Tuesday, January 15, 2008

CEDD: Color and Edge Directivity Descriptor

Update your bookmarks: Read more about CEDD desctiptor and download an open source implementation from my personal website http://chatzichristofis.info/?page_id=15 

My paper "CEDD: Color and Edge Directivity Descriptor. A Compact Descriptor for Image Indexing and Retrieval" has been accepted for inclusion in the ICVS2008 proceedings.

Abstract.
This paper deals with a new low level feature that is extracted from the images and can be used for indexing and retrieval. This feature is called “Color and Edge Directivity Descriptor” and incorporates in a histogram color and texture information. CEDD size is limited to 54 bytes per image, rendering this descriptor suitable for use in large image databases. This descriptor is appropriate for accurately retrieving images even in distortion cases such as deformation, noise and smoothing. It was tested on a large number of images selected from proprietary image databases or randomly retrieved from popular search engines. Important attribute of the CEDD is the low computational power needed for its extraction, in comparison to the needs of the most MPEG-7 descriptors. To evaluate the performance of the proposed feature, the objective measure called ANMRR is used.
Keywords: Image Retrieval, Image Indexing, Compact Descriptors, Low Level Features, Color and Texture Histogram.


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) [5] is used. The ANMRR is always in range of 0 to 1 and the smaller the value of this measure is the better the matching quality of the query.







No comments: