TOFD Defect Image Recognition Based on YOLOv7
نویسندگان
چکیده
Abstract Welding technology is an important link in shipbuilding, and ultrasonic diffraction time difference method one of its inspection means, but the identification TOFD image still mainly relies on manual evaluation. In this paper, order to solve problems low accuracy unbalanced categories defect recognition existing automatic research, by reclassifying defects into primary defects, secondary tertiary according degree harm weld, constituting a dataset containing 934 images, then using YOLOv7 model, adding mixup enhancement combined with mosaic enhancement, The mAP value improved model was about 42% 93.41% compared original AP0.5 values for were 30%, 38%, 58% respectively, introducing CBAM attention mechanism optimize insufficient data sample size imbalance between foreground background; AP 0.75 16%, 45%, model; detection speed 7.8 sheets per second.
منابع مشابه
Research on Defect Image Enhancement in Ultrasonic TOFD Detection
when testing the defect by ultrasonic time of flight diffraction (TOFD), the image signal detected is often reshaped and resulted in inaccuracy of defect measurements because the probe beam has a limited range. This paper proposed an image enhancement method based on synthetic aperture focusing technique (SAFT). A mathematical model of testing image was first established based on the generation...
متن کاملImage Defect Recognition Based on 'Super Fuzzy' Characteristic
In this paper, we propose a new defects recognition algorithm for dynamic image based on “super fuzzy” feature. With this algorithm, the image is divided into some variable windows, and the eigenvector of each window is constructed. We introduce “super fuzzy” vector to make window vectors “super fuzzy” processing, thus the window feature has “super fuzzy” characteristic with the difference of t...
متن کاملResearch on Chips’ Defect Extraction Based on Image-matching
Image-matching is a basic task in image procession used to (geometrically) match two or more images such as different times, different sensors and different view points. Improved image-matching technology has been widely applied in medical image, remote sensing image, computer vision military and so on. What put forward at the present can be most divided into matching method based on gray and f...
متن کاملDynamic Gesture Recognition based on Image Sequence
This paper proposed an algorithm for 3D hands tracking on the learned hierarchical latent variable space, which employs a Hierarchical Gaussian Process Latent Variable Model(HGPLVM) to learn the hierarchical latent space of hands motion and the nonlinear mapping from the hierarchical latent space to the pose space simultaneously. Nonlinear mappings from the hierarchical latent space to the spac...
متن کاملHorror Image Recognition Based on Emotional Attention
Along with the ever-growing Web, people benefit more and more from sharing information. Meanwhile, the harmful and illegal content, such as pornography, violence, horror etc., permeates the Web. Horror images, whose threat to children’s health is no less than that from pornographic content, are nowadays neglected by existing Web filtering tools. This paper focuses on horror image recognition, w...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Journal of physics
سال: 2023
ISSN: ['0022-3700', '1747-3721', '0368-3508', '1747-3713']
DOI: https://doi.org/10.1088/1742-6596/2560/1/012047