Proceedings of the 1st International Conference on Science and Technology for an Internet of Things, 20 October 2018, Yogyakarta, Indonesia

Research Article

Automatic Recognition of the NIK in Electronic KTP

Download377 downloads
  • @INPROCEEDINGS{10.4108/eai.19-10-2018.2282544,
        author={Sekar Mirah and Anastasia Rita Widiarti},
        title={Automatic Recognition of the NIK in Electronic KTP},
        proceedings={Proceedings of the 1st International Conference on Science and Technology for an Internet of Things,  20 October 2018, Yogyakarta, Indonesia},
        publisher={EAI},
        proceedings_a={ICSTI},
        year={2019},
        month={4},
        keywords={segmentation invariant moment intensity of character},
        doi={10.4108/eai.19-10-2018.2282544}
    }
    
  • Sekar Mirah
    Anastasia Rita Widiarti
    Year: 2019
    Automatic Recognition of the NIK in Electronic KTP
    ICSTI
    EAI
    DOI: 10.4108/eai.19-10-2018.2282544
Sekar Mirah1,*, Anastasia Rita Widiarti1
  • 1: Universitas Sanata Dharma
*Contact email: sekarmirah012@gmail.com

Abstract

Automatic recognition of NIK is a process carried out to perform numeric character recognition stages. The purpose of automatic recognition of NIK is to produce a text that contains images by processing E-KTP images. The preprocessing stage has 4 steps, namely resizing, grayscaling, binarization and segmentation. The segmentation method which is the projection profile. The extraction phase uses invariant moments of HU and Intensity of Character (IoC). The accuracy of our results obtained for the segmentation process is 98.57% of 70 E-KTP data. The accuracy of our results obtained to reach the peak has a value of 1-fold of 86.96%, a 2-fold of 91.30% and a 3-fold of 78.26%.