Feature: API-Endpoint, Filter Enhanced, Added Features, etc. #52
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
added 2 commits
June 18, 2021 10:01
>> - Added and enhanced the filter >> - Added option to check single characters or one whole licenseplate >> - Added Time print for Total Excecution and Modal Load >> - Extended the Licence Plate Recognizer with help text >> - Fixed the --plate function, and checks only the cropped licenseplate and not the whole image >> - Little bug Fixes >>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
First of all, I'm not a native Python developer I learned Python while doing Advent of Code and working on this project.
Some context I did some research about open-source/free ANPR systems and commercial ANPR systems. Long story short we choose this system, because it met all the requirements and I learn something on the way.
During the research, I did some testing on how good the detection and OCR algorithms are. Results are as following:
Dutch License Plates: 2/10
Foreign License Plates: 2/10
Time Per License Plate: More than 50 sec*
*: did not have a GPU available, so don't know possible time enhancement of a GPU
So I started working on this system and implemented some new features, enhanced old ones, and did some fixes.
New Features:
**: You don't want the API to be slow so I choose to use Tensor Flow Lite
Enhanced:
Fixed:
When running the same tests the results are as following:
Dutch License Plates: 8/10
Foreign License Plates: 3/10 ***
Time Per License Plate: More than 3 to 4 sec
***: Mostly missed on 0's and O's and concluded that that test dataset wasn't representative of normal circumstances.