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

DOI10.1155/S1110865702000768MaRDI QIDQ1607692zbMATH OpenFDO

Authors R. Smith

Publication date 14 October 2002

Published in EURASIP Journal on Applied Signal Processing (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1155/S1110865702000768

zbMATH Keywords

image indexingimage retrievalwatermaking

Mathematics Subject Classification ID

Computing methodologies for image processing (68U10) Image processing (compression, reconstruction, etc.) in information and communication theory (94A08) Authentication, digital signatures and secret sharing (94A62)

Review text

The authors present a content-based image indexing method, where information about image objects is stored using watermaking in the image itself. Images are segmented into large connected regions which should correspond to image (semantical) objects; the segmentation algorithm uses a combination of position, intensity and texture information of image pixels, and the segmentation labels are embedded in the blue component of RGB. Region descriptors (64 bits) are calculated using the region's color, position and shape; this indexing information is embedded in the red component. Some test experiments on image retrieval are described.

Recommendations

• Region-based image indexing and retrieval using color and texture
• Region-based image watermarking
• scientific article; zbMATH DE number 1745024
• scientific article; zbMATH DE number 2087644
• A color image segmentation approach for content-based image retrieval

Cited in

(2)

• scientific article; zbMATH DE number 2080169 (Why is no real title available?)
• Region based QIM digital watermarking scheme for image database in DCT domain

This page was built for publication: Segmentation and content-based watermarking for color image and image region indexing and retrieval

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1607692)