Segmentation and content-based watermarking for color image and image region indexing and retrieval

  • Authors:
  • Nikolaos V. Boulgouris;Ioannis Kompatsiaris;Vasileios Mezaris;Dimitrios Simitopoulos;Michael G. Strintzis

  • Affiliations:
  • Informatics and Telematics Institute (ITI), Thermi-Thessaloniki, Greece;Informatics and Telematics Institute (ITI), Thermi-Thessaloniki, Greece;Information Processing Laboratory, Electrical and Computer Engineering Department, Aristotle University of Thessaloniki, Thessaloniki, Greece;Informatics and Telematics Institute (ITI), Thermi-Thessaloniki, Greece;Information Processing Laboratory, Electrical and Computer Engineering Department, Aristotle University of Thessaloniki, Thessaloniki, Greece

  • Venue:
  • EURASIP Journal on Applied Signal Processing
  • Year:
  • 2002

Quantified Score

Hi-index 0.00

Visualization

Abstract

An entirely novel approach to image indexing is presented using content-based watermarking. The proposed system uses color-image segmentation and watermarking in order to facilitate content-based indexing, retrieval and manipulation of digital images and image regions. A novel segmentation algorithm is applied on reduced images and the resulting segmentation mask is embedded in the image using watermarking techniques. In each region of the image, indexing information is additionally embedded. In this way, the proposed system is endowed with content-based access and indexing capabilities which can be easily exploited via a simple watermark detection process. Several experiments have shown the potential of this approach.