<![CDATA[The Indonesian National Identity Card (Kartu Tanda Penduduk or KTP) serves as the primary identification document for Indonesian citizens in various administrative processes across both the public and private sectors. However, manual data entry of KTP information is still commonly practiced, leading to potential input errors, delays, and inefficiencies. This study aims to develop an Android-based application capable of automatically scanning and extracting KTP data using Optical Character Recognition (OCR) enhanced with a Convolutional Neural Network (CNN). The CNN is applied during the image preprocessing stage to improve text area segmentation and detection accuracy prior to the OCR process. The application is developed using Python, Dart, and PHP, and is designed with a user-friendly interface. Extracted data—including name, national identification number (NIK), place and date of birth, and address—are stored in a MySQL database through web API integration. The research adopts a software engineering approach comprising requirement analysis, system design, implementation, and testing. Experimental results indicate that the integration of CNN into the OCR system improves character recognition accuracy up to 86.7%, particularly for low-quality or noisy images. Therefore, the proposed application is expected to provide an effective solution for faster, more accurate, and more efficient population data digitization.]]>
Copyrights © 2026
