Abstract | ||
---|---|---|
Superpixel segmentation targets at grouping pixels in an image into atomic regions whose boundaries align well with the natural object boundaries. This paper first proposes a new feature representation for superpixel segmentation that holistically embraces color, contour, texture, and spatial features. Then, we introduce a clustering-based discriminability measure to iteratively evaluate the impor... |
Year | DOI | Venue |
---|---|---|
2018 | 10.1109/TIP.2018.2810541 | IEEE Transactions on Image Processing |
Keywords | DocType | Volume |
Image color analysis,Image segmentation,Histograms,Shape,Feature extraction,Computational efficiency,Measurement | Journal | 27 |
Issue | ISSN | Citations |
6 | 1057-7149 | 2 |
PageRank | References | Authors |
0.37 | 14 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Xiaolin Xiao | 1 | 36 | 6.57 |
Zhou, Y. | 2 | 26 | 1.50 |
Yue-jiao Gong | 3 | 691 | 41.19 |