Vehicle and Car Plate Detection :

Deep Learning Project II

This is a course project from ENSC424, SFU. Completed with other three students:
  • Ricky Chen
  • Toky Saleh
  • Karambeer Dhillon
Our project is divided into two major components: vehicle detection and license plate character recognition.
Phase I is detecting whether an input contains vehicles or not. If the algorithm predicts that the input contains vehicles, then we need to define a method which will precisely locate and crop the vehicle from the original data. Starting with the output from Phase I as the input, Phase II should search for the vehicle’s license plate and have the ability to recognize the number on the car plate.
Through investigating, we found that vehicle detection is already quite developed and there are numerous existing methods online;; however, we still decided to explore deep learning through this project. We attempt to improve the accuracy with some pre-­trained models. What’s more, in consideration of time and resource limitation, (we neither have enough time nor access to any GPU machine), we decide to challenge image based detection rather than video based.