Structure‐Texture Decomposition of Images with Interval Gradient. (31st May 2016)

• Record Type: Journal Article
• Authors: Lee, Hyunjoon; Jeon, Junho; Kim, Junho; Lee, Seungyong
• Is Part Of: Computer graphics forum. Volume 36:Number 6(2017)
• Page Start: 262
• Page End: 274
• Publication Date: 2016-05-31
• Subjects: texture filtering -- interval gradient -- gradient‐domain image decomposition -- 1D filtering -- I.4.3 [Image Processing and Computer Vision]: Enhancement–Smoothing; I.3.7 [Computer Graphics]: Three‐Dimensional Graphics and Realism–Colour, shading, shadowing, and texture; Computer graphics -- Periodicals; 006.605
• DOI: 10.1111/cgf.12875
• Languages: English
• ISSNs: 0167-7055

Abstract

Abstract : This paper presents a novel filtering‐based method for decomposing an image into structures and textures. Unlike previous filtering algorithms, our method adaptively smooths image gradients to filter out textures from images. A new gradient operator, the interval gradient, is proposed for adaptive gradient smoothing. Using interval gradients, textures can be distinguished from structure edges and smoothly varying shadings. We also propose an effective gradient‐guided algorithm to produce high‐quality image filtering results from filtered gradients. Our method avoids gradient reversal in the filtering results and preserves sharp features better than existing filtering approaches, while retaining simplicity and highly parallel implementation. Abstract: This paper presents a novel filtering‐based method for decomposing an image into structures and textures. Unlike previous filtering algorithms, our method adaptively smooths image gradients to filter out textures from images. A new gradient operator, the interval gradient, is proposed for adaptive gradient smoothing. Using interval gradients, textures can be distinguished from structure edges and smoothly varying shadings. We also propose an effective gradient‐guided algorithm to produce high‐quality image filtering results from filtered gradients. Our method avoids gradient reversal in the filtering results and preserves sharp features better than existing filtering approaches, while retaining simplicity and highly parallel implementation. The proposed method can be utilized for various applications that require accurate structure‐texture decomposition of images.