The effectiveness of image features based on fractal image coding for image annotation

Cho Wei Shih, Hui Chuan Chu, Yuh-Min Chen, Chuin Cheng Wen

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Image annotation is a process of assigning metadata to digital images in the form of captions or keywords, and has been regarded as image management and one of the most crucial processes of image retrieval. And many automatic methods have been proposed. However, these methods still have some problems respectively. Fractals are fragmented geometries and can be considered separate parts; each part is similar to the contracted overall shape. Fractal features provide geometric information of an image that is irrelevant to the shape and size of an object in the image; therefore, fractal features are more robust than color and texture features. Therefore, this study proposed a fractal-driven image annotation (FIA) schema that extracts fractal features through fractal image coding and integrates color and texture as new visual features to conduct image-based annotation. Experimental results indicate that the effect of thresholds on annotating accuracy is insignificant. This finding supports the application of FIA on complex practical environments, reduces the time for identifying the optimal thresholds, and improves the practicality of using FIA in real environments.

Original languageEnglish
Pages (from-to)12897-12904
Number of pages8
JournalExpert Systems With Applications
Volume39
Issue number17
DOIs
Publication statusPublished - 2012 Dec 1

Fingerprint

Image coding
Fractals
Textures
Color
Image retrieval
Metadata
Geometry

All Science Journal Classification (ASJC) codes

  • Engineering(all)
  • Computer Science Applications
  • Artificial Intelligence

Cite this

Shih, Cho Wei ; Chu, Hui Chuan ; Chen, Yuh-Min ; Wen, Chuin Cheng. / The effectiveness of image features based on fractal image coding for image annotation. In: Expert Systems With Applications. 2012 ; Vol. 39, No. 17. pp. 12897-12904.
@article{fae2e807a0f44e33b930110422060b71,
title = "The effectiveness of image features based on fractal image coding for image annotation",
abstract = "Image annotation is a process of assigning metadata to digital images in the form of captions or keywords, and has been regarded as image management and one of the most crucial processes of image retrieval. And many automatic methods have been proposed. However, these methods still have some problems respectively. Fractals are fragmented geometries and can be considered separate parts; each part is similar to the contracted overall shape. Fractal features provide geometric information of an image that is irrelevant to the shape and size of an object in the image; therefore, fractal features are more robust than color and texture features. Therefore, this study proposed a fractal-driven image annotation (FIA) schema that extracts fractal features through fractal image coding and integrates color and texture as new visual features to conduct image-based annotation. Experimental results indicate that the effect of thresholds on annotating accuracy is insignificant. This finding supports the application of FIA on complex practical environments, reduces the time for identifying the optimal thresholds, and improves the practicality of using FIA in real environments.",
author = "Shih, {Cho Wei} and Chu, {Hui Chuan} and Yuh-Min Chen and Wen, {Chuin Cheng}",
year = "2012",
month = "12",
day = "1",
doi = "10.1016/j.eswa.2012.05.003",
language = "English",
volume = "39",
pages = "12897--12904",
journal = "Expert Systems with Applications",
issn = "0957-4174",
publisher = "Elsevier Limited",
number = "17",

}

The effectiveness of image features based on fractal image coding for image annotation. / Shih, Cho Wei; Chu, Hui Chuan; Chen, Yuh-Min; Wen, Chuin Cheng.

In: Expert Systems With Applications, Vol. 39, No. 17, 01.12.2012, p. 12897-12904.

Research output: Contribution to journalArticle

TY - JOUR

T1 - The effectiveness of image features based on fractal image coding for image annotation

AU - Shih, Cho Wei

AU - Chu, Hui Chuan

AU - Chen, Yuh-Min

AU - Wen, Chuin Cheng

PY - 2012/12/1

Y1 - 2012/12/1

N2 - Image annotation is a process of assigning metadata to digital images in the form of captions or keywords, and has been regarded as image management and one of the most crucial processes of image retrieval. And many automatic methods have been proposed. However, these methods still have some problems respectively. Fractals are fragmented geometries and can be considered separate parts; each part is similar to the contracted overall shape. Fractal features provide geometric information of an image that is irrelevant to the shape and size of an object in the image; therefore, fractal features are more robust than color and texture features. Therefore, this study proposed a fractal-driven image annotation (FIA) schema that extracts fractal features through fractal image coding and integrates color and texture as new visual features to conduct image-based annotation. Experimental results indicate that the effect of thresholds on annotating accuracy is insignificant. This finding supports the application of FIA on complex practical environments, reduces the time for identifying the optimal thresholds, and improves the practicality of using FIA in real environments.

AB - Image annotation is a process of assigning metadata to digital images in the form of captions or keywords, and has been regarded as image management and one of the most crucial processes of image retrieval. And many automatic methods have been proposed. However, these methods still have some problems respectively. Fractals are fragmented geometries and can be considered separate parts; each part is similar to the contracted overall shape. Fractal features provide geometric information of an image that is irrelevant to the shape and size of an object in the image; therefore, fractal features are more robust than color and texture features. Therefore, this study proposed a fractal-driven image annotation (FIA) schema that extracts fractal features through fractal image coding and integrates color and texture as new visual features to conduct image-based annotation. Experimental results indicate that the effect of thresholds on annotating accuracy is insignificant. This finding supports the application of FIA on complex practical environments, reduces the time for identifying the optimal thresholds, and improves the practicality of using FIA in real environments.

UR - http://www.scopus.com/inward/record.url?scp=84865036182&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84865036182&partnerID=8YFLogxK

U2 - 10.1016/j.eswa.2012.05.003

DO - 10.1016/j.eswa.2012.05.003

M3 - Article

VL - 39

SP - 12897

EP - 12904

JO - Expert Systems with Applications

JF - Expert Systems with Applications

SN - 0957-4174

IS - 17

ER -