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

Y.Z. Song; C.P. Town

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

Y.Z. Song, C.P. Town

Department of Computer Science

University of Cambridge

Research output: Chapter or section in a book/report/conference proceeding › Chapter in a published conference proceeding

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 language	English
Title of host publication	Vision, video, and graphics 2005: University of Edinburgh July 7-8th, 2005
Place of Publication	Aire-la-Ville
Publisher	Eurographics: European Association for Computer Graphics
Pages	159-166
Number of pages	8
ISBN (Print)	9783905673579
Publication status	Published - 2005
Event	2nd International Conference on Video, Vision and Graphics, VVG 2005 - Edinburgh, UK United Kingdom Duration: 7 Jul 2005 → 8 Jul 2005

Conference

Conference	2nd International Conference on Video, Vision and Graphics, VVG 2005
Country/Territory	UK United Kingdom
City	Edinburgh
Period	7/07/05 → 8/07/05

Cite this

Visual recognition of man-made materials and structures in an office environment. / Song, Y.Z.; Town, C.P.
Vision, video, and graphics 2005: University of Edinburgh July 7-8th, 2005. Aire-la-Ville: Eurographics: European Association for Computer Graphics, 2005. p. 159-166.

Research output: Chapter or section in a book/report/conference proceeding › Chapter in a published conference proceeding

Song, YZ & Town, CP 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. Eurographics: European Association for Computer Graphics, Aire-la-Ville, pp. 159-166, 2nd International Conference on Video, Vision and Graphics, VVG 2005, Edinburgh, UK United Kingdom, 7/07/05.

@inproceedings{60f44e1ae72d4b5ab4f4dd7fe38f49c7,

title = "Visual recognition of man-made materials and structures in an office environment",

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.",

author = "Y.Z. Song and C.P. Town",

year = "2005",

language = "English",

isbn = "9783905673579",

pages = "159--166",

booktitle = "Vision, video, and graphics 2005: University of Edinburgh July 7-8th, 2005",

publisher = "Eurographics: European Association for Computer Graphics",

note = "2nd International Conference on Video, Vision and Graphics, VVG 2005 ; Conference date: 07-07-2005 Through 08-07-2005",

}

TY - GEN

T1 - Visual recognition of man-made materials and structures in an office environment

AU - Song, Y.Z.

AU - Town, C.P.

PY - 2005

Y1 - 2005

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=84880406974&partnerID=8YFLogxK

M3 - Chapter in a published conference proceeding

AN - SCOPUS:84880406974

SN - 9783905673579

SP - 159

EP - 166

BT - Vision, video, and graphics 2005: University of Edinburgh July 7-8th, 2005

PB - Eurographics: European Association for Computer Graphics

CY - Aire-la-Ville

T2 - 2nd International Conference on Video, Vision and Graphics, VVG 2005

Y2 - 7 July 2005 through 8 July 2005

ER -

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

Abstract

Conference

Other files and links

Fingerprint

Cite this