Natural scene retrieval based on graph semantic similarity for adaptive scene classification

Nuraini Jamil, and Sanggil Khang, (2009) Natural scene retrieval based on graph semantic similarity for adaptive scene classification. In: First International Conference, ICCCI 2009, 5-7 October 2009, Wrocław, Poland.

Full text not available from this repository.

Official URL: http://link.springer.com/chapter/10.1007/978-3-642...

Abstract

In this paper, we introduce our method for image retrieval to access and measuring the similarity of natural scenes by using graph semantic similarity. The proposed method is motivated by continuing effort from our previous work in adaptive image classification based on semantic concepts and edge detection. The method will learn the image information by concept occurrence vector of semantic concepts such as water, grass, sky and foliage. We constructed the graph using this information and illustrate the similarity with connecting edges. The empirical results demonstrated promising performance in terms of accuracy.

Item Type:Conference Paper (UNSPECIFIED)
Uncontrolled Keywords:Image retrieval, Graph, Semantic similarity, Semantic concepts
Subjects:Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions:SCHOOL > Labuan School of Informatics Science
ID Code:6869
Deposited By:IR Admin
Deposited On:23 Sep 2013 15:01
Last Modified:30 Dec 2014 14:32

Repository Staff Only: item control page


Browse Repository
Collection
   Articles
   Book
   Speeches
   Thesis
   UMS News
Search
Quick Search

   Latest Repository

Link to other Malaysia University Institutional Repository

Malaysia University Institutional Repository