Paper Info
Title
Majority based ranking approach in web image retrieval
Abstract
In this paper, we address a ranking problem in web image retrieval. Due to the growing availability of web images, comprehensive retrieval of web images has been expected. Conventional systems for web image retrieval are based on keyword- based retrieval. However, we often find undesirable retrieval results from the keyword based web image retrieval system since the system uses the limited and inaccurate text information of web images ; a typical system uses text information such as surrounding texts and/or image filenames, etc. To alleviate this situation, we propose a new ranking approach which is the integration of results of text and image content via analyzing the retrieved results. We define four ranking methods based on the image contents analysis of the retrieved images; (1) majority-first method, (2) centroid-of-all method, (3) centroid-of-top K method, and (4) centroid-of-largest-cluster method. We evaluate the retrieval performance of our methods and conventional one using precision and recall graphs. The experimental results show that the proposed methods are more effective than conventional keyword-based retrieval methods.
Year
DOI
Venue
2003
10.1007/3-540-45113-7_12
CIVR
Keywords
Field
DocType
ranking approach,retrieval performance,image content,comprehensive retrieval,image filenames,web image retrieval,web image,web image retrieval system,undesirable retrieval result,image contents analysis,conventional keyword-based retrieval method,image retrieval,content analysis
Information system,Data mining,Human–computer information retrieval,Automatic image annotation,Information retrieval,Ranking,Computer science,Precision and recall,Image retrieval,Adversarial information retrieval,Visual Word
Conference
Volume
ISSN
ISBN
2728
0302-9743
3-540-40634-4
Citations 
PageRank 
References 
12
1.20
11
Authors
3
Name
Order
Citations
PageRank
Gunhan Park1523.58
Yunju Baek215623.54
Heung-kyu Lee3101687.53