Localising Surface Defects in Random Colour Textures using Multiscale Texem Analysis in Image Eigenchannels

Xie Xianghua; M Mirmehdi

Localising Surface Defects in Random Colour Textures using Multiscale Texem Analysis in Image Eigenchannels

Xie Xianghua
, M Mirmehdi

Bristol Robotics Laboratory

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

12 Citations (Scopus)

Abstract

A novel method is presented to detect defects in random colour textures which requires only a very few normal samples for unsupervised training. We decorrelate the colour image by generating three eigenchannels in each of which the surface texture image is divided into overlapping patches of various sizes. Then, a mixture model and EM is applied to reduce groupings of patches to a small number of textural exemplars, or texems. Localised defect detection is achieved by comparing the learned texems to patches in the unseen image eigenchannels.

Translated title of the contribution	Localising Surface Defects in Random Colour Textures using Multiscale Texem Analysis in Image Eigenchannels
Original language	English
Title of host publication	Unknown
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	1124 - 1127
Number of pages	3
Publication status	Published - Sept 2005

Bibliographical note

Conference Proceedings/Title of Journal: Proceedings of the 12th IEEE International Conference on Image Processing

Access to Document

http://www.cs.bris.ac.uk/Publications/pub_info.jsp?id=2000389

Handle.net

Persistent link

Cite this

@inproceedings{8d38e77ec97541f8806c11efbcd9018c,

title = "Localising Surface Defects in Random Colour Textures using Multiscale Texem Analysis in Image Eigenchannels",

abstract = "A novel method is presented to detect defects in random colour textures which requires only a very few normal samples for unsupervised training. We decorrelate the colour image by generating three eigenchannels in each of which the surface texture image is divided into overlapping patches of various sizes. Then, a mixture model and EM is applied to reduce groupings of patches to a small number of textural exemplars, or texems. Localised defect detection is achieved by comparing the learned texems to patches in the unseen image eigenchannels. ",

author = "Xie Xianghua and M Mirmehdi",

note = "Conference Proceedings/Title of Journal: Proceedings of the 12th IEEE International Conference on Image Processing",

year = "2005",

month = sep,

language = "English",

pages = "1124 -- 1127",

booktitle = "Unknown",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

address = "United States",

}

TY - GEN

T1 - Localising Surface Defects in Random Colour Textures using Multiscale Texem Analysis in Image Eigenchannels

AU - Xianghua, Xie

AU - Mirmehdi, M

N1 - Conference Proceedings/Title of Journal: Proceedings of the 12th IEEE International Conference on Image Processing

PY - 2005/9

Y1 - 2005/9

N2 - A novel method is presented to detect defects in random colour textures which requires only a very few normal samples for unsupervised training. We decorrelate the colour image by generating three eigenchannels in each of which the surface texture image is divided into overlapping patches of various sizes. Then, a mixture model and EM is applied to reduce groupings of patches to a small number of textural exemplars, or texems. Localised defect detection is achieved by comparing the learned texems to patches in the unseen image eigenchannels.

AB - A novel method is presented to detect defects in random colour textures which requires only a very few normal samples for unsupervised training. We decorrelate the colour image by generating three eigenchannels in each of which the surface texture image is divided into overlapping patches of various sizes. Then, a mixture model and EM is applied to reduce groupings of patches to a small number of textural exemplars, or texems. Localised defect detection is achieved by comparing the learned texems to patches in the unseen image eigenchannels.

M3 - Conference Contribution (Conference Proceeding)

SP - 1124

EP - 1127

BT - Unknown

PB - Institute of Electrical and Electronics Engineers (IEEE)

ER -

Localising Surface Defects in Random Colour Textures using Multiscale Texem Analysis in Image Eigenchannels

Abstract

Bibliographical note

Access to Document

Handle.net

Fingerprint

Cite this