A Survey on Feature Based Image Retrieval Techniques

A Survey on Feature Based Image Retrieval Techniques

Ling Shao (University of Sheffield, UK)
Copyright: © 2012 |Pages: 16
DOI: 10.4018/978-1-61350-126-9.ch007
OnDemand PDF Download:
Available
$37.50
Current Special Offers
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

In this chapter, we review classical and state of the art Content-Based Image Retrieval algorithms. Techniques on representing and extracting visual features, such as color, shape, and texture, are first presented. Several well-known image retrieval systems using those features are also summarized. Then, two recent trends on image retrieval, namely semantic based methods and local invariant regions based methods, are discussed. We analyze the drawbacks of current approaches and propose directions for future work.
Chapter Preview
Top

Visual Feature Representation And Extraction

The representation of visual features in images is a fundamental issue in Content-Based Image Retrieval. Computer vision and pattern recognition algorithms provide the means to extract numerical descriptors which give a quantitative measure to such features. The features employed in most CBIR techniques include: color, texture, local shape and spatial layout. The following is a brief description of some current methods for extracting such features and the similarity measures between such features.

Complete Chapter List

Search this Book:
Reset