HYBRID MOBILENETV2-SVM FOR ROBUST INDONESIAN  BATIK MOTIF IDENTIFICATION

Irawati Putri Utami; Asrul Sani

doi:10.33330/jurteksi.v12i2.4449

Irawati Putri Utami Universitas Nasional
Asrul Sani Universitas Nasional

DOI: https://doi.org/10.33330/jurteksi.v12i2.4449

Keywords: Batik Classification; MobileNetV2; Support Vector Machine; Hybrid Model; Com putational Efficiency

Abstract

Abstract: Automated batik motif classification is challenged by high inter-class similarity and texture complexity. This study proposes a hybrid model integrating MobileNetV2 as a feature extractor and Support Vector Machine (SVM) as the classifier to optimize accuracy and efficiency. Utilizing a Kaggle dataset of 8,640 images across 20 batik categories, the data was partitioned into 420 training images per class (Dayak: 360) and 15 testing images per class. The results demonstrate superior performance with 96.00% accuracy, exceeding the 90% target. The system showed high computational efficiency with a total execution time of 359.92 seconds and feature extraction taking only 22.63 seconds. This hybrid approach provides an ideal performance balance for resource-constrained mobile applications.

Keywords: batik classification; MobileNetV2; support vector machine; hybrid model; computational efficiency

Abstrak: Klasifikasi motif batik secara otomatis menghadapi tantangan kemiripan visual antar-kelas yang tinggi. Penelitian ini bertujuan mengoptimalkan akurasi dan efisiensi pengenalan batik menggunakan model hibrida MobileNetV2 sebagai pengekstraksi fitur dan Support Vector Machine (SVM) sebagai klasifikator. Menggunakan dataset Kaggle berisi 8.640 citra dari 20 kategori batik, data dibagi menjadi 420 citra latih per kelas (kecuali Batik Dayak 360) dan 15 citra uji per kelas. Hasil eksperimen menunjukkan performa impresif dengan akurasi 96,00%, melampaui target awal 90%. Sistem ini sangat efisien dengan total waktu eksekusi 359,92 detik, di mana ekstraksi fitur hanya membutuhkan 22,63 detik. Kombinasi MobileNetV2 dan SVM memberikan keseimbangan performa ideal untuk implementasi pada perangkat bergerak dengan sumber daya terbatas.

Kata kunci: klasifikasi batik; MobileNetV2; Support Vector Machine; Hybrid Model; efisiensi komputasi

References

[1] Riqqah Fadiyah Alya, Merlinda Wibowo, and Paradise, “CLASSIFICATION OF BATIK MOTIF USING TRANSFER LEARNING ON CONVOLUTIONAL NEURAL NETWORK (CNN),” vol. 4, no. 1, pp. 161–170, 2023 .

[2] Ira Puspita Sari, Luluk Elvitaria, and Rudiansyah, “Data-driven approach for batik pattern classification using convolutional neural network (CNN),” vol. 13, no. 3, pp. 323–331, 2025 .

[3] Mohammad Arif Rasyidi, Ruktin Handayani, and Fauzul Aziz, “Identification of batik making method from images using convolutional neural network with limited amount of data,” Bulletin of Electrical Engineering and Informatics, vol. 10, no. 3, pp. 1300–1307, 2021 .

[4] Khairul Azmi, Sarjon Defit, and Sumijan, “Implementasi Convolutional Neural Network (CNN) Untuk Klasifikasi Batik Tanah Liat Sumatera Barat,” vol. 16, no. 1, 2023 .

[5] Ananda Rizki Dani and Irma Handayani, “KLASIFIKASIMOTIF BATIK YOGYAKARTA MENGGUNAKAN METODE GLCM DAN CNN,” 2024.

[6] Ratih Addina Hapsari and Imam Yuadi, “Batik Pattern Classification Using Logistic Regression, SVM, and Deep Learning Features,” Jurnal Informatika, vol. 12, no. 2, pp. 97–105, 2025 .

[7] G. Pramuja et al., “Pengenalan Citra Batik Tradisional Menggunakan Deep Learning untuk Klasifikasi Motif Daerah,” 2025.

[8] Zufar Faiil Haq et al., “Implementasi Convolutional Neural Network (CNN) untuk Klasifikasi Citra Batik Nusantara,” Jurnal Ilmiah Teknik Informatika dan Komunikasi, vol. 5, no. 1, pp. 426–441, 2025 .

[9] Yesicha Amilia Putri, Yufis Azhar, and Agus Eko Minarno, “Klasifikasi Jenis Batik Menggunakan Algoritma Convolutional Neural Network,” REPOSITOR, vol. 3, no. 2, pp. 199–206, 2021 .

[10] Amin Padmo Azam Masa and Hamdani Hamdan, “Klasifikasi Motif Citra Batik Menggunakan Convolutional Neural Network Berdasarkan K-means Clustering,” JURNAL MEDIA INFORMATIKA BUDIDARMA, vol. 5, no. 4, p. 1292, 2021 .

[11] Arleen Chrysantha Gunardi, “Pemanfaatan CNN dalam Klasifikasi Motif Batik Indonesia,” 2024.

[12] Maria Misela A. Wona et al., “Klasifikasi Batik Indonesia Menggunakan Convolutional Neural Network (CNN),” 2023 .

[13] M. Taufik et al., “Batiknet: Batik Classification-based Management Application for Inexperienced User,” 2024 .

[14] Shiuan Wan, Mei-Ling Yeh, and Hong-Lin Ma, “An innovative intelligent system with integrated CNN and SVM: Considering various crops through hyperspectral image data,” ISPRS Int. J. Geoinf., vol. 10, no. 4, 2021 .

[15] Adithya Kusuma Whardana and Umar Alfaruq Abdul Aziz, “Klasifikasi Motif Batik Menggunakan Convolutional Neural Network (CNN) dengan Otsu thresholding dan Median filter,” 2025.