Automatic Image Interpolation Using Homography. (20th May 2010)

• Record Type: Journal Article
• Authors: Wu Wu, Yi-Leh Yi-Leh; Tang Tang, Cheng-Yuan Cheng-Yuan; Hor Hor, Maw-Kae Maw-Kae; Liu Liu, Chi-Tsung Chi-Tsung
• Other Names: Marshall Marshall Stephen Stephen Academic Editor.
• Is Part Of: EURASIP journal on advances in signal processing. Volume 2010(2010)
• Publication Date: 2010-05-20
• Subjects: Signal processing -- Periodicals; Traitement du signal; Signal processing; Periodicals; 621.3822
• DOI: 10.1155/2010/307546
• Languages: English
• ISSNs: 1687-6172

Abstract

Abstract : While taking photographs, we often face the problem that unwanted foreground objects (e.g., vehicles, signs, and pedestrians) occlude the main subject(s). We propose to apply image interpolation (also known as inpainting ) techniques to remove unwanted objects in the photographs and to automatically patch the vacancy after the unwanted objects are removed. When given only a single image, if the information loss after the unwanted objects in images being removed is too great, the patching results are usually unsatisfactory. The proposed inpainting techniques employ the homographic constraints in geometry to incorporate multiple images taken from different viewpoints. Our experiment results showed that the proposed techniques could effectively reduce process in searching for potential patches from multiple input images and decide the best patches for the missing regions.