L ₀ Gradient-Regularization and Scale Space Representation Model for Cartoon and Texture Decomposition

• Published in: IEEE transactions on image processing Vol. 33; pp. 4016 - 4028
• Main Authors: Pan, Huan, Wen, You-Wei, Huang, Ya
• Format: Journal Article
• Language: English
• Published: New York The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024
• Subjects: Decomposition; Effectiveness; Penalty function; Regularization; Representations; Texture
• ISSN: 1057-7149; 1941-0042
• DOI: 10.1109/TIP.2024.3403505

In this paper, we consider decomposing an image into its cartoon and texture components. Traditional methods, which mainly rely on the gradient amplitude of images to distinguish between these components, often show limitations in decomposing small-scale, high-contrast texture patterns and large-scale, low-contrast structural components. Specifically, these methods tend to decompose the former to the cartoon image and the latter to the texture image, neglecting the scale features inherent in both components. To overcome these challenges, we introduce a new variational model which incorporates an [Formula Omitted]-based total variation norm for the cartoon component and an [Formula Omitted] norm for the scale space representation of the texture component. We show that the texture component has a small [Formula Omitted] norm in the scale space representation. We apply a quadratic penalty function to handle the non-separable [Formula Omitted] norm minimization problem. Numerical experiments are given to illustrate the efficiency and effectiveness of our approach.