Generating High-quality Superpixels in Textured Images
Authors: Zhang, Z., Xu, P., Chang, J., Wang, W., Zhao, C. and Zhang, J.J.
Journal: Computer Graphics Forum
Volume: 39
Issue: 7
Pages: 421-431
eISSN: 1467-8659
ISSN: 0167-7055
DOI: 10.1111/cgf.14156
Abstract:Superpixel segmentation is important for promoting various image processing tasks. However, existing methods still have difficulties in generating high-quality superpixels in textured images, because they cannot separate textures from structures well. Though texture filtering can be adopted for smoothing textures before superpixel segmentation, the filtering would also smooth the object boundaries, and thus weaken the quality of generated superpixels. In this paper, we propose to use the adaptive scale box smoothing instead of the texture filtering to obtain more high-quality texture and boundary information. Based on this, we design a novel distance metric to measure the distance between different pixels, which considers boundary, color and Euclidean distance simultaneously. As a result, our method can achieve high-quality superpixel segmentation in textured images without texture filtering. The experimental results demonstrate the superiority of our method over existing methods, even the learning-based methods. Benefited from using boundaries to guide superpixel segmentation, our method can also suppress noise to generate high-quality superpixels in non-textured images.
https://eprints.bournemouth.ac.uk/34964/
Source: Scopus
Generating High-quality Superpixels in Textured Images
Authors: Zhang, Z., Xu, P., Chang, J., Wang, W., Zhao, C. and Zhang, J.J.
Journal: COMPUTER GRAPHICS FORUM
Volume: 39
Issue: 7
Pages: 421-431
eISSN: 1467-8659
ISSN: 0167-7055
DOI: 10.1111/cgf.14156
https://eprints.bournemouth.ac.uk/34964/
Source: Web of Science (Lite)
Generating High-quality Superpixels in Textured Images
Authors: Zhang, Z., Xu, P., Chang, J., Wang, W., Zhao, C. and Zhang, J.J.
Journal: Computer Graphics Forum
Volume: 39
Issue: 7
Pages: 421-431
ISSN: 0167-7055
Abstract:Superpixel segmentation is important for promoting various image processing tasks. However, existing methods still have difficulties in generating high-quality superpixels in textured images, because they cannot separate textures from structures well. Though texture filtering can be adopted for smoothing textures before superpixel segmentation, the filtering would also smooth the object boundaries, and thus weaken the quality of generated superpixels. In this paper, we propose to use the adaptive scale box smoothing instead of the texture filtering to obtain more high-quality texture and boundary information. Based on this, we design a novel distance metric to measure the distance between different pixels, which considers boundary, color and Euclidean distance simultaneously. As a result, our method can achieve high-quality superpixel segmentation in textured images without texture filtering. The experimental results demonstrate the superiority of our method over existing methods, even the learning-based methods. Benefited from using boundaries to guide superpixel segmentation, our method can also suppress noise to generate high-quality superpixels in non-textured images.
https://eprints.bournemouth.ac.uk/34964/
Source: BURO EPrints