Real-Time Color Classification of Objects with an Improved MobileNetV2 CNN Model

Resti Apriliyanti; Denny Kurniadi; Dony Novaliendry; Sandi Rahmadika; Muhammad Farhan

doi:10.24036/jtip.v18i2.969

Authors

Resti Apriliyanti Universitas Negeri Padang
Denny Kurniadi Universitas Negeri Padang
Dony Novaliendry Universitas Negeri Padang
Sandi Rahmadika Universitas Negeri Padang
Muhammad Farhan Universitas Negeri Padang

DOI:

https://doi.org/10.24036/jtip.v18i2.969

Keywords:

Color classification, Convolutional Neural Network, MobileNetV2, Transfer learning, Graphical User Interface, Real-time system

Abstract

This research aimed to develop a Convolutional Neural Network (CNN) model for automatic object color classification using MobileNetV2. To determine the optimal configuration, the training process adjusted several hyperparameters, with particular focus on identifying the most suitable learning rate. The dataset consisted of 3,212 images grouped into five color categories: red, green, blue, random (including yellow, orange, and brown), and none (no object detected). Data augmentation techniques were applied to enhance the variety and robustness of the dataset. The model was trained using the Adam optimizer alongside the categorical crossentropy loss function, with various learning rate settings tested during training. Evaluation results showed that the model worked best with a learning rate of 0.0001 and a batch size of 32, with an average accuracy of 94%. To display prediction results in real time, the top-performing model was integrated into a graphical user interface (GUI). These findings demonstrate the effectiveness of the MobileNetV2-based CNN model in recognizing object colors and highlight its suitability for integration into real-time industrial sorting applications

References

K. Kisno, N. Fatmawati, R. Rizqiyani, S. Kurniasih, and E. M. Ratnasari, “Pemanfaatan Teknologi Artificial Intelligences (AI) Sebagai Respon Positif Mahasiswa Piaud dalam Kreativitas Pembelajaran dan Transformasi Digital,” IJIGAEd: Indonesian Journal of Islamic Golden Age Education, vol. 4, no. 1, p. 44, Dec. 2023, doi: 10.32332/ijigaed.v4i1.7878.

M. Firmansyah and P. Jaya, “Rancang Bangun Alat Pemilah Kematangan Buah Jeruk Manis Menggunakan Metode SVM,” Voteteknika (Vocational Teknik Elektronika dan Informatika), vol. 11, no. 4, p. 391, Dec. 2023, doi: 10.24036/voteteknika.v11i4.124547.

M. Z. Andrekha and Y. Huda, “Deteksi Warna Manggis Menggunakan Pengolahan Citra dengan Opencv Python,” Voteteknika (Vocational Teknik Elektronika dan Informatika), vol. 9, no. 4, p. 27, Dec. 2021, doi: 10.24036/voteteknika.v9i4.114251.

F. Nurdiyansyah et al., “Penerapan Convolutional Neural Network Untuk Deteksi Kualitas Telur Ayam Ras Berdasarkan Warna Cangkang,” Jurnal MNEMONIC, vol. 7, no. 1, pp. 40–47, 2024.

A. Wibowo, Poningsih, I. Parlina, Suhanda, and A. Wanto, “Rancang Bangun Mesin Sortir Buah Kelapa Sawit Berdasarkan Tingkat Kematangan Menggunakan Sensor Warna TCS3200 Berbasis Arduino Uno,” STORAGE – Jurnal Ilmiah Teknik dan Ilmu Komputer, vol. 1, no. 2, pp. 9–15, May 2022, doi: 10.55123.

A. Chairi and R. Mukhaiyar, “Sistem Kontrol Color Sorting Machine Dengan Pengolahan Citra Digital,” JTEIN: Jurnal Teknik Elektro Indonesia, vol. 4, no. 1, pp. 387–396, Jul. 2023, doi: 10.24036/jtein.v4i1.393.

Y. Hatur Puspita and A. Sabri, “Transfer Learning Model Pralatih MobileNetV2 dan DenseNet121 untuk Klasifikasi Tanaman Rempah,” Jurnal Ilmiah Komputasi, vol. 23, no. 1, pp. 67–74, Mar. 2024, doi: 10.32409/jikstik.23.1.3502.

Y. O. L. Rema, “Deteksi Plat Nomor Kendaraan Bermotor dengan Segmentasi Gambar,” Jurnal Saintek Lahan Kering, vol. 2, no. 1, pp. 20–23, Jun. 2019, doi: 10.32938/slk.v2i1.794.

N. B. Pamungkas and A. Suhendar, “Penerapan Metode Convolutional Neural Network pada Sistem Klasifikasi Penyakit Tanaman Apel berdasarkan Citra Daun,” Edumatic: Jurnal Pendidikan Informatika, vol. 8, no. 2, pp. 675–684, Dec. 2024, doi: 10.29408/edumatic.v8i2.27958.

M. R. R. Allaam and A. T. Wibowo, “Klasifikasi Genus Tanaman Anggrek Menggunakan Metode Convolutional Neural Network (CNN),” e-Proceeding of Engineering, vol. 8, no. 2, pp. 3147–3179, Apr. 2021.

W. Nengsih, J. N. S. Juni Nurma Sari, C. Angresta, and H. F. Dwinas, “DeepSun: Klasifikasi Fase Cahaya Matahari Berdasarkan Warna Menggunakan CNN,” Jurnal Komputer Terapan, vol. 9, no. 2, pp. 182–190, Dec. 2023, doi: 10.35143/jkt.v9i2.6182.

U. Ungkawa and G. Al Hakim, “Klasifikasi Warna pada Kematangan Buah Kopi Kuning menggunakan Metode CNN Inception V3,” ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika, vol. 11, no. 3, p. 731, Jul. 2023, doi: 10.26760/elkomika.v11i3.731.

A. Nada Nafisa, E. Nia Devina Br Purba, F. Aulia Alfarisi Harahap, and N. Adawiyah Putri, “Implementasi Algoritma Convolutional Neural Network Arsitektur Model MobileNetV2 dalam Klasifikasi Penyakit Tumor Otak Glioma, Pituitary dan Meningioma,” Jurnal Teknologi Informasi, Komputer dan Aplikasinya (JTIKA), vol. 5, no. 1, pp. 53–61, Mar. 2023, [Online]. Available: http://jtika.if.unram.ac.id/index.php/JTIKA/

A. Z. Hibatullah, M. F. Rahman, and A. P. Sari, “Pemanfaatan Metode Convolutional Neural Network (CNN) Dengan Arsitektur MobileNetV2 Untuk Penilaian Kelayakan Rumah,” ALINIER JURNAL, vol. 5, no. 2, pp. 129–139, Nov. 2024, [Online]. Available: www.elektro.itn.ac.id

S. M. Hawibowo and I. Muhimmah, “Aplikasi Pendeteksi Tingkat Kematangan Pepaya menggunakan Metode Convolutional Neural Network (CNN) Berbasis Android,” 2024.