Academic Journals Database
Disseminating quality controlled scientific knowledge

Segmentation Technique for Image Indexing and Retrieval on Discrete Cosines Domain

ADD TO MY LIST
 
Author(s): Suhendro Yusuf Irianto

Journal: TELKOMNIKA
ISSN 1693-6930

Volume: 11;
Issue: 1;
Start page: 119;
Date: 2013;
Original page

ABSTRACT
This paper uses region growing segmentation technique to segment the Discrete Cosines (DC)  image. The problem of content Based image retrieval (CBIR) is the luck of accuracy in matching between image query and image in the database as it matches object and background in the same time.   This the reason previous CBIR techniques inaccurate and time consuming. The CBIR   based on the segmented region proposed in this work  separates object from background as CBIR need only match the object not the background.  By using region growing technique on DC image, it reduces the number of image       regions.    The proposed of recursive region growing is not new technique but its application on DC images to build    indexing keys is quite new and not yet presented by many     authors. The experimental results show  that the proposed methods on   segmented images present good precision which are higher than 0.60 on all classes . It can be concluded that  region growing segmented based CBIR more efficient    compare to DC images  in term of their precision 0.59 and 0.75, respectively. Moreover,  DC based CBIR  can save time and simplify algorithm compare to DCT images.
Why do you need a reservation system?      Save time & money - Smart Internet Solutions