Liquid foreign matter visual detection method and system
A visual detection and foreign object technology, applied in neural learning methods, biological neural network models, image data processing, etc., can solve the problems of lack of system defect monitoring and alarm, low registration accuracy of sequence images, inaccurate detection results, etc. Conducive to adjustment and improvement, function update, and the effect of expanding production efficiency
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0062] figure 1 For the flow chart of the liquid foreign matter visual detection method according to the present invention, the following will refer to figure 1 , the method for visual detection of liquid foreign matter of the present invention will be described in detail.
[0063] First, in step 101, image registration is performed based on Fourier-Mellin transform and an unsupervised deformation registration model.
[0064] In the embodiment of the present invention, image registration is performed based on Fourier-Mellin transform (FMT), which has certain robustness to target translation transformation, scale transformation, and rotation transformation, and the algorithm has a small amount of computation, which can meet the requirements of visible foreign objects. real-time detection requirements. First, the calculation of image scale and rotation is converted into the translation of the magnitude of the Fourier transform of the image in the logarithmic polar coordinate s...
Embodiment 2
[0092] Figure 5 It is a schematic structural diagram of the liquid foreign matter visual detection system according to the present invention, as Figure 5 As shown, the liquid foreign matter visual detection system of the present invention includes an image registration module 51, an image preprocessing module 52, an image sequence frame difference module 53, an image postprocessing module 54, and an adaptive deep learning model acquisition module 55 , and the system defect acquisition module 56, wherein,
[0093] An image registration module 51, which performs image registration based on Fourier-Mellin transform and an unsupervised deformation registration model.
[0094] Image preprocessing module 52, which performs preprocessing operations on the registered images, including intercepting the image area according to the preset ROI region of interest parameters, performing grayscale processing on the image, and performing grayscale processing on the image after grayscale pr...
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, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com