Saturday, January 26, 2008

FCTH: FUZZY COLOR AND TEXTURE HISTOGRAM

My paper "FCTH: FUZZY COLOR AND TEXTURE HISTOGRAM. A LOW LEVEL FEATURE FOR ACCURATE IMAGE RETRIEVAL" has been accepted in the "The International Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS)"

This paper deals with the extraction of a new low level feature that combines, in one histogram, color and texture information. This feature is named FCTH - Fuzzy Color and Texture Histogram - and results from the combination of 3 fuzzy systems. FCTH size is limited to 72 bytes per image, rendering this descriptor suitable for use in large image databases. The proposed feature is appropriate for accurately retrieving images even in distortion cases such as deformations, noise and smoothing. It is tested on a large number of images selected from proprietary image databases or randomly retrieved from popular search engines. To evaluate the performance of the proposed feature, the averaged normalized modified retrieval rank was used.
An online demo that implements the proposed feature in an image retrieval system is available at: http://orpheus.ee.duth.gr/image_retrieval.


The proposed low level feature has been integrated in the retrieval software system Img (Rummager), which has been developed in the “Automatic Control Systems & Robotics” laboratory of “Democritus University of Thrace - Greece”.

To evaluate the performance of the image retrieval system, the objective measure called ANMRR (Averaged Normalized Modified Retrieval Rank) is used. In particular experiments we used as ground truth, the groups of images as proposed in the MIRROR image retrieval system. This system separates the Wang’s database in 20 queries. In table 2 that follows certain indicative results appear while in table 3 the values of ANMRR for the total of the 20 queries have been calculated.






No comments: