Comparative Evaluation of Thresholding Methods for Optimized Digital Document Parsing Accuracy

Authors

  • Muhammad Noko Darpito Universitas Ahmad Dahlan
  • Kartika Firdausy Universitas Ahmad Dahlan
  • Abdul Fadlil Universitas Ahmad Dahlan

DOI:

https://doi.org/10.29207/resti.v10i2.6982

Keywords:

digitalization, document, image thresholding, parsing

Abstract

Automated parsing of semi-structured documents has become increasingly important, particularly in standardized formats like SATS-LN, which contain fixed-layout fields such as permit number, addresses, validity period, and item types. This study investigates the impact of two thresholding methods Otsu and Sauvola on object detection accuracy using Faster R-CNN with Detectron2. A dataset of 200 SATS-LN documents, captured via scanner and camera, was augmented into 3,600 images and labeled for seven key fields. Image quality was evaluated using PSNR, SSIM, and MSE, while detection performance was measured through mAP, AP50, AP75, AR@100, precision, recall, and F1-score. Results showed that Sauvola preserved structural layout more effectively (SSIM: 0.76 for scanner, 0.47 for camera), although Otsu achieved higher PSNR on scanned images. Sauvola attained the highest macro and weighted F1-score (0.998), with near-perfect label detection and consistent performance across augmentations. Overall, Sauvola is more reliable for enhancing segmentation and detection in layout-based document processing.

Downloads

Download data is not yet available.

References

M. D. S. Saraswati and N. N. S. A. Yanti, “Manajemen Dokumen Digital Dalam Mendukung Layanan Informasi Di PT Air Minum Giri Menang (Perseroda),” Guna Sewaka, vol. 5, no. 1, pp. 16–26, Feb. 2025, doi: 10.53977/jgs.v5i1.2395.

I. G. Suputra Widharma, I. G. N. Sangka, I. N. Sunaya, I. M. Sajayasa, and I. G. K. Sri Budarsa, “Proses Digitalisasi Dokumen Laboratorium Dengan Menggunakan Omnipage Software,” Jurnal Ilmiah Vastuwidya, vol. 6, no. 1, pp. 78–83, Feb. 2023, doi: 10.47532/jiv.v6i1.796.

Z. Jing and B. Tang, “Improved image segmentation method based on Otsu thresholding and level set techniques,” J. Phys. Conf. Ser., vol. 2813, no. 1, p. 012017, Aug. 2024, doi: 10.1088/1742-6596/2813/1/012017.

S. Singh, N. Mittal, H. Singh, and D. Oliva, “Improving the segmentation of digital images by using a modified Otsu’s between-class variance,” Multimed. Tools Appl., vol. 82, no. 26, pp. 40701–40743, Nov. 2023, doi: 10.1007/s11042-023-15129-y.

J. Xing, P. Yang, and L. Qingge, “Robust 2D Otsu’s Algorithm for Uneven Illumination Image Segmentation,” Comput. Intell. Neurosci., vol. 2020, pp. 1–14, Aug. 2020, doi: 10.1155/2020/5047976.

T. Eelbode et al., “Optimization for Medical Image Segmentation: Theory and Practice When Evaluating With Dice Score or Jaccard Index,” IEEE Trans. Med. Imaging, vol. 39, no. 11, pp. 3679–3690, Nov. 2020, doi: 10.1109/TMI.2020.3002417.

K. Wang, Y. Pu, Y. Zhang, and P. Wang, “Fully Automatic Measurement of Intima-Media Thickness in Ultrasound Images of the Common Carotid Artery Based on Improved Otsu’s Method and Adaptive Wind Driven Optimization,” Ultrason. Imaging, vol. 42, no. 6, pp. 245–260, Nov. 2020, doi: 10.1177/0161734620956897.

R. Supriyanti, M. R. Kurniawan, Y. Ramadhani, and H. B. Widodo, “Calculating the area of white spots on the lungs of patients with COVID-19 using the Sauvola thresholding method,” International Journal of Electrical and Computer Engineering (IJECE), vol. 13, no. 1, p. 315, Feb. 2023, doi: 10.11591/ijece.v13i1.pp315-324.

M. Rofi’i and D. R. Ningtias, “Local Adaptive Thresholding Menggunakan Metode Sauvola sebagai Tahapan Pra Pengolahan pada Data Citra Isyarat ECG,” Jurnal Teori dan Aplikasi Fisika, vol. 10, no. 1, p. 103, Jan. 2022, doi: 10.23960/jtaf.v10i1.2904.

J. Bhatt, K. A. Hashmi, M. Z. Afzal, and D. Stricker, “A Survey of Graphical Page Object Detection with Deep Neural Networks,” Applied Sciences, vol. 11, no. 12, p. 5344, Jun. 2021, doi: 10.3390/app11125344.

S. Naik, K. A. Hashmi, A. Pagani, M. Liwicki, D. Stricker, and M. Z. Afzal, “Investigating Attention Mechanism for Page Object Detection in Document Images,” Applied Sciences (Switzerland), vol. 12, no. 15, p. 7486, Jul. 2022, doi: 10.3390/app12157486.

S. Satheakeerthy et al., “Zero-Shot LLM-based Visual Acuity Extraction: A Pilot Study,” Nov. 08, 2024. doi: 10.21203/rs.3.rs-5287278/v1.

Z. Yang, S. Zuo, Y. Zhou, J. He, and J. Shi, “A Review of Document Binarization: Main Techniques, New Challenges, and Trends,” Electronics (Basel)., vol. 13, no. 7, p. 1394, Apr. 2024, doi: 10.3390/electronics13071394.

B. Bataineh et al., “A Comprehensive Review on Document Image Binarization,” J. Imaging, vol. 11, no. 5, 2025, doi: 10.3390/jimaging11050133.

P. R. Sankpal and P. A. Vijaya, “Performance Evaluation of Nested Watermarked Scheme using Objective Image Quality Metrics,” Journal of University of Shanghai for Science and Technology, vol. 23, no. 06, pp. 306–314, Jun. 2021, doi: 10.51201/JUSST/21/05273.

A. W. Dini, S. N. Neyman, and T. Haryanto, “Robust Digital Watermarking on Vital Archives using Hybrid SVD and DWT Methods,” Jurnal RESTI, vol. 7, no. 5, pp. 1211–1223, Oct. 2023, doi: 10.29207/resti.v7i5.5003.

M. B. DARICI and Z. ERDEM, “A Comparative Study on Denoising from Facial Images Using Convolutional Autoencoder,” Gazi University Journal of Science, vol. 36, no. 3, pp. 1122–1138, Sep. 2023, doi: 10.35378/gujs.1051655.

N. Hasan, M. S. Islam, W. Chen, M. A. Kabir, and S. Al-Ahmadi, “Encryption Based Image Watermarking Algorithm in 2DWT-DCT Domains,” Sensors, vol. 21, no. 16, p. 5540, Aug. 2021, doi: 10.3390/s21165540.

I. Hidayati, M. A. Budiman, and M. Zarlis, “Analysis of Embedding Locations in the Subband Frequency DCT on Scanned Images,” Data Science: Journal of Computing and Applied Informatics, vol. 7, no. 1, pp. 1–14, Jan. 2023, doi: 10.32734/jocai.v7.i1-10359.

S. Yang, W. Xiao, M. Zhang, Suhan Guo, J. Zhao, and F. Shen, “Image Data Augmentation for Deep Learning: A Survey,” arXiv Prepr. arXiv2204.08610., 2022, doi: https://doi.org/10.48550/arXiv.2204.08610.

M. Zhang, Y. Guo, H. Wang, and H. Shangguan, “OFIDA: Object-focused image data augmentation with attention-driven graph convolutional networks,” PLoS One, vol. 19, no. 5 May, p. e0302124, May 2024, doi: 10.1371/journal.pone.0302124.

N. Wulandari, I. Ardiyanto, and H. Adi Nugroho, “A Comparison of Deep Learning Approach for Underwater Object Detection,” Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), vol. 6, no. 2, pp. 252–258, Apr. 2022, doi: 10.29207/resti.v6i2.3931.

B. Chen, C. Yu, S. Zhao, and H. Song, “An Anchor-Free Method Based on Transformers and Adaptive Features for Arbitrarily Oriented Ship Detection in SAR Images,” IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., vol. 17, pp. 2012–2028, 2024, doi: 10.1109/JSTARS.2023.3325573.

S. S. Alrumiah, N. Alrebdi, and D. M. Ibrahim, “Augmenting healthy brain magnetic resonance images using generative adversarial networks,” PeerJ Comput. Sci., vol. 9, p. e1318, Apr. 2023, doi: 10.7717/peerj-cs.1318.

W. Sapitri, Y. N. Kunang, I. Z. Yadi, and M. Mahmud, “The Impact of Data Augmentation Techniques on the Recognition of Script Images in Deep Learning Models,” Jurnal Online Informatika, vol. 8, no. 2, pp. 169–176, Dec. 2023, doi: 10.15575/join.v8i2.1073.

D. Efendi, J. Jasril, S. Sanjaya, F. Syafria, and E. Budianita, “Penerapan Algoritma Convolutional Neural Network Arsitektur ResNet-50 untuk Klasifikasi Citra Daging Sapi dan Babi,” JURIKOM (Jurnal Riset Komputer), vol. 9, no. 3, p. 607, Jun. 2022, doi: 10.30865/jurikom.v9i3.4176.

M. Rafif, D. U. Kusumaning Putri, and L. Awaludin, “Penggunaan Pre-trained Model untuk Klasifikasi Kualitas Sekrup,” IJEIS (Indonesian Journal of Electronics and Instrumentation Systems), vol. 12, no. 2, p. 133, Oct. 2022, doi: 10.22146/ijeis.78112.

C. Anwar, “Deteksi Objek Berbasis Web Menggunakan Tensorflow Js dan Coco Dataset pada Framework React Js,” Jurnal Nasional Komputasi dan Teknologi Informasi (JNKTI), vol. 5, no. 6, pp. 1008–1015, Dec. 2022, doi: 10.32672/jnkti.v5i6.5464.

S. Lasniari, J. Jasril, S. Sanjaya, F. Yanto, and M. Affandes, “Klasifikasi Citra Daging Babi dan Daging Sapi Menggunakan Deep Learning Arsitektur ResNet-50 dengan Augmentasi Citra,” Jurnal Sistem Komputer dan Informatika (JSON), vol. 3, no. 4, p. 450, Jun. 2022, doi: 10.30865/json.v3i4.4167.

A. Wibowo, L. Lusiana, and T. K. Dewi, “Implementasi Algoritma Deep Learning You Only Look Once (YOLOv5) Untuk Deteksi Buah Segar Dan Busuk,” Paspalum: Jurnal Ilmiah Pertanian, vol. 11, no. 1, p. 123, Mar. 2023, doi: 10.35138/paspalum.v11i1.489.

Downloads

Published

2026-04-26

Issue

Section

Computer Vision and Pattern Recognition

How to Cite

Muhammad Noko Darpito, Kartika Firdausy, & Abdul Fadlil. (2026). Comparative Evaluation of Thresholding Methods for Optimized Digital Document Parsing Accuracy. Jurnal RESTI (Rekayasa Sistem Dan Teknologi Informasi), 10(2), 453-464. https://doi.org/10.29207/resti.v10i2.6982

Most read articles by the same author(s)