A New Algorithm for Remotely Sensed Image Texture Classification and Segmentation

Yao Wei Wang; Yan Fei Wang; Yong Xue; Wen Gao

A New Algorithm for Remotely Sensed Image Texture Classification and Segmentation

Yao Wei Wang^*
, Yan Fei Wang
, Yong Xue
, Wen Gao

^*Corresponding author for this work

CAS - Institute of Computing Technology
CAS - Institute of Remote Sensing Application
London Metropolitan University

Research output: Contribution to conference › Paper › peer-review

4 Scopus citations

Abstract

We propose a new algorithm for remotely sensed image texture classification and segmentation in this paper. We observe that the traditional method LSE is unstable in practical applications. This motivates us to develop more stable method. We have proposed the regularization technique to suppress the instability of LSE in previous research. Our contribution in this paper is that we propose a new stable method, which is based on the total variation, abbreviated TV, for reducing instability in texture analysis, and apply which to remotely sensed image texture classification and segmentation. Experiment results on remotely sensed images demonstrate our new algorithm is superior to LSE and seems promising in applications.

Original language	English
Pages	3534-3536
Number of pages	3
State	Published - 2003
Externally published	Yes
Event	2003 IGARSS: Learning From Earth's Shapes and Colours - Toulouse, France Duration: 21 Jul 2003 → 25 Jul 2003

Conference

Conference	2003 IGARSS: Learning From Earth's Shapes and Colours
Country/Territory	France
City	Toulouse
Period	21/07/03 → 25/07/03

Cite this

@conference{33d16e63d8b446dc8f7564f04dc1291e,

title = "A New Algorithm for Remotely Sensed Image Texture Classification and Segmentation",

abstract = "We propose a new algorithm for remotely sensed image texture classification and segmentation in this paper. We observe that the traditional method LSE is unstable in practical applications. This motivates us to develop more stable method. We have proposed the regularization technique to suppress the instability of LSE in previous research. Our contribution in this paper is that we propose a new stable method, which is based on the total variation, abbreviated TV, for reducing instability in texture analysis, and apply which to remotely sensed image texture classification and segmentation. Experiment results on remotely sensed images demonstrate our new algorithm is superior to LSE and seems promising in applications.",

author = "Wang, \{Yao Wei\} and Wang, \{Yan Fei\} and Yong Xue and Wen Gao",

year = "2003",

language = "英语",

pages = "3534--3536",

note = "2003 IGARSS: Learning From Earth's Shapes and Colours ; Conference date: 21-07-2003 Through 25-07-2003",

}

TY - CONF

T1 - A New Algorithm for Remotely Sensed Image Texture Classification and Segmentation

AU - Wang, Yao Wei

AU - Wang, Yan Fei

AU - Xue, Yong

AU - Gao, Wen

PY - 2003

Y1 - 2003

N2 - We propose a new algorithm for remotely sensed image texture classification and segmentation in this paper. We observe that the traditional method LSE is unstable in practical applications. This motivates us to develop more stable method. We have proposed the regularization technique to suppress the instability of LSE in previous research. Our contribution in this paper is that we propose a new stable method, which is based on the total variation, abbreviated TV, for reducing instability in texture analysis, and apply which to remotely sensed image texture classification and segmentation. Experiment results on remotely sensed images demonstrate our new algorithm is superior to LSE and seems promising in applications.

AB - We propose a new algorithm for remotely sensed image texture classification and segmentation in this paper. We observe that the traditional method LSE is unstable in practical applications. This motivates us to develop more stable method. We have proposed the regularization technique to suppress the instability of LSE in previous research. Our contribution in this paper is that we propose a new stable method, which is based on the total variation, abbreviated TV, for reducing instability in texture analysis, and apply which to remotely sensed image texture classification and segmentation. Experiment results on remotely sensed images demonstrate our new algorithm is superior to LSE and seems promising in applications.

UR - https://www.scopus.com/pages/publications/0242540911

M3 - 论文

AN - SCOPUS:0242540911

SP - 3534

EP - 3536

T2 - 2003 IGARSS: Learning From Earth's Shapes and Colours

Y2 - 21 July 2003 through 25 July 2003

ER -

A New Algorithm for Remotely Sensed Image Texture Classification and Segmentation

Abstract

Conference

Other files and links

Fingerprint

Cite this