Please use this identifier to cite or link to this item:
https://hdl.handle.net/10356/85383
Title: | Intrinsic manifold SLIC : a simple and efficient method for computing content-sensitive superpixels | Authors: | Liu, Yong-Jin Yu, Minjing Li, Bing-Jun He, Ying |
Keywords: | Superpixel Image Segmentation Engineering::Computer science and engineering |
Issue Date: | 2017 | Source: | Liu, Y.-J., Yu, M., Li, B.-J., & He, Y. (2018). Intrinsic manifold SLIC : a simple and efficient method for computing content-sensitive superpixels. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(3), 653-666. doi:10.1109/TPAMI.2017.2686857 | Series/Report no.: | IEEE Transactions on Pattern Analysis and Machine Intelligence | Abstract: | Superpixels are perceptually meaningful atomic regions that can effectively capture image features. Among various methods for computing uniform superpixels, simple linear iterative clustering (SLIC) is popular due to its simplicity and high performance. In this paper, we extend SLIC to compute content-sensitive superpixels, i.e., small superpixels in content-dense regions with high intensity or colour variation and large superpixels in content-sparse regions. Rather than using the conventional SLIC method that clusters pixels in R 5 , we map the input image Ito a 2-dimensional manifold M ⊂ R 5 , whose area elements are a good measure of the content density in I. We propose a simple method, called intrinsic manifold SLIC (IMSLIC), for computing a geodesic centroidal Voronoi tessellation (GCVT)-a uniform tessellation-on M, which induces the content-sensitive superpixels in I. In contrast to the existing algorithms, IMSLIC characterizes the content sensitivity by measuring areas of Voronoi cells on M. Using a simple and fast approximation to a closed-form solution, the method can compute the GCVT at a very low cost and guarantees that all Voronoi cells are simply connected. We thoroughly evaluate IMSLIC and compare it with eleven representative methods on the BSDS500 dataset and seven representative methods on the NYUV2 dataset. Computational results show that IMSLIC outperforms existing methods in terms of commonly used quality measures pertaining to superpixels such as compactness, adherence to boundaries, and achievable segmentation accuracy. We also evaluate IMSLIC and seven representative methods in an image contour closure application, and the results on two datasets, WHD and WSD, show that IMSLIC achieves the best foreground segmentation performance. | URI: | https://hdl.handle.net/10356/85383 http://hdl.handle.net/10220/49216 |
ISSN: | 0162-8828 | DOI: | 10.1109/TPAMI.2017.2686857 | Schools: | School of Computer Science and Engineering | Rights: | © 2017 IEEE. All rights reserved. | Fulltext Permission: | none | Fulltext Availability: | No Fulltext |
Appears in Collections: | SCSE Journal Articles |
SCOPUSTM
Citations
5
78
Updated on Mar 22, 2024
Web of ScienceTM
Citations
5
64
Updated on Oct 25, 2023
Page view(s)
416
Updated on Mar 28, 2024
Google ScholarTM
Check
Altmetric
Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.