Image mining by content

Image mining presents special characteristics due to the richness of the data that an image can show. Effective evaluation of the results of image mining by content requires that the user point of view (of likeness) is used on the performance parameters. Comparison among different mining by similarity systems is particularly challenging owing to the great variety of methods implemented to represent resemblance and the dependence that the results present of the used image set. Other obstacle is the lag of parameters for comparing experimental performance. In this paper we propose an evaluation framework for comparing the influence of the distance function on image mining by colour. Experiments with colour similarity mining by quantisation on colour space and measures of likeness between a sample and the image results have been carried out to illustrate the proposed scheme. Important aspects of this type of mining are also described. (C) 2002 Elsevier Science Ltd. All rights reserved.