Analisis Unjuk Kerja Klasifikasi Citra Motif Kain Bali Menggunakan Model Inception Dan EfficientNet
DOI:
https://doi.org/10.35889/progresif.v21i1.2568Abstract
Bali, with its rich culture and diverse symbolism reflected in the traditional fabric motifs. However, the manual recognition of Balinese fabric motifs faces challenges such as pattern complexity, similarity between motifs, and limited public knowledge. This study aims to address these challenges by using Artificial Intelligence (AI) to automate the process of accurately and efficiently identifying Bali fabric motifs. The research develops a motif recognition model for Bali fabrics using Inception V3 and EfficientNet B1 algorithms in image classification analysis. The research methodology used is experimental, starting with dataset collection, data augmentation, feature extraction, modeling, and testing. The results show that the EfficientNet model achieved an accuracy of 99% on the 25th iteration, much higher than Inception V3, which only achieved 62% accuracy. These results indicate that the EfficientNet model is more effective in recognizing and classifying Bali fabric motifs and strengthen the potential of artificial intelligence in cultural preservation.
Keywords: Bali; Classification; EfficientNet; Inception; Pattern
Abstrak
Bali, dengan kekayaan budaya yang kompleks serta beragam simbolisme. Salah satunya tercermin dalam rupa motif kain tradisional Bali. Namun, pengenalan manual motif kain Bali sering terhambat oleh tantangan seperti kerumitan pola, kesamaan antara motif, dan keterbatasan pengetahuan masyarakat. Penelitian ini bertujuan untuk mengatasi tantangan tersebut dengan menggunakan kecerdasan buatan (AI) untuk mengotomatisasi proses identifikasi motif kain Bali secara akurat dan efisien. Penelitian ini mengembangkan model pengenalan motif kain Bali dengan menggunakan algoritma Inception V3 dan EfficientNet B1 dalam analisis klasifikasi citra. Metode penelitian yang digunakan adalah eksperimen, dimulai dengan pengumpulan dataset, augmentasi data, ekstraksi fitur, pemodelan, dan pengujian. Hasil penelitian menunjukkan bahwa model EfficientNet B1 mencapai akurasi 99% pada iterasi ke-25, jauh lebih tinggi dibandingkan dengan Inception V3 yang hanya memperoleh akurasi 62%. Hasil ini menunjukkan bahwa model EfficientNet lebih efektif dalam mengenali dan mengklasifikasikan motif kain Bali serta memperkuat potensi kecerdasan buatan dalam pelestarian budaya.
Kata kunci: Bali; EfficientNet; Inception; Klasifikasi; Motif
References
Kemendikbud, “Indeks Pembangunan Kebudayaan | Provinsi Bali.” [Daring]. Tersedia pada: https://ipk.kemdikbud.go.id/provinsi/51
A. Parameswara, I. a. N. Saskara, I. M. S. Utama, dan N. P. W. Setyari, “Exploring Cultural Value and its Sustainability of Balinese Handwoven Textiles,” TEXTILE, vol. 21, no. 1, hlm. 174–197, 2022, doi: 10.1080/14759756.2022.2043517.
N. S. Budi, N. T. B. Affanti, dan N. S. Mataram, “Ornamental patterns of contemporary Indonesian batik: clothing for strengthening the articulation of appearance characteristics,” Wacana Seni Journal of Arts Discourse, vol. 23, no. 2, hlm. 16–28, 2024, doi: 10.21315/ws2024.23.2.
D. Kodžoman, “The psychology of clothing,” Textile & Leather Review, vol. 2, no. 2, hlm. 90–103, 2019, doi: 10.31881/tlr.2019.22.
M. R. Mahhendra, D. A. R. Putra, dan L. Luerdi, “Eksplorasi Diplomasi Budaya Indonesia Dalam Perhelatan Bali Street Carnival,” Complex: Jurnal Multidisiplin Ilmu Nasional, vol. 2, hlm. 32–39, 2025.
A. Christia dkk., Kecerdasan Buatan: Arah dan Eksplorasinya. Prasetiya Mulya Publishing, 2024.
A. Irawan, M. Lestari, W. Rahayu, dan R. Wulan, “Ethnomathematics batik design Bali island,” J Phys Conf Ser, vol. 1338, no. 1, hlm. 012045, 2019, doi: 10.1088/1742-6596/1338/1/012045.
I. M. A. Mahawan dan A. Harjoko, “Pattern recognition of Balinese carving motif using Learning Vector Quantization (LVQ),” dalam Communications in Computer and Information Science, 2017, hlm. 43–55. doi: 10.1007/978-981-10-7242-0_4.
C.V. Haritha, “An overview of Pattern Recognition,” International Journal Of Research Publication And Review, Vol 3, Issue 7, pp 1883-1889, July 2022, doi: https://doi.org/10.55248/gengpi.2022.3.7.49
V. H. Athala, A. H. Rangkuti, N. F. Luthfi, S. V. Aditama, dan J. M. Kerta, “Improved pattern recognition of various traditional clothes with Convolutional neural network,” dalam 3rd International Symposium on Material and Electrical Engineering Conference (ISMEE), Bandung, Indonesia, 2021, hlm. 15–20. doi: 10.1109/ISMEE54273.2021.9774136.
G. Lakshmi dan N. Sharada, “Artificial Intelligence based Pattern Recognition,” International Journal of Engineering and Management Research, vol. 9, no. 2, hlm. 29–32, 2019, doi: 10.31033/ijemr.9.2.4.
M. Ghazal dan K. Abdullah, “Face recognition based on curvelets, invariant moments features and SVM,” TELKOMNIKA Indonesian Journal of Electrical Engineering, vol. 18, hlm. 733–739, Apr 2020, doi: 10.12928/Telkomnika.v18i2.14106.
Z. Feng dan X. Hua, “Pattern recognition and its application in image processing,” J Phys Conf Ser, vol. 1518, no. 1, hlm. 012071, 2020, doi: 10.1088/1742-6596/1518/1/012071.
H. A. Zhou dkk., “Generative AI in Industrial Machine Vision -- A review,” 2024. [Daring]. Tersedia pada: https://arxiv.org/abs/2408.10775
T. Shafira dan A. Fauzy, “Implementasi image classification menggunakan metode Convolutional Neural Network (CNN) pada citra kain tenun,” 2021.
S. Shakya, B. Shrestha, S. Thapa, A. Chauhan, dan S. Adhikari, “Clothes Identification Using Inception ResNet V2 and MobileNet V2,” SSRN Electronic Journal, Okt 2021, doi: 10.2139/SSRN.3949190.
T. Hendrawati, D. a. P. Wulandari, I. G. S. S. Dharma, dan C. P. Yanti, “Penerapan deep learning dalam pengenalan Endek Bali menggunakan convolutional Neural network,” Jurnal Media Informatika Budidarma, vol. 7, no. 4, hlm. 2118, 2023, doi: 10.30865/mib.v7i4.6721.
W. K. Mutlag, S. K. Ali, Z. M. Aydam, dan B. H. Taher, “Feature extraction methods: a review,” J Phys Conf Ser, vol. 1591, no. 1, hlm. 012028, 2020, doi: 10.1088/1742-6596/1591/1/012028.
S. Kirstein, H. Wersing, H. Gross, dan E. Körner, “A Vector Quantization Approach for Life-Long Learning of Categories,” dalam Lecture Notes in Computer Science, 2009, hlm. 805–812. doi: 10.1007/978-3-642-02490-0_98.
C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, dan Z. Wojna, “Rethinking the inception architecture for computer vision,” 2015. [Daring]. Tersedia pada: https://arxiv.org/abs/1512.00567
M. Tan dan Q. V Le, “EfficientNet: Rethinking model scaling for convolutional neural networks,” 2015. [Daring]. Tersedia pada: https://arxiv.org/abs/1905.11946
F. Ferdiawan dan N. B. Hartono, “Deteksi Suara Chord Piano Menggunakan Metode Convolutional Neural Network,” Jurnal Informatika Dan Rekayasa Elektronik, vol. 5, no. 1, hlm. 62–68, 2022, doi: 10.36595/jire.v5i1.552.
W. Setiawan dan F. Damayanti, “Layers modification of convolutional neural network for pneumonia detection,” J Phys Conf Ser, vol. 1477, no. 5, hlm. 052055, 2020, doi: 10.1088/1742-6596/1477/5/052055.
