Announcement
Starting on July 4, 2018 the Indonesian Publication Index (IPI) has been acquired by the Ministry of Research Technology and Higher Education (RISTEKDIKTI) called GARUDA Garba Rujukan Digital (http://garuda.ristekdikti.go.id)
For further information email to portalgaruda@gmail.com

Thank you
Logo IPI  
Journal > Jurnal Kursor > SUPERRESOLUTION USING PAPOULIS-GERCHBERG ALGORITHM BASED PHASE BASED IMAGE MATCHING

 

Full Text PDF (230 kb)
Jurnal Kursor
Vol 6, No 3 (2012)
SUPERRESOLUTION USING PAPOULIS-GERCHBERG ALGORITHM BASED PHASE BASED IMAGE MATCHING
Article Info   ABSTRACT
Published date:
22 Nov 2016
 
SUPERRESOLUTION USING PAPOULIS-GERCHBERG ALGORITHM BASEDPHASE BASED IMAGE MATCHINGaBudi Setiyono, bMochamad Hariadi, cMauridhi Hery PurnomoaMathematical Dept., Faculty of Mathematics and Natural ScienceSepuluh Nopember Institute of Technology, Surabaya 60111b,cElectrical Engineering Dept., Faculty of Industrial TechnologySepuluh Nopember Institute of Technology, Surabaya 60111E-Mail: amasbudisetiyono@gmail.comAbstrakCitra resolusi tinggi (High Resolution Image) akan memberikan informasi yang lebihdetail, sehingga analisis terhadap citra tersebut menjadi lebih akurat. Banyak bidangmemerlukan citra resolusi tinggi antara lain adalah medical, penginderaan satelite,citra dari teleskop serta pengenalan pola.Pada penelitian ini dilakukan proses untukmendapatkan citra resolusi tinggi, yang dikenal dengan superresolution. Sebagai citrareferensi, digunakan lebih dari satu citra, namun demikian, citra-citra tersebut beradapada scene yang sama. Dua tahap utama dalam superresolution adalah registrasi danrekonstruksi. Registrasi yang akurat diperlukan untuk mendapatkan hasil rekonstruksiyang baik. Phase-Based Image Matching (PBIM) digunakan untuk estimasi translasipada tahap registrasi. Hanya translasi sampai ketelitian sub pixel yang berkontribusidalam rekonstruksi. Untuk mendapatkan translasi sampai level sub pixel, dilakukanfitting disekitar puncak. Sedangkan untuk rekonstruksi ke dalam Grid Resolusi tinggidigunakan algoritma Papoulis-Gerchberg. Penulis melakukan kolaborasi antararegistrasi dengan PBIM dan rekonstruksi menggunakan algoritma Papoulis-Gerchberg. Uji coba dilakukan penulis dengan obyek serangkaian citra dengan banyaktekstur dan sedikit tekstur. Dari hasil uji coba, citra dengan banyak tekstur akanmenghasilkan Peak Signal to Noise Ratio (PSNR) rata-rata 21,62. Sedangkan untukcitra yang kurang mengandung tekstur 19,54.Kata kunci: Superresolution, Registrasi, Rekonstruksi, Phased Based ImageMatching.AbstractHigh Resolution Image provide more detail information, so that it obtain moreaccurate image analysis. Many areas require high resolution image, such as medical,sensing satellite, image of the telescope and pattern recognition. This research make aprocess to obtain high resolution images, known as superresolution. Thissuperresolution using a series of images in the same scene as the reference image.Two main stages in the super resolution are the registration and reconstruction. Anaccurate registration is required to obtain a great reconstruction results. Phase-BasedImage Matching (PBIM) will be used to estimate pixels translation at the registrationstage. Only sub-pixels translation which contribute to the reconstruction phase. Weused the function fitting around the peak point, to obtain sub pixel accurate shift.While reconstruct a high-resolution image use Papoulis-Gerchberg algorithm. Theauthor collaborate registration and reconstruction. Registration using PBIM andreconstruction using Papoulis-Gerchberg algorithm. Experiments have been donewith a series of images that contain much texture and less texture. The experimentalresults with images contain much texture produces an average Peak Signal to NoiseRatio (PSNR) 21.62. While image contain less texture produces PSNR 19.54.Keyword: Superresolution, Registration, Reconstruction, Phased Based ImageMatching.
Copyrights © 2016