For a long time, the detection and extraction of printed surfacedefects has been a hot issue in the print industry. Nowadays, defect detectionof a large number of products still relies on traditional image processinga...For a long time, the detection and extraction of printed surfacedefects has been a hot issue in the print industry. Nowadays, defect detectionof a large number of products still relies on traditional image processingalgorithms such as scale invariant feature transform (SIFT) and orientedfast and rotated brief (ORB), and researchers need to design algorithms forspecific products. At present, a large number of defect detection algorithmsbased on object detection have been applied but need lots of labeling sampleswith defects. Besides, there are many kinds of defects in printed surface,so it is difficult to enumerate all defects. Most defect detection based onunsupervised learning of positive samples use generative adversarial networks(GAN) and variational auto-encoders (VAE) algorithms, but these methodsare not effective for complex printed surface. Aiming at these problems, Inthis paper, an unsupervised defect detection and extraction algorithm forprinted surface based on positive samples in the complex printed surface isproposed innovatively. We propose a kind of defect detection and extractionnetwork based on image matching network. This network is divided into thefull convolution network of feature points extraction, and the graph attentionnetwork using self attention and cross attention. Though the key pointsextraction network, we can get robustness key points in the complex printedimages, and the graph network can solve the problem of the deviation becauseof different camera positions and the influence of defect in the differentproduction lines. Just one positive sample image is needed as the benchmarkto detect the defects. The algorithm in this paper has been proved in “TheFirst ZhengTu Cup on Campus Machine Vision AI Competition” and gotexcellent results in the finals. We are working with the company to apply it inproduction.展开更多
FDM （fused deposition modeling） has become popular among Additive Manufacturing technologies due to its speed, geometric scalability, and low cost; however, the primitive nature of the FDM build surface fundamentall...FDM （fused deposition modeling） has become popular among Additive Manufacturing technologies due to its speed, geometric scalability, and low cost; however, the primitive nature of the FDM build surface fundamentally limits the utility of FDM in terms of reliability, autonomy, and material selection. Currently, FDM relies on adhesive forces between the first layer of a print and the build surface; depending on the materials involved, this adhesive bond may or may not be reliable. Thermal contraction between the build plate and build materials can break that bond, which causes warpage and delamination of the part from the build surface and subsequent failure of the part. Furthermore, with each print, the user must use tools or manual maneuvering to separate the printed part from the build surface as well as retexture or replace the used build surface. In this paper, we present a novel build platform that allows for a mechanical bond between the print and build surface by using dovetail-shaped features. The first layer of the print flows into the features and becomes mechanically captivated by the build platform. Once the print is completed, the platform is rolled or flexed open to release the part from the mechanical bond. This design not only lowers the risk of delamination during printing but also eliminates the need for a user to reset or replace the build surface between print jobs. The effectiveness of each geometry was determined by measuring the distance at the pinch point compared to the distance that the extrusion filled below the pinch point. The captivation ratio was measured to compare the different geometries tested and determine which direction of extrusion creates a better ratio.展开更多
基金This work is supported by the National Natural Science Foundation of China(61976028,61572085,61806026,61502058).
文摘For a long time, the detection and extraction of printed surfacedefects has been a hot issue in the print industry. Nowadays, defect detectionof a large number of products still relies on traditional image processingalgorithms such as scale invariant feature transform (SIFT) and orientedfast and rotated brief (ORB), and researchers need to design algorithms forspecific products. At present, a large number of defect detection algorithmsbased on object detection have been applied but need lots of labeling sampleswith defects. Besides, there are many kinds of defects in printed surface,so it is difficult to enumerate all defects. Most defect detection based onunsupervised learning of positive samples use generative adversarial networks(GAN) and variational auto-encoders (VAE) algorithms, but these methodsare not effective for complex printed surface. Aiming at these problems, Inthis paper, an unsupervised defect detection and extraction algorithm forprinted surface based on positive samples in the complex printed surface isproposed innovatively. We propose a kind of defect detection and extractionnetwork based on image matching network. This network is divided into thefull convolution network of feature points extraction, and the graph attentionnetwork using self attention and cross attention. Though the key pointsextraction network, we can get robustness key points in the complex printedimages, and the graph network can solve the problem of the deviation becauseof different camera positions and the influence of defect in the differentproduction lines. Just one positive sample image is needed as the benchmarkto detect the defects. The algorithm in this paper has been proved in “TheFirst ZhengTu Cup on Campus Machine Vision AI Competition” and gotexcellent results in the finals. We are working with the company to apply it inproduction.
文摘FDM （fused deposition modeling） has become popular among Additive Manufacturing technologies due to its speed, geometric scalability, and low cost; however, the primitive nature of the FDM build surface fundamentally limits the utility of FDM in terms of reliability, autonomy, and material selection. Currently, FDM relies on adhesive forces between the first layer of a print and the build surface; depending on the materials involved, this adhesive bond may or may not be reliable. Thermal contraction between the build plate and build materials can break that bond, which causes warpage and delamination of the part from the build surface and subsequent failure of the part. Furthermore, with each print, the user must use tools or manual maneuvering to separate the printed part from the build surface as well as retexture or replace the used build surface. In this paper, we present a novel build platform that allows for a mechanical bond between the print and build surface by using dovetail-shaped features. The first layer of the print flows into the features and becomes mechanically captivated by the build platform. Once the print is completed, the platform is rolled or flexed open to release the part from the mechanical bond. This design not only lowers the risk of delamination during printing but also eliminates the need for a user to reset or replace the build surface between print jobs. The effectiveness of each geometry was determined by measuring the distance at the pinch point compared to the distance that the extrusion filled below the pinch point. The captivation ratio was measured to compare the different geometries tested and determine which direction of extrusion creates a better ratio.
