Pengenalan Plat Kendaraan Bermotor dengan Menggunakan Metode Template Matching dan Deep Belief Network

  • Michael Michael Universitas Prima Indonesia
  • Frenky Tanoto Universitas Prima Indonesia
  • Eric Wibowo Universitas Prima Indonesia
  • Frenky Lutan Universitas Prima Indonesia
  • Abdi Dharma Universitas Prima Indonesia
Keywords: deep belief network, vehicle plat, template matching, python, identification

Abstract

The license plate of the vehicle is unique and is only owned by one vehicle per vehicle plate series, to make it easier for the police, especially the traffic police, to track traffic violators through the vehicle number plate. The Deep Belief Network algorithm works by processing the dataset through 3 stages, where the first layer is trained, the results of the first layer are then re-trained, and the results of the second layer calculation are made into the third layer count, the mean results on the calculation of the third layer become the result of learning Deep Belief Network then with the Template Matching algorithm, Deep Belief Network is assisted with the introduction of vehicle plates. In a study conducted using the DBN algorithm with the Template Matching method succeeded in recognizing a vehicle plate with a success percentage of 80% from 20 trials. The experiments carried out included plates that were not clearly seen. Failures that occur in the trials are generally due to under- or over-lighting on the vehicle plate.

Downloads

Download data is not yet available.
Published
2019-11-02
How to Cite
Michael, M., Tanoto, F., Wibowo, E., Lutan, F., & Dharma, A. (2019). Pengenalan Plat Kendaraan Bermotor dengan Menggunakan Metode Template Matching dan Deep Belief Network. MATRIK : Jurnal Manajemen, Teknik Informatika Dan Rekayasa Komputer, 19(1), 27-36. https://doi.org/https://doi.org/10.30812/matrik.v19i1.475
Section
Articles