Neural network combines with a rotational invariant feature set in texture classification

Yongping Zhang; Ruili Wang

doi:10.1007/978-3-540-28633-2_47

Neural network combines with a rotational invariant feature set in texture classification

Yongping Zhang, Ruili Wang

Research output: Journal Publication › Conference article › peer-review

Abstract

In this paper, a new combine method for texture description is introduced, which has successfully applied to pollen surface image discrimination in combination with a multilayer perceptron (MLP) neural network. Through wavelet decomposition and a details reconstruction process, a set of rotation invariant statistic features was formed to characterize textures. In this method, the joint probability of a grey level image and its corresponding details image was calculated. By using MLP as classifier, in experiments with sixteen types of airborne pollen grains, more than 95 percent pollen images were correctly classified.

Original language	English
Pages (from-to)	436-444
Number of pages	9
Journal	Lecture Notes in Computer Science
Volume	3157
DOIs	https://doi.org/10.1007/978-3-540-28633-2_47
Publication status	Published - 2004
Externally published	Yes
Event	8th Pacific Rim International Conference on Artificial Intelligence, PRICAI 2004: Trends in Artificial Intelligence - Auckland, New Zealand Duration: 9 Aug 2004 → 13 Aug 2004

ASJC Scopus subject areas

Theoretical Computer Science
General Computer Science

Access to Document

10.1007/978-3-540-28633-2_47

Cite this

@article{8c6fb70401924dbb89f603a3c01add7e,

title = "Neural network combines with a rotational invariant feature set in texture classification",

abstract = "In this paper, a new combine method for texture description is introduced, which has successfully applied to pollen surface image discrimination in combination with a multilayer perceptron (MLP) neural network. Through wavelet decomposition and a details reconstruction process, a set of rotation invariant statistic features was formed to characterize textures. In this method, the joint probability of a grey level image and its corresponding details image was calculated. By using MLP as classifier, in experiments with sixteen types of airborne pollen grains, more than 95 percent pollen images were correctly classified.",

author = "Yongping Zhang and Ruili Wang",

year = "2004",

doi = "10.1007/978-3-540-28633-2_47",

language = "English",

volume = "3157",

pages = "436--444",

journal = "Lecture Notes in Computer Science",

issn = "0302-9743",

publisher = "Springer Science and Business Media Deutschland GmbH",

note = "8th Pacific Rim International Conference on Artificial Intelligence, PRICAI 2004: Trends in Artificial Intelligence ; Conference date: 09-08-2004 Through 13-08-2004",

}

TY - JOUR

T1 - Neural network combines with a rotational invariant feature set in texture classification

AU - Zhang, Yongping

AU - Wang, Ruili

PY - 2004

Y1 - 2004

N2 - In this paper, a new combine method for texture description is introduced, which has successfully applied to pollen surface image discrimination in combination with a multilayer perceptron (MLP) neural network. Through wavelet decomposition and a details reconstruction process, a set of rotation invariant statistic features was formed to characterize textures. In this method, the joint probability of a grey level image and its corresponding details image was calculated. By using MLP as classifier, in experiments with sixteen types of airborne pollen grains, more than 95 percent pollen images were correctly classified.

AB - In this paper, a new combine method for texture description is introduced, which has successfully applied to pollen surface image discrimination in combination with a multilayer perceptron (MLP) neural network. Through wavelet decomposition and a details reconstruction process, a set of rotation invariant statistic features was formed to characterize textures. In this method, the joint probability of a grey level image and its corresponding details image was calculated. By using MLP as classifier, in experiments with sixteen types of airborne pollen grains, more than 95 percent pollen images were correctly classified.

UR - http://www.scopus.com/inward/record.url?scp=22944471114&partnerID=8YFLogxK

U2 - 10.1007/978-3-540-28633-2_47

DO - 10.1007/978-3-540-28633-2_47

M3 - Conference article

AN - SCOPUS:22944471114

SN - 0302-9743

VL - 3157

SP - 436

EP - 444

JO - Lecture Notes in Computer Science

JF - Lecture Notes in Computer Science

T2 - 8th Pacific Rim International Conference on Artificial Intelligence, PRICAI 2004: Trends in Artificial Intelligence

Y2 - 9 August 2004 through 13 August 2004

ER -

Neural network combines with a rotational invariant feature set in texture classification

Abstract

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this