Automatic Number Plate Detection System and Automating the Fine Generation Using YOLO-v3.

Abstract

Vehicles violating traffic rules must be charged with fines. Recognizing the vehicle number in
the complex traffic conditions is difficult. An Android phone platform based automated
number plate recognition system is proposed. The captured image is processed to get the
optical characters. The built-in GPS module can be used to geo-tag images. The system that
we are developing sends a trigger to the nearby traffic policeman as soon as the person
breaks the signal. This is real time and the driver will be able to view where and when a
person broke the rule. Previous methods for this, like R-CNN and its variations, used a
pipeline to perform this task in multiple steps. This can be slow to run and also hard to
optimize, because each individual component must be trained separately. This system is
designed using YOLO-v3 and Django framework, and the application is developed using
React-Native framework.