eprintid: 6379
rev_number: 2
eprint_status: archive
userid: 1
dir: disk0/00/00/63/79
datestamp: 2023-11-09 16:18:09
lastmod: 2023-11-09 16:18:09
status_changed: 2023-11-09 16:05:52
type: article
metadata_visibility: show
creators_name: Zarif, S.
creators_name: Faye, I.
creators_name: Rohaya, D.
title: Image completion based on statistical texture analysis
ispublished: pub
keywords: Computer graphics; Image processing; Repair; Textures; Video signal processing, Gray level co-occurrence matrix; Image and video processing; Image completion; Image Inpainting; State-of-the-art methods; Texture analysis; Texture synthesis; Visual artifacts, Image texture
note: cited By 6
abstract: Image completion is an active subject in image and video processing, which deals with the recovery of original data. Most previous image completion techniques required extensive searches to find the most suited texture to repair the damaged area. In addition, visual artifacts tend to appear when the damaged area is large. We present a fast texture synthesis and image completion method that does not require an extensive search process. The proposed method is based on gray-level co-occurrence matrix and weighted two-side hole filling. The method gives high quality results compared with state-of-the-art methods. It reduces the time from hundreds of seconds to a few milliseconds and is able to repair large damaged areas without artifacts or shadows. © 2015 SPIE and IS&T.
date: 2015
publisher: SPIE
official_url: https://www.scopus.com/inward/record.uri?eid=2-s2.0-84924145145&doi=10.1117%2f1.JEI.24.1.013032&partnerID=40&md5=50e94a5a3fed2596257b3a40ef4ac540
id_number: 10.1117/1.JEI.24.1.013032
full_text_status: none
publication: Journal of Electronic Imaging
volume: 24
number: 1
refereed: TRUE
issn: 10179909
citation:   Zarif, S. and Faye, I. and Rohaya, D.  (2015) Image completion based on statistical texture analysis.  Journal of Electronic Imaging, 24 (1).   ISSN 10179909