Detect license plate

Therefore, YOLO is the most potential candidate which match up all requirement of the project. Especially, Yolo-v2-tiny is properly available on most of mobile devices. Skip to content. Star 0. Branches Tags. Could not load branches. Could not load tags. Latest commit. Git stats 25 commits. Failed to load latest commit information.

View code. License Plate detection This project aims at developing methodology able to detect license plate and extract information at high speed processing. Introduction Several traffic-related applications , such as detection of stolen vehicles, toll control and parking lot access validation involve indentification, which is performed by Automatic Licencse Plate Recognition ALPR systems.

How it work Model : In order to deploy the project to an mobile device, WPOD-NET model is the best choice which should be small enough yet still maintains its effectiveness. Getting Started These instructions will get you a copy of the project up and running on your local machine for development and testing purposes. Prerequisites Make sure you have python 3 and Anaconda installed on your environment. Project Structure There are 3 main part of the project.

AppDetectLicense: This application is actualization bunch of theses above. Android-yolo-v2: For purpose of deploying on mobile, we need to change the model because of low computation of mobile devices.

Traffic Management Detect and read plates to flag vehicles violating traffic rules. Toll Management Detect and read plates on cars at toll gates. Parking Management Ensure vehicles adhere to parking rules on the premises. Solution Efficiency Our solution is trained to work in a range of different conditions and factors like. Blurry Images. Insufficient Lighting. Fast Moving Vehicles. Images at an Angle. Images with Multiple Vehicles. Have any Additional Questions?

Interested in Pricing Details? Reach out today for a consultation with our experts! Learn how AI can help detect food types with ease. Detect, classify, and count vehicles in images and videos with ease. Detect people and activities to automate key workflows. Closing is useful to fill small black regions between white regions in a thresholded image.

It reveals the rectangular white box of license plate. To detect the plate we need to find contours in the image. It is important to binarize and morph the image before finding contours so that it can find more relevant and less number of contours in the image.

If you draw all the extracted contours on original image, it would look like this: 6. Now find the minimum area rectangle enclosed by each of the contour and validate their side ratios and area. We have defined the minimum and maximum area of the plate as and respectively. Now find the contours in the validated region and validate the side ratios and area of the bounding rectangle of the largest contour in that region.

After validating you will get a perfect contour of a license plate. Now extract that contour from the original image. To recognize the characters on license plate precisely, we have to apply image segmentation. It would look like. Skip to content. Change Language. Related Articles. Table of Contents. Improve Article.