L 0梯度极小化耦合梯度保真的保结构图像平滑
| Autor: | Zhipeng Ding, Zhangye Wang, Jiazhou Chen, Shaoxiong Zhang, Qunsheng Peng |
|---|---|
| Rok vydání: | 2014 |
| Předmět: |
Morphological gradient
General Computer Science business.industry ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Image processing computer.file_format JPEG Structure tensor Edge detection Computer graphics Piecewise Computer vision Artificial intelligence business Engineering (miscellaneous) computer Smoothing Mathematics |
| Zdroj: | SCIENTIA SINICA Informationis. 44:1370-1384 |
| ISSN: | 1674-7267 |
| DOI: | 10.1360/n112014-00202 |
| Popis: | Image smoothing is a fundamental tool in computer graphics and image processing, whose major challenge is to smooth the input image while preserving its salient structure features. Recently, a piecewise smooth approach called L 0 gradient minimization has been proposed for image smoothing. It employs gradient sparsity to achieve locally identical effect, which excels existing methods, making the visual performance more satisfying. However, methods based on L 0 gradient minimization can easily cause staircase effect and lose part of structure. In this paper, we make the best of L 0 gradient minimization and gradient fidelity term to present a new smoothing method. Our method can maintain the main structure of the image and restrain the staircase effect to make the gradient smoother. The essential structure in similar RGB values is preserved as well. Experimental results illustrate that our method applies widely, and particularly beneficial to image composition, edge detection and clip-art JPEG artifact removal, etc. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|