Affine invariant texture signatures

Jianguo Zhang; Tieniu Tan

doi:10.1109/ICIP.2001.958569

Affine invariant texture signatures

Jianguo Zhang, Tieniu Tan

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

4 Citations (Scopus)

Abstract

We develop a new approach for texture classification independent of affine transforms. Based on a spectral representation of texture images under affine transform, anisotropic scale invariant signatures of the orientation spectrum distribution are extracted. A peaks distribution vector (PDV) obtained on the distribution of these signatures captures texture properties invariant to affine distortion. The PDV is used to measure the similarity between textures. Experimental results show the efficiency of the PDV for affine invariant texture classification

Original language	English
Title of host publication	Proceedings. 2001 International Conference on Image Processing
Publisher	IEEE
Pages	618-621
Number of pages	4
Volume	2
ISBN (Print)	0780367251
DOIs	https://doi.org/10.1109/ICIP.2001.958569
Publication status	Published - 2001
Event	2001 International Conference on Image Processing - Thessaloniki, Thessaloniki, Greece Duration: 7 Oct 2001 → 10 Oct 2001

Conference

Conference	2001 International Conference on Image Processing
Abbreviated title	ICIP 2001
Country/Territory	Greece
City	Thessaloniki
Period	7/10/01 → 10/10/01

Access to Document

10.1109/ICIP.2001.958569

Cite this

@inproceedings{9641643a366d48468208b3fbf36a1c58,

title = "Affine invariant texture signatures",

abstract = "We develop a new approach for texture classification independent of affine transforms. Based on a spectral representation of texture images under affine transform, anisotropic scale invariant signatures of the orientation spectrum distribution are extracted. A peaks distribution vector (PDV) obtained on the distribution of these signatures captures texture properties invariant to affine distortion. The PDV is used to measure the similarity between textures. Experimental results show the efficiency of the PDV for affine invariant texture classification",

author = "Jianguo Zhang and Tieniu Tan",

year = "2001",

doi = "10.1109/ICIP.2001.958569",

language = "English",

isbn = "0780367251 ",

volume = "2",

pages = "618--621",

booktitle = "Proceedings. 2001 International Conference on Image Processing",

publisher = "IEEE",

note = "2001 International Conference on Image Processing, ICIP 2001 ; Conference date: 07-10-2001 Through 10-10-2001",

}

TY - GEN

T1 - Affine invariant texture signatures

AU - Zhang, Jianguo

AU - Tan, Tieniu

PY - 2001

Y1 - 2001

N2 - We develop a new approach for texture classification independent of affine transforms. Based on a spectral representation of texture images under affine transform, anisotropic scale invariant signatures of the orientation spectrum distribution are extracted. A peaks distribution vector (PDV) obtained on the distribution of these signatures captures texture properties invariant to affine distortion. The PDV is used to measure the similarity between textures. Experimental results show the efficiency of the PDV for affine invariant texture classification

AB - We develop a new approach for texture classification independent of affine transforms. Based on a spectral representation of texture images under affine transform, anisotropic scale invariant signatures of the orientation spectrum distribution are extracted. A peaks distribution vector (PDV) obtained on the distribution of these signatures captures texture properties invariant to affine distortion. The PDV is used to measure the similarity between textures. Experimental results show the efficiency of the PDV for affine invariant texture classification

U2 - 10.1109/ICIP.2001.958569

DO - 10.1109/ICIP.2001.958569

M3 - Conference contribution

SN - 0780367251

VL - 2

SP - 618

EP - 621

BT - Proceedings. 2001 International Conference on Image Processing

PB - IEEE

T2 - 2001 International Conference on Image Processing

Y2 - 7 October 2001 through 10 October 2001

ER -

Affine invariant texture signatures

Abstract

Conference

Access to Document

Fingerprint

Cite this