Turning Turnitin Highlights into Structured Data with Report-Aware HSV Segmentation and GPU-Accelerated OCR
Keywords:
Turnitin, HSV color segmentation, optical character recognition, document analysis, similarity analyticsAbstract
Laporan kesamaan Turnitin memuat informasi spasial, warna, dan tekstual yang kaya, tetapi bagian yang disorot umumnya masih dibaca secara visual dan belum diubah menjadi data terstruktur. Penelitian ini mengembangkan pipeline berbasis laporan untuk mengekstraksi highlight berwarna dari PDF Turnitin menjadi rekaman yang dapat dianalisis. Metode menggabungkan rendering PDF, klasifikasi tipe halaman, segmentasi hue–saturation–value (HSV), operasi morfologi, connected-component analysis, filter geometri, dan optical character recognition (OCR) berbasis GPU, dengan pemeriksaan text layer PDF sebagai informasi pendukung. Dataset evaluasi terdiri atas 106 laporan dengan 3.057 halaman. Klasifikasi halaman mengidentifikasi 1.315 halaman yang mengandung highlight dan mengalihkan 56,98% halaman dari pemrosesan rinci. Segmentasi HSV menghasilkan delapan kelas warna dan 11.471 komponen awal. Setelah penyaringan dan ekstraksi teks, diperoleh 7.530 rekaman terstruktur; 76,75% memenuhi kriteria keterbacaan baik, 20,04% berupa fragmen sangat pendek, dan 3,21% noisy, garbled, atau kosong. Distribusi beban dokumen sangat menceng ke kanan. Sistem menunjukkan bahwa anotasi visual laporan kesamaan dapat dioperasionalkan sebagai data dokumen yang auditable, tanpa menganggap kesamaan sebagai bukti otomatis plagiarisme.
Downloads
References
Abdelsadek, D. A., Al-Berry, M. N., Ebied, H. M., & Hassaan, M. (2022). Impact of using different color spaces on image segmentation. Lecture Notes on Data Engineering and Communications Technologies, 113, 456–471. https://doi.org/10.1007/978-3-031-03918-8_39
Kementerian PPN/Bappenas. Proyeksi kebutuhan pembiayaan revitalisasi sarana dan prasarana pendidikan 2025–2029. Kementerian PPN/Bappenas; 2025.
Peraturan Presiden Republik Indonesia Nomor 12 Tahun 2021 tentang Perubahan atas Peraturan Presiden Nomor 16 Tahun 2018 tentang Pengadaan Barang/Jasa Pemerintah, (2021).
Alanazi AH, Al-Gahtani KS, Alsugair AM, Bin Mahmoud AA, Alsanabani NM. Assessment and ranking of criteria for engineering firm performance using RII, entropy weight method, and TOPSIS. Applied Sciences. 2026;16(11).
Elsherbeny HA, Gunduz M, Ugur LO. A hybrid model for enhancing risk management and operational performance of AEC consultants: An integrated PLS–ANN approach. Sustainability. 2025;17(4):1467.
Ogbu CP, Imafidon MO. Influence of selection criteria on clients’ satisfaction with construction consultancy services in Nigeria. Journal of Engineering, Design and Technology. 2022;20(6):1519-37.
Briliyanti A, Rojewski J, Colbry DJL, Colbry KL. Training the trainers: Preparing facilitators to provide professional development for engineers and scientists. ASEE Annual Conference and Exposition Conference Proceedings. 2022.
Bekele AA, Mahesh G. Impact of contractor development programs on the competency of small and medium contractors in Ethiopia. International Journal of Construction Education and Research. 2025;21(1):94-116.
da Alves TCL. The Silo Game: A simulation on interdisciplinary collaboration. Proceedings of the International Group for Lean Construction. 2022. p. 1052–1063.
Ibrahim FSB, Ebekozien A, Khan PAM, Aigbedion M, Ogbaini IF, Amadi GC. Appraising fourth industrial revolution technologies’ role in the construction sector: How prepared are construction consultants? Facilities. 2022;40(7–8):515-32.
Kaboré SS, Ngangue P, Soubeiga D, Barro A, Pilabré AH, Bationo N, et al. Barriers and facilitators for the sustainability of digital health interventions in low- and middle-income countries: A systematic review. Frontiers in Digital Health. 2022;4:1014375.
Chung H, Cha K, Lee HS. What drives and hinders the use of new e-customs systems in developing countries of Sub-Saharan Africa? An empirical study from Cameroon. Information and Media. 2023;96:40-64.
Amin B, Ashad H, Maricar H. Kajian peranan konsultan manajemen konstruksi pada proyek konstruksi di Makassar. Jurnal Teknik Industri Terintegrasi. 2024;7(3):1598-605.
Putra IKAA, Pagehgiri J, Ariyanta IPG. Analisis kinerja konsultan pengawas konstruksi dalam pelaksanaan proyek gedung Puskesmas di Kabupaten Tabanan. Jurnal Teknik Gradien. 2021;13(1):48-60.
Taqiudin M, Anggara D, Nukman N. Analisis pengawasan konstruksi: Kajian kinerja konsultan pengawas di proyek gedung RSUD Awet Muda Narmada. Jurnal Ilmiah Telsinas Elektro, Sipil dan Teknik Informasi. 2023;6(2):189-95.
Damayanti T, Yuni NKSE, Yuliana NPI, Wahyudi IGB. Identifikasi kesenjangan kinerja konsultan pengawas konstruksi di Kota Denpasar. Menara: Jurnal Teknik Sipil. 2025;20(1):84-92.
Wulandari A, Dewantoro, Puspasari VH. Analisis kinerja konsultan pengawas konstruksi dalam pelaksanaan proyek di Kota Palangka Raya. Portal: Jurnal Teknik Sipil. 2024;16(2):142-51.
Wijaya A, Andi A, Rahardjo J. Tingkat kepuasan kontraktor terhadap kinerja konsultan manajemen konstruksi di Surabaya. Dimensi Utama Teknik Sipil. 2023;10(2):137-55.
Ali SHSHA, Habtoor AAA, Alnuaimi AS, Šaljić E, Tomašević V, Raut J. A Delphi and Importance–Performance Analysis framework for fire safety competencies of architects and fire safety engineering consultants in the UAE. Buildings. 2026;16(12).
Abas D, Ahadian ER, Saputra MT. Analisis kepuasan pengguna jasa terhadap kinerja konsultan pengawas pada pekerjaan konstruksi di Kota Ternate. Journal of Science and Engineering. 2021;4(2):120-31.
Ogourtsova T, Gonzalez M, Zerbo A, Gavin F, Shikako K, Weiss J, Majnemer A. Lessons learned in measuring patient engagement in a Canada-wide childhood disability network. Research Involvement and Engagement. 2024;10(1).
Duque Monsalve LF, Navarrete Valladares CP, Sandoval Díaz J. Relationship between political participation and community resilience in the disaster risk process: A systematic review. International Journal of Disaster Risk Reduction. 2024;111:104751.
Nooteboom LA, Mulder EA, Vermeiren RRJM, Eilander J, Van Den Driesschen SI, Kuiper CHZ. Practical recommendations for youth care professionals to improve evaluation and reflection during multidisciplinary team discussions: An action research project. International Journal of Integrated Care. 2022;22(1).
Nabelsi V, Plouffe V, Leclerc MC. Barriers to and facilitators of implementing overnight nursing teleconsultation in small, rural long-term care facilities: Qualitative interview study. JMIR Aging. 2025;8:e71950.
Chigara B, Moyo T. Factors affecting the delivery of optimum health and safety on construction projects during the COVID-19 pandemic in Zimbabwe. Journal of Engineering, Design and Technology. 2022;20(1):24-46.
Hong S, Chae GY, Lim HS. Revitalizing regional industries through public innovation intermediaries: A multi-stage evaluation of the maritime Open Lab model. Sustainability. 2026;18(10).
Marengo LL, Soares AN, Romão HRDS, de Araújo DLA, Zilber SN. The evolution of the local innovation agents program methodology and its contribution to innovation management. REGEPE Entrepreneurship and Small Business Journal. 2022;11(2).
Published
How to Cite
Issue
Section
Copyright (c) 2026 Mutiara yusuf, Rizki Yusliana Bakti, Titin Wahyuni
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms: (1) Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal; (2) Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal; (3) Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
Greenplex Research Journal of Green Complex Engineering is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
