Melola Discovery

← Melola Discovery

Jurnal Tanpa peringkat SINTA

Performance Evaluation of Otsu and Sauvola Thresholding for Structured Document Binarization

Scientific Journal of Informatics · Vol. 13 No. 1 (2026) · hlm. 189–200

DOI
10.15294/sji.v13i1.40245
ISSN
2407-7658, 2460-0040
Terbit
2026-03-31
Penerbit
Universitas Negeri Semarang
Bahasa
eng

Abstrak

Purpose: Digitizing public administration records, particularly structured forms such as the Transport of Plants and Wildlife Abroad (Surat Angkut Tumbuhan dan Satwa Liar Luar Negeri / SATS-LN), necessitates meticulous preparation for precise subsequent analysis. Most of the photos in the SATS-LN archives are scanned, and they have inconsistent lighting, varying resolution, and background noise, which makes it difficult to separate the text from the backdrop and read it clearly. This work identifies the optimal SATS-LN binarization approach for preserving textual structure and suppressing background artifacts. Methods: A four-stage pipeline is used. First, Detectron2 localizes seven important SATS-LN fields. Second, binarization is investigated with global Otsu and adaptive Sauvola thresholding under three parameter configurations. Third, following binarization, Contrast-Limited Adaptive Histogram Equalization (CLAHE) boosts local contrast. Finally, Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM), Difference from Reference for Distortion (DRD), Precision, Recall, F1-score, and Foreground Ratio are assessed on 200 annotated SATS-LN documents (150 scanner-based/DOC and 50 camera captured/CAM). Result: The acquisition domain and assessment model affect binarization performance on 200 SATS-LN documents (150 DOC scans and 50 CAM images). Global Otsu_T10 has the highest median PSNR (21.19 dB) and the lowest median MSE (494.69), indicating a visually cleaner background. However, segmentation-based metrics show better stroke preservation with Sauvola, as Sauvola_k05 has the strongest DOC text–background separation (F1 = 0.938). In the CAM domain, where illumination variability dominates, Sauvola performs better across structural and segmentation indicators, with Sauvola_k04 performing best overall (F1 = 0.980) and mitigating the over-segmentation tendency of strict global thresholds. The Sauvola window (25x25) and CLAHE clip limit (1.0) results suggest using Sauvola_k05 for DOC and Sauvola_k04 for CAM to preserve text integrity and reduce background artifacts. Novelty: This study presents a novel field-level binarization assessment that combines automated cropping and ground-truth evaluation, providing practical guidance for robust preprocessing that supports scalable, reliable, and cross-device public document digitization.

Kata kunci

Jaringan kolaborasi para penulis

40 penulis · 98 tautan kepenulisan bersama · 17 lintas organisasi · menampilkan 40 yang paling banyak terhubung

Arahkan kursor atau ketuk sebuah nama untuk menyorot rekan penulisnya. Klik dua kali untuk membuka halaman penulis.

  • Universitas Ahmad Dahlan
  • University of Technology Malaysia
  • Universiti Teknikal Malaysia Melaka
  • Universitas Islam Al-Azhar
  • National Chung Hsing University
  • Muhammadiyah University of Yogyakarta
  • Islamic University of Indonesia
  • Organisasi lain
  • Afiliasi tidak diketahui
  • Organisasi berbeda
  • Organisasi sama
  • Afiliasi tidak diketahui
  • Garis lebih tebal = lebih banyak artikel bersama · lingkaran lebih besar = lebih banyak artikel
Tampilkan sebagai tabel
Rekan penulisOrganisasiArtikel bersama
Anton YudhanaUniversitas Ahmad Dahlan5
Rusydi UmarUniversitas Ahmad Dahlan4
Muhammad Kunta BiddinikaUniversitas Ahmad Dahlan3
Imam RiadiUniversitas Ahmad Dahlan3
Muhajir YunusUniversitas Ahmad Dahlan2
Sunardi SunardiUniversitas Ahmad Dahlan2
Dianda RifaldiUniversitas Ahmad Dahlan1
HermanUniversitas Ahmad Dahlan1
Maulana Muhammad Jogo SamodroUniversitas Ahmad Dahlan1
Yuminah yuminahUniversitas Ahmad Dahlan1
Suprianto SupriantoAfiliasi tidak diketahui1
Frandika SeptaUniversitas Ahmad Dahlan1
Siti HelmiyahUniversitas Ahmad Dahlan1
Abdullah HanifUniversitas Ahmad Dahlan1
Musri Iskandar NasutionUniversitas Ahmad Dahlan1
Kharis Hudaiby HanifUniversitas Ahmad Dahlan1
Wahid Alfaridsi Achmad ZeinAfiliasi tidak diketahui1
HermanAfiliasi tidak diketahui1
Eko PriantoUniversitas Ahmad Dahlan1
Tole SutiknoUniversitas Ahmad Dahlan1
Mohd Hatta JopriUniversiti Teknikal Malaysia Melaka1
Hendril Satrian PurnamaAfiliasi tidak diketahui1
Anggit PamungkasAfiliasi tidak diketahui1
Ibrahim Mohd AlsofyaniUniversity of Technology Malaysia1
Firmansyah FirmansyahUniversitas Ahmad Dahlan1
Fahmi AnwarUniversitas Ahmad Dahlan1
Firmansyah FirmansyahUniversitas Islam Al-Azhar1
Herman YuliansyahUniversitas Ahmad Dahlan1
Itsnaini Irvina KhoirunnisaUniversitas Ahmad Dahlan1
Sunardi SunardiUniversitas Ahmad Dahlan1
Haris Imam Karim FathurrahmanUniversitas Ahmad Dahlan1
Yu‐Hao LinNational Chung Hsing University1
Farhah KamilahMuhammadiyah University of Yogyakarta1
Saifudin SaifudinIslamic University of Indonesia1
ArdiansyahAfiliasi tidak diketahui1
SunardiUniversitas Pamulang1
retno wahyusariAfiliasi tidak diketahui1

Afiliasi berasal dari OpenAlex; metadata OAI-PMH jurnal tidak memuatnya. Penulis tanpa ID OpenAlex dicocokkan berdasarkan nama, sehingga dua orang bisa tergabung atau satu orang bisa terpisah.

Sumber metadata: OAI-PMH (metadata jurnal) https://journal.unnes.ac.id/journals/sji/oai, pertama di-harvest 6 Nov 2026, terakhir terlihat 8 Nov 2026.
Metadata asli (oai_dc)
<oai_dc:dc xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/  http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
	<dc:title xml:lang="en">Performance Evaluation of Otsu and Sauvola Thresholding for Structured Document Binarization</dc:title>
	<dc:creator xml:lang="en">Darpito, Muhammad Noko</dc:creator>
	<dc:creator xml:lang="en">Kartika Firdausy</dc:creator>
	<dc:creator xml:lang="en">Abdul Fadlil</dc:creator>
	<dc:subject xml:lang="en">Image thresholding</dc:subject>
	<dc:subject xml:lang="en">Otsu</dc:subject>
	<dc:subject xml:lang="en">Sauvola</dc:subject>
	<dc:subject xml:lang="en">Clahe</dc:subject>
	<dc:subject xml:lang="en">Document scanned</dc:subject>
	<dc:description xml:lang="en">Purpose: Digitizing public administration records, particularly structured forms such as the Transport of Plants and Wildlife Abroad (Surat Angkut Tumbuhan dan Satwa Liar Luar Negeri / SATS-LN), necessitates meticulous preparation for precise subsequent analysis. Most of the photos in the SATS-LN archives are scanned, and they have inconsistent lighting, varying resolution, and background noise, which makes it difficult to separate the text from the backdrop and read it clearly. This work identifies the optimal SATS-LN binarization approach for preserving textual structure and suppressing background artifacts.
Methods: A four-stage pipeline is used. First, Detectron2 localizes seven important SATS-LN fields. Second, binarization is investigated with global Otsu and adaptive Sauvola thresholding under three parameter configurations. Third, following binarization, Contrast-Limited Adaptive Histogram Equalization (CLAHE) boosts local contrast. Finally, Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM), Difference from Reference for Distortion (DRD), Precision, Recall, F1-score, and Foreground Ratio are assessed on 200 annotated SATS-LN documents (150 scanner-based/DOC and 50 camera captured/CAM).
Result: The acquisition domain and assessment model affect binarization performance on 200 SATS-LN documents (150 DOC scans and 50 CAM images). Global Otsu_T10 has the highest median PSNR (21.19 dB) and the lowest median MSE (494.69), indicating a visually cleaner background. However, segmentation-based metrics show better stroke preservation with Sauvola, as Sauvola_k05 has the strongest DOC text–background separation (F1 = 0.938). In the CAM domain, where illumination variability dominates, Sauvola performs better across structural and segmentation indicators, with Sauvola_k04 performing best overall (F1 = 0.980) and mitigating the over-segmentation tendency of strict global thresholds. The Sauvola window (25x25) and CLAHE clip limit (1.0) results suggest using Sauvola_k05 for DOC and Sauvola_k04 for CAM to preserve text integrity and reduce background artifacts.
Novelty: This study presents a novel field-level binarization assessment that combines automated cropping and ground-truth evaluation, providing practical guidance for robust preprocessing that supports scalable, reliable, and cross-device public document digitization.</dc:description>
	<dc:publisher xml:lang="en">Universitas Negeri Semarang</dc:publisher>
	<dc:date>2026-03-31</dc:date>
	<dc:type>info:eu-repo/semantics/article</dc:type>
	<dc:type>info:eu-repo/semantics/publishedVersion</dc:type>
	<dc:type xml:lang="en">Peer-reviewed Article</dc:type>
	<dc:format>application/pdf</dc:format>
	<dc:identifier>https://journal.unnes.ac.id/journals/sji/article/view/40245</dc:identifier>
	<dc:identifier>10.15294/sji.v13i1.40245</dc:identifier>
	<dc:source xml:lang="en">Scientific Journal of Informatics; Vol. 13 No. 1: Regular Issue; 189-200</dc:source>
	<dc:source>2407-7658</dc:source>
	<dc:source>2460-0040</dc:source>
	<dc:source>10.15294/sji.v13i1</dc:source>
	<dc:language>eng</dc:language>
	<dc:relation>https://journal.unnes.ac.id/journals/sji/article/view/40245/8880</dc:relation>
	<dc:rights xml:lang="en">Copyright (c) 2026 Scientific Journal of Informatics</dc:rights>
</oai_dc:dc>