PENGEMBANGAN MODEL DETEKSI POLA KARAKTER BAHASA ARAB PADA CITRA AL-QUR’AN MENGGUNAKAN PENDEKATAN HYBRID TRANSFORMASI SLANT DAN ADABOOST
DOI:
https://doi.org/10.33143/jics.v11i2.5785Kata Kunci:
Pengenalan Karakter Arab, Transformasi Slant, AdaBoost, Model Hybrid, Computer Vision, Deteksi PolaAbstrak
Perkembangan computer vision dan machine learning telah memberikan kontribusi signifikan dalam pengembangan sistem cerdas untuk analisis teks digital, termasuk pengenalan aksara Arab pada citra Al-Qur’an. Penelitian ini bertujuan untuk mengembangkan model hybrid dalam mendeteksi pola karakter Bahasa Arab, khususnya Dhamir Raf’a Munfasil (kata ganti terpisah dalam posisi nominatif), pada citra Al-Qur’an digital menggunakan kombinasi Transformasi Slant dan algoritma AdaBoost. Model yang diusulkan mengintegrasikan ekstraksi fitur menggunakan Transformasi Slant untuk menangkap karakteristik domain frekuensi dari pola karakter, kemudian dilanjutkan dengan proses klasifikasi menggunakan algoritma ensemble learning AdaBoost guna meningkatkan kinerja pendeteksian. Sistem diuji menggunakan 150 baris teks Al-Qur’an yang memuat 14 pola. Pengukuran kinerja dilakukan menggunakan metrik precision dan recall. Hasil eksperimen menunjukkan bahwa model hybrid Slant–AdaBoost memberikan performa yang lebih baik dibandingkan metode tunggal, dengan nilai precision sebesar 86% dan recall sebesar 93%, yang menunjukkan peningkatan akurasi dan keandalan dalam pendeteksian pola. Temuan penelitian ini membuktikan bahwa kombinasi transformasi fitur dan klasifikasi berbasis boosting mampu meningkatkan kinerja sistem pengenalan pola karakter Bahasa Arab secara signifikan. Penelitian ini berkontribusi pada pengembangan sistem informasi cerdas untuk analisis teks Al-Qur’an digital dan pengenalan aksara Arab.
Unduhan
Diterbitkan
Terbitan
Bagian
Lisensi
COPYRIGHT TRANSFER FORM
The copyright to this article is transferred to Universitas Ubudiyah Indonesia (UUI) if and when the article is accepted for publication. The undersigned hereby transfers any and all rights in and to the paper including without limitation all copyrights to UUI. The undersigned hereby represents and warrants that the paper is original and that he/she is the author of the paper, except for material that is clearly identified as to its original source, with permission notices from the copyright owners where required. The undersigned represents that he/she has the power and authority to make and execute this assignment.
We declare that:
- This paper has not been published in the same form elsewhere.
- It will not be submitted anywhere else for publication prior to acceptance/rejection by this Journal.
- A copyright permission is obtained for materials published elsewhere and which require this permission for reproduction.
Furthermore, I/We hereby transfer the unlimited rights of publication of the above mentioned paper in whole to UUI. The copyright transfer covers the right to reproduce and distribute the article, including reprints, translations, photographic reproductions, microform, electronic form (offline, online) or any other reproductions of similar nature. The corresponding author signs for and accepts responsibility for releasing this material on behalf of any and all co-authors. After submission of this agreement signed by the corresponding author, changes of authorship or in the order of the authors listed will not be accepted.
Retained Rights/Terms and Conditions
- Authors retain all proprietary rights in any process, procedure, or article of manufacture described in the work.
- Authors may reproduce or authorize others to reproduce the work or derivative works for the author’s personal use or for company use, provided that the source and the UUI copyright notice are indicated, the copies are not used in any way that implies UUI endorsement of a product or service of any employer, and the copies themselves are not offered for sale.
- Although authors are permitted to re-use all or portions of the work in other works, this does not include granting third-party requests for reprinting, republishing, or other types of re-use.
.png)
