A Simplified pulse-coupled neural network for adaptive segmentation of fabric defects

Shi, Meihong; Jiang, Shoushan; Wang, Huiran; Xu, Bugao

doi:10.1007/s00138-007-0113-z

Cited by 30 publications

(17 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This equation means that for two neurons C ij and C kl , the more similar the two neuron gray scales are, the smaller the gray difference between them is, the larger the weight coefficient W ijkl is. And the influence from neighboring neuron is in inverse proportion to the spatial distance (Shi et al, 2009). …”

Section: Adaptive Parameters Determinationmentioning

confidence: 99%

See 1 more Smart Citation

Adaptive detection of weft-knitted fabric defects based on machine vision system

Sun

Long

2011

TJTI

View full text Add to dashboard Cite

This paper describes a machine vision system for the detection of weft-knitted fabric defects based on an adaptive pulse-coupled neural network (PCNN) and Ridgelet transform. In order to classify defects according to their different texture features, two methods are implemented: an improved PCNN method to segment the defects such as hole and dropped stitch from background image and a Ridgelet transform method based on wavelet analysis to identify the defect such as course mark. In implementing the PCNN model, necessary parameters of PCNN model such as linking coefficient, connection weight, and iteration number are automatically calculated in accordance with the spatial distance of neurons, mean, and variance value of whole image, and the cross-entropy criterion. The function of Ridgelet transform is to identify the straight line marks and fit the regression equation for simulating the course mark in the image. The Ridgelet transform model can be simplified as the combination of Radon and wavelet transforms. The parameters of detected line are acquired by wavelet analysis in Fourier semicircle region. The experiment materials were several plain and interlocked weft-knitted fabrics with hole, dropped stitch, and course mark defects. The fabric images were captured by an area-scan camera with a resolution of 600 × 800 pixels, and signal processing was controlled by a digital signal processing multiprocessor on the inspection machine. The validation tests proved that the system performed well.

show abstract

Section: Adaptive Parameters Determinationmentioning

confidence: 99%

“…Also, more novel algorithms have been adopted to segment the defects such as cellular neural network, pulse-coupled neural network (PCNN), etc. (Shi, Jiang, Wang, & Xu, 2009;Sun & Long, 2009). However, the determination for parameters of those methods is still being studied.…”

Section: Introductionmentioning

confidence: 96%

Adaptive detection of weft-knitted fabric defects based on machine vision system

Sun

Long

2011

TJTI

View full text Add to dashboard Cite

show abstract

“…In view of this, [3][4] utilized Gabor filter transformation which is highly suitable for texture image analysis to attain the goal of defect inspection and recognition. Neural network means the simulation of the function of biological neurons whose most distinguishing characteristic being the capability to approximate to any complicated linear relations as well as dynamically adjust network parameters by learning, so [5][6] applied this method in defect inspection. In this paper, computer vision technology is exploited to complete the detection of the common fabric defects such as broken ends, missing picks, oil stain and holes.…”

Section: Introductionmentioning

confidence: 99%

Fabric Defect Detection Based on Computer Vision

Sun

Zhou

2011

Artificial Intelligence and Computational Intelligence

View full text Add to dashboard Cite

Abstract. Broken ends, missing picks, oil stain and holes are the most common fabric defects. To deal with the situation that manual fabric detection will affected by the subjective factors of inspectors, an automatic computer vision based fabric defect detection method is introduced in this paper. The system uses threshold segmentation method to identify if there are any defects existed in the fabric, adopts image feature based approach to recognize oil stain and holes, and uses training based technique to detect broken ends and missing picks. Experimental results show that the proposed approach has the advantage of easy implementation, high inspection speed, good noise immunity, greatly meeting the needs for automatic fabric defect inspection.

show abstract

“…If a multicolored fabric contains irregular color patterns, colorfastness evaluation must rely on color segmentation and is performed on distinctive color regions separately . Neural network‐based segmentation techniques were also applied to cotton fiber color grading and weave defect detection . In the painting conservation, color segmentation techniques can help conservators to analyze severity of color deterioration and to evaluate the impact of environment parameters (light, humidity, and temperature) on different pigments .…”

Section: Introductionmentioning

confidence: 99%

“…3 Neural network-based segmentation techniques were also applied to cotton fiber color grading 4 and weave defect detection. 5 In the painting conservation, color segmentation techniques can help conservators to analyze severity of color deterioration and to evaluate the impact of environment parameters (light, humidity, and temperature) on different pigments. 6 In some types of medical images, for example, X-ray, magnetic resonance imaging, ultrasonography and endoscopy images, complex and intricate inner body structures are indicated by different colors and thus can be discerned with color segmentation techniques to locate tumors and other pathologies, 7,8 to measure tissue volumes, 9 or to diagnose anatomical structures.…”

Section: Introductionmentioning

confidence: 99%

Color segmentation in multicolor images using node‐growing self‐organizing map

Ouyang

Yuan

2018

Color Research & Application

Self Cite

View full text Add to dashboard Cite

This article presents a clustering algorithm based on node‐growing self‐organizing map (NGSOM) to classify colors on color images automatically and accurately partition the regions of different colors for color measurement. Based on the CIEDE2000 criterion, pixels in a multicolor image are grouped into a number of visually distinguishable color regions in which pixel distribution information is provided as the input of the NGSOM network for further segmentation. As an unsupervised clustering algorithm, the NGSOM randomly selects two initial nodes from the input source without a predefined network structure and grows nodes according to color differences between the first best matching unit (FBMU) and the second best matching unit (SBMU) of the current input data. Unlike a traditional SOM, the NGSOM utilizes learning rates varying with the pixel distributions of major color regions. The node‐growing procedure is terminated when all the input data are examined. Compared with some commonly used color clustering algorithms, the proposed algorithm possesses a better peak signal‐to‐noise ratio (PSNR) and higher time efficiency. The NGSOM can be used for a wide range of applications, including fabric colorfastness assessment, painting conservation, and scenic identification in aerial images.

show abstract

A Simplified pulse-coupled neural network for adaptive segmentation of fabric defects

Cited by 30 publications

References 10 publications

Adaptive detection of weft-knitted fabric defects based on machine vision system

Adaptive detection of weft-knitted fabric defects based on machine vision system

Fabric Defect Detection Based on Computer Vision

Color segmentation in multicolor images using node‐growing self‐organizing map

Contact Info

Product

Resources

About