Visual recognition of man-made materials and structures in an office environment

Y.Z. Song, C.P. Town

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper demonstrates a new approach towards object recognition founded on the development of Neural Network classifiers and Bayesian Networks. The mapping from segmented image region descriptors to semantically meaningful class membership terms is achieved using Neural Networks. Bayesian Networks are then employed to probabilistically detect objects within an image by means of relating region class labels and their surrounding environments. Furthermore, it makes use of an intermediate level of image representation and demonstrates how object recognition can be achieved in this way.
Original languageEnglish
Title of host publicationVision, video, and graphics 2005: University of Edinburgh July 7-8th, 2005
Place of PublicationAire-la-Ville
PublisherEurographics: European Association for Computer Graphics
Pages159-166
Number of pages8
ISBN (Print)9783905673579
Publication statusPublished - 2005
Event2nd International Conference on Video, Vision and Graphics, VVG 2005 - Edinburgh, UK United Kingdom
Duration: 7 Jul 20058 Jul 2005

Conference

Conference2nd International Conference on Video, Vision and Graphics, VVG 2005
CountryUK United Kingdom
CityEdinburgh
Period7/07/058/07/05

Fingerprint Dive into the research topics of 'Visual recognition of man-made materials and structures in an office environment'. Together they form a unique fingerprint.

  • Cite this

    Song, Y. Z., & Town, C. P. (2005). Visual recognition of man-made materials and structures in an office environment. In Vision, video, and graphics 2005: University of Edinburgh July 7-8th, 2005 (pp. 159-166). Eurographics: European Association for Computer Graphics.