Segmentasi Area KTP dari Image untuk Otomatisasi Pembacaan Data

Jonathan Hans Soeseno, Liliana Lililana


Datas which are stored in Indonesia National ID Card are common usually used in several administration process. In order to be able to extract the data a program which can segment the ID card area out of an image is needed.

The first step of this method is to extract only the area of National ID Card. The area of National ID Card is determined using blueness level of every pixel. Then Canny Edge Detection is used to mark the edges of National ID Card, which later processed by using dilation to thicken the edges. The next step involves converting the image into binary image. By dividing each edge into twelve partitions and using lines to mark each edge. That way the area of National ID Card is extracted from the image by using certain fixed ratio.

The application which is used in this paper can determine the area of National ID Card successfully regardless of skew and rotation, yet the application fails to determine the area of National ID Card when there exist an object with similar color to the National ID Card.


National ID card;segmentation;blue ratio

Full Text:



Adhikari S, Kar J, Dastidar JG. 2014. An automatic and efficient foreground object extraction scheme. International Journal of Science and Applied Information Technology, 3(2):40-43.

De, K., & Masilamani, V. (2013). Image Sharpness Measure for Blurred Images in Frequency Domain. Procedia Engineering 64 ( 2013 ) (pp. 149-158). Chennai, India: Elsevier Ltd.

Eranna K, Girishkumar D. 2014. 2-Dimentional object extraction by using color feature and KNN classification. International Journal of Engineering Research & Technology, 3(10):1146-1150.

Kang, C.-C., Wanga, W.-J., & Kang, C.-H. (2012). Image segmentation with complicated background by using seeded region growing. International Journal of Electronics and Communications (AEÜ), 767-771.

Kim S, Park S, Kim M. 2003. Central object extraction for object-based image retrieval. Conference on Image and Video Retrieval, 2728:39-49.

Kumar, J., Chen, F., & Doermann, D. (2012). Sharpness estimation for document and scene images. 21st International Conference on Pattern Recognition (ICPR 2012), (pp. 3292-3295). Tsukuba, Japan.

Podpora, M., & Grzegorz Paweł Korbas, A. K.-J. (2014). YUV vs RGB – Choosing a Color Space for Human-Machine Interaction. Computer Science and Information Systems (pp. 29-34). Opole: ACSIS.


  • There are currently no refbacks.