Integration of Google ML Kit and OpenCV for Android-Based Document Digitization and Archive Management

Sugiyanto Sugiyanto, Eka Bagus Surya, Achmad Wahyu Satrio Wibisono

Abstract

Digitalization of documents is an important necessity for supporting more efficient, practical, and easily accessible archive storage through mobile devices. However, document scanning using a smartphone camera still frequently produces suboptimal images due to lighting conditions, image-capture angle, and perspective distortion. This research develops the Android-based application Digital Portable Archive and Document Assistant (D-PANDA) by integrating the Google ML Kit Document Scanner API for automatic document detection and OpenCV for image quality enhancement, with a PHP Native backend and MariaDB database. Unlike commercial black-box solutions, D-PANDA provides full algorithmic transparency through its documented OpenCV-based post-processing pipeline, and offers a self-hosted backend alternative for organizations prioritizing data sovereignty. Testing was conducted using Black Box Testing to verify that all application functions operate according to requirements, as well as the User Experience Questionnaire Short (UEQ-S) with 15 respondents to evaluate the user experience. Black Box testing results indicate that all application features function correctly, with no functional errors detected. Meanwhile, the UEQ-S evaluation yielded scores of Pragmatic Quality = 2.232, Hedonic Quality = 2.286, and Overall = 2.259, all in the Excellent category, indicating that the application ranks among the top 10% of results according to the UEQ-S benchmark. The research findings demonstrate that D-PANDA effectively supports document digitalization and management while delivering a very positive user experience.

Keywords

Blackbox Testing; Construction Project; Cost Control Management; ISO 9126; V-Model

Full Text:

PDF

References

K. Kyamakya, A. Haj Mosa, F. A. Machot, and J. C. Chedjou, “Document-Image Related Visual Sensors and Machine Learning Techniques,” Sensors, vol. 21, no. 17, p. 5849, Jan. 2021, doi: 10.3390/s21175849.

R. Bernardino, R. D. Lins, and R. da S. Barboza, “A Quality, Size and Time Assessment of the Binarization of Documents Photographed by Smartphones,” J. Imaging, vol. 9, no. 2, p. 41, Feb. 2023, doi: 10.3390/jimaging9020041.

H. Feng, W. Zhou, J. Deng, Q. Tian, and H. Li, “DocScanner: Robust Document Image Rectification with Progressive Learning,” Dec. 24, 2022, arXiv: arXiv:2110.14968. doi: 10.48550/arXiv.2110.14968.

N. Skoryukina, D. P. Nikolaev, A. Sheshkus, and D. Polevoy, “Real time rectangular document detection on mobile devices,” in Seventh International Conference on Machine Vision (ICMV 2014), SPIE, Feb. 2015, p. 458. doi: 10.1117/12.2181377.

X. Li, B. Zhang, J. Liao, and P. V. Sander, “Document Rectification and Illumination Correction using a Patch-based CNN,” Sep. 20, 2019, arXiv: arXiv:1909.09470. doi: 10.48550/arXiv.1909.09470.

H. Feng, W. Zhou, J. Deng, Y. Wang, and H. Li, “Geometric Representation Learning for Document Image Rectification,” Oct. 15, 2022, arXiv: arXiv:2210.08161. doi: 10.48550/arXiv.2210.08161.

J. Canny, “A Computational Approach to Edge Detection,” IEEE Trans. Pattern Anal. Mach. Intell., vol. PAMI-8, no. 6, pp. 679–698, Nov. 1986, doi: 10.1109/TPAMI.1986.4767851.

P. Arbeláez, M. Maire, C. Fowlkes, and J. Malik, “Contour Detection and Hierarchical Image Segmentation,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 33, no. 5, pp. 898–916, May 2011, doi: 10.1109/TPAMI.2010.161.

N. A. Rehman and F. Haroon, “Adaptive Gaussian and Double Thresholding for Contour Detection and Character Recognition of Two-Dimensional Area Using Computer Vision,” Eng. Proc., vol. 32, no. 1, p. 23, 2023, doi: 10.3390/engproc2023032023.

N. Otsu, “A Threshold Selection Method from Gray-Level Histograms,” IEEE Trans. Syst. Man Cybern., vol. 9, no. 1, pp. 62–66, Jan. 1979, doi: 10.1109/TSMC.1979.4310076.

J. Sauvola and M. Pietikäinen, “Adaptive document image binarization,” Pattern Recognit., vol. 33, no. 2, pp. 225–236, Feb. 2000, doi: 10.1016/S0031-3203(99)00055-2.

“ML Kit,” Google for Developers. Accessed: Jun. 18, 2026. [Online]. Available: https://developers.google.com/ml-kit/vision/doc-scanner/android

“Android Developers Blog: Easily add document scanning capability to your app with ML Kit Document Scanner API.” Accessed: Jun. 18, 2026. [Online]. Available: https://android-developers.googleblog.com/2024/02/ml-kit-document-scanner-api.html

A. Neumann, N. Laranjeiro, and J. Bernardino, “An Analysis of Public REST Web Service APIs,” IEEE Trans. Serv. Comput., vol. 14, no. 4, pp. 957–970, Jul. 2021, doi: 10.1109/TSC.2018.2847344.

A. Belkhir, M. Abdellatif, R. Tighilt, N. Moha, Y.-G. Guéhéneuc, and É. Beaudry, “An Observational Study on the State of REST API Uses in Android Mobile Applications,” in 2019 IEEE/ACM 6th International Conference on Mobile Software Engineering and Systems (MOBILESoft), May 2019, pp. 66–75. doi: 10.1109/MOBILESoft.2019.00020.

“User Experience Questionnaire Handbook.” Accessed: Jun. 27, 2026. [Online]. Available: https://www.researchgate.net/publication/281973617_User_Experience_Questionnaire_Handbook

“Sosialisasi Dan Pelatihan Aplikasi Google Form Sebagai Kuisioner Online Untuk Meningkatkan Kualitas Pelayanan.” Accessed: Jun. 27, 2026. [Online]. Available: https://www.researchgate.net/publication/335500269_Sosialisasi_Dan_Pelatihan_Aplikasi_Google_Form_Sebagai_Kuisioner_Online_Untuk_Meningkatkan_Kualitas_Pelayanan

S. Ellen, “Slovin’s Formula Sampling Techniques,” Sciencing. Accessed: Jun. 30, 2026. [Online]. Available: https://www.sciencing.com/slovins-formula-sampling-techniques-5475547/

DOI: https://doi.org/10.31284/j.jtm.2026.v7i2.9264

Refbacks

  • There are currently no refbacks.