Kernel Likelihood Estimation for Superpixel Image Parsing

详细信息    查看全文

• 关键词：Image parsing ; Image segmentation ; Superpixel ; Kernel density estimation
• 刊名：Lecture Notes in Computer Science
• 出版年：2016
• 出版时间：2016
• 年：2016
• 卷：9730
• 期：1
• 页码：234-242
• 全文大小：1,086 KB
• 参考文献：1.Van de Sande, K.E.A., Gevers, T., Snoek, C.G.M.: Evaluating color descriptors for object and scene recognition. IEEE Trans. Pattern Anal. Mach. Intell. 32(9), 1582–1596 (2010)CrossRef
  2.Fulkerson, B., Vedaldi, A., Soatto, S.: Class segmentation and object localization with superpixel neighborhoods. In: IEEE 12th International Conference Computer Vision I (ICCV), pp. 670–677 (2009)
  3.Achanta, R., et al.: SLIC superpixels compared to state-of-the-art superpixel methods. IEEE Trans. Pattern Anal. Mach. Intell. 34(11), 2274–2282 (2012)CrossRef
  4.Vedaldi, A., Soatto, S.: Quick shift and kernel methods for mode seeking. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part IV. LNCS, vol. 5305, pp. 705–718. Springer, Heidelberg (2008)CrossRef
  5.Felzenszwalb, P.F., Huttenlocher, D.P.: Efficient graph-based image segmentation. Int. J. Comput. Vis. 59(2), 167–181 (2004)CrossRef
  6.Kluckner, S., Donoser, M., Bischof, H.: Super-pixel class segmentation in large-scale aerial imagery. In: Proceedings of Annual Workshop Austrian Association for Pattern Recognition (2010)
  7.Shotton, J., Johnson, M., Cipolla, R.: Semantic texton forests for image categorization and segmentation. In: IEEE Conference on Computer Vision Pattern Recognition (CVPR) (2008)
  8.Gould, S., Fulton, R., Koller, D.: Decomposing a scene into geometric and semantically consistent regions. In: ICCV (2009)
  9.Liu, C., et al.: SIFT flow: dense correspondence across difference scenes. In: ECCV (2008)
  10.Tighe, J., Lazebnik, S.: SuperParsing: scalable nonparametric image parsing with superpixels. Int. J. Comput. Vis. 101(2), 329–349 (2013)MathSciNet CrossRef
  11.Eigen, D., Fergus, R.: Nonparametric image parsing using adaptive neighbor sets. In: CVPR, pp. 2799–2806 (2012)
  12.Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. In: CVPR (2006)
  13.Oliva, A., Torralba, A.: Building the gist of a scene: the role of global image features in recognition. Vis. Percept. Progress Brain Res. 155, 23–36 (2006)CrossRef
  14.Torralba, A., Fergus, R., Freeman, W.T.: 80 million tiny images: a large dataset for non-parametric object and scene recognition. IEEE Trans. Pattern Anal. Mach. Intell. 30, 1958–1970 (2008)CrossRef
  15.Shimazaki, H., Shinomoto, S.: Kernel bandwidth optimization in spike rate estimation. J. Comput. Neurosci. 29, 171–182 (2010)MathSciNet CrossRef
  16.Ak, K.E., Ates, H.F.: Scene segmentation and labeling using multi-hypothesis superpixels. In: Signal Processing and Communications Applications Conference (SIU), pp. 847–850 (2015)
  17.George, M.: Image parsing with a wide range of classes and scene-level context. In: CVPR, pp. 3622–3630 (2015)
  
• 作者单位：Hasan F. Ates (15)
  Sercan Sunetci (15)
  Kenan E. Ak (15)
  
  15. Department of Electrical and Electronics Engineering, Isik University, Istanbul, Turkey
  
• 丛书名：Image Analysis and Recognition
• ISBN：978-3-319-41501-7
• 刊物类别：Computer Science
• 刊物主题：Artificial Intelligence and Robotics
  Computer Communication Networks
  Software Engineering
  Data Encryption
  Database Management
  Computation by Abstract Devices
  Algorithm Analysis and Problem Complexity
  
• 出版者：Springer Berlin / Heidelberg
• ISSN：1611-3349
• 卷排序：9730

文摘

In superpixel-based image parsing, the image is first segmented into visually consistent small regions, i.e. superpixels; then superpixels are parsed into different categories. SuperParsing algorithm provides an elegant nonparametric solution to this problem without any need for classifier training. Superpixels are labeled based on the likelihood ratios that are computed from class conditional density estimates of feature vectors. In this paper, local kernel density estimation is proposed to improve the estimation of likelihood ratios and hence the labeling accuracy. By optimizing kernel bandwidths for each feature vector, feature densities are better estimated especially when the set of training samples is sparse. The proposed method is tested on the SIFT Flow dataset consisting of 2,688 images and 33 labels, and is shown to outperform SuperParsing and some of its extended versions in terms of classification accuracy.