skip to main content
10.1145/3458380.3458382acmotherconferencesArticle/Chapter ViewAbstractPublication PagesicdspConference Proceedingsconference-collections
research-article

Region Quality Based Scale-aware Selection for Hierarchical Image Segmentation

Published: 23 September 2021 Publication History

Abstract

In this paper, we propose a scale selection method for hierarchical image segmentation task, which is based on the quality of regions. Firstly, the tree-like representation of hierarchical segmentation result is used to establish the region level relationship. Then the region quality is calculated based on defined region features and a graphical model is constructed to obtain the optimal scale labels for each of the lowest level regions. Lastly, the final segmentation is achieved by combining the corresponding regions from the optimal hierarchy. The experimental results show that the proposed method outperforms the traditional thresholding method for scale selection, and can improve the local and global segmentation quality. As a post-processing method, it can largely improve the output quality of the hierarchical segmentation in vision tasks.

References

[1]
Duda, R. O., & Hart, P. E. 2006. Pattern classification. John Wiley & Sons.
[2]
Vincent, L., & Soille, P. 1991. Watersheds in digital spaces: an efficient algorithm based on immersion simulations. IEEE Transactions on Pattern Analysis & Machine Intelligence, (6), 583-598.
[3]
Panagiotakis, C., Grinias, I., & Tziritas, G. 2011. Natural image segmentation based on tree equipartition, bayesian flooding and region merging. IEEE Transactions on Image Processing, 20(8), 2276-2287.
[4]
Sharon, E., Galun, M., Sharon, D., Basri, R., & Brandt, A. 2006. Hierarchy and adaptivity in segmenting visual scenes. Nature, 442(7104), 810-813.
[5]
Arbelaez, P., Maire, M., Fowlkes, C., & Malik, J. 2010. Contour detection and hierarchical image segmentation. IEEE transactions on pattern analysis and machine intelligence, 33(5), 898-916.
[6]
Syu, J. H., Wang, S. J., & Wang, L. C. 2017. Hierarchical image segmentation based on iterative contraction and merging. IEEE Transactions on Image Processing, 26(5), 2246-2260.
[7]
Chen, Y., Dai, D., Pont-Tuset, J., & Van Gool, L. 2016. Scale-aware alignment of hierarchical image segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition ,pp. 364-372.
[8]
Wang, X. F., Min, H., & Zhang, Y. G. 2015. Multi-scale local region based level set method for image segmentation in the presence of intensity inhomogeneity. Neurocomputing, 151, 1086-1098.
[9]
Seyedhosseini, M., & Tasdizen, T. 2015. Semantic image segmentation with contextual hierarchical models. IEEE transactions on pattern analysis and machine intelligence, 38(5), 951-964.
[10]
Munoz, D., Bagnell, J. A., & Hebert, M. 2010. Stacked hierarchical labeling. In European Conference on Computer Vision ,pp. 57-70.
[11]
Bertasius, G., Shi, J., & Torresani, L. 2015. Deepedge: A multi-scale bifurcated deep network for top-down contour detection. In Proceedings of the IEEE conference on computer vision and pattern recognition ,pp. 4380-4389.
[12]
Shen, W., Wang, X., Wang, Y., Bai, X., & Zhang, Z. 2015. Deepcontour: A deep convolutional feature learned by positive-sharing loss for contour detection. In Proceedings of the IEEE conference on computer vision and pattern recognition ,pp. 3982-3991.
[13]
Xie, S., & Tu, Z. 2015. Holistically-nested edge detection. In Proceedings of the IEEE international conference on computer vision ,pp. 1395-1403.
[14]
Maninis, K. K., Pont-Tuset, J., Arbeláez, P., & Van Gool, L. 2016. Convolutional oriented boundaries. In European Conference on Computer Vision ,pp. 580-596.
[15]
Everingham, M., Van Gool, L., Williams, C. K., Winn, J., & Zisserman, A. 2010. The pascal visual object classes (voc) challenge. International journal of computer vision, 88(2), 303-338.
[16]
Hariharan, B., Arbeláez, P., Bourdev, L., Maji, S., & Malik, J. 2011. Semantic contours from inverse detectors. In 2011 International Conference on Computer Vision ,pp. 991-998.
[17]
Pont-Tuset, J., Arbelaez, P., Barron, J. T., Marques, F., & Malik, J. 2016. Multiscale combinatorial grouping for image segmentation and object proposal generation. IEEE transactions on pattern analysis and machine intelligence, 39(1), 128-140.
[18]
Isola, P., Zoran, D., Krishnan, D., & Adelson, E. H. 2014. Crisp boundary detection using pointwise mutual information. In European Conference on Computer Vision ,pp. 799-814.
[19]
Pont-Tuset, J., & Marques, F. 2015. Supervised evaluation of image segmentation and object proposal techniques. IEEE transactions on pattern analysis and machine intelligence, 38(7), 1465-1478.
[20]
Shi, J., & Malik, J. 2000. Normalized cuts and image segmentation. IEEE Transactions on pattern analysis and machine intelligence, 22(8), 888-905.
[21]
Comaniciu, D., & Meer, P. 2002. Mean shift: A robust approach toward feature space analysis. IEEE Transactions on pattern analysis and machine intelligence, 24(5), 603-619.
[22]
Felzenszwalb, P. F., & Huttenlocher, D. P. 2004. Efficient graph-based image segmentation. International journal of computer vision, 59(2), 167-181.
[23]
Ren, Z., & Shakhnarovich, G. 2013. Image segmentation by cascaded region agglomeration. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition ,pp. 2011-2018.
[24]
Zhao, Q. 2015. Segmenting natural images with the least effort as humans. In BMVC ,pp. 110-1.
[25]
Boykov, Y., Veksler, O., & Zabih, R. 2001. Fast approximate energy minimization via graph cuts. IEEE Transactions on pattern analysis and machine intelligence, 23(11), 1222-1239.
[26]
Cai, Q., Liu, H., Zhou, S., Sun, J., & Li, J. 2018. An adaptive-scale active contour model for inhomogeneous image segmentation and bias field estimation. Pattern Recognition, 82, 79-93.
[27]
Peng, B., Al-Huda, Z., Xie, Z., & Wu, X. 2020. Multi-scale region composition of hierarchical image segmentation. Multimedia Tools and Applications, 79(43), 32833-32855.
[28]
 Khan W., 2013. Image Segmentation Techniques: A Survey, Journal of Image and Graphics, 1(4), 166-170.
[29]
Richard N, Fernandez-Maloigne C., Bonanomi C., & Rizzi A. 2013, Fuzzy Color Image Segmentation using Watershed Transform. Journal of Image and Graphics, 1(3): 157-160

Index Terms

  1. Region Quality Based Scale-aware Selection for Hierarchical Image Segmentation
          Index terms have been assigned to the content through auto-classification.

          Recommendations

          Comments

          Information & Contributors

          Information

          Published In

          cover image ACM Other conferences
          ICDSP '21: Proceedings of the 2021 5th International Conference on Digital Signal Processing
          February 2021
          336 pages
          ISBN:9781450389365
          DOI:10.1145/3458380
          Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

          Publisher

          Association for Computing Machinery

          New York, NY, United States

          Publication History

          Published: 23 September 2021

          Permissions

          Request permissions for this article.

          Check for updates

          Author Tags

          1. graphical model
          2. hierarchical image segmentation
          3. scale selection
          4. segmentation quality

          Qualifiers

          • Research-article
          • Research
          • Refereed limited

          Funding Sources

          Conference

          ICDSP 2021

          Contributors

          Other Metrics

          Bibliometrics & Citations

          Bibliometrics

          Article Metrics

          • 0
            Total Citations
          • 25
            Total Downloads
          • Downloads (Last 12 months)1
          • Downloads (Last 6 weeks)0
          Reflects downloads up to 16 Feb 2025

          Other Metrics

          Citations

          View Options

          Login options

          View options

          PDF

          View or Download as a PDF file.

          PDF

          eReader

          View online with eReader.

          eReader

          HTML Format

          View this article in HTML Format.

          HTML Format

          Figures

          Tables

          Media

          Share

          Share

          Share this Publication link

          Share on social media