Publication detail

Image Search Using Similarity Measures Based on Circular Sectors

MAŠEK, J. BURGET, R. POVODA, L. HARVÁNEK, M.

Original Title

Image Search Using Similarity Measures Based on Circular Sectors

English Title

Image Search Using Similarity Measures Based on Circular Sectors

Type

conference paper

Language

en

Original Abstract

With growing number of stored image data, image search and image similarity problem become more and more important. The answer can be solved by Content-Based Image Retrieval systems. This paper deals with an image search using similarity measures based on circular sectors method. The method is inspired by human eye functionality. The main contribution of the paper is a modified method that increases accuracy for about 8% in comparison with original approach. Here proposed method has used HSB colour model and median function for feature extraction. The original approach uses RGB colour model with mean function. Implemented method was validated on 10 image categories where overall average precision was 67%.

English abstract

With growing number of stored image data, image search and image similarity problem become more and more important. The answer can be solved by Content-Based Image Retrieval systems. This paper deals with an image search using similarity measures based on circular sectors method. The method is inspired by human eye functionality. The main contribution of the paper is a modified method that increases accuracy for about 8% in comparison with original approach. Here proposed method has used HSB colour model and median function for feature extraction. The original approach uses RGB colour model with mean function. Implemented method was validated on 10 image categories where overall average precision was 67%.

Keywords

CBIR; circular sectors; cross-validation; image features; image processing; image similarity; optimization

RIV year

2015

Released

06.11.2015

Location

Dubaj, Spojené arabské emiráty

ISBN

978-1-921987-43-4

Book

Computer Science & Information Technology (CS & IT)

Pages from

241

Pages to

251

Pages count

11

BibTex


@inproceedings{BUT118127,
  author="Jan {Mašek} and Radim {Burget} and Lukáš {Povoda} and Martin {Harvánek}",
  title="Image Search Using Similarity Measures Based on Circular Sectors",
  annote="With growing number of stored image data, image search and image similarity problem become more and more important. The answer can be solved by Content-Based Image Retrieval systems. This paper deals with an image search using similarity measures based on circular sectors method. The method is inspired by human eye functionality. The main contribution of the paper is a modified method that increases accuracy for about 8% in comparison with original approach. Here proposed method has used HSB colour model and median function for feature extraction. The original approach uses RGB colour model with mean function. Implemented method was validated on 10 image categories where overall average precision was 67%.",
  booktitle="Computer Science & Information Technology (CS & IT)",
  chapter="118127",
  doi="10.5121/csit.2015.51519",
  howpublished="print",
  year="2015",
  month="november",
  pages="241--251",
  type="conference paper"
}