An efficient approach for region-based image classification and retrieval

Samy Sadek; Ayoub Al-Hamadi; Bernd Michaelis; Usama Sayed

doi:10.1007/978-3-642-10546-3_8

An efficient approach for region-based image classification and retrieval

Samy Sadek, Ayoub Al-Hamadi, Bernd Michaelis, Usama Sayed

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Scopus citations

Abstract

In this paper, a fast and efficient approach for region-based image classification and retrieval using multi-level neural network model is proposed. The advantages of this particular model in image classification and retrieval domain will be highlighted. The proposed approach accomplishes its goal in two main steps. First, by aid of a mean-shift based segmentation algorithm, significant regions of the image are isolated. Then, features of these regions are extracted and then classified by the multi-level model into five categories, i.e., "Sky", "Building", "Sand\Rock", "Grass" and "Water". Features extraction is done by using color moments and 2D wavelets decomposition technique. Experimental results show that the proposed approach can achieve precision of better than 93% that justifies the viability of the proposed approach compared with other state-of-the-art classification and retrieval approaches.

Original language	English
Title of host publication	Signal Processing, Image Processing and Pattern Recognition
Subtitle of host publication	International Conference, SIP 2009, Held as Part of the Future Generation Information Technology Conference, FGIT 2009, Jeju Island, Korea
Editors	Dominik Slezak, Sankar K. Pal, Byeong-Ho Kang, Junzhong Gu, Hideo Kuroda, Tai-hoon Kim
Pages	56-64
Number of pages	9
DOIs	https://doi.org/10.1007/978-3-642-10546-3_8
State	Published - 2009
Externally published	Yes

Publication series

Name	Communications in Computer and Information Science
Volume	61
ISSN (Print)	1865-0929

Keywords

Content-based image retrieval
Feature extraction
Multi-level neural networks
Wavelets decomposition

Access to Document

10.1007/978-3-642-10546-3_8

Cite this

Sadek, S., Al-Hamadi, A., Michaelis, B., & Sayed, U. (2009). An efficient approach for region-based image classification and retrieval. In D. Slezak, S. K. Pal, B.-H. Kang, J. Gu, H. Kuroda, & T. Kim (Eds.), Signal Processing, Image Processing and Pattern Recognition: International Conference, SIP 2009, Held as Part of the Future Generation Information Technology Conference, FGIT 2009, Jeju Island, Korea (pp. 56-64). (Communications in Computer and Information Science; Vol. 61). https://doi.org/10.1007/978-3-642-10546-3_8

Sadek, Samy ; Al-Hamadi, Ayoub ; Michaelis, Bernd et al. / An efficient approach for region-based image classification and retrieval. Signal Processing, Image Processing and Pattern Recognition: International Conference, SIP 2009, Held as Part of the Future Generation Information Technology Conference, FGIT 2009, Jeju Island, Korea. editor / Dominik Slezak ; Sankar K. Pal ; Byeong-Ho Kang ; Junzhong Gu ; Hideo Kuroda ; Tai-hoon Kim. 2009. pp. 56-64 (Communications in Computer and Information Science).

@inproceedings{2654c66c88614efc8bc60ad861e52d96,

title = "An efficient approach for region-based image classification and retrieval",

abstract = "In this paper, a fast and efficient approach for region-based image classification and retrieval using multi-level neural network model is proposed. The advantages of this particular model in image classification and retrieval domain will be highlighted. The proposed approach accomplishes its goal in two main steps. First, by aid of a mean-shift based segmentation algorithm, significant regions of the image are isolated. Then, features of these regions are extracted and then classified by the multi-level model into five categories, i.e., {"}Sky{"}, {"}Building{"}, {"}Sand\textbackslash{}Rock{"}, {"}Grass{"} and {"}Water{"}. Features extraction is done by using color moments and 2D wavelets decomposition technique. Experimental results show that the proposed approach can achieve precision of better than 93\% that justifies the viability of the proposed approach compared with other state-of-the-art classification and retrieval approaches.",

keywords = "Content-based image retrieval, Feature extraction, Multi-level neural networks, Wavelets decomposition",

author = "Samy Sadek and Ayoub Al-Hamadi and Bernd Michaelis and Usama Sayed",

year = "2009",

doi = "10.1007/978-3-642-10546-3\_8",

language = "English",

isbn = "9783642105456",

series = "Communications in Computer and Information Science",

pages = "56--64",

editor = "Dominik Slezak and Pal, \{Sankar K.\} and Byeong-Ho Kang and Junzhong Gu and Hideo Kuroda and Tai-hoon Kim",

booktitle = "Signal Processing, Image Processing and Pattern Recognition",

}

Sadek, S, Al-Hamadi, A, Michaelis, B & Sayed, U 2009, An efficient approach for region-based image classification and retrieval. in D Slezak, SK Pal, B-H Kang, J Gu, H Kuroda & T Kim (eds), Signal Processing, Image Processing and Pattern Recognition: International Conference, SIP 2009, Held as Part of the Future Generation Information Technology Conference, FGIT 2009, Jeju Island, Korea. Communications in Computer and Information Science, vol. 61, pp. 56-64. https://doi.org/10.1007/978-3-642-10546-3_8

An efficient approach for region-based image classification and retrieval. / Sadek, Samy; Al-Hamadi, Ayoub; Michaelis, Bernd et al.
Signal Processing, Image Processing and Pattern Recognition: International Conference, SIP 2009, Held as Part of the Future Generation Information Technology Conference, FGIT 2009, Jeju Island, Korea. ed. / Dominik Slezak; Sankar K. Pal; Byeong-Ho Kang; Junzhong Gu; Hideo Kuroda; Tai-hoon Kim. 2009. p. 56-64 (Communications in Computer and Information Science; Vol. 61).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - An efficient approach for region-based image classification and retrieval

AU - Sadek, Samy

AU - Al-Hamadi, Ayoub

AU - Michaelis, Bernd

AU - Sayed, Usama

PY - 2009

Y1 - 2009

N2 - In this paper, a fast and efficient approach for region-based image classification and retrieval using multi-level neural network model is proposed. The advantages of this particular model in image classification and retrieval domain will be highlighted. The proposed approach accomplishes its goal in two main steps. First, by aid of a mean-shift based segmentation algorithm, significant regions of the image are isolated. Then, features of these regions are extracted and then classified by the multi-level model into five categories, i.e., "Sky", "Building", "Sand\Rock", "Grass" and "Water". Features extraction is done by using color moments and 2D wavelets decomposition technique. Experimental results show that the proposed approach can achieve precision of better than 93% that justifies the viability of the proposed approach compared with other state-of-the-art classification and retrieval approaches.

AB - In this paper, a fast and efficient approach for region-based image classification and retrieval using multi-level neural network model is proposed. The advantages of this particular model in image classification and retrieval domain will be highlighted. The proposed approach accomplishes its goal in two main steps. First, by aid of a mean-shift based segmentation algorithm, significant regions of the image are isolated. Then, features of these regions are extracted and then classified by the multi-level model into five categories, i.e., "Sky", "Building", "Sand\Rock", "Grass" and "Water". Features extraction is done by using color moments and 2D wavelets decomposition technique. Experimental results show that the proposed approach can achieve precision of better than 93% that justifies the viability of the proposed approach compared with other state-of-the-art classification and retrieval approaches.

KW - Content-based image retrieval

KW - Feature extraction

KW - Multi-level neural networks

KW - Wavelets decomposition

UR - http://www.scopus.com/inward/record.url?scp=77952262634&partnerID=8YFLogxK

U2 - 10.1007/978-3-642-10546-3_8

DO - 10.1007/978-3-642-10546-3_8

M3 - Conference contribution

AN - SCOPUS:77952262634

SN - 9783642105456

T3 - Communications in Computer and Information Science

SP - 56

EP - 64

BT - Signal Processing, Image Processing and Pattern Recognition

A2 - Slezak, Dominik

A2 - Pal, Sankar K.

A2 - Kang, Byeong-Ho

A2 - Gu, Junzhong

A2 - Kuroda, Hideo

A2 - Kim, Tai-hoon

ER -

Sadek S, Al-Hamadi A, Michaelis B, Sayed U. An efficient approach for region-based image classification and retrieval. In Slezak D, Pal SK, Kang BH, Gu J, Kuroda H, Kim T, editors, Signal Processing, Image Processing and Pattern Recognition: International Conference, SIP 2009, Held as Part of the Future Generation Information Technology Conference, FGIT 2009, Jeju Island, Korea. 2009. p. 56-64. (Communications in Computer and Information Science). doi: 10.1007/978-3-642-10546-3_8

An efficient approach for region-based image classification and retrieval

Abstract

Publication series

Keywords

Access to Document

Other files and links

Fingerprint

Cite this