SEGMENTASI MODEL FASET 3D BERDASARKAN FITUR INTRINSIK DAN EKSTRINSIK VERTEKS MENGGUNAKAN PENDEKATAN CONVEX HULL

Priadhana Edi Kresnha, Yana Adharani, Gandjar Kiswanto, Rahmat Widyanto

Abstract


Segmentasi adalah pembagian suatu bidang, baik bidang 2D maupun 3D, ke dalam beberapa segmen atau region. Pada penelitian ini, segmentasi dilakukan terhadap model faset 3D. Berbeda dengan gambar 2D, model 3D melibatkan posisi titik pada bidang 3D, arah vektor normal, dan kecederungan bentuk pada sculptured surface. Proses segmentasi dilakukan 2 kali. Segmentasi pertama dilakukan menggunakan thresholding, dimana setiap titik dibagi berdasarkan nilai dari feature yang dimiliki, setelah itu segmentasi dilanjutkan dengan Convex Hull untuk memperhalus hasil thresholding. Setelah dilakukan percobaan dengan beberapa model, hasil menunjukkan segmentasi dengan pendekatan Convex Hull mampu meningkatkan akurasi hingga 85%, dan untuk model tertentu akurasi mencapai 100%. Hasil tersebut bisa menjadi pertimbangan penggunaan Convex Hull sebagai salah satu metode segmentasi unggulan untuk bidang 3D.

Full Text:

PDF

References


Pradeep, S., Malliga, L. Content Based Image Retrieval and Segmentation of Medical Image Database with Fuzzy Values. International Conference on Information Communication and Embedded Systems (ICICES), 27-28 Feb. 2014, pp. 1-7

Karatzas, D., Rusinol, M., Antens, C., Ferrer, M. Segmentation robust to the vignette effect for machine vision systems. 19th International Conference on Pattern Recognition 8-11 Dec. 2008, pp. 1-4

Chitsaz, M., Seng, W., C. Medical Image Segmentation by Using Reinforcement Learning Agent. International Conference on Digital Image Processing. 7-9 March 2009, pp. 216-219

Gong, J., Jiang, Y., Xiong, G., Guan, C., Tao, G., Chen, H. The Recognition and Tracking of Traffic Lights Based on Color Segmentation and CAMSHIFT for Intelligent Vehicles. Intelligent Vehicles Symposium (IV). 21-24 June 2010, pp. 431-435

Mohammedsayeemuddin, S., Pithadia, P., V., Vandra, D. A Simple and Novel Fingerprint Image Segmentation Algorithm. International Conference on Issues and Challenges in Intelligent Computing Techniques (ICICT). 7-8 Feb. 2014, pp. 756-759

Cuevas, C., Blanco D., C., R., Garcia, N., Jaureguizar, F. Segmentation-Tracking Feedback Approach for High-Performance Video Surveillance Applications. IEEE Southwest Symposium on Image Analysis & Interpretation (SSIAI). 23-25 May 2010, pp. 41-44

Junwei, L., Shaokai, L. A Novel Image Segmentation Technology in Intelligent Traffic Light Control Systems. 20-22 Nov. 2013, pp. 26-29

Surazhky, T., Magid, E., Soldea, O., Elber, G., Rivlin, E. A Comparison of Gaussian and Mean Curvatures Estimation Methods on Triangular Meshes. IEEE International Conference on Robotics and Automation (Vol. 1). 14-19 Sept. 2003, pp. 1021-1026

Meek., D., S., Walton, D., J. On surface normal and Gaussian curvature approximations given data sampled from a smooth surface. Journal of Computer Aided Geometric Design Archive. 2000; Vol. 17(Issue 6): pp.521-543

Kresnha, P., E., Kiswanto, G., Widyanto, R. Segmentasi 3D Berbasis Model Faset Menggunakan Metode Region Growing Termodifikasi. Seminar Nasional Teknologi. 12 Nov 2014, pp 123-132

Berg, M., Cheong, O., Kreveld, M., Overmars, M. Computational Geometry, Algorithm and Applications. Berlin : Springer. 2008




DOI: https://doi.org/10.22219/sentra.v0i1.2093

Refbacks

  • There are currently no refbacks.


Seketariat

Fakultas Teknik

Universitas Muhammadiyah Malang Kampus III

Jl. Raya Tlogomas 246 Malang, 65144