Pengenalan Karakter Plat Nomor Kendaraan Bermotor Menggunakan Zoning dan Fitur Freeman Chain Code

Taufik Fuadi Abidin, Abbas Adam AzZuhri, Fitri Arnia

Abstract


A license plate is one of the vehicle identities. It consists of alphabetic characters and numbers and represents provincial and area code where the vehicle is registered. This article discusses the character recognition of plate number using zoning and Freeman Chain Code (FCC). Zoning divides character image into several zones i.e. 4, 6, and 8, and then, the pattern of each character in the zone is extracted using FCC as the numerical features. The character is then classified using Support Vector Machines (SVM). It is a multi-class classification problem with 36 categories. The results show that FCC features with 8 zones give the best accuracy (87%) when compared to the other two zones.


Keywords


Pattern Recognition; Feature Extraction; Freeman Chain Code; Zoning; Support Vector Machines

Full Text:

PDF


DOI: https://doi.org/10.17529/jre.v14i1.8932

Refbacks

  • There are currently no refbacks.


hits counter View JRE Stats

 

Creative Commons License   

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.