Image completion via texture direction analysis. Issue 19 (11th November 2019)

• Record Type: Journal Article
• Authors: Chen, Qiaochuan; Li, Guangyao; Xie, Li; Xiao, Qingguo; Xiao, Mang
• Is Part Of: Journal of modern optics. Volume 66:Issue 19(2019)
• Page Start: 1880
• Page End: 1888
• Publication Date: 2019-11-11
• Subjects: Image completion -- image inpainting -- texture analysis -- direction map -- objective function; Optics -- Periodicals; 535
• DOI: 10.1080/09500340.2019.1682704
• Languages: English
• ISSNs: 0950-0340

Abstract

ABSTRACT: Image completion is an approach to repair a damaged region (a hole) in an image. In this study, a novel image completion algorithm is proposed using texture direction to guide the completion process. We first analyse and detect the dominant texture direction using a gray-level co-occurrence matrix (GLCM). Based on the detected direction, we then generate a direction map that serves as a soft constraint during the completion process. Further, we propose an objective function that can balance the global texture structure and local coherency in order to maintain the structure consistency. Experimental results show that the proposed method has potential performance in maintaining the structure continuity and texture smoothness.