The automatic defect detection for fabric images is an essential mission in textile industry. However, there are some inherent difficulties in the detection of fabric images, such as complexity of the background and the highly uneven scales of defects. Moreover, the trade-off between accuracy and speed should be considered in real applications. To address these problems, we propose a novel model based on YOLOv4 to detect defects in fabric images, called Feature Augmentation YOLO (FA-YOLO). In terms of network structure, FA-YOLO adds an additional detection head to improve the detection ability of small defects and builds a powerful Neck structure to enhance feature fusion. First, to reduce information loss during feature fusion, we perform the residual feature augmentation (RFA) on the features after dimensionality reduction by using 1×1 convolution. Afterward, the attention module (SimAM) is embedded into the locations with rich features to improve the adaptation ability to complex backgrounds. Adaptive spatial feature fusion (ASFF) is also applied to output of the Neck to filter inconsistencies across layers. Finally, the cross-stage partial (CSP) structure is introduced for optimization. Experimental results based on three real industrial datasets, including Tianchi fabric dataset (72.5% mAP), ZJU-Leaper fabric dataset (0.714 of average F1-score) and NEU-DET steel dataset (77.2% mAP), demonstrate the proposed FA-YOLO achieves competitive results compared to other state-of-the-art (SoTA) methods.

This paper presents an improved YOLOv3 network, named MSFF-YOLOv3, for precisely detecting variable surface defects of aluminum profiles in practice. First, we introduce a larger prediction scale to provide detailed information for small defect detection; second, we design an efficient attention-guided block to extract more features of defects with less overhead; third, we design a bottom-up pyramid and integrate it with the existing feature pyramid network to construct a twin-tower structure to improve the circulation and fusion of features of different layers. In addition, we employ the K-median algorithm for anchor clustering to speed up the network reasoning. Experimental results showed that the mean average precision of the proposed network MSFF-YOLOv3 is higher than all conventional networks for surface defect detection of aluminum profiles. Moreover, the number of frames processed per second for our proposed MSFF-YOLOv3 could meet real-time requirements.

Automatic thresholding is an important technique for rail defect detection, but traditional methods are not competent enough to fit the characteristics of this application. This paper proposes the Maximum Weighted Object Correlation (MWOC) thresholding method, fitting the features that rail images are unimodal and defect proportion is small. MWOC selects a threshold by optimizing the product of object correlation and the weight term that expresses the proportion of thresholded defects. Our experimental results demonstrate that MWOC achieves misclassification error of 0.85%, and outperforms the other well-established thresholding methods, including Otsu, maximum correlation thresholding, maximum entropy thresholding and valley-emphasis method, for the application of rail defect detection.

In this paper a novel method for the purpose of random texture defect detection using a collection of 1-D HMMs is presented. The sound textural content of a sample of training texture images is first encoded by a compressed LBP histogram and then the local patterns of the input training textures are learned, in a multiscale framework, through a series of HMMs according to the LBP codes which belong to each bin of this compressed LBP histogram. The hidden states of these HMMs at different scales are used as a texture descriptor that can model the normal behavior of the local texture units inside the training images. The optimal number of these HMMs (models) is determined in an unsupervised manner as a model selection problem. Finally, at the testing stage, the local patterns of the input test image are first predicted by the trained HMMs and a prediction error is calculated for each pixel position in order to obtain a defect map at each scale. The detection results are then merged by an inter-scale post fusion method for novelty detection. The proposed method is tested with a database of grayscale ceramic tile images.

In this paper, a 2-D iteratively reweighted least squares lattice algorithm, which is robust to the outliers, is introduced and is applied to defect detection problem in textured images. First, the philosophy of using different optimization functions that results in weighted least squares solution in the theory of 1-D robust regression is extended to 2-D. Then a new algorithm is derived which combines 2-D robust regression concepts with the 2-D recursive least squares lattice algorithm. With this approach, whatever the probability distribution of the prediction error may be, small weights are assigned to the outliers so that the least squares algorithm will be less sensitive to the outliers. Implementation of the proposed iteratively reweighted least squares lattice algorithm to the problem of defect detection in textured images is then considered. The performance evaluation, in terms of defect detection rate, demonstrates the importance of the proposed algorithm in reducing the effect of the outliers that generally correspond to false alarms in classification of textures as defective or nondefective.

This paper proposes a new supply current test method for detecting floating gate defects in CMOS ICs. In the method, unusual increase of the supply current caused by defects is promoted by superposing an AC component on the DC power supply. Feasibility of the test is examined by some experiments on four DUTs with an intentionally caused defect. The results showed that our method could detect clearly all the defects, one of which may be detected by neither any functional logic test nor any conventional supply current test.

This paper deals with the fundamental problem of automatic assessment of appearance of seam puckers on suits, and suggests possibilities for practical usage. Presently, evaluations are done by inspectors who compare standard photographs of suits to test samples. In order to avoid human errors, however, a method of automatic evaluation is desired. We process the problem as pattern recognition. As a feature we use fractal dimensions. The fractal dimensions obtained from standard photographs are used as template patterns. To make it easier to calculate fractal dimensions, we plot a curve representing the appearance of seam puckers, from which fractal dimensions of the curve can be calculated. The seam puckers in gray-scale images are confused with the material's texture, so the seam puckers must be enhanced for a precise evaluation. By using the concept of variance, we select images with seam puckers and enhance only the images with seam puckers. This is the novel aspect of this work. Twenty suits are used for the evaluation experiment and we obtain a result almost the same to the evaluation gained by inspection. That is, the evaluation of 11 samples is the same as that gained by inspection, the results of 8 samples differ by 1 grade, and the evaluation of 1 sample has a 2-grade difference. The results are also compared to the evaluation of the system using the Daubechies wavelet feature. The result of comparison shows that the present method gives a better evaluation than the system using the Daubechies wavelet.

This paper describes a defect detection method which automatically extracts defect information from complicated background LSI patterns. Based on a scanning electron microscope (SEM) image, the defects on the wafer are characterized in terms of their locations, sizes and the shape of defects. For this purpose, two image processing techniques, the Hough transform and wavelet transform, have been employed. Especially, the Hough Transform for circles is applied to non-circular defects for estimating the shapes of defects. By experiments, it has been demonstrated that the system is very effective in defect identification and will be used as an integral part in future automatic defect pattern classification systems.

We have improved the optical beam induced resistance change (OBIRCH) system so as to detect (1) a current path as small as 10-50 µA from the rear side of a chip, (2) current paths in silicide lines as narrow as 0. 2 µm, (3) high-resistance Ti-depleted polysilicon regions in 0. 2 µm wide silicide lines, and (4) high-resistance amorphous thin layers as thin as a few nanometers at the bottoms of vias. All detections were possible even in observation areas as wide as 5 mm 5 mm. The physical causes of these detections were characterized by focused ion beam and transmission electron microscopy.