Defect Image Segmentation Research Articles

An efficient unsupervised approach for textile defect detection through unifying texture reconstruction and semantic localization

Deep learning has shown promise in textile defect detection, but its reliance on large high-quality labeled datasets poses challenges in real-world industrial applications. This study presents a novel unsupervised defect detection framework that effectively detects various types of texture defects with limited defect-free texture samples. The framework integrates texture and semantic information using a bilateral-branch network architecture (TSUBB-Net). Specifically, TSUBB-Net employs a weighted centering loss to cluster complex texture units, emphasizing semantic information within defect regions through a channel attention mechanism. It further fuses contextual semantic information to achieve precise defect localization. Thus, the efficient fusion method combines texture and semantic information, enabling the representation of complex texture structures and mitigating the impact of image acquisition quality on defect recognition. To evaluate the effectiveness of our proposed method, we build a unique dedicated database of textile defect image segmentation, which serves as the benchmark for textile defect detection. Experimental results demonstrate that TSUBB-Net surpasses state-of-the-art methods, exhibiting excellent performance in textile defect detection. The proposed framework holds significant potential for practical applications in the textile industry, improving defect detection capabilities.

Investigation into defect image segmentation algorithms for galvanised steel sheets under texture backgrounds

Image segmentation is a significant step in image analysis and computer vision. Many entropy-based approaches have been presented on this topic. Among them, Tsallis entropy is one of the best-performing methods. In this paper, the surface defect images of galvanised steel sheets were studied. A two-dimensional asymmetric Tsallis cross-entropy image segmentation algorithm based on chaotic bee colony algorithm optimisation was used to investigate the segmentation of surface defects under complex texture backgrounds. On the basis of Tsallis entropy threshold segmentation, a more concise expression form was used to define the asymmetric Tsallis cross-entropy in order to reduce the calculation complexity of the algorithm. The chaotic algorithm was combined with the artificial bee colony (ABC) algorithm to construct the chaotic bee colony algorithm, so that the optimal threshold of Tsallis entropy could be quickly identified. The experimental results showed that compared with the maximum Shannon entropy algorithm, the calculation time of this algorithm decreased by about 58% and the threshold value increased by about (26%, 54%). Compared with the two-dimensional Tsallis cross-entropy algorithm, the calculation time of this algorithm decreased by about 35% and about 20% was improved in the g-axis direction only. Compared with the two-dimensional asymmetric Tsallis cross-entropy algorithm, the calculation time of this algorithm decreased by about 30% and the threshold values of the two algorithms were almost the same. The algorithm proposed in this paper can rapidly and effectively segment defect targets, making it a more suitable method for detecting surface defects in factories with a rapid production pace.

The Application of Convolutional Neural Networks (CNNs) to Recognize Defects in 3D-Printed Parts.

Cracks and pores are two common defects in metallic additive manufacturing (AM) parts. In this paper, deep learning-based image analysis is performed for defect (cracks and pores) classification/detection based on SEM images of metallic AM parts. Three different levels of complexities, namely, defect classification, defect detection and defect image segmentation, are successfully achieved using a simple CNN model, the YOLOv4 model and the Detectron2 object detection library, respectively. The tuned CNN model can classify any single defect as either a crack or pore at almost 100% accuracy. The other two models can identify more than 90% of the cracks and pores in the testing images. In addition to the application of static image analysis, defect detection is also successfully applied on a video which mimics the AM process control images. The trained Detectron2 model can identify almost all the pores and cracks that exist in the original video. This study lays a foundation for future in situ process monitoring of the 3D printing process.

基于改进生成对抗网络的铝板缺陷电涡流检测图像分割

基于改进生成对抗网络的铝板缺陷电涡流检测图像分割

Electrowetting defect image segmentation based on improved Otsu method

Aiming at the effect of pixel defects on the display of electrowetting electronic paper, an automatic threshold detection method based on Otsu is proposed to detect defects. Otsu is a commonly used automatic threshold method that gives satisfactory results when the image histogram is bimodal. However, the electrowetting defect image histogram is usually a single peak, and Otsu method fails. Electrowetting differs from the background contrast due to the filling inks of different colors, making segmentation more difficult. In this paper, the weighting coefficient is introduced before the target variance, and the weight decreases as the cumulative probability of defects increases. The weight keeps a large value before the threshold crosses the peak, and the weight decreases after the peak, ensuring that the threshold is always to the left of the peak in the case of a single peak. The experimental results show that the proposed method can effectively segment the electrowetting defect region, especially in the electrowetting defect image with lower contrast ratio. The method is closer to 0 compared to the ME value of Otsu, VE, WOV and entropy weighting methods. The proposed method has a better segmentation effect.

Application of Phase Congruency n the Image Segmentation of Greige Defects

In view of that the texture interferes with image segmentation of the greige defect, a greige defect image segmentation method based on phase consistency is proposed. Firstly, the phase consistency algorithm is analyzed. Secondly, the phase consistency algorithm is improved based on the characteristics of the greige defect image. Then, adaptive double threshold is adopted, and the image segmentation for the contour image extracted by phase consistency based on Otsu algorithm is carried out. Finally, the experimental verification is carried out. The experimental results show the validity of the method.

An Adaptive Background Adjusting Algorithm for Rail Surface Defect Image Segmentation

Aiming at the problem of false segmentation caused by the change of illumination and properties of surface reflection when extracting rail surface defects, this paper proposes an adaptive background adjusting algorithm for rail surface defect image segmentation based on the background subtraction method. Firstly, a new similarity measure is proposed by combining Coefficient of Variation (CV) of the pixel gray level with the non-local normalization factor in the image. Secondly, by adjusting the size of window for neighborhood averaging adaptively according to the similarity measurement results, the background image model is established. Finally, the image subtraction operation is made and the segmentation of rail surface defect is realized by setting up dynamic threshold value for the differential image. The experimental results show that this method has a good effect on segmentation of both block and linear defects distributed discretely in the image.

Wood Surface Defect Image Segmentation Method based on Canny Operator and GGAC Model of Reaction Diffusion Equation

GGAC is an improvement based on geodesic active contour model (GAC). GGAC model is a widely used method for image segmentation. But, it will be difficult to achieve satisfactory segmentation results to the texture, uneven structure, edge particles, weak edge and other features of the wood surface image. Therefore, the author proposes a segmentation method that integrates the improved Canny edge detection result integrated into the improved GGAC model redrawing boundary stop function, and uses the improved variational level set method to achieve the numerical solution. The algorithm has reduced the choice sensitivity to the initial contour and enhanced the scalability, which can make the profile curve converge to defect edges more rapidly, avoid the local optimum, and improve segmentation effects of weak edges and uneven image. The results are clearer, more consistent and real-time. It has provided a more effective way to segment the wood surface defects, and broadened the application scope of Canny operator and an improved geodesic active contour model.

基于改进Chan-Vese模型的液晶显示屏Mura缺陷分割

基于改进Chan-Vese模型的液晶显示屏Mura缺陷分割

Fabric defect image segmentation based on the visual attention mechanism of the wavelet domain

In order to explore the accurate image segmentation of fabric defects, we will introduce the visual attention mechanism of the wavelet domain to the dynamic detection of fabric defects. First of all, feature maps are formed by extracting simple features from a collection image. Secondly, feature maps by multi-layer wavelet decomposition are decomposed into a lot of feature sub-maps of the wavelet domain. On this basis, the center-surround operator among feature sub-maps of the wavelet domain is adopted to build the feature difference sub-maps, which are fused into feature saliency maps through fuse strategy. Finally, the defect interest areas are segmented based on the maximum between-cluster variance method in saliency maps, and the fabric defects through the region growing method are detected in the defect interest areas. Comparing with the wavelet transform algorithm, experimental results show that the proposed method is able to segment the defect information completely, and it has a strong ability to resist noise interference, which can improve the accuracy of defect detection.

Research of Postprocessing Algorithm after Fabric Defect Image Segmentation Based on Downsampling

This paper research the algorithm after image segmentation based on using downsampling to preprocess the image and Otsu to segment the image, because defect region is weakened in the process of preprocessing to remove the texture, which lead to the defect region in the binary image can not reflect the original defect information. In view of this shortcoming, this paper put forward a new method to link the different connected regions which belong to a defect region and the new method solve the problem of weakening the defect region in the process of preprocessing, and then the integral information of defect region can be obtained. At last, the experiments’ results prove the validity of the arithmetic in this paper.

Fabric defect detection method based on texture structure analysis

A new fabric defect segmentation was proposed based on texture structure analysis in this paper.Firstly in accordance with the characteristics of the well-regulated texture,texture primitive template was calculated using auto-correlation function and defect image was enhanced using difference between each texture primitive and primitive template.Secondly local roughness of texture image was calculated to locate defect,and defect image was segmented using threshold value gained according to Otsu's approach to detect fabric defect.Lastly validity and robustness of this approach is proved by different fabric defect image segmentation in our experiment.