Occlusion removal of faç ade texture with constrained image inpainting

Ping Shen Chen, Fuan Tsai

研究成果: 書貢獻/報告類型會議論文篇章同行評審

3 引文 斯高帕斯(Scopus)

摘要

Image inpainting is an effective approach to remove unwanted objects and fill holes in digital images. However, directly applying existing general-purpose digital inpainting algorithms to the correction of façade texture images with occlusions may not produce satisfactory results. This research developed a constrained image inpainting algorithm specifically designed for the correction of occluded façade texture images. The objective is to remove selected occlusions of façade texture images and restore the damaged texture blocks with reasonable textures identified with the developed constrained inpainting algorithm. In comparison with existing inpainting approaches, it can restore the occluded texture blocks more reasonably based on façade structures such as pillars, girders and window frames. Important inpainting parameters, such as window size and search area of inpainting were also investigated to achieve better inpainting results. The developed constrained inpainting algorithms were applied to real building façade images to validate their performance and to identify appropriate inpainting parameters for correcting façade texture occlusions.

原文???core.languages.en_GB???
主出版物標題30th Asian Conference on Remote Sensing 2009, ACRS 2009
頁面1195-1200
頁數6
出版狀態已出版 - 2009
事件30th Asian Conference on Remote Sensing 2009, ACRS 2009 - Beijing, China
持續時間: 18 10月 200923 10月 2009

出版系列

名字30th Asian Conference on Remote Sensing 2009, ACRS 2009
2

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???30th Asian Conference on Remote Sensing 2009, ACRS 2009
國家/地區China
城市Beijing
期間18/10/0923/10/09

指紋

深入研究「Occlusion removal of faç ade texture with constrained image inpainting」主題。共同形成了獨特的指紋。

引用此