Small Object Segmentation Based on Visual Saliency in Natural Images


Huynh Trung Manh, Gueesang Lee, Journal of Information Processing Systems
Vol. 9, No. 4, pp. 592-601, Aug. 2013
10.3745/JIPS.2013.9.4.592
Keywords: Gaussian Mixture Model (GMM), Visual Saliency, Segmentation, Object Detection.
Fulltext:

Abstract

Object segmentation is a challenging task in image processing and computer vision. In this paper, we present a visual attention based segmentation method to segment small sized interesting objects in natural images. Different from the traditional methods, we first search the region of interest by using our novel saliency-based method, which is mainly based on band-pass filtering, to obtain the appropriate frequency. Secondly, we applied the Gaussian Mixture Model (GMM) to locate the object region. By incorporating the visual attention analysis into object segmentation, our proposed approach is able to narrow the search region for object segmentation, so that the accuracy is increased and the computational complexity is reduced. The experimental results indicate that our proposed approach is efficient for object segmentation in natural images, especially for small objects. Our proposed method significantly outperforms traditional GMM based segmentation.


Statistics
Show / Hide Statistics

Statistics (Cumulative Counts from November 1st, 2017)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.




Cite this article
[APA Style]
Huynh Trung Manh and Gueesang Lee (2013). Small Object Segmentation Based on Visual Saliency in Natural Images. Journal of Information Processing Systems, 9(4), 592-601. DOI: 10.3745/JIPS.2013.9.4.592.

[IEEE Style]
H. T. Manh and G. Lee, "Small Object Segmentation Based on Visual Saliency in Natural Images," Journal of Information Processing Systems, vol. 9, no. 4, pp. 592-601, 2013. DOI: 10.3745/JIPS.2013.9.4.592.

[ACM Style]
Huynh Trung Manh and Gueesang Lee. 2013. Small Object Segmentation Based on Visual Saliency in Natural Images. Journal of Information Processing Systems, 9, 4, (2013), 592-601. DOI: 10.3745/JIPS.2013.9.4.592.