A class hierarchy approach for the segmentation of natural scenes
A class hierarchy approach for the segmentation of natural scenes
- Author(s): M.J.A. Strens ; J.F. Boyce ; J.F. Haddon
- DOI: 10.1049/cp:19970872
For access to this article, please select a purchase option:
Buy conference paper PDF
Buy Knowledge Pack
IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.
6th International Conference on Image Processing and its Applications — Recommend this title to your library
Thank you
Your recommendation has been sent to your librarian.
- Author(s): M.J.A. Strens ; J.F. Boyce ; J.F. Haddon Source: 6th International Conference on Image Processing and its Applications, 1997 p. 146 – 150
- Conference: 6th International Conference on Image Processing and its Applications
- DOI: 10.1049/cp:19970872
- ISBN: 0 85296 692 X
- Location: Dublin, Ireland
- Conference date: 14-17 July 1997
- Format: PDF
Scene segmentation techniques normally model scene content in terms of a set of mutually-exclusive classes. This model is used both by local feature classifiers and by later stages of processing such as relaxation labelling. This paper generalises these schemes to a hierarchical class model where the labelling of each pixel is the result of a path down the class hierarchy. The benefits of the hierarchical scheme are discussed, and an efficient relaxation labelling algorithm for the class hierarchy is given. The technique is demonstrated on synthetic textured images with added noise and a comparison in terms of performance and complexity is made with the traditional model.
Inspec keywords: image classification; noise; feature extraction; image texture; image segmentation
Subjects: Optical information, image and video signal processing; Computer vision and image processing techniques; Pattern recognition
Related content
content/conferences/10.1049/cp_19970872
pub_keyword,iet_inspecKeyword,pub_concept
6
6