An experimental comparison of superpixels detection methods for contour detection
- 50 Downloads
Recently, many superpixels detection methods have been proposed and used in various applications. We are interested in which method is more suitable for the application of contour detection. In this paper, superpixels are evaluated on BSDS500 dataset in two different aspects. On the one hand, contours are directly provided by the boundaries of superpixels and experiments show that better results could be achieved by the superpixels with irregular shapes than those with regular shapes and similar sizes. On the other hand, contours are further detected from those candidate positions which are confirmed by the boundaries of superpixels through the operation of dilation. In this situation, experiments show that competitive results could also be achieved by some superpixels with regular shapes and similar sizes. Besides, we propose a superpixels detection method called watershed-based graph (WG), by which superpixels with irregular shapes could be produced. Firstly, a graph is constructed from an over-segmented map which is achieved through a watershed algorithm. Then, to get the desired superpixels, the graph is segmented by merging neighbor segments in an order of decreasing similarity. Experiments show that higher efficiency could be achieved by WG with a moderate worse contour quality than its original graph-based method.
KeywordsSuperpixels Region merging Contour detection Image segmentation
This work is supported by the Science Fund for Creative Research Groups of National Natural Science Foundation of China (Grant No. 51521064) and by the innovation fund of Shanghai Academy of Spaceflight Technology (Grant No. SAST2015086).
- 4.Ren, Z., Shakhnarovich, G.: Image segmentation by cascaded region agglomeration. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2011–2018 (2013)Google Scholar
- 15.Li, Z., Chen, J.: Superpixel segmentation using linear spectral clustering. In: Computer Vision and Pattern Recognition (2015)Google Scholar
- 20.Moore, A.P., Prince, S.J.D., Warrell, J., Mohammed, U., Jones, G.: Superpixel lattices, pp. 1–8 (2008)Google Scholar
- 21.Moore, A.P., Prince, S.J.D., Warrell, J.: Lattice cut—constructing superpixels using layer constraints. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117–2124 (2010)Google Scholar
- 22.Veksler, O., Boykov, Y., Mehrani, P.: Superpixels and supervoxels in an energy optimization framework. In: Computer Vision—ECCV 2010—European Conference on Computer Vision, Heraklion, Crete, Greece, September 5–11, 2010, Proceedings, pp. 211–224 (2010)Google Scholar
- 23.Zhang, Y., Hartley, R., Mashford, J., Burn, S.: Superpixels via pseudo-boolean optimization. In: International Conference on Computer Vision, pp. 1387–1394 (2011)Google Scholar
- 24.Liu, M.Y., Tuzel, O., Ramalingam, S., Chellappa, R.: Entropy rate superpixel segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2097–2104 (2011)Google Scholar
- 27.Neubert, P., Protzel, P.: Compact watershed and preemptive slic: On improving trade-offs of superpixel segmentation algorithms. In: International Conference on Pattern Recognition, pp. 996–1001 (2014)Google Scholar
- 34.Deng, Y., Manjunath, B.S., Shin, H.: Color image segmentation. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2. IEEE (1999)Google Scholar
- 37.Martin, D., Fowlkes, C., Tal, D., Malik, J.: A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In: Eighth IEEE International Conference on Computer Vision, 2001. ICCV 2001. Proceedings, vol. 2, pp. 416–423 (2001)Google Scholar