New texture descriptor for high-speed Web inspection applications

Cuenca, S.; Câmara, Andréa Cruz

doi:10.1109/icip.2003.1247300

Cited by 6 publications

(8 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Performance comparison between the MSMD approaches discussed in [7] and shown in Fig. 10, in addition to the advantages of the MSMD ACFs approach (Tables 6, 7) indicate the promising performance of the MSMD ACF approach compared with MSMD other approaches.…”

Section: Discussionmentioning

confidence: 90%

“…Excellent reviews of recent advances in surface defect detection using texture analysis approaches have been provided in [2][3][4][5][6][7]. These reviews have discussed statistical-, structural-, filter-and modelbased approaches to AVI.…”

Section: Overview Of Multiscale-multidirectional Feature Extraction Amentioning

confidence: 99%

“…In Cuenca and Cámara [7], experiments on samples from TILDA [10] have shown that the MSMD-Gabor filter-based approach showed the best classification rate although their computational complexity is the highest.…”

Section: Overview Of Multiscale-multidirectional Feature Extraction Amentioning

confidence: 99%

See 2 more Smart Citations

A novel multiscale-multidirectional autocorrelation approach for defect detection in homogeneous flat surfaces

Tolba

2011

Machine Vision and Applications

View full text Add to dashboard Cite

Defect detection in flat web surface products is a challenging task. Reliable vision-based systems for detection of defects require the suitable selection of a huge set of parameters which highly impact the performance of these systems such as image resolution/scale, size of the scanning window, feature extraction, direction of scanning, classifier type and parameters and system performance evaluation measures. This paper addresses these issues and introduces a novel multi-scale and multi-directional (MSMD) autocorrelation function (ACF)-based approach for reliable defect detection and localization in homogeneous web surfaces. The proposed approach has been experimentally tested on samples from the well-known TILDA textiles database and wallboards. Performance evaluation using the system Precision, Recall (Sensitivity), Specificity, Accuracy, Youden's index, F-measure and Matthews correlation coefficient has shown that the MSMD ACF approach outperforms the state-of-theart approaches like MSMD Log-Gabor filters. The MSMD ACFs approach results in better performance indicators for defect detection than the Log-Gabor based approach in addition to being about 2-6 times faster in defect detection.

show abstract

Section: Discussionmentioning

confidence: 90%

Section: Overview Of Multiscale-multidirectional Feature Extraction Amentioning

confidence: 99%

See 1 more Smart Citation

A novel multiscale-multidirectional autocorrelation approach for defect detection in homogeneous flat surfaces

Tolba

2011

Machine Vision and Applications

View full text Add to dashboard Cite

show abstract

“…The overview given above and the results summarized in Table 2, clearly indicate that most of the comparative studies [3,[5][6][7][8][9][10][11][12][13][14] related to texture classification, texture segmentation and defect detection cannot identify an optimal set of features to perform these tasks. Some features like those based on GLCM, LBP are effective in texture characterization.…”

Section: Overview Of Existing Automated Visual Inspection Approachesmentioning

confidence: 99%

Decision Fusion for Visual Inspection of Textiles

Tolba

Khan

Mutawa

et al. 2010

Textile Research Journal

View full text Add to dashboard Cite

Automated Visual Inspection (AVI) is the process of detecting, analyzing and classifying abnormal structures in a surface using machine vision techniques. The increasing competition in the industrial sector imposes high requirements on controlling the quality of flat surface products such as textiles, paper, steel slabs, glass, plastic films, foils, parquet slabs, ceramics etc. Automation of the visual inspection process saves companies a lot of time and raises the quality of their products by avoiding the subjectivity, boredom and slowness of the traditional human-based inspection process. When a defective product reaches the consumer, the company's reputation will suffer. AVI makes 100% quality control and documentation possible. The proposed decision fusion architecture is shown in Figure 1.The paper is organized as follows: the next section gives an overview of the existing AVI approaches. Following sections describe the role of homogeneity for faster defect detection; the adaptive window sizing; the feature sets used Abstract Defect detection of textiles is a necessary requirement for quality control and customer satisfaction. This paper presents a system for decision fusion in order to enhance the accuracy of defect detection in textiles. A multi-classifier decision fusion technique based on majority voting is presented to solve the problems of sensitivity to parameter variation and to make use of the advantages of the individual feature sets for accurate texture characterization. Features based on Gray Level Co-occurrence Matrix (GLCM), Laws Energy (LE) Filter, Local Binary Patterns (LBP), HU Moment invariants, Moment of Inertia (MOI) and Standard Deviation of Gray levels are used to train a set of Learning Vector Quantization (LVQ) classifiers. Detection accuracies of classifiers trained on single-feature sets are compared with those of the majority voting among the individual classifiers. The results obtained from majority voting indicate that the decision fusion technique improves the accuracy and reliability of the detection process. Empirical results indicate the high accuracy of the presented approach. The correct defect detection rate of the proposed approach is 98.64% with an average false acceptance rate of 0.0012.

show abstract

“…A kind of common inspection method for web printing is template matching, which is to use subtraction to the image for inspecting and the standard image. Because of the tensile force it is hard to select an ideal template which may cause the imprecision of the inspection [4] .…”

Section: Introductionmentioning

confidence: 99%

High speed web printing inspection with multiple linear cameras

Shi

2011

MIPPR 2011: Remote Sensing Image Processing, Geographic Information Systems, and Other Applications

View full text Add to dashboard Cite

Purpose: To detect the defects during the high speed process of web printing, such as smudges, doctor streaks, pin holes, character misprints, foreign matters, hazing, wrinkles, etc., which are the main infecting factors to the quality of printing presswork. Methods: A set of novel machine vision system is used to detect the defects. This system consists of distributed data processing with multiple linear cameras, effective anti-blooming illumination design and fast image processing algorithm with blob searching. Also, pattern matching adapted to paper tension and snake-moving are emphasized. Results: Experimental results verify the speed, reliability and accuracy of the proposed system, by which most of the main defects are inspected at real time under the speed of 300 m/min. Conclusions: High speed quality inspection of large-size web requires multiple linear cameras to construct distributed data processing system. Also material characters of the printings should also be stressed to design proper optical structure, so that tiny web defects can be inspected with variably angles of illumination.

show abstract

New texture descriptor for high-speed Web inspection applications

Cited by 6 publications

References 6 publications

A novel multiscale-multidirectional autocorrelation approach for defect detection in homogeneous flat surfaces

A novel multiscale-multidirectional autocorrelation approach for defect detection in homogeneous flat surfaces

Decision Fusion for Visual Inspection of Textiles

High speed web printing inspection with multiple linear cameras

Contact Info

Product

Resources

About