Penerapan Metode Transformasi Wavelet Diskrit pada Image Inpainting

Fitriani, Kharisma Nur (2021) Penerapan Metode Transformasi Wavelet Diskrit pada Image Inpainting. Undergraduate thesis, Institut Teknologi Sepuluh Nopember.

Text 06111640000092_Undergraduated_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2023. Download (4MB) | Request a copy

Abstract

Pengisian bagian yang hilang dalam sebuah gambar dikenal sebagai Image Inpainting. Image inpainting adalah seni memodifikasi gambar atau video dalam bentuk yang tidak mudah dideteksi oleh pengamat biasa. Image inpainting telah diselidiki secara luas dalam aplikasi efek digital (yaitu penghilangan objek, pengeditan gambar, pengubahan ukuran gambar), restorasi gambar (misalnya penghapusan goresan atau teks dalam foto), pengkodean dan transmisi gambar (misalnya pemulihan blok yang hilang) dll. Transformasi Wavelet telah digunakan untuk berbagai hal masalah analisis gambar karena sifat multi-resolusi dan karakteristik decouplingnya yang baik. Keuntungan dari Transformasi Wavelet ini dimanfaatkan untuk inpainting gambar. Pada Tugas Akhir ini, penerapan metode Transformasi Wavelet Diskrit pada image inpainting dilakukan untuk mendapatkan informasi pada citra yang hilang. Proses image inpainting menggunakan Transformasi Wavelet Diskrit adalah proses dekomposisi citra, proses inpainting, dan proses rekonstruksi. Pada pengujian citra hasil inpainting, data citra dibagi 5 kategori. Berdasarkan hasil perhitungan PSNR, hasil terbaik didapat pada citra dengan ukuran target objek kecil dan background yang sederhana dengan nilai PSNR sebesar 43,5809 db.
======================================================================================================
ge Inpainting. Image inpainting is the art of modifying an image or video in a form that is not easily detectable by ordinary observers. Image inpainting has been extensively investigated in digital effects applications (i.e. object removal, image editing, image resizing), image restoration (e.g. removal of scratches or text in photos), image encoding and transmission (e.g. recovery of lost blocks) etc. Wavelet transforms have been used for various image analysis problems because of their multi-resolution properties and good decoupling characteristics. The advantage of this wavelet transform is utilized for inpainting images. In this final project, the application of the Discrete Wavelet Transform method on image inpainting is carried out to obtain information on the missing image. The image inpainting process using Discrete Wavelet Transform is decomposition process, inpainting process, and reconstruction process. In testing the inpainting image, the image data is divided into 5 categories. Based on the results of PSNR calculations, the best results are obtained in images with a small object target size and a simple background with a PSNR value was 43.5809 db.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Image Inpainting, Transformasi Wavelet Diskrit, Analisis Multiresolusi, Penghilangan Objek, Discrete Wavelet Transform, Multiresolution Analysis, Object Removal
Subjects:	Q Science > QA Mathematics > QA403.3 Wavelets (Mathematics) Q Science > QA Mathematics > QA76.6 Computer programming. Q Science > QA Mathematics > QA76.76.A63 Application program interfaces Q Science > QA Mathematics > QA76.9.U83 Graphical user interfaces. User interfaces (Computer systems)--Design. Q Science > QA Mathematics > QA9.58 Algorithms T Technology > TA Engineering (General). Civil engineering (General) > TA1637 Image processing--Digital techniques
Divisions:	Faculty of Science and Data Analytics (SCIENTICS) > Mathematics > 44201-(S1) Undergraduate Thesis
Depositing User:	Kharisma Nur Fitriani
Date Deposited:	07 Sep 2021 07:27
Last Modified:	07 Sep 2021 07:27
URI:	http://repository.its.ac.id/id/eprint/91710

Actions (login required)

View Item