Abstract
In this article, we present a fast-marching based algorithm for generating superpixel (FMS) partitions of images. The idea behind the algorithm is to draw an analogy between waves propagating in a heterogeneous medium and regions growing on an image at a rate depending on the local color and texture. The FMS algorithm is evaluated on the Berkeley Segmentation Dataset 500. It yields results in terms of boundary adherence that are slightly better than the ones obtained with similar approaches including the Simple Linear Iterative Clustering, the Eikonal-based region growing for efficient clustering and the Iterative Spanning Forest framework for superpixel segmentation algorithms. An interesting feature of the proposed algorithm is that it can take into account texture information to compute the superpixel partition. We illustrate the interest of adding texture information on a specific set of images obtained by recombining textures patches extracted from images representing stripes, originally constructed by Giraud et al. [20]. On this dataset, our approach works significantly better than color based superpixel algorithms.
References
[1] Radhakrishna Achanta, Appu Shaji, Kevin Smith, Aurelien Lucchi, Pascal Fua, and Sabine Süsstrunk. Slic superpixels compared to state-of-the-art superpixel methods. IEEE transactions on pattern analysis and machine intelligence, 34(11):2274–2282, 2012.10.1109/TPAMI.2012.120Search in Google Scholar PubMed
[2] Radhakrishna Achanta and Sabine Susstrunk. Superpixels and Polygons Using Simple Non-iterative Clustering. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 4895–4904, Honolulu, HI, July 2017. IEEE.10.1109/CVPR.2017.520Search in Google Scholar
[3] Pablo Arbelaez, Michael Maire, Charless Fowlkes, and Jitendra Malik. Contour detection and hierarchical image segmentation. IEEE Trans. Pattern Anal. Mach. Intell., 33(5):898–916, May 2011.10.1109/TPAMI.2010.161Search in Google Scholar PubMed
[4] Jihane Belhadj, Thomas Romary, Alexandrine Gesret, Mark Noble, and Bruno Figliuzzi. New parameterizations for bayesian seismic tomography. Inverse Problems, 34(6):065007, 2018.10.1088/1361-6420/aabce7Search in Google Scholar
[5] Serge Beucher and Fernand Meyer. The morphological approach to segmentation: the watershed transformation. Optical Engineering-New York-Marcel Dekker Incorporated-, 34:433–433, 1992.10.1201/9781482277234-12Search in Google Scholar
[6] Vincent Bortolussi, Bruno Figliuzzi, François Willot, Matthieu Faessel, and Michel Jeandin. Morphological modeling of cold spray coatings. Image Analysis & Stereology, 37(2):145–158, 2018.10.5566/ias.1894Search in Google Scholar
[7] Vincent Bortolussi, Bruno Figliuzzi, François Willot, Matthieu Faessel, and Michel Jeandin. Electrical conductivity of metal– polymer cold spray composite coatings onto carbon fiber-reinforced polymer. Journal of Thermal Spray Technology, pages 1–15, 2020.10.1007/s11666-020-00999-7Search in Google Scholar
[8] Pierre Buyssens, Isabelle Gardin, and Su Ruan. Eikonal based region growing for superpixels generation: Application to semi-supervised real time organ segmentation in CT images. IRBM, 35(1):20–26, December 2014.10.1016/j.irbm.2013.12.007Search in Google Scholar
[9] Pierre Buyssens, Isabelle Gardin, Su Ruan, and Abderrahim Elmoataz. Eikonal-based region growing for efficient clustering. Image and Vision Computing, 32(12):1045–1054, December 2014.10.1016/j.imavis.2014.10.002Search in Google Scholar
[10] Pierre Buyssens, Matthieu Toutain, Abderrahim Elmoataz, and Olivier Lézoray. Eikonal-based vertices growing and iterative seeding for efficient graph-based segmentation. In IEEE International Conference on Image Processing (ICIP 2014), page 5 pp., Paris, France, October 2014.10.1109/ICIP.2014.7025886Search in Google Scholar
[11] Pierre Cettour-Janet, Clément Cazorla, Vaïa Machairas, Quentin Delannoy, Nathalie Bednarek, François Rousseau, Etienne Decencière, and Nicolas Passat. Watervoxels. Image Processing On Line IPOL, 9:317–328, 2019.10.5201/ipol.2019.250Search in Google Scholar
[12] Kaiwen Chang and Bruno Figliuzzi. Hierarchical segmentation based upon multi-resolution approximations and the water-shed transform. In Angulo J., Velasco-Forero S., Meyer F.(eds) Mathematical Morphology and Its Applications to Signal and Image Processing. ISMM 2017. Lecture Notes in Computer Science, vol 10225. Springer, Cham, 2017.Search in Google Scholar
[13] Kaiwen Chang and Bruno Figliuzzi. Fast marching based superpixels generation. In International Symposium on Mathematical Morphology and Its Applications to Signal and Image Processing, pages 350–361. Springer, 2019.10.1007/978-3-030-20867-7_27Search in Google Scholar
[14] Dorin Comaniciu and Peter Meer. Mean shift: A robust approach toward feature space analysis. IEEE Transactions on pattern analysis and machine intelligence, 24(5):603–619, 2002.10.1109/34.1000236Search in Google Scholar
[15] Eva Dejnozková and Petr Dokládal. A parallel algorithm for solving the eikonal equation. In 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings.(ICASSP’03)., volume 3, pages III–325. IEEE, 2003.Search in Google Scholar
[16] Pedro F Felzenszwalb and Daniel P Huttenlocher. Efficient graph-based image segmentation. International journal of computer vision, 59(2):167–181, 2004.10.1023/B:VISI.0000022288.19776.77Search in Google Scholar
[17] Bruno Figliuzzi. Eikonal-based models of random tessellations. Image Analysis & Stereology, 38(1):15–23, 2019.10.5566/ias.2061Search in Google Scholar
[18] Bruno Figliuzzi, Dominique Jeulin, Matthieu Faessel, François Willot, Masataka Koishi, and Naoya Kowatari. Modelling the microstructure and the viscoelastic behaviour of carbon black filled rubber materials from 3d simulations. Technische Mechanik, 32(1-2):22–46, 2016.Search in Google Scholar
[19] Brian Fulkerson, Andrea Vedaldi, and Stefano Soatto. Class segmentation and object localization with superpixel neighborhoods. In Computer Vision, 2009 IEEE 12th International Conference on, pages 670–677. IEEE, 2009.10.1109/ICCV.2009.5459175Search in Google Scholar
[20] Remi Giraud, Vinh-Thong Ta, Nicolas Papadakis, and Yannick Berthoumieu. Texture-Aware Superpixel Segmentation. arXiv:1901.11111 [cs], January 2019.10.1109/ICIP.2019.8803085Search in Google Scholar
[21] Alex Levinshtein, Adrian Stere, Kiriakos N Kutulakos, David J Fleet, Sven J Dickinson, and Kaleem Siddiqi. Turbopixels: Fast superpixels using geometric flows. IEEE transactions on pattern analysis and machine intelligence, 31(12):2290–2297, 2009.10.1109/TPAMI.2009.96Search in Google Scholar
[22] Zhengqin Li and Jiansheng Chen. Superpixel segmentation using Linear Spectral Clustering. In 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 1356–1363, June 2015.10.1109/CVPR.2015.7298741Search in Google Scholar
[23] Vaïa Machairas, Matthieu Faessel, David Cárdenas-Peña, Théodore Chabardes, Thomas Walter, and Etienne Decencière. Waterpixels. IEEE Transactions on Image Processing, 24(11):3707–3716, 2015.10.1109/TIP.2015.2451011Search in Google Scholar PubMed
[24] Jitendra Malik, Serge Belongie, Thomas Leung, and Jianbo Shi. Contour and texture analysis for image segmentation. International journal of computer vision, 43(1):7–27, 2001.Search in Google Scholar
[25] Peer Neubert and Peter Protzel. Superpixel benchmark and comparison. In Forum Bildverarbeitung 2010, pages 205–218, 2012.Search in Google Scholar
[26] Alexander Schick, Mika Fischer, and Rainer Stiefelhagen. Measuring and evaluating the compactness of superpixels. In Proceedings of the 21st international conference on pattern recognition (ICPR2012), pages 930–934. IEEE, 2012.Search in Google Scholar
[27] James A Sethian. A fast marching level set method for monotonically advancing fronts. Proceedings of the National Academy of Sciences, 93(4):1591–1595, 1996.10.1073/pnas.93.4.1591Search in Google Scholar PubMed PubMed Central
[28] James A Sethian. Fast marching methods. SIAM review, 41(2):199–235, 1999.10.1137/S0036144598347059Search in Google Scholar
[29] Jianbo Shi and Jitendra Malik. Normalized cuts and image segmentation. IEEE Transactions on pattern analysis and machine intelligence, 22(8):888–905, 2000.10.1109/34.868688Search in Google Scholar
[30] David Stutz, Alexander Hermans, and Bastian Leibe. Superpixels: An Evaluation of the State-of-the-Art. Computer Vision and Image Understanding, April 2017.10.1016/j.cviu.2017.03.007Search in Google Scholar
[31] John E Vargas-Muñoz, Ananda S Chowdhury, Eduardo B Alexandre, Felipe L Galvão, Paulo A Vechiatto Miranda, and Alexandre X Falcão. An iterative spanning forest framework for superpixel segmentation. IEEE Transactions on Image Processing, 28(7):3477–3489, 2019.10.1109/TIP.2019.2897941Search in Google Scholar PubMed
[32] Luc Vincent and Pierre Soille. Watersheds in digital spaces: an efficient algorithm based on immersion simulations. IEEE Transactions on Pattern Analysis & Machine Intelligence, (6):583–598, 1991.10.1109/34.87344Search in Google Scholar
[33] Xiaolin Xiao, Yue-Jiao Gong, and Yicong Zhou. Adaptive superpixel segmentation aggregating local contour and texture features. In 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 1902–1906. IEEE, 2017.10.1109/ICASSP.2017.7952487Search in Google Scholar
[34] C Lawrence Zitnick and Sing Bing Kang. Stereo for image-based rendering using image over-segmentation. International Journal of Computer Vision, 75(1):49–65, 2007.10.1007/s11263-006-0018-8Search in Google Scholar
© 2020 Kaiwen Chang et al., published by De Gruyter
This work is licensed under the Creative Commons Attribution 4.0 International License.
