• DocumentCode
    2514664
  • Title

    Classifying Textile Designs Using Bags of Shapes

  • Author

    Jia, Wei ; McKenna, Stephen J.

  • Author_Institution
    Sch. of Comput., Univ. of Dundee, Dundee, UK
  • fYear
    2010
  • fDate
    23-26 Aug. 2010
  • Firstpage
    294
  • Lastpage
    297
  • Abstract
    The use of region shape descriptors was investigated for categorisation of textile design images. Images were segmented using MRF pixel labelling and the shapes of regions obtained were described with generic Fourier descriptors. Each image was represented as a bag of shapes. A simple yet competitive classification scheme based on nearest neighbour class-based matching was used. Classification performance was compared to that obtained when using bags of SIFT features.
  • Keywords
    Fourier transforms; image classification; image matching; production engineering computing; textile industry; textiles; bags of SIFT features; bags of shapes; generic Fourier descriptors; nearest neighbour class-based matching; region shape descriptors; textile design image categorisation; textile design image classification; Accuracy; Image segmentation; Kernel; Labeling; Pixel; Shape; Training; Markov random field; classification; region segmentation; shape descriptors; textile design;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Pattern Recognition (ICPR), 2010 20th International Conference on
  • Conference_Location
    Istanbul
  • ISSN
    1051-4651
  • Print_ISBN
    978-1-4244-7542-1
  • Type

    conf

  • DOI
    10.1109/ICPR.2010.81
  • Filename
    5597790