Metode Penggabungan Citra (Image Stitching) Menggunakan Algoritma SIFT (Scale Invariant Feature Transform) dengan Variasi Daerah Overlapping

https://doi.org/10.22146/jfi.v25i1.63111

Widhi Mahardi Darma(1*), Riva Fauzia(2), Gede Bayu Suparta(3)

(1) Departemen Fisika, Fakultas Matematika dan Ilmu Pengetahuan Alam, Universitas Gadjah Mada
(2) Departemen Fisika, Fakultas Matematika dan Ilmu Pengetahuan Alam, Universitas Gadjah Mada
(3) Departemen Fisika, Fakultas Matematika dan Ilmu Pengetahuan Alam, Universitas Gadjah Mada
(*) Corresponding Author

Abstract


Radiografi digital biasanya dapat mencitrakan area obyek yang pendak untuk sekali ekposi. Citra yang mencakup area obyek yang lebih panjang diperlukan untuk mendiagnostik penyakit. Pada penelitian ini dikembangkan upaya untuk mendapatkan citra yang panjang dengan resolusi yang tinggi. Data yang digunakan pada penelitian ini adalah data citra radiografi digital simulasi. Citra simulasi yang digunakan berupa citra tubuh manusia. Data citra dipotong menjadi dua bagian dengan daerah overlapping yang variasi 100 piksel, 125 piksel dan 150 piksel. kedua citra tersebut disambung dengan algoritma SIFT (Scale Invariant Feature Transform) pada OpenCV di Python. Hasil penggabungan dibandingkan dengan citra asli berdasarkan profil image subtraction, histogram dan DIC (Digital Image Correlation). Hasil berdasarkan citra subtraction menunjukkan citra hasil penggabungan sama dengan citra asli pada daerah overlapping 150 piksel. hasil histogram menunjukkan daerah distribusi gray level berada pada nilai piksel 0 (hitam). Hasil analisis DIC menunjukkan nilai regresi 1,0 pada daerah overlapping 150 piksel.


Keywords


image stitching, subtraction, digital image correlation, histogram

Full Text:

PDF


References

  1. Samei E, Saunders RS, Lo JY, Dobbins III JT, Jesneck JL, Floyd CE, et al. Fundamental imaging characteristics of a slot-scan digital chest radiographic system. Medical physics. 2004;31(9):2687–2698.
  2. Yang F, He Y, Deng ZS, Yan A. Improvement of automated image stitching system for DR X-ray images. Computers in biology and medicine. 2016;71:108–114.
  3. Bassi S, Baldini S, Rebuffat C, Sarti R, Ferretti F. First test on three stitching methods with digital detectors used in radiography. Radiological physics and technology. 2013;6(1):187–196.
  4. Juan L, Gwun O. A comparison of sift, pca-sift and surf. International Journal of Image Processing (IJIP). 2009;3(4):143–152.
  5. Lowe DG. Object recognition from local scale-invariant features. In: Proceedings of the seventh IEEE international conference on computer vision. vol. 2. Ieee; 1999. p. 1150–1157.
  6. Lowe DG. Distinctive image features from scale-invariant keypoints. International journal of computer vision. 2004;60(2):91–110.
  7. Min Z, Jiguo Z, Xusheng XIE. Panorama stitching based on sift algorithm and levenberg-marquardt optimization. Physics Procedia. 2012;33:811–818.
  8. Mudassar AA, Butt S. Improved digital image correlation method. Optics and Lasers in Engineering. 2016;87:156–167.
  9. Solomon C, Breckon T. Fundamentals of Digital Image Processing: A practical approach with examples in Matlab. John Wiley & Sons; 2011.
  10. Perkasa TR. TA: Rancang Bangun Pendeteksi Gerak Menggunakan Metode Image Subtraction pada Single Board Computer (SBC). Institut Bisnis dan Informatika Stikom Surabaya; 2014.
  11. Pan B, Li K. A fast digital image correlation method for deformation measurement. Optics and Lasers in Engineering. 2011;49(7):841–847.
  12. Zhong F, Quan C. Efficient digital image correlation using gradient orientation. Optics & Laser Technology. 2018;106:417–426.
  13. Tang Z, Liang J, Xiao Z, Guo C. Large deformation measurement scheme for 3D digital image correlation method. Optics and Lasers in Engineering. 2012;50(2):122–130.



DOI: https://doi.org/10.22146/jfi.v25i1.63111

Article Metrics

Abstract views : 1671 | views : 1802

Refbacks

  • There are currently no refbacks.


Copyright (c) 2022 widhi mahardi darma

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

JFI Editorial Office

Departement of Physics, Faculty of Mathematics and Natural Sciences, Universitas Gadjah Mada

Sekip Utara PO BOX BLS 21, 55281, Yogyakarta, Indonesia

Email: jfi.mipa@ugm.ac.id

JFI is indexed by:


Creative Commons License
Jurnal Fisika Indonesia, its website and the articles published are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License

Social media icon made by Freepik from www.flaticon.com

Social media icon made by Freepik from www.flaticon.com

web
analytics View My Stats