SEGMENTASI WARNA PADA GAMBAR MENGGUNAKAN K-MEANS CLUSTERING UNTUK PENGOLAHAN CITRA DIGITAL

Agil Abiansyah; Bambang Irawan; Ahmad Faqih; Ade Rizki Rinaldi

Authors

Agil Abiansyah STMIK IKMI Cirebon, Indonesia
Bambang Irawan STMIK IKMI Cirebon, Indonesia
Ahmad Faqih STMIK IKMI Cirebon, Indonesia
Ade Rizki Rinaldi STMIK IKMI Cirebon, Indonesia

Keywords:

Segmentasi Warna, K-Means Clustering, Pengolahan Citra Digital, Ruang Warna, Morfologi Closing, spektrum warna

Abstract

Segmentasi citra merupakan tahapan fundamental dalam pengolahan citra digital untuk memisahkan objek dari latar belakang, namun tantangan utama terletak pada sensitivitas algoritma K-Means Clustering terhadap inisialisasi, variasi pencahayaan, dan pemilihan ruang warna. Penelitian ini bertujuan untuk menganalisis komparasi efektivitas algoritma K-Means dalam melakukan segmentasi warna pada tiga ruang warna berbeda: RGB, HSV, dan CIE LAB, metode penelitian menggunakan desain eksperimental terhadap 4 citra uji dengan parameter klaster statis (k=5), yang melibatkan tahapan pra-pemrosesan, implementasi klasterisasi, dan pasca-pemrosesan morfologi Closing. Evaluasi kinerja dilakukan secara kuantitatif menggunakan metrik Davies-Bouldin Index (DBI), Silhouette Score, Mean Squared Error (MSE), dan Structural Similarity Index (SSIM). Hasil penelitian menunjukkan adanya trade-off yang jelas antara validitas klaster dan fidelitas citra. Ruang warna HSV terbukti unggul dalam membentuk kepadatan struktur klaster dengan nilai rata-rata Silhouette Score tertinggi (0,718). Sebaliknya, ruang warna RGB unggul mutlak dalam mempertahankan kemiripan warna asli citra serta stabilitas separasi wilayah dengan nilai rata-rata MSE terendah (235,57), SSIM tertinggi (0,792), dan DBI terendah (0,703). Sementara itu, ruang warna CIE LAB menunjukkan performa yang moderat dalam menjaga struktur visual objek. Penelitian ini menyimpulkan bahwa HSV direkomendasikan untuk aplikasi yang mengutamakan kekompakan partisi wilayah warna, sedangkan RGB lebih sesuai untuk akurasi rekonstruksi visual.

References

Y. Yu et al., “Techniques and challenges of image segmentation: A review,” Electronics, vol. 12, no. 5, p. 1199, 2023, doi: 10.3390/electronics12051199.

X. Chai et al., “Image segmentation based on the optimized K-Means algorithm with the improved hybrid Grey Wolf optimization: Application in ore particle size detection,” Sensors, vol. 25, no. 9, p. 2785, 2025, doi: 10.3390/s25092785.

H. Armağan, “Colour based segmentation with K-Means clustering algorithm and numerical analysis of the effect of colour spaces on image quantities,” El-Cezeri Journal of Science and Engineering, vol. 9, no. 4, pp. 1506–1517, 2022, doi: 10.31202/ecjse.1141148.

Y. Yu et al., “Techniques and challenges of image segmentation: A review,” Electronics, vol. 12, no. 5, p. 1199, 2023, doi: 10.3390/electronics12051199.

M. Henke, K. Neumann, T. Altmann, and E. Gladilin, “Semi-Automated Ground Truth Segmentation and Phenotyping of Plant Structures Using k-Means Clustering of Eigen-Colors (kmSeg),” Agriculture, vol. 11, no. 11, p. 1098, 2021, doi: 10.3390/agriculture11111098.

H. M. Yuan, A. Khalid, Z. Sallow, and F. M. Mustafa, “Exploring Image Representation and Colour Spaces in Computer Vision: A Comprehensive Review,” Indonesian Journal of Computer Science, vol. 13, no. 3, p. 3998, 2024, doi: 10.33022/ijcs.v13i3.3998.

H. Zhan, Y. Shou, L. Wen, F. Xu, and L. Zhang, “Colour detection of printing based on improved superpixel segmentation algorithm,” Scientific Reports, vol. 14, p. 23449, 2024, doi: 10.1038/s41598-024-74179-w.

A. Nayyer, A. Kumar, A. Rajput, S. Patil, and S. Wagle, “Colour-Driven Object Recognition: A Novel Approach Combining Colour Detection and Machine Learning Techniques,” EAI Endorsed Transactions on Internet of Things, vol. 10, p. 5495, 2024, doi: 10.4108/eai.ios.2024-5495.

S. Jardim, J. António, and C. Mora, “Graphical Image Region Extraction with K-Means Clustering and Watershed,” J. Imaging, vol. 8, no. 6, p. 163, 2022, doi: 10.3390/jimaging8060163.

P. Mazurek and D. Bak, “Video Sequence Segmentation Based on K-Means in Air-Gap Data Transmission for a Cluttered Environment,” Sensors, vol. 23, no. 2, p. 665, 2023, doi: 10.3390/s23020665.

N. Liao, B. Guo, C. Li, H. Liu, and C. Zhang, “BACA: Superpixel segmentation with boundary awareness and content adaptation,” Remote Sensing, vol. 14, no. 18, p. 4572, 2022, doi: 10.3390/rs14184572.

S. Han and J. Lee, “Parallelized Inter-Image k-Means Clustering Algorithm for Unsupervised Classification of Series of Satellite Images,” Remote Sensing, vol. 16, no. 1, p. 102, 2024, doi: 10.3390/rs16010102.

L. Chai, Y. Xu, and T. Zhang, “Adaptive K-Means optimization with dynamic stopping criteria for efficient color image segmentation,” Pattern Recognition Letters, vol. 180, pp. 1–12, 2025, doi: 10.1016/j.patrec.2024.11.005.