Segmentation of natural images for CBIR

Author

Williams, Paul Stefan ; Alder, Michael D.

Author_Institution

Dept. of Electr. & Electron. Eng., Western Australia Univ., Nedlands, WA, Australia

Volume

1

fYear

1998

fDate

16-20 Aug 1998

Firstpage

468

Abstract

Examines the problem of segmenting colour images into homogeneous regions for use in content based image retrieval (CBIR) or object recognition in general. Low level features provide intensity, colour and texture characteristics across the entire image. From these feature vectors a measure of local homogeneity is obtained. Through iterative modelling a seed and grow style algorithm is used to locate each segment. The final segment models provide sufficient information for higher level processing or classification. Segmentation and classification results are illustrated from a database of 1000 Corel Photo CD images

Keywords

content-based retrieval; feature extraction; image classification; image colour analysis; image segmentation; object recognition; CBIR; Corel Photo CD images; colour images; content based image retrieval; homogeneous regions; intensity; iterative modelling; local homogeneity; low level features; natural images; object recognition; seed and grow style algorithm; texture characteristics; Australia; Color; Electrical capacitance tomography; Feature extraction; Image classification; Image resolution; Image retrieval; Image segmentation; Information processing; Intelligent systems;

fLanguage

English

Publisher

ieee

Conference_Titel

Pattern Recognition, 1998. Proceedings. Fourteenth International Conference on

Conference_Location

Brisbane, Qld.

ISSN

1051-4651

Print_ISBN

0-8186-8512-3

Type

conf

DOI

10.1109/ICPR.1998.711182

Filename

711182