An integrated segmentation technique for interactive image retrieval

Author

Aditya, R. ; Ghosal, S.

Author_Institution

Biomorphic VLSI Inc., Westlake Village, CA, USA

Volume

3

fYear

2000

fDate

2000

Firstpage

762

Abstract

Many content-based image retrieval (CBIR) systems utilize image segmentation for enabling the user to perform object-level database querying. We propose an integrated segmentation technique for interactive image retrieval, that is reasonably accurate and fast. An initial over-segmentation is generated by finding the dominant color modes in the global histogram of the image using the mean-shift algorithm. Edge-based processing is performed at the initial segment boundaries to merge non-obvious segments. Finally segment shapes are regularized using a Hopfield (1985) type neural network to improve their perceptual quality. A scalable implementation is presented for ensuring fast serial execution of the Hopfield network. The entire segmentation process takes less than 10 seconds to segment 128×192 stock photos on a standard workstation

Keywords

Hopfield neural nets; content-based retrieval; image colour analysis; image retrieval; image segmentation; interactive systems; Hopfield type neural network; content-based image retrieval; dominant color modes; edge-based processing; fast serial execution; global histogram; initial segment boundaries; integrated image segmentation; interactive image retrieval; mean-shift algorithm; object-level database querying; over-segmentation; perceptual quality; scalable implementation; segment shapes; workstation; Content based retrieval; Histograms; Hopfield neural networks; Image databases; Image retrieval; Image segmentation; Information retrieval; Neural networks; Shape; Workstations;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Processing, 2000. Proceedings. 2000 International Conference on

Conference_Location

Vancouver, BC

ISSN

1522-4880

Print_ISBN

0-7803-6297-7

Type

conf

DOI

10.1109/ICIP.2000.899566

Filename

899566