Classification-driven object-based image retrieval

Author

Jia, Linhui ; Kitchen, Leslie

Author_Institution

Dept. of Comput. Sci. & Software Eng., Melbourne Univ., Parkville, Vic., Australia

Volume

1

fYear

1999

fDate

36342

Firstpage

618

Abstract

This paper describes an approach for object-based image retrieval based on classes of objects in images. In this approach, contours of objects are extracted from images and are represented under a scheme which satisfies scale, rotation and translation invariance. Classifier learning techniques are used to classify objects in images into different classes. Image similarity calculation is performed based on class information of objects. Experimental results show that the method is effective and efficient

Keywords

image classification; image representation; image retrieval; multimedia databases; visual databases; classifier learning techniques; experimental results; image classification; image representation; image similarity calculation; object contours; object-based image retrieval; rotation invariance; scale invariance; translation invariance; Classification tree analysis; Computer science; Computer vision; Decision trees; Image databases; Image retrieval; Image segmentation; Machine intelligence; Object recognition; Shape;

fLanguage

English

Publisher

ieee

Conference_Titel

Multimedia Computing and Systems, 1999. IEEE International Conference on

Conference_Location

Florence

Print_ISBN

0-7695-0253-9

Type

conf

DOI

10.1109/MMCS.1999.779271

Filename

779271