Generating High-quality Superpixels in Textured Images

dc.contributor.authorZhang, Zheen_US
dc.contributor.authorXu, Panpanen_US
dc.contributor.authorChang, Jianen_US
dc.contributor.authorWang, Wenchengen_US
dc.contributor.authorZhao, Chongen_US
dc.contributor.authorZhang, Jian Junen_US
dc.contributor.editorEisemann, Elmar and Jacobson, Alec and Zhang, Fang-Lueen_US
dc.date.accessioned2020-10-29T18:51:01Z
dc.date.available2020-10-29T18:51:01Z
dc.date.issued2020
dc.description.abstractSuperpixel 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.en_US
dc.description.number7
dc.description.sectionheadersVision Meets Graphics
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume39
dc.identifier.doi10.1111/cgf.14156
dc.identifier.issn1467-8659
dc.identifier.pages421-431
dc.identifier.urihttps://doi.org/10.1111/cgf.14156
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf14156
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectComputing methodologies
dc.subjectImage processing
dc.subjectTexturing
dc.subjectImage segmentation
dc.titleGenerating High-quality Superpixels in Textured Imagesen_US
Files
Collections