Welding visual detection method and device based on convolutional neural network
A convolutional neural network and visual detection technology, applied in the field of crawlers, can solve problems such as the difficulty of explicit feature extraction and the inability to guarantee accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0074] The present invention will be further described below in conjunction with the drawings.
[0075] Reference Figure 1 ~ Figure 7 , A welding visual inspection method based on convolutional neural network, including the following processes:
[0076] In the training phase, it is first necessary to collect training samples. In this embodiment, a total of 10,000 training samples are collected. Among these 10,000 samples, 500 are welding defect pictures, and the remaining 9,500 are the aforementioned 500 welding defect pictures. Adding Gaussian white noise, picture rotation, color transformation, translation, contrast stretching, flipping and other image processing methods to obtain welding defect pictures. Then input these samples into the convolutional neural network for training, and obtain the connection weight and bias value of the convolutional neural network.
[0077] In this embodiment, the structure of the convolutional neural network adopts image 3 In the structure show...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap