Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Phase information extraction method, storage medium and equipment based on convolutional neural network

A technology of convolutional neural network and phase information, which is applied in the field of phase information extraction based on Hypercolumns convolutional neural network, can solve the problem that closed fringe images cannot accurately extract phase information, and achieve improved phase extraction accuracy, accurate phase extraction function, The effect of improving network performance

Active Publication Date: 2022-06-07
XI AN JIAOTONG UNIV
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the application of this method has certain limitations, and the phase information cannot be accurately extracted for images with closed fringes

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Phase information extraction method, storage medium and equipment based on convolutional neural network
  • Phase information extraction method, storage medium and equipment based on convolutional neural network
  • Phase information extraction method, storage medium and equipment based on convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] The invention provides a phase information extraction method, storage medium and equipment based on a convolutional neural network. The problem of phase data extraction in three-dimensional profile measurement is regarded as a regression task, and a Hypercolumns convolutional neural network constructed based on deep learning technology is used. The network implements this function. First, the Hypercolumns convolutional neural network model is constructed, and the definition of each layer and functional modules are introduced in detail; then four different mathematical functions are used to generate training data sets to train the neural network model, and the training strategy of the method of the present invention is determined at the same time. Finally, aiming at the data flaws in the initial results predicted by the network model, the polynomial three-dimensional surface fitting technology is used to eliminate local errors and optimize the phase extraction results.

...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a phase information extraction method, storage medium and equipment based on a convolutional neural network, constructs a Hypercolumns convolutional neural network model, analyzes and predicts interference fringe images to obtain corresponding phase data; uses sine / cosine respectively The phase data in the sample set is generated by four different mathematical functions of the shape data set, the quadric surface data set, the wavy data set and the free-form surface data set, and then the interference image corresponding to the phase data is obtained by the light intensity distribution formula of the interference fringe image, etc. After the samples are generated, N sets of data in the training set and M sets of data in the verification set are formed; then, based on all the generated sample data, the Hypercolumns convolutional neural network model is trained; the polynomial 3D surface fitting method is used to eliminate the initial hypercolumns convolutional neural network. Predict the local error of the result and realize the optimization of the phase extraction result. The invention has fast processing speed and high phase extraction precision, and can realize the phase extraction function of a single-frame interferogram.

Description

technical field [0001] The invention belongs to the technical field of interference fringe image processing in the field of three-dimensional contour precision measurement, and particularly relates to a phase information extraction method, storage medium and device based on a Hypercolumns convolutional neural network. Background technique [0002] Optical 3D profilometry technology is widely used in industrial manufacturing, reverse engineering, aerospace, medical diagnosis and other fields. It has the characteristics of non-contact, high precision and high resolution, and is recognized as one of the most promising profilometry methods. There are many methods to achieve optical profilometry, including time method, structured light method, projection method, interferometry, etc. In the interferometric measurement process, the test light is reflected by the workpiece and interferes with the reference light to form an interference fringe pattern carrying the surface shape infor...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06T7/13G06T5/30G06N3/04G06N3/08
CPCG06T7/13G06T5/30G06N3/08G06T2207/20081G06T2207/20084G06T2207/30164G06N3/045
Inventor 李兵赵卓路嘉晟康晓清刘桐坤
Owner XI AN JIAOTONG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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