A method for the automatic indexing of colour images for effective image retrieval

1 January 1997

journal article
research article
Published by Taylor & Francis in New Review of Hypermedia and Multimedia

Vol. 3 (1) , 201-224
https://doi.org/10.1080/13614569708914690

Abstract

The authors propose a new colour-based indexing method for image databases. This method, integrating different approaches for describing colour information, can be more satisfactory than standard techniques in fields such as textiles, ceramics, and paintings, when the user would like to retrieve from the database those images that actually resemble the query image selected in their colour distribution characteristics. Experimental trials on a database of complex antique textile images are reported and compared with human perceptual judgments, using an innovative procedure for estimating retrieval effectiveness.

Keywords

This publication has 16 references indexed in Scilit:

Color image retrieval based on hidden Markov models
IEEE Transactions on Image Processing, 1997
Image retrieval using color and shape
Pattern Recognition, 1996
Colorimetric calibration of color scanners by back-propagation
Pattern Recognition Letters, 1995
Efficient color histogram indexing for quadratic form distance functions
Published by Institute of Electrical and Electronics Engineers (IEEE) ,1995
Color matching for image retrieval
Pattern Recognition Letters, 1995
IMAGE RETRIEVAL USING FUZZY EVALUATION OF COLOR SIMILARITY
International Journal of Pattern Recognition and Artificial Intelligence, 1994
Fuzzy reasoning approach to similarity evaluation in image analysis
International Journal of Intelligent Systems, 1993
Neural network applications to the color scanner and printer calibrations
Journal of Electronic Imaging, 1992
Colour image quantization for high resolution graphics display
Image and Vision Computing, 1991
Calibration of a video camera digitising system in the CIE L∗u∗v∗ colour space
Pattern Recognition Letters, 1990