Closed fringe compatible single interferogram phase solution method and device based on deep learning
A technology of deep learning and interferogram, applied in the field of closed fringe compatible single interferogram phase resolution device based on deep learning
Active Publication Date: 2022-03-11
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF9 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, these methods have more or less limitations
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0030] Such as figure 1 As shown, this closed fringe based on deep learning is compatible with a single interferogram phase solution method, which includes the following steps:
[0031] (1) Interferogram preprocessing, normalize the gray scale range of the input interferogram to obtain a normalized interferogram;
[0032] (2) Establish a neural network, and obtain the package phase of the normalized interferogram through the neural network;
[0033] (3) Perform phase unwrapping on the wrapped phase to obtain the absolute phase of the interferogram;
[0034] Wherein step (2) comprises following sub-steps:
[0035] (2.1) Establish a neural network with the following structure: the normalized interferogram is the input of the neural network, and the neural network includes: two-dimensional convolutional layer Conv2D, dense block DenseBlock, average pooling layer AvgPool, upsampling layer UpSample, Connection layer Concat, fixed layer Clamp;
[0036] (2.2) Use the data set to ...
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
Login to View More Abstract
The closed fringe based on deep learning is compatible with a single interferogram phase solution method and device. The measurement process only needs one interferogram, which can realize dynamic measurement, simple structure and high precision. The method includes: (1) interferogram preprocessing, normalizing the gray scale range of the input interferogram to obtain a normalized interferogram; (2) establishing a neural network, and obtaining the package phase of the normalized interferogram through the neural network ; (3) Unwrapping the wrapped phase to obtain the absolute phase of the interferogram; Step (2) includes: (2.1) Establishing a neural network: the normalized interferogram is the input of the neural network, and the neural network includes: two-dimensional volume Multilayer Conv2D, dense block DenseBlock, average pooling layer AvgPool, upsampling layer UpSample, connection layer Concat, fixed layer Clamp; (2.2) use the data set to train the neural network, or load the trained network parameters to make the neural network The network reaches a usable state; (2.3) Input the normalized interferogram into the neural network, and the neural network outputs the wrapped phase.
Description
technical field [0001] The present invention relates to the technical field of photoelectric measurement, in particular to a deep learning-based closed fringe compatible single-frame interferogram phase solution method, and a deep-learning-based closed fringe compatible single-frame interferogram phase solution device. Background technique [0002] Optical interferometry is an important non-contact surface profile measurement method. The coherent light waves produce a bright and dark interferogram through interference, and the interferogram carries the surface profile information of the measured object. By analyzing the interferogram, the phase distribution in it is obtained, and then the surface profile of the measured object can be obtained. Interferogram phase resolution, that is, obtaining the phase distribution of the interferogram, is the core issue in optical interferometry. The accuracy of the interferogram phase resolution will directly determine the accuracy of th...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G01B11/24G06N3/04G06N3/08
CPCG01B11/2441G06N3/08G06N3/045
Inventor 郝群胡摇袁诗翥张韶辉
Owner BEIJING INSTITUTE OF TECHNOLOGYGY