A general approach to defect detection in textured materials using a wavelet domain model and level sets

Chan, Hung-Yam; Raju, C Heera; Sari‐Sarraf, Hamed; Héquet, Eric

doi:10.1117/12.633204

Cited by 10 publications

(9 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Though MRF models captured local spatial contextual information [52,112] in an image, feature extraction was weak at identifying small defects on fabric according to [94]. A recent method [113] has proposed a wavelet-domain Hidden Markov Tree model with a level set segmentation technique, but no detailed evaluation was given.…”

Section: Markov Random Fieldsmentioning

confidence: 99%

Automated fabric defect detection—A review

Ngan

Pang

Yung

2011

Image and Vision Computing

443

190

View full text Add to dashboard Cite

Section: Markov Random Fieldsmentioning

confidence: 99%

Automated fabric defect detection—A review

Ngan

Pang

Yung

2011

Image and Vision Computing

443

190

View full text Add to dashboard Cite

“…Cohen et al [10] suggest applying Gaussian Markov random field to model defect-free textures of fabric images. Recently, a wavelet-domain hidden Markov tree model combining with the level set segmentation technique is proposed by Chan et al [5]. However, the detection results of these methods are not very satisfying and they usually share a high computational complexity.…”

Section: Fabric Defect Detectionmentioning

confidence: 99%

“…λ is the trade-off parameter in (5). The irregularity maps with different parameters are shown in Fig.…”

Section: Parameter Insensitivitymentioning

confidence: 99%

Fabric defect inspection using prior knowledge guided least squares regression

Cao

Zhang

Wen

et al. 2015

Multimed Tools Appl

View full text Add to dashboard Cite

This paper proposes an unsupervised model to inspect various detects in fabric images with diverse textures. A fabric image with defects is usually composed of a relatively consistent background texture and some sparse defects, which can be represented as a low-rank matrix plus a sparse matrix in a certain feature space. The process is formulated as a least squares regression based subspace segmentation model, which is convex, smooth and can be solved efficiently. A simple and effective prior is also learnt from local texture features of the image itself. Instead of considering only the feature space' s global structure, the local prior is incorporated with it seamlessly by the proposed subspace segmentation model to guide and improve the segmentation. Experiments on a variety of fabric images demonstrate the effectiveness and robustness of the proposed method. Compared with existing methods, our method is more robust and locates various defects more precisely.

show abstract

“…In 2000, Baykut et al [130] applied the aforementioned GMRF method in real-time application with a dedicated DSP system. In 2005, Chan et al [128] proposed a wavelet-domain Hidden Markov Tree model with a level set segmentation technique. Recently, in [129], the authors described a defect pavement detection method, and improved a quality of image segmentation by Markov random fields and Graph cuts method with an unsupervised Random Forest learning methodology for classification.…”

Section: Model-based Approaches (Mbas)mentioning

confidence: 99%

Visual-Based Defect Detection and Classification Approaches for Industrial Applications—A SURVEY

Czimmermann

Ciuti

Milazzo

et al. 2020

Sensors

277

100

View full text Add to dashboard Cite

This paper reviews automated visual-based defect detection approaches applicable to various materials, such as metals, ceramics and textiles. In the first part of the paper, we present a general taxonomy of the different defects that fall in two classes: visible (e.g., scratches, shape error, etc.) and palpable (e.g., crack, bump, etc.) defects. Then, we describe artificial visual processing techniques that are aimed at understanding of the captured scenery in a mathematical/logical way. We continue with a survey of textural defect detection based on statistical, structural and other approaches. Finally, we report the state of the art for approaching the detection and classification of defects through supervised and non-supervised classifiers and deep learning.

show abstract

A general approach to defect detection in textured materials using a wavelet domain model and level sets

Cited by 10 publications

References 6 publications

Automated fabric defect detection—A review

Automated fabric defect detection—A review

Fabric defect inspection using prior knowledge guided least squares regression

Visual-Based Defect Detection and Classification Approaches for Industrial Applications—A SURVEY

Contact Info

Product

Resources

About