Car Plate Recognition Using Machine Learning

Abstract

Security has consistently been a significant worry for mankind. Today we have video surveillance cameras in schools, hospitals and every other public place that help keep these spaces secure. This is also including places with vehicles such as parking spaces and garages, and it would be embedded with a security guard that would also help monitor and verify entrance of any incoming vehicle, as well as controlling the opening and closing of the gate. The project will aim to develop a smart car plate recognition device that can monitor and survey the area, as well as detect and analyze vehicle license plates. A sensor will detect the incoming vehicle, then a camera will take a screenshot of the front of the vehicle with the license plate. The license plate is scanned then checked whether it is registered to determine whether it is allowed or denied entry, and the device will troubleshoot by sending SMS to a fixed phone number regarding any issues. We will use a supervised Machine Learning Optical Character Recognition model known as Tesseract AI. This pre-trained, multi-language AI will detect and extract the numbers and letters on the license plate. Before this process starts, we will clean the image of any noise by performing changes to the original image, such as switching to grayscale and brightening, in-order to increase the accuracy of the OCR and minimize error. These extracted numbers and letters will then be checked within the database one entry after the other until it detects a match. This device will be a direct upgrade over the traditional system of simply including a CCTV camera and a guard as the device will operate independently to a point that no human input is required and will require no installation of on-site servers or setup of databases, thus saving manpower and reducing cost and complexity.