Klasifikasi Citra Gerakan Takbir Berdasarkan Fikih Syaikh Al-Albani Menggunakan Model Hibrida CNN-SVM
Abstract
Penelitian ini mengklasifikasikan kebenaran gerakan takbir dalam salat berdasarkan parameter fikih Syaikh Al-Albani menggunakan pendekatan hibrida CNN dan SVM. Alur kerja mencakup prapemrosesan citra melalui deteksi tepi operator Prewitt dan operasi morfologi untuk pemurnian kontur, diikuti normalisasi. Fitur mendalam diekstraksi dengan VGG16 melalui transfer learning, sedangkan klasifikasi dilakukan menggunakan Support Vector Machine dengan penalaan hiperparameter serta mekanisme ambang (threshold) untuk penetapan keputusan. Dataset terdiri atas 184 citra beranotasi (146 benar, 38 tidak benar) dengan pembagian 80:20 untuk pelatihan dan pengujian. Evaluasi menggunakan akurasi, precision, recall, F1-score, dan confusion matrix. Model mencapai akurasi 95% pada data uji, menunjukkan bahwa kombinasi prapemrosesan berbasis tepi, ekstraksi fitur konvolusional, dan klasifikasi margin-maksimum efektif membedakan variasi halus pada postur takbir. Temuan ini berimplikasi pada pengembangan alat bantu pembelajaran dan koreksi gerakan salat, termasuk skenario umpan balik real-time. Keterbatasan meliputi ukuran serta ketidakseimbangan dataset dan rujukan fikih tunggal; penelitian lanjutan diarahkan pada perluasan data, validasi eksternal, dan pengujian pada perangkat nyata.
Full Text:
PDFReferences
S. M. N. Al-Albani, Sifat Shalat Nabi Shallallaahu 'Alaihi Wa sallam: Seakan-akan Anda Menyaksikannya = Shifatu Shalat an-Nabi Shallallaahu 'Alaihi Wa sallam: Min at-Takbir Ila at Taslim Ka’ annaka TarahaSifat Shalat Nabi Shallallaahu ’Alaihi Wa sallam: Seakan-akan Anda Meny, Indonesia. Jakarta: Darul Haq, 2013.
A. Fadhil, K. Kasman, and P. Pujiono, “Methodology For Determining The Quality Of Hadith Nashiruddin Al-Albani (Analysis Of The Book Silsilat Al-Ahadits Al-Shahihah And Silsilat Al-Ahadits Al-Dha’ifah),” Int. J. Educ. Res. Soc. Sci., vol. 4, no. 4, pp. 746–754, 2023, doi: 10.51601/ijersc.v4i4.704.
F. Nikmah and R. Imawan, “Penyuluhan Fiqh Ibadah tentang Syarat-Syarat Sah Sholat untuk Meningkatkan Pengetahuan Jama’ah Masjid Al-Hikmah Desa Sekuning Besowo Kediri,” J. Pengabdi. Kpd. Masy. Desa, vol. 4, no. 2, pp. 162–170, 2023.
K. Jamal, R. Kurniawan, A. S. Batubara, M. Z. A. Nazri, F. Lestari, and P. Papilo, “Text Classification on Islamic Jurisprudence using Machine Learning Techniques,” J. Phys. Conf. Ser., vol. 1566, no. 1, p. 012066, 2020, doi: 10.1088/1742-6596/1566/1/012066.
I. Ahmed, M. Ahmad, J. J. P. C. Rodrigues, and G. Jeon, “Edge computing-based person detection system for top view surveillance: Using CenterNet with transfer learning,” Appl. Soft Comput., vol. 107, no. 1, p. 107489, 2021, doi: 10.1016/j.asoc.2021.107489.
A. Rácz, D. Bajusz, and K. Héberger, “Effect of Dataset Size and Train / Test Split Ratios in,” Eff. Dataset Size Train/Test Split Ratios QSAR/QSPR Multiclass Classif., vol. 26(4), no. 1111, pp. 1–16, 2021, [Online]. Available: https://doi.org/10.3390/molecules26041111
M. F. Qureshi, Z. Mushtaq, M. Z. u. Rehman, and E. N. Kamavuako, “Spectral Image-Based Multiday Surface Electromyography Classification of Hand Motions Using CNN for Human–Computer Interaction,” IEEE Sens. J., vol. 22, no. 21, pp. 20676–20683, 2022, doi: 10.1109/JSEN.2022.3204121.
L. Chaplot, S. Houshmand, K. B. Martinez, J. Andersen, and H. Rouhani, “Optimizing Sensor Placement and Machine Learning Techniques for Accurate Hand Gesture Classification,” Electron., vol. 13, no. 15, pp. 1–12, 2024, doi: 10.3390/electronics13153072.
S. K. Zhou et al., “A Review of Deep Learning in Medical Imaging: Imaging Traits, Technology Trends, Case Studies with Progress Highlights, and Future Promises,” Proc. IEEE, vol. 109, no. 5, pp. 820–838, 2021, doi: 10.1109/JPROC.2021.3054390.
R. O. Ogundokun, R. Maskeliūnas, and R. Damaševičius, “Human Posture Detection Using Image Augmentation and Hyperparameter-Optimized Transfer Learning Algorithms,” Appl. Sci., vol. 12, no. 19, p. 10156, 2022, doi: 10.3390/app121910156.
Sunardi, A. Yudhana, and M. Fahmi, “SVM-CNN Hybrid Classification for Waste Image Using Morphology and HSV Color Model Image Processing,” Trait. du Signal, vol. 40, no. 4, pp. 1763–1769, 2023, doi: 10.18280/ts.400446.
M. Fahmi, A. Yudhana, and S. Sunardi, “Image Processing Using Morphology on Support Vector Machine Classification Model for Waste Image,” MATRIK J. Manajemen, Tek. Inform. dan Rekayasa Komput., vol. 22, no. 3, pp. 553–566, 2023, doi: 10.30812/matrik.v22i3.2819.
M. Fahmi and A. Yudhana, “Pemilahan Sampah Menggunakan Model Klasifikasi Support Vector Machine Gabungan dengan Convolutional Neural Network,” J. Ris. Komputer), vol. 10, no. 1, pp. 2407–389, 2023, doi: 10.30865/jurikom.v10i1.5468.
I. Muhammad Nurdin and A. Fadlil, “Identification of Feasibility of Canned Based Foods Image Processing Techniques Using Thresholding,” Bul. Ilm. Sarj. Tek. Elektro, vol. 3, no. 1, p. 10, 2021, doi: 10.12928/biste.v3i1.1608.
F. Zhuang et al., “A Comprehensive Survey on Transfer Learning,” Proc. IEEE, vol. 109, no. 1, pp. 43–76, 2021, doi: 10.1109/JPROC.2020.3004555.
M. U. Ahmad, S. Ashiq, G. Badshah, A. H. Khan, and M. Hussain, “Feature Extraction of Plant Leaf Using Deep Learning,” Complexity, vol. 2022, no. 1, p. 6976112, 2022, doi: 10.1155/2022/6976112.
W. Muhammad, R. Wan, A. Y. Dak, and T. R. Razak, “A Survey on Various Edge Detection Techniques in Image Processing and Applied Disease Detection,” vol. 9, no. 2, pp. 23–32, 2024, doi: 10.24191/jcrinn.v9i2.415.
DOI: http://dx.doi.org/10.30872/jurti.v9i3.21327
Refbacks
- There are currently no refbacks.
Copyright (c) 2025 Jurnal Rekayasa Teknologi Informasi (JURTI)
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Alamat Redaksi :
Program Studi Informatika
Fakultas Teknik
Jl. Sambaliung No. 9 Kampus Gunung Kelua Samarinda 75119 - Kalimantan Timur
e-mail : jurti.unmul@fkti.unmul.ac.id
Url : http://e-journals.unmul.ac.id/index.php/INF
Contact Person : Medi Taruk [081543438301]
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.