Segmentation of 3D textured images using continuous wavelet transform

Chun Shien Lu, Wen Liang Hwang, Pau Choo Chung

Research output: Contribution to conferencePaper

2 Citations (Scopus)

Abstract

A common assumption of the shape from texture problem is that a perceived image mainly contains only one type of texture with the same surface orientation. Unfortunately, a natural image is often composed of more than one textures. In order to solve the shape from texture problem in a practical manner, we need to segment 3D textured images. In this paper, we propose a new algorithm for the task. We estimate the local surface orientations from the the scales of the ridge points of continuous wavelet transform. Then, the local surface orientations are used as the features for texture segmentation. Textured images synthesized from Brodatz's album and several natural images demonstrate the performance of our method.

Original languageEnglish
Pages235-238
Number of pages4
Publication statusPublished - 1997 Dec 1
EventProceedings of the 1997 International Conference on Image Processing. Part 2 (of 3) - Santa Barbara, CA, USA
Duration: 1997 Oct 261997 Oct 29

Other

OtherProceedings of the 1997 International Conference on Image Processing. Part 2 (of 3)
CitySanta Barbara, CA, USA
Period97-10-2697-10-29

Fingerprint

Wavelet transforms
Textures

All Science Journal Classification (ASJC) codes

  • Hardware and Architecture
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Cite this

Lu, C. S., Hwang, W. L., & Chung, P. C. (1997). Segmentation of 3D textured images using continuous wavelet transform. 235-238. Paper presented at Proceedings of the 1997 International Conference on Image Processing. Part 2 (of 3), Santa Barbara, CA, USA, .
Lu, Chun Shien ; Hwang, Wen Liang ; Chung, Pau Choo. / Segmentation of 3D textured images using continuous wavelet transform. Paper presented at Proceedings of the 1997 International Conference on Image Processing. Part 2 (of 3), Santa Barbara, CA, USA, .4 p.
@conference{2adc28232ee94ae3b1d4abf580bd87a9,
title = "Segmentation of 3D textured images using continuous wavelet transform",
abstract = "A common assumption of the shape from texture problem is that a perceived image mainly contains only one type of texture with the same surface orientation. Unfortunately, a natural image is often composed of more than one textures. In order to solve the shape from texture problem in a practical manner, we need to segment 3D textured images. In this paper, we propose a new algorithm for the task. We estimate the local surface orientations from the the scales of the ridge points of continuous wavelet transform. Then, the local surface orientations are used as the features for texture segmentation. Textured images synthesized from Brodatz's album and several natural images demonstrate the performance of our method.",
author = "Lu, {Chun Shien} and Hwang, {Wen Liang} and Chung, {Pau Choo}",
year = "1997",
month = "12",
day = "1",
language = "English",
pages = "235--238",
note = "Proceedings of the 1997 International Conference on Image Processing. Part 2 (of 3) ; Conference date: 26-10-1997 Through 29-10-1997",

}

Lu, CS, Hwang, WL & Chung, PC 1997, 'Segmentation of 3D textured images using continuous wavelet transform' Paper presented at Proceedings of the 1997 International Conference on Image Processing. Part 2 (of 3), Santa Barbara, CA, USA, 97-10-26 - 97-10-29, pp. 235-238.

Segmentation of 3D textured images using continuous wavelet transform. / Lu, Chun Shien; Hwang, Wen Liang; Chung, Pau Choo.

1997. 235-238 Paper presented at Proceedings of the 1997 International Conference on Image Processing. Part 2 (of 3), Santa Barbara, CA, USA, .

Research output: Contribution to conferencePaper

TY - CONF

T1 - Segmentation of 3D textured images using continuous wavelet transform

AU - Lu, Chun Shien

AU - Hwang, Wen Liang

AU - Chung, Pau Choo

PY - 1997/12/1

Y1 - 1997/12/1

N2 - A common assumption of the shape from texture problem is that a perceived image mainly contains only one type of texture with the same surface orientation. Unfortunately, a natural image is often composed of more than one textures. In order to solve the shape from texture problem in a practical manner, we need to segment 3D textured images. In this paper, we propose a new algorithm for the task. We estimate the local surface orientations from the the scales of the ridge points of continuous wavelet transform. Then, the local surface orientations are used as the features for texture segmentation. Textured images synthesized from Brodatz's album and several natural images demonstrate the performance of our method.

AB - A common assumption of the shape from texture problem is that a perceived image mainly contains only one type of texture with the same surface orientation. Unfortunately, a natural image is often composed of more than one textures. In order to solve the shape from texture problem in a practical manner, we need to segment 3D textured images. In this paper, we propose a new algorithm for the task. We estimate the local surface orientations from the the scales of the ridge points of continuous wavelet transform. Then, the local surface orientations are used as the features for texture segmentation. Textured images synthesized from Brodatz's album and several natural images demonstrate the performance of our method.

UR - http://www.scopus.com/inward/record.url?scp=0031378543&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031378543&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0031378543

SP - 235

EP - 238

ER -

Lu CS, Hwang WL, Chung PC. Segmentation of 3D textured images using continuous wavelet transform. 1997. Paper presented at Proceedings of the 1997 International Conference on Image Processing. Part 2 (of 3), Santa Barbara, CA, USA, .