differing formats, regular expressions are a poor choice. – indico Jul 24 '14 at 2:07
How many different variations are there? I'm from a different country. – germcd Jul 24 '14 at 12:53
A conservative estimate would be 51, probably close to a few hundred. – indico Jul 24 '14 at 16:18
Ah right I see the problem. I was thinking that I could find all the plates registered here with 3 regular expressions. – germcd Jul 24 '14 at 16:55
@germcd Thanks for the attempt though! Glad to hear I wasn't the only person to think of regex too. – howdyjessie Jul 24 '14 at 17:42

Your Answer


By posting your answer, you agree to the privacy policy and terms of service.

Not the answer you're looking for? Browse other questions tagged or ask your own question.