1st International Conference on Science and Technology, ICOST 2019, 2-3 May, Makassar, Indonesia

Research Article

Tracking of Vehicle Tax Violations Using Vehicle Type and Plate Number Identification

Download893 downloads
  • @INPROCEEDINGS{10.4108/eai.2-5-2019.2284610,
        author={Arsan Kumala Jaya and Zahir  Zainuddin and Syafruddin  Syarif},
        title={Tracking of Vehicle Tax Violations Using Vehicle Type and Plate Number Identification},
        proceedings={1st International Conference on Science and Technology, ICOST 2019, 2-3 May, Makassar, Indonesia},
        publisher={EAI},
        proceedings_a={ICOST},
        year={2019},
        month={6},
        keywords={vehicle tax vehicle type number plate gmm anpr knn},
        doi={10.4108/eai.2-5-2019.2284610}
    }
    
  • Arsan Kumala Jaya
    Zahir Zainuddin
    Syafruddin Syarif
    Year: 2019
    Tracking of Vehicle Tax Violations Using Vehicle Type and Plate Number Identification
    ICOST
    EAI
    DOI: 10.4108/eai.2-5-2019.2284610
Arsan Kumala Jaya1,*, Zahir Zainuddin1, Syafruddin Syarif1
  • 1: Department of Electrical Engineering, Faculty of Engineering, Universitas Hasanuddin Makassar, Indonesia, 92119
*Contact email: jayaak17d@student.unhas.ac.id

Abstract

This paper describes tracking violations of vehicle tax using the identification of type and number plates on vehicles. The case study of this research is in Sulawesi Selatan (Indonesia). The Gaussian Mixture Model (GMM) algorithm is used to detect vehicle types and the Automatic Number Plate Recognition (ANPR) algorithm for detecting vehicle license numbers. The proposed system uses a digital camera with a camera height of 250 cm and a camera tilt angle of 55 degrees. The proposed system design is the stages of preprocessing, feature extraction, feature selection, model selection, and database. For the introduction of types of vehicles are classified based on predetermined ROI while the introduction of vehicle numbers is trained using k-Nearest Neighbor (KNN). The results of the proposed system accuracy are 91% for vehicle type detection and 70% for vehicle license number detection.