Indonesian Plate Number Identification Using YOLACT and Mobilenetv2 in the Parking Management System

I Kadek Gunawan,Kadek Suar Wibawa,I Made Sukarsa,I Putu Agung Bayupati,Laurensius Adi Kurniawan

doi:10.30595/juita.v9i1.9230

Abstract

A vehicle registration plate is used for vehicle identity. In recent years, technology to identify plate numbers automatically or known as Automatic License Plate Recognition (ALPR) has grown over time. Convolutional Neural Network and YOLACT are used to do plate number recognition from a video. The number plate recognition process consists of 3 stages. The first stage determines the coordinates of the number plate area on a video frame using YOLACT. The second stage is to separate each character inside the plat number using morphological operations, horizontal projection, and topological structural. The third stage is recognizing each character candidate using CNN MobileNetV2. To reduce computation time by only take several frames in the video, frame sampling is performed. This experiment study uses frame sampling, YOLACT epoch, MobileNet V2 epoch, and the ratio of validation data as parameters. The best results are with 250ms frame sampling succeed to reduce computational times up to 78%, whereas the accuracy is affected by the MobileNetV2 model with 100 epoch and ratio of split data validation 0,1 which results in 83,33% in average accuracy. Frame sampling can reduce computational time however higher frame sampling value causes the system fails to obtain plate region area.

Highlights

The number of vehicles in the world, especially in Indonesia, is increasing annually, which has an impact on the need for parking spaces is increasing in particular urban areas
Indonesia possesses several types of the vehicle registration plate, the black color with white lettering is intended for a personal vehicle, yellow color with black lettering for the public transport vehicle, red color intended for government vehicle, and particular plate number for military and police departments which has different letters and bearing the logo of the relevant agencies
There are 3 different parameters used for each video dataset, namely the YOLACT model, the Mobilenetv2 model, and the frame sampling value

Summary

Introduction

The number of vehicles in the world, especially in Indonesia, is increasing annually, which has an impact on the need for parking spaces is increasing in particular urban areas. Indonesia's statistical agency recorded the number of vehicle ownership in Indonesia in 2018 as many as 146,858,759 vehicles, an increase of nearly 8 million vehicles compared to the previous year [1]. This rapid growth should be followed by the development of sophisticated technology in detecting vehicle number plates automatically. Indonesia possesses several types of the vehicle registration plate, the black color with white lettering is intended for a personal vehicle, yellow color with black lettering for the public transport vehicle, red color intended for government vehicle, and particular plate number for military and police departments which has different letters and bearing the logo of the relevant agencies

Methods

Results

Conclusion