Please use this identifier to cite or link to this item: https://hdl.handle.net/20.500.14279/3497
Title: Image indexing based on web page segmentation and clustering
Authors: Tsapatsoulis, Nicolas 
Tryfou, Georgina 
metadata.dc.contributor.other: Τσαπατσούλης, Νικόλας
Τρύφου, Τζωρτζίνα
Major Field of Science: Engineering and Technology
Field Category: Electrical Engineering - Electronic Engineering - Information Engineering
Keywords: Image indexing;Automatic annotation;Web page segmentation
Issue Date: 2012
Source: 11th International Conference on Applications of Computer Engineering, 2012, Athens, Greece, 7-9 March
Abstract: Thousands of images are nowadays available on the web. These images are accompanied by a wide range of textual descriptors, such as image file names, anchor texts and, of course, surrounding text. Existing systems that attempt to mine information for images using surrounding text suffer from several problems, such as the inability to correctly assign all relevant text to an image and discard the irrelevant. In this paper, we propose a novel method for indexing web images which is based on textual descriptors. The web document is segmented into visual blocks of text and then each block of text is assigned to the closet image. The text extraction is improved by assigning the text to an image following the intuitive understanding of how close two visual blocks are. The evaluation confirms the validity of the proposed method and demonstrates its possible extensions.
URI: https://hdl.handle.net/20.500.14279/3497
Type: Conference Papers
Affiliation : Cyprus University of Technology 
Appears in Collections:Δημοσιεύσεις σε συνέδρια /Conference papers or poster or presentation

Files in This Item:
File Description SizeFormat
Tsapatsoulis_2012.pdf566.76 kBAdobe PDFView/Open
CORE Recommender
Show full item record

Page view(s) 50

435
Last Week
0
Last month
2
checked on Dec 23, 2024

Download(s) 50

113
checked on Dec 23, 2024

Google ScholarTM

Check


Items in KTISIS are protected by copyright, with all rights reserved, unless otherwise indicated.