Analisis Kinerja TrOCR dan EasyOCR pada Iklan Judi Online Berbasis Deteksi YOLOv8
DOI:
https://doi.org/10.29407/d5sa5403Abstract
Maraknya penyebaran visual iklan judi online pada media digital menuntut pengembangan sistem deteksi otomatis yang mampu mengekstraksi informasi tekstual secara akurat. Penelitian ini menganalisis kinerja TrOCR dan EasyOCR pada proses ekstraksi teks visual iklan judi online dengan memanfaatkan YOLOv8 untuk mendeteksi region teks. Dataset penelitian terdiri atas 229 potongan citra teks hasil deteksi yang dievaluasi menggunakan Character Error Rate (CER), Word Error Rate (WER), dan akurasi exact match. Hasil pengujian menunjukkan bahwa TrOCR memberikan performa lebih baik dibandingkan EasyOCR dengan rata-rata CER sebesar 0.1309, rata-rata WER sebesar 0.4219, dan akurasi sebesar 44.98%, sedangkan EasyOCR memperoleh CER sebesar 0.1938 dengan akurasi sebesar 35.81%. Temuan ini menunjukkan bahwa pendekatan berbasis transformer lebih efektif dalam mengenali teks pada visual dengan kompleksitas tinggi, seperti font dekoratif dan efek grafis khas iklan judi online. Penelitian ini berkontribusi pada pengembangan sistem moderasi konten digital otomatis berbasis ekstraksi teks
Keywords:
Optical Character Recognition, EasyOCR, Iklan Judi Online, TrOCR, YOLOv8##plugins.themes.default.displayStats.downloads##
References
[1] A. Muzakir, U. Ependi, and Suyanto, "A Deep Learning and AutoML-Based Multimodal Text Extraction Framework for Detecting Online Gambling Advertisements in Indonesian Social Media," Int. J. Saf. Secur. Eng., vol. 15, no. 9, Sep. 2025, doi: 10.18280/ijsse.150908.
[2] B. Shi, X. Bai, and C. Yao, "An End-to-End Trainable Neural Network for Image-Based Sequence Recognition and Its Application to Scene Text Recognition," IEEE Trans. Pattern Anal. Mach. Intell., vol. 39, no. 11, pp. 2298-2304, Nov. 2017, doi: 10.1109/TPAMI.2016.2646371.
[3] J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, "You Only Look Once: Unified, Real-Time Object Detection," in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, Jun. 2016, pp. 779-788. doi: 10.1109/CVPR.2016.91.
[4] C.-Y. Wang, A. Bochkovskiy, and H.-Y. M. Liao, "YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors," in 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, Jun. 2023, pp. 7464-7475. doi: 10.1109/CVPR52729.2
[5] M. Li et al., "TrOCR: Transformer-Based Optical Character Recognition with Pre-trained Models," Proc. AAAI Conf. Artif. Intell., vol. 37, no. 11, pp. 13094-13102, Jun. 2023, doi: 10.1609/aaai.v37i11.26538.
[6] J. Baek et al., "What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis," in 2019 IEEE/CVF International Conference on Computer Vision (ICCV), IEEE, Oct. 2019, pp. 4714-4722. doi: 10.1109/ICCV.2019.00481.
[7] M. Liao, Z. Wan, C. Yao, K. Chen, and X. Bai, "Real-Time Scene Text Detection with Differentiable Binarization," Proc. AAAI Conf. Artif. Intell., vol. 34, no. 07, pp. 11474-11481, Apr. 2020, doi: 10.1609/aaai.v34i07.6812.
[8] D. B. Santoso and M. Fachrie, "Intelligent Document Processing Berbasis OCR + Transformers dan CNN untuk Verifikasi Dokumen Bantuan Pangan," Jutisi J. Ilm. Tek. Inform. dan Sist. Inf., vol. 14, no. 3, pp. 1652-1663, Dec. 2025, doi: 10.35889/JUTISI.V14I3.3351.
[9] Y. Liu, H. Chen, C. Shen, T. He, L. Jin, and L. Wang, "ABCNet: Real-Time Scene Text Spotting With Adaptive Bezier-Curve Network," in 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, Jun. 2020, pp. 9806-9815. doi: 10.1109/CVPR42600.2020.00983.
[10] R. Akbar, R. A. Siroj, M. Win Afgani, and U. Islam Negeri Raden Fatah Palembang Abstract, "Experimental Research Dalam Metodologi Pendidikan," J. Ilm. Wahana Pendidik., vol. 9, no. 2, pp. 465-474, Jan. 2023, doi: 10.5281/ZENODO.7579001.
[11] E. Apriani and N. Pratiwi, "Perancangan Sistem Pengenalan Tulisan Tangan pada Jawaban Esai Menggunakan Metode CNN-LSTM Berbasis Android," Metik J., vol. 9, no. 2, pp. 385-396, 2025, doi: 10.47002/metik.v9i2.1094.
[12] E. William and A. Zahra, "Speech Recognition Dengan Whisper Dalam Bahasa Indonesia," Action Res. Lit., vol. 9, no. 2, pp. 386-397, 2025, doi: 10.46799/arl.v9i2.2573.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Copyright on any article is retained by the author(s).
- The author grants 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 acknowledgment of the work’s authorship and initial publication in this journal.
- 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 acknowledgment of its initial publication in this journal.
- 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.
- The article and any associated published material is distributed under the Creative Commons Attribution-ShareAlike 4.0 International License
