The investment in an automated fabric defect detection system is more than economical when reduction in labor cost and associated benefits are considered. The development of a fully automated web inspection system requires robust and efficient fabric defect detection algorithms. The inspection of real fabric defects is particularly challenging due to the large number of fabric defect classes, which are characterized by their vagueness and ambiguity. Numerous techniques have been developed to detect fabric defects and the purpose of this paper is to categorize and/or describe these algorithms. This paper attempts to present the first survey on fabric defect detection techniques presented in about 160 references. Categorization of fabric defect detection techniques is useful in evaluating the qualities of identified features. The characterization of real fabric surfaces using their structure and primitive set has not yet been successful. Therefore, on the basis of the nature of features from the fabric surfaces, the proposed approaches have been characterized into three categories; statistical, spectral and model-based. In order to evaluate the state-of-the-art, the limitations of several promising techniques are identified and performances are analyzed in the context of their demonstrated results and intended application. The conclusions from this paper also suggest that the combination of statistical, spectral and model-based approaches can give better results than any single approach, and is suggested for further research.

/pdf/computer-vision-based-fabric-defect-detection-a-survey-27mr8b2pf3.pdf

Computer-Vision-Based Fabric Defect Detection: A Survey

In this paper, we systematically review recent advances in surface inspection using computer vision and image processing techniques, particularly those based on texture analysis methods. The aim is to review the state-of-the-art techniques for the purposes of visual inspection and decision making schemes that are able to discriminate the features extracted from normal and defective regions. This field is so vast that it is impossible to cover all the aspects of visual inspection. This paper focuses on a particular but important subset which generally treats visual surface inspection as texture analysis problems. Other topics related to visual inspection such as imaging system and data acquisition are out of the scope of this survey. The surface defects are loosely separated into two types. One is local textural irregularities which is the main concern for most visual surface inspection applications. The other is global deviation of colour and/or texture, where local pattern or texture does not exhibit abnormalities. We refer this type of defects as shade or tonality problem. The second type of defects have been largely neglected until recently, particularly when colour imaging system has been widely used in visual inspection and where chromatic consistency plays an important role in quality control. The emphasis of this survey though is still on detecting local abnormalities, given the fact that majority of the reported works are dealing with the first type of defects. The techniques used to inspect textural abnormalities are discussed in four categories, statistical approaches, structural approaches, filter based methods, and model based approaches, with a comprehensive list of references to some recent works. Due to rising demand and practice of colour texture analysis in application to visual inspection, those works that are dealing with colour texture analysis are discussed separately. It is also worth noting that processing vector-valued data has its unique challenges, which conventional surface inspection methods have often ignored or do not encounter. We also compare classification approaches with novelty detection approaches at the decision making stage. Classification approaches often require supervised training and usually provide better performance than novelty detection based approaches where training is only carried out on defect-free samples. However, novelty detection is relatively easier to adapt and is particularly desirable when training samples are incomplete.

/pdf/a-review-of-recent-advances-in-surface-defect-detection-1z8rcmv73x.pdf

A Review of Recent Advances in Surface Defect Detection using Texture analysis Techniques

We report the observation of unidirectional plasmon propagation in metallic nanowires over distances >10 μm. Through control of the incident excitation wavelength and rod composition, we demonstrate the selective coupling of photons into the plasmon mode of a 20 nm diameter nanowire. This mode then propagates in a nonemissive fashion down the wire length before being emitted as an elastically scattered photon at the distal end. As expected from previous studies of plasmon excitation in nanoparticles and thin films, we observe a strong wavelength and material dependence of this phenomenon. This metal-dependent plasmon propagation is exploited to produce a wire through which plasmons propagate unidirectionally. A bimetallic wire with a sharp Au/Ag heterojunction is shown to display both wavelength dependence and unidirectionality with respect to plasmon propagation across the heterojunction. It is expected that these results will contribute to the growing interest in optical energy transport in molecular-le...

Unidirectional Plasmon Propagation in Metallic Nanowires

Automated surface inspection (ASI) is a challenging task in industry, as collecting training dataset is usually costly and related methods are highly dataset-dependent. In this paper, a generic approach that requires small training data for ASI is proposed. First, this approach builds classifier on the features of image patches, where the features are transferred from a pretrained deep learning network. Next, pixel-wise prediction is obtained by convolving the trained classifier over input image. An experiment on three public and one industrial data set is carried out. The experiment involves two tasks: 1) image classification and 2) defect segmentation. The results of proposed algorithm are compared against several best benchmarks in literature. In the classification tasks, the proposed method improves accuracy by 0.66%–25.50%. In the segmentation tasks, the proposed method reduces error escape rates by 6.00%–19.00% in three defect types and improves accuracies by 2.29%–9.86% in all seven defect types. In addition, the proposed method achieves 0.0% error escape rate in the segmentation task of industrial data.

A Generic Deep-Learning-Based Approach for Automated Surface Inspection

Automated defect inspection has long been a challenging task especially in industrial applications, where collecting and labeling large amounts of defective samples are usually harsh and impracticable. In this paper, we propose an approach to detect and localize defects with only defect-free samples for model training. This approach is carried out by reconstructing image patches with convolutional denoising autoencoder networks at different Gaussian pyramid levels, and synthesizing detection results from these different resolution channels. Reconstruction residuals of the training patches are used as the indicator for direct pixelwise defect prediction, and the reconstruction residual map generated in each channel is combined to generate the final inspection result. This novel method has two prominent characteristics, which benefit the implementation of automatic defect inspection in practice. First, it is absolutely unsupervised that no human intervention is needed throughout the inspection process. Second, multimodal strategy is utilized in this method to synthesize results from multiple pyramid levels. This strategy is capable of improving the robustness and accuracy of the method. To evaluate this approach, experiments on convergence, noise immunity, and defect inspection accuracy are conducted. Furthermore, comparative tests with some excellent algorithms on actual and simulated data sets are performed. Experimental results demonstrated the effectiveness and superiority of the proposed method on homogeneous and nonregular textured surfaces.

An Unsupervised-Learning-Based Approach for Automated Defect Inspection on Textured Surfaces

Morphological operations such as erosion and opening are applied to both direct and spatially filtered images of test fabrics to identify defects. Detecting defects morpholog ically on spatially filtered images of fabrics produces better results, particularly when the fabric is fine and contains defects of small size. The diffraction pattern of the test fabric is obtained optically by illuminating it with a collimated laser beam. A spatial filter is placed at the Fourier plane to remove the periodic grating structure of the fabric from the image. Morphological operations with a critically selected structuring element are then applied to the image after suitable pre-processing.

Detecting Defects in Fabric with Laser-Based Morphological Image Processing

Face detection and recognition are the nonintrusive biometrics of choice in many security applications. Examples of their use include border control, drivers license issuance, law enforcement investigations, and physical access control. Face Detection and Recognition: Theory and Practice elaborates on and explains the theory and practice of face detection and recognition systems currently in vogue. The book begins with an introduction to the state of the art, offering a general review of the available methods and an indication of future research using cognitive neurophysiology. The text then: Explores subspace methods for dimensionality reduction in face image processing, statistical methods applied to face detection, and intelligent face detection methods dominated by the use of artificial neural networks Covers face detection with colour and infrared face images, face detection in real time, face detection and recognition using set estimation theory, face recognition using evolutionary algorithms, and face recognition in frequency domain Discusses methods for the localization of face landmarks helpful in face recognition, methods of generating synthetic face images using set estimation theory, and databases of face images available for testing and training systems Features pictorial descriptions of every algorithm as well as downloadable source code (in MATLAB/PYTHON) and hardware implementation strategies with code examples Demonstrates how frequency domain correlation techniques can be used supplying exhaustive test results Face Detection and Recognition: Theory and Practice provides students, researchers, and practitioners with a single source for cutting-edge information on the major approaches, algorithms, and technologies used in automated face detection and recognition.

Face Detection and Recognition: Theory and Practice

On propose dans cet article une combinaison diverse d'operations de nombres, a la fois binaires et ternaires, pour la soustraction et l'addition en calcul optique

New coding scheme for addition and subtraction using the modified signed-digit number representation in optical computation.

The paper proposes an improved strategy for face recognition using correlation filter under varying lighting conditions and occlusion where spatial domain preprocessing is carried out by two convolution kernels. The first convolution kernel is a contour kernel for emphasizing high frequency components of face image and the other kernel is a smoothing kernel used for minimization of noise those may arise due to preprocessing. The convolution kernels are obtained by training a generalized regression neural network using enhanced face features. Face features are enhanced by conventional principal component analysis. The proposed method reduces the false acceptance rate and false rejection rate in comparison to other standard correlation filtering techniques. Moreover, the processing is fast when compared to the existing illumination normalization techniques. A scheme of hardware implementation of all optical correlation technique is also suggested based on single spatial light modulator in a beam folding architecture. Two benchmark databases YaleB and PIE are used for performance verification of the proposed scheme and the improved results are obtained for both illumination variations and occlusions in test face images.

Generalized regression neural network trained preprocessing of frequency domain correlation filter for improved face recognition and its optical implementation

Basic morphological operations such as the erosion, dilation, opening, and closing often fail to detect various types of defects that may be present in woven fabric, mainly because of the heuristic selection of structuring element needed for these operations. In this paper, an artificial neural network (ANN) is utilized for the selection of structuring element, where ANN is trained by two pre‐assigned normalized numbers related to the warp and weft counts of the test fabric. The test gray fabric image is pre‐processed to remove noise and the interlaced grating structure of weft and warp and then converted to a binary image by thresholding. An intensity threshold value of the processed fabric image and the dimension of a sliding window needed for correlation operation are obtained from the trained ANN. Defects are detected after morphological reconstruction of the processed binary fabric image, where an ANN trained structuring element is used. The technique is tested on 317 samples for eight different type...

Asit K. Datta

Papers

Detecting Defects in Fabric with Laser-Based Morphological Image Processing

Face Detection and Recognition: Theory and Practice

New coding scheme for addition and subtraction using the modified signed-digit number representation in optical computation.

Generalized regression neural network trained preprocessing of frequency domain correlation filter for improved face recognition and its optical implementation

Neural network trained morphological processing for the detection of defects in woven fabric