CN111079893B - Acquisition method and device for generator network for interference fringe pattern filtering - Google Patents
Acquisition method and device for generator network for interference fringe pattern filtering Download PDFInfo
- Publication number
- CN111079893B CN111079893B CN201911069537.2A CN201911069537A CN111079893B CN 111079893 B CN111079893 B CN 111079893B CN 201911069537 A CN201911069537 A CN 201911069537A CN 111079893 B CN111079893 B CN 111079893B
- Authority
- CN
- China
- Prior art keywords
- interference fringe
- network
- fringe pattern
- filtering
- interference
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000001914 filtration Methods 0.000 title claims abstract description 117
- 238000000034 method Methods 0.000 title claims abstract description 100
- 238000012549 training Methods 0.000 claims abstract description 77
- 230000006870 function Effects 0.000 claims description 31
- 230000010363 phase shift Effects 0.000 claims description 30
- 238000004590 computer program Methods 0.000 claims description 19
- 238000004088 simulation Methods 0.000 claims description 6
- 230000014509 gene expression Effects 0.000 claims description 5
- 239000011159 matrix material Substances 0.000 claims description 4
- 230000003287 optical effect Effects 0.000 abstract description 10
- 238000005305 interferometry Methods 0.000 abstract description 9
- 230000008569 process Effects 0.000 description 27
- 238000004422 calculation algorithm Methods 0.000 description 15
- 238000010586 diagram Methods 0.000 description 13
- 238000004364 calculation method Methods 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 8
- 238000005259 measurement Methods 0.000 description 5
- 238000013528 artificial neural network Methods 0.000 description 4
- 238000013527 convolutional neural network Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000004044 response Effects 0.000 description 4
- 230000008485 antagonism Effects 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 230000004913 activation Effects 0.000 description 2
- 230000003190 augmentative effect Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000000354 decomposition reaction Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 230000002194 synthesizing effect Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 235000019800 disodium phosphate Nutrition 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000005693 optoelectronics Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/088—Non-supervised learning, e.g. competitive learning
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D5/00—Mechanical means for transferring the output of a sensing member; Means for converting the output of a sensing member to another variable where the form or nature of the sensing member does not constrain the means for converting; Transducers not specially adapted for a specific variable
- G01D5/26—Mechanical means for transferring the output of a sensing member; Means for converting the output of a sensing member to another variable where the form or nature of the sensing member does not constrain the means for converting; Transducers not specially adapted for a specific variable characterised by optical transfer means, i.e. using infrared, visible, or ultraviolet light
- G01D5/266—Mechanical means for transferring the output of a sensing member; Means for converting the output of a sensing member to another variable where the form or nature of the sensing member does not constrain the means for converting; Transducers not specially adapted for a specific variable characterised by optical transfer means, i.e. using infrared, visible, or ultraviolet light by interferometric means
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The application is applicable to the technical field of optical interferometry, and provides a method and a device for acquiring a generator network for interference fringe pattern filtering, an interference fringe pattern filtering method based on the generator network, electronic equipment and a computer readable storage medium. An acquisition method of a generator network for interference fringe pattern filtering includes: acquiring a plurality of groups of training sample graphs; each group of training sample images comprises an interference fringe image and a label image corresponding to the interference fringe image, wherein the label image is an image obtained by filtering the background of the interference fringe image; training the generated countermeasure network to be trained according to the plurality of groups of training sample graphs to obtain a trained generated countermeasure network, wherein the trained generated countermeasure network is used for carrying out background filtering on the interference fringe graph, and the generated countermeasure network comprises a generated countermeasure network and a discriminator network. The embodiment of the application improves the accuracy of filtering the interference pattern.
Description
Technical Field
The application belongs to the technical field of optical interferometry, and particularly relates to a method and a device for acquiring a generator network for interference fringe pattern filtering, an interference fringe pattern filtering method based on the generator network, electronic equipment and a computer readable storage medium.
Background
Optical interferometry is a fundamental metrology method that utilizes the interference principle of light to achieve high-precision measurements. In recent decades, optical interferometry technology has been combined with optoelectronic image sensing technology, computer technology, precision mechanical technology, phase shift technology, optical signal processing technology, etc., so that the accuracy and rapidity of optical interferometry can be greatly improved, and quantitative measurement of complex amplitude, phase shift and phase from an interference fringe pattern is also realized, so that the optical interferometry technology is also called optical phase measurement technology, and submicron order can be achieved in microscopic interferometry. The two-step phase shift algorithm based on schmitt orthogonalization is a commonly used phase shift optical interferometry algorithm.
The two-step phase shift algorithm is to calculate and obtain a phase result by using the two interferograms, and the method has higher accuracy of phase recovery and higher calculation speed. But is susceptible to noise, background and amplitude non-uniformity during phase demodulation, resulting in low accuracy of phase demodulation.
In order to solve the problem, the conventional method is to remove the background noise of the fringe pattern by using a gaussian high-pass filter, and other methods, such as a method of calculating the residual interference pattern term by using enhanced fast empirical mode decomposition (Enhanced Fast Empirical Mode Decomposition, EFEMD) transformation to filter the background interference pattern term, can also achieve the purpose of improving the phase calculation precision.
However, filtering with conventional gaussian high pass filters and EFEMD algorithms has several disadvantages: firstly, the filtering precision is low, and residual background items still exist in the interference pattern after filtering, so that the precision of phase measurement is reduced. Secondly, the size of a filtering window of the Gaussian high-pass filter is related to the shape of a phase object, the size of the filtering window directly influences the filtering precision, the filtering precision is insufficient if the filtering window is unreasonable, and the size of the filtering window needs to be adjusted in a plurality of times in order to obtain a better filtering effect, so that the filtering process by using the Gaussian high-pass filter is relatively complicated.
Disclosure of Invention
In view of this, the embodiments of the present application provide a method and apparatus for obtaining a generator network for filtering an interference fringe pattern, an interference fringe pattern filtering method based on the generator network, an electronic device, and a computer-readable storage medium, which can solve the problem of low filtering precision in the related art.
A first aspect of an embodiment of the present application provides a method for acquiring a generator network for interference fringe pattern filtering, including:
acquiring a plurality of groups of training sample graphs; each group of training sample images comprises an interference fringe image and a label image corresponding to the interference fringe image, wherein the label image is an image obtained by filtering the background of the interference fringe image;
training the generated countermeasure network to be trained according to the plurality of groups of training sample graphs to obtain a trained generated countermeasure network, wherein the trained generated countermeasure network is used for carrying out background filtering on the interference fringe graph, and the generated countermeasure network comprises a generated countermeasure network and a discriminator network.
A second aspect of the embodiments of the present application provides a method for filtering an interference fringe pattern based on a generator network, including:
obtaining an interference fringe pattern to be filtered;
and filtering the interference fringe pattern to be filtered by using the generator network acquired by the acquisition method in the first aspect to generate an interference fringe pattern with the background filtered.
A third aspect of the embodiments of the present application provides an acquisition apparatus of a generator network for interference fringe pattern filtering, including:
the acquisition unit is used for acquiring a plurality of groups of training sample graphs; each group of training sample images comprises an interference fringe image and a label image corresponding to the interference fringe image, wherein the label image is an image of the interference fringe image subjected to background filtering;
the training unit is used for training the generated countermeasure network to be trained according to the plurality of groups of training sample graphs to obtain a trained generated countermeasure network, the trained generated countermeasure network is used for carrying out background filtering on the interference fringe graph, and the generated countermeasure network comprises a generated countermeasure network and a discriminator network.
A fourth aspect of the embodiments of the present application provides an interference fringe pattern filtering apparatus based on a generator network, including:
the acquisition unit is used for acquiring an interference fringe pattern to be filtered;
and the filtering unit is used for filtering the interference fringe pattern to be filtered by utilizing the generator network acquired by the acquisition device of the third aspect to generate an interference fringe pattern with the background filtered.
A fifth aspect of the embodiments of the present application provides an electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the method of the first or second aspect when the computer program is executed.
A sixth aspect of the embodiments of the present application provides a computer readable storage medium storing a computer program which, when executed by a processor, implements the steps of the method of the first or second aspect described above.
A seventh aspect of embodiments of the present application provides a computer program product for, when run on an electronic device, causing the electronic device to perform the method according to the first or second aspect.
In the embodiment of the application, the countermeasure network is generated in a countermeasure training mode, and the generator for generating the countermeasure network has the function of a filter, so that the performance is better, the background of the interference fringe pattern can be filtered, the filtering precision is greatly improved, and in addition, compared with the filtering by adopting a Gaussian high-pass filter, the setting of the size of a filtering window is not needed, and the filtering process is simplified.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required for the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of an implementation of a method for obtaining a generator network for interference fringe pattern filtering according to an embodiment of the present application;
FIG. 2 is a schematic diagram of a process for synthesizing an interference fringe pattern according to one embodiment of the present application;
FIG. 3 is a schematic diagram of a process for synthesizing a label map according to one embodiment of the present application;
FIG. 4 is a diagram illustrating an exemplary process of steps S121 to S125 in a method for obtaining a generator network for interference fringe pattern filtering according to an embodiment of the present application;
FIG. 5 an embodiment of the present application provides a schematic diagram of a generator network;
FIG. 6 an embodiment of the present application provides a schematic diagram of a discriminator network;
FIG. 7 is a schematic flow chart of an implementation of a method for filtering an interference fringe pattern based on a generator network according to an embodiment of the present application;
FIG. 8 is a process schematic diagram of a method for generator network-based interference fringe pattern filtering according to one embodiment of the present application;
FIG. 9 is a flow chart illustrating another method for generating network-based interference fringe pattern filtering according to an embodiment of the present application;
FIG. 10 is a schematic diagram of an acquisition device of a generator network for interference fringe pattern filtering according to one embodiment of the present application;
FIG. 11 is a schematic diagram of another interference fringe pattern filtering apparatus based on a generator network according to an embodiment of the present application;
fig. 12 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In order to make the present application solution better understood by those skilled in the art, the following description will make clear and complete descriptions of the technical solutions in the embodiments of the present application with reference to the accompanying drawings, and it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. It should be noted that, in the case of no conflict, the embodiments and features in the embodiments may be combined with each other.
In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system configurations, techniques, etc. in order to provide a thorough understanding of the embodiments of the present application. It will be apparent, however, to one skilled in the art that the present application may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.
It should be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It should also be understood that the term "and/or" as used in this specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations.
As used in this specification and the appended claims, the term "if" may be interpreted as "when..once" or "in response to a determination" or "in response to detection" depending on the context. Similarly, the phrase "if a determination" or "if a [ described condition or event ] is detected" may be interpreted in the context of meaning "upon determination" or "in response to determination" or "upon detection of a [ described condition or event ]" or "in response to detection of a [ described condition or event ]".
In addition, in the description of the present application and the appended claims, the terms "first," "second," "third," and the like are used merely to distinguish between descriptions and are not to be construed as indicating or implying relative importance.
Reference in the specification to "one embodiment" or "some embodiments" or the like means that a particular feature, structure, or characteristic described in connection with the embodiment is included in one or more embodiments of the application. Thus, appearances of the phrases "in one embodiment," "in some embodiments," "in other embodiments," and the like in the specification are not necessarily all referring to the same embodiment, but mean "one or more but not all embodiments" unless expressly specified otherwise. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless expressly specified otherwise.
In the prior art, a Gaussian high-pass filter and an EFEMD algorithm are generally adopted for filtering, on one hand, the filtering precision is low, and residual background items still exist in the interference pattern after filtering, so that the precision of phase measurement is reduced; on the other hand, when the gaussian high-pass filter is adopted for filtering, the size of the filtering window needs to be adjusted in a plurality of attempts, and the filtering process is complicated.
Aiming at the defects of the prior art, the application discloses an acquisition method and an acquisition device for generating an countermeasure network for interference fringe pattern filtering, which are based on the interference fringe pattern filtering method for generating the countermeasure network, electronic equipment and a computer readable storage medium, can realize the function of filtering the background of an interference fringe pattern, improve the filtering precision, do not need to set the size of a filtering window, and simplify the filtering process.
In order to illustrate the technical solutions described in the present application, the following description is made by specific examples.
Fig. 1 shows an implementation flow of a method for obtaining a generator network for interference fringe pattern filtering according to an embodiment of the present application.
The acquiring method is applied to electronic equipment, including but not limited to mobile phones, tablet computers, wearable equipment, vehicle-mounted equipment, augmented reality (augmented reality, AR)/Virtual Reality (VR) equipment, notebook computers, ultra-mobile personal computer (UMPC), netbooks, personal digital assistants (personal digital assistant, PDA), servers and the like, and the specific type of the electronic equipment is not limited in the embodiments of the present application. The servers include, but are not limited to, independent servers, cloud servers, distributed servers, server clusters, and the like.
As shown in fig. 1, the acquisition method of the generator network for interference fringe pattern filtering includes steps S110 to S120. The specific implementation principle of each step is as follows.
S110, acquiring a plurality of groups of training sample graphs; each group of training sample images comprises an interference fringe image and a label image corresponding to the interference fringe image, wherein the label image is an image of the interference fringe image subjected to background filtering.
The training sample images form a training set, and each training sample image comprises an interference fringe image and a label image obtained by filtering the interference fringe image by background.
In a non-limiting example of the application, a multi-frame experimental interference image is collected as an interference fringe image in a training set by constructing an interference imaging light path; filtering the collected interference fringe patterns, namely filtering the background, and taking the interference fringe patterns as a label pattern in a training set.
In another non-limiting example of the present application, the training set is generated by a method of analog simulation.
Illustratively, the training set includes N sets of training sample patterns, N being a positive integer. In the phase-shift interferometry, after the light wave passes through the interference light path, the light intensity expression of the nth frame of interference fringe pattern in all the collected N frames of random phase-shift interference fringe patterns is assumed to be:
where n=1, 2, …, N is the phase shift order of the interference fringe pattern, N is the total number of steps of the phase shift, (x, y) represents the position in the interference fringe pattern, a (x, y) and B (x, y) represent the background light intensity and fringe modulation amplitude distribution of the interference fringe pattern, respectively,
representing the measured phase distribution, θ n The phase shift amount corresponding to the nth frame of interference fringe pattern.
In analog computation, phase distribution
Satisfy->
Wherein, the liquid crystal display device comprises a liquid crystal display device,the value of r is related to the density program of the stripes, the larger the value of r is, the denser the stripes are, and the value of r is not particularly limited in the application; (a, b) represents the fringe center coordinates and the phase object G (x, y) conforms to the distribution of a two-dimensional Gaussian function. Wherein the background term a (x, y) is represented by the following formula (2), and the modulation intensity B (x, y) is represented by the following formula (3).
Wherein a is 1 、a 2 、b 1 、b 2 、x 1 、y 2 Are random numbers; the noise is a normal distribution with the mean value equal to 0 and the standard deviation equal to 1
For point-by-point random number superposition in the interferogram. Phase shift amount theta n Randomly distributed within a certain range, e.g. [0,2 pi ]]。
The images synthesized according to the formula (1) and the simulation method are used as interference patterns of network training, as shown in fig. 2. The interference fringe pattern of the network training is subtracted by the background term a (x, y) to be used as a label pattern of the network training, as shown in fig. 3. Thus, several sets of interference fringe patterns and label patterns are generated as training sets for the neural network of the present application. The training set obtained by the method is rich and more complete in samples, and the background filtering precision of the label graph is higher, so that the network performance obtained by subsequent training is better.
S120, training the generated countermeasure network to be trained according to the plurality of groups of training sample graphs to obtain a trained generated countermeasure network, wherein the trained generated countermeasure network generator network is used for carrying out background filtering on the interference fringe patterns.
Wherein the generation countermeasure network includes a generator network and a discriminator network.
According to the multiple groups of training sample graphs, using a generator network and a discriminator network to perform countermeasure training to obtain a trained generated countermeasure network, wherein the generator network of the trained generated countermeasure network is used for performing background filtering on the interference fringe graph.
In a non-limiting example of the present application, several interferograms generated by simulation using the method shown in fig. 2 are used, and the same number of interferograms without background items a (x, y) generated by simulation using the method shown in fig. 3 are used as label graphs, and are used together as training sets to train the generated countermeasure network, so as to obtain the trained generated countermeasure network. The generator network that generates the countermeasure network has the function of a filter for background filtering the interferogram.
In the embodiment of the application, the countermeasure network is generated in a countermeasure training mode, and the generator for generating the countermeasure network has the function of a filter, so that the performance is better, the background of the interference fringe pattern can be filtered, the filtering precision is greatly improved, in addition, the setting of the size of a filtering window is not needed, and the filtering process is simplified.
Alternatively, on the basis of the embodiment shown in fig. 1 described above, step S120 includes the following steps S121 to S125.
S121, using a plurality of the label graphs as real samples to primarily train a discriminator network, and obtaining the primarily trained discriminator network; the output of the discriminator network is used to represent the probability that the input graph is a true graph.
And training the identifier network by using a plurality of label graphs as real samples, optimizing parameters of the identifier network in the training process until the output result of the identifier network after optimizing the parameters meets a second preset condition, or stopping training when the iteration number of the training process reaches the preset iteration number, and obtaining the identifier network after preliminary training.
As a non-limiting example of the application, taking a plurality of label graphs as real samples, respectively inputting the real samples into an initial discriminator network to obtain an output result corresponding to each label graph, calculating an error between the output result and a preset result value (such as a numerical value 1), and stopping training if the error meets a second preset condition or the iteration number reaches the maximum iteration number; if the error does not meet the second preset condition, optimizing parameters of the identifier network until the output result of the optimized identifier network meets the second preset condition or the iteration number reaches the maximum iteration number, stopping training, and obtaining the identifier network after preliminary training. The second preset condition is that the error is smaller than or equal to a preset error threshold, and the preset error threshold is an empirical value, which is not limited in the application.
For example, a label graph is randomly selected from a training set and input into a discriminator network, the discriminator network outputs a number between 0 and 1, and the number 1 represents that the input graph is a true graph, and in the process, the output of the discriminator network is made to approach 1 as much as possible, so that the discriminator network is primarily trained.
S122, generating: taking the interference fringe pattern as input of a generator network to obtain a pseudo pattern corresponding to the interference fringe pattern; the generator network is used for carrying out background filtering on the interference fringe pattern.
S123, authentication: and respectively inputting the pseudo graph and the label graph corresponding to the interference fringe graph into the identifier network after preliminary training, and outputting a first probability value corresponding to the pseudo graph and a second probability value corresponding to the label graph.
S124, optimizing: generating a loss function from the first probability value and the second probability value, optimizing parameters of the generator network based on the loss function.
And S125, repeating the generating step, the identifying step and the optimizing step until the optimized generator network meets a first preset condition, and obtaining the trained generating countermeasure network.
In the example of the implementation process of steps S121 to S125, please refer to fig. 4, the interferogram is randomly selected from the training set as the data of the generator network, and then a new image matrix data is generated as the pseudo-image after passing through the generator network. And then converting the label graph corresponding to the selected interference graph into a vector, and taking the vector as a real graph. And finally, taking the pseudo-graph and the real graph as inputs of a discriminator network for preliminary training, and using output values after passing through the discriminator network to represent the probability that the input image is the real graph. The loss function is calculated based on the output values corresponding to both the pseudo-graph and the real-graph. The purpose of the network training is to reduce the value of the loss function, and thus, the training to generate the countermeasure network is completed by optimizing the generation of the countermeasure network to reduce the loss function value.
It should be noted that, in an example of the present application, the output value may be a number between 0 and 1 after passing through the discriminator network, which is used to represent the probability that the input picture is a true picture, and is true 1 and false 0. In other examples of the present application, the output value may also be a number between-1 and 1, or other numerical ranges, which are not limited by the present application.
In the embodiment of the application, the output value of the pseudo graph after the identifier network is subjected to preliminary training is a first probability value, the output value of the true graph after the identifier network is subjected to preliminary training is a second probability value, and the loss function is calculated based on the first probability value and the second probability value.
Alternatively, the loss function includes, but is not limited to, a cross entropy loss function, an exponential loss function, a hinge loss function, or the like.
As a non-limiting example of the present application, the loss function is a cross entropy loss function.
Specifically, the loss function is calculated by the formula log [1-D (G (z)) ] +log (D (w)), where G (z) represents a pseudo-pattern generated by the generator network and corresponding to the interference fringe pattern z, D (G (z)) represents a first probability value obtained by the discriminator network for the input of G (z), and D (w) represents a second probability value obtained by the discriminator network for the input of the label pattern w.
In embodiments of the present application, both the generator network and the discriminator network that generate the challenge network employ deep learning neural networks. The generator network may be a deep learning neural network based on a U-Net structure, and the discriminator network may be a deep learning neural network based on a convolutional neural network (Convolutional Neural Networks, CNN) structure.
Illustratively, the block diagrams for generating the antagonism network are shown in fig. 5 and 6, wherein fig. 5 is a schematic diagram of the structure of the generator network for generating the antagonism network, and fig. 6 is a schematic diagram of the structure of the discriminator network for generating the antagonism network.
As shown in fig. 5, the generator network is based on a U-Net structure, comprising 8 convolutional layers and 7 deconvolution layers, each of which is followed by a leak_relu as an activation function.
As shown in fig. 6, the discriminator network is based on a CNN structure, and comprises 6 convolutional layers, each of which is followed by a leak_relu as an activation function.
It is to be understood that fig. 5 and 6 are merely exemplary descriptions and are not to be construed as limiting the application in any way. In other embodiments of the present application, the generator network may also include other numbers of convolution layers and deconvolution layers. The discriminator network may also include other numbers of convolutional layers.
As shown in fig. 7, an embodiment of the present application provides a method for interference fringe pattern filtering based on a generator network. As shown in fig. 7, the method includes steps S710 to S720.
S710, obtaining an interference fringe pattern to be filtered.
S720, filtering the interference pattern to be filtered by using the generator network acquired by the acquisition method in any embodiment, and generating an interference fringe pattern with the background filtered.
In the embodiment of the application, the interference fringe pattern may be an interference pattern acquired by the electronic device in real time, or may be an interference pattern acquired from an internal or external memory of the electronic device, or may be an interference pattern acquired from a third-party electronic device. The interference fringe pattern is the subject of filtering.
After the interference fringe pattern to be filtered is obtained, the interference fringe pattern to be filtered is input into a trained generator network for generating an countermeasure network, and the generator network outputs the interference fringe pattern with the background filtered.
Illustratively, referring to FIG. 8, a process of filtering with a generator network that generates an countermeasure network is illustrated. As shown in fig. 8, after an interference imaging experimental light path is set up and a new set of experimental interferograms is acquired, the set of experimental interferograms is input into a trained generator network for generating an countermeasure network, and matrix data is obtained through calculation by means of weight data and bias data trained by the network, so that an image with background items filtered is output.
Optionally, another embodiment of the present application provides a method of interference fringe pattern filtering based on a generator network. As shown in fig. 9, the method further includes step S730 on the basis of the embodiment shown in fig. 7.
And S730, calculating the phase information of the interference fringe pattern after the background is filtered by a two-step phase shift method.
After the interference fringe pattern of the filtered background item is obtained in step S720, the phase information of the interference fringe pattern of the filtered background output by the network is calculated by using a two-step phase shift algorithm, that is, the phase calculation result is obtained by using the two-step phase shift algorithm.
For example, please continue to refer to fig. 8, the generator network outputs an image with the background term filtered out, and then calculates the image output by the network using a two-step phase shift algorithm, resulting in a phase calculation result.
By comparing the filtering method with the traditional filtering method, aiming at the same set of experimental graphs, the filtering method provided by the application combines the two-step phase shift algorithm to obtain the root mean square error of the phase result as 0.0740rad, the Gaussian high-pass filter combines the two-step phase shift algorithm to obtain the root mean square error of the phase result as 0.2594rad, and the EFEMD combines the two-step phase shift algorithm to obtain the root mean square error of the phase result as 0.4547rad. Therefore, the filtering method provided by the generation countermeasure network has better filtering effect and the accuracy of the phase result obtained by combining the two-step phase shift algorithm is higher.
The method and the device have the advantages that the function of filtering the interference pattern background item is realized by using the generated countermeasure network as a tool, compared with a traditional Gaussian high-pass filter and an EFEMD algorithm, the filtering precision and the phase calculation precision obtained by using a two-step phase shift algorithm are higher, and compared with the Gaussian high-pass filter, the filtering step is simpler.
It should be understood that the sequence number of each step in the foregoing embodiment does not mean that the execution sequence of each process should be determined by the function and the internal logic of each process, and should not limit the implementation process of the embodiment of the present application in any way.
Corresponding to the methods described in the embodiments above, the following illustrates embodiments of the apparatus provided in the embodiments of the present application, and for convenience of explanation, only the portions relevant to the embodiments of the apparatus of the present application are shown.
As shown in fig. 10, an obtaining apparatus of a generator network for interference fringe pattern filtering according to an embodiment of the present application includes: an acquisition unit M101 and a training unit M102.
An obtaining unit M101, configured to obtain a plurality of sets of training sample graphs; each group of training sample images comprises an interference fringe image and a label image corresponding to the interference fringe image, wherein the label image is an image of the interference fringe image subjected to background filtering;
the training unit M102 is configured to train the generated countermeasure network to be trained according to the multiple sets of training sample graphs, so as to obtain a trained generated countermeasure network, where the trained generated countermeasure network is used for performing background filtering on the interference fringe graph, and the generated countermeasure network includes a generated network and a discriminator network.
It should be noted that, the implementation process of the obtaining device of the generator network for interference fringe pattern filtering provided in this embodiment may refer to the implementation process of the obtaining method of the generator network for interference fringe pattern filtering provided in fig. 1, and will not be described herein.
Optionally, on the basis of the embodiment shown in fig. 10, the training unit M102 includes:
the identifier network preliminary training unit is used for preliminarily training the identifier network by using a plurality of tag images as real samples to obtain a identifier network after preliminary training; the output of the discriminator network is used for representing the probability that the input graph is a true graph;
the generation unit is used for taking the interference fringe pattern as the input of a generator network to obtain a pseudo pattern corresponding to the interference fringe pattern; the generator network is used for carrying out background filtering on the interference fringe pattern;
the identification unit is used for respectively inputting the pseudo-graph and the label graph corresponding to the interference fringe graph into the identifier network after preliminary training and outputting a first probability value corresponding to the pseudo-graph and a second probability value corresponding to the label graph;
an optimizing unit, configured to generate a loss function according to the first probability value and the second probability value, and optimize parameters of the generated countermeasure network based on the loss function;
the operations executed by the generating unit, the identifying unit and the optimizing unit are repeatedly executed until the optimized generator network meets a first preset condition, and a trained generating countermeasure network is obtained.
It should be noted that, the implementation process of the obtaining device of the generator network for interference fringe pattern filtering provided in this embodiment may refer to the implementation process of the obtaining method of the generator network for interference fringe pattern filtering provided in fig. 2, and will not be described herein.
As shown in fig. 11, an interference fringe pattern filtering apparatus based on a generator network according to an embodiment of the present application includes: an acquisition unit M111, and a filtering unit M112.
An acquisition unit M111 for acquiring an interference fringe pattern to be filtered;
the filtering unit M112 is configured to filter the interference fringe pattern to be filtered by using the generator network acquired by the acquiring device in any of the foregoing embodiments, and generate an interference fringe pattern with the background filtered.
It should be noted that, the implementation process of the interference fringe pattern filtering apparatus based on the generator network provided in this embodiment may refer to the implementation process of the interference fringe pattern filtering method based on the generator network provided in fig. 7, and will not be described herein again.
Optionally, on the basis of the embodiment shown in fig. 11, the filtering device further comprises a phase information calculation unit.
The phase information calculation unit is used for calculating the phase information of the interference fringe pattern after the background is filtered through a two-step phase shift method.
It should be noted that, the implementation process of the interference fringe pattern filtering apparatus based on the generator network provided in this embodiment may refer to the implementation process of the interference fringe pattern filtering method based on the generator network provided in fig. 9, and will not be described herein again.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions. The functional units and modules in the embodiment may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit, where the integrated units may be implemented in a form of hardware or a form of a software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working process of the units and modules in the above system may refer to the corresponding process in the foregoing method embodiment, which is not described herein again.
Fig. 12 is a schematic diagram of an electronic device according to an embodiment of the present application. As shown in fig. 12, the electronic device 12 of this embodiment includes: at least one processor 120 (only one processor is shown in fig. 12), a memory 121, and a computer program 122 stored in the memory 121 and executable on the at least one processor 120, such as an acquisition program for a generator network of interference fringe pattern filtering, or a program of interference fringe pattern filtering based on the generator network. The steps of the method embodiments described above are implemented by the processor 120 when executing the computer program 122. For example, the steps in the foregoing embodiment of the method for acquiring a generator network for interference fringe pattern filtering, such as steps S110 to S120 shown in fig. 1; alternatively, the steps in the foregoing embodiment of the generator network-based interference fringe pattern filtering method are as shown in steps S710 through S720 of fig. 7.
The electronic device may include, but is not limited to, a processor 120, a memory 121. It will be appreciated by those skilled in the art that fig. 12 is merely an example of an electronic device 12 and is not intended to limit the electronic device 12, and may include more or fewer components than shown, or may combine certain components, or different components, e.g., the electronic device may further include an input-output device, a network access device, a bus, etc.
The processor 120 may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSPs), application specific integrated circuits (Application Specific Integrated Circuit, ASICs), off-the-shelf programmable gate arrays (Field-Programmable Gate Array, FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 121 may be an internal storage unit of the electronic device 12, such as a hard disk or a memory of the electronic device 12. The memory 121 may also be an external storage device of the electronic device 12, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the electronic device 12. Further, the memory 121 may also include both internal storage units and external storage devices of the electronic device 12. The memory 121 is used to store the computer program and other programs and data required by the electronic device. The memory 121 may also be used to temporarily store data that has been output or is to be output.
Embodiments of the present application also provide a computer readable storage medium storing a computer program which, when executed by a processor, implements steps that may implement the various method embodiments described above.
Embodiments of the present application provide a computer program product which, when run on a mobile terminal, causes the mobile terminal to perform steps that may be performed in the various method embodiments described above.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the present application implements all or part of the flow of the method of the above embodiments, and may be implemented by a computer program to instruct related hardware, where the computer program may be stored in a computer readable storage medium, where the computer program, when executed by a processor, may implement the steps of each of the method embodiments described above. Wherein the computer program comprises computer program code which may be in source code form, object code form, executable file or some intermediate form etc. The computer readable medium may include at least: any entity or device capable of carrying the computer program code to the electronic device, a recording medium, a computer Memory, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), an electrical carrier signal, a telecommunications signal, and a software distribution medium. Such as a U-disk, removable hard disk, magnetic or optical disk, etc. In some jurisdictions, computer readable media may not be electrical carrier signals and telecommunications signals in accordance with legislation and patent practice.
In the foregoing embodiments, the descriptions of the embodiments are emphasized, and in part, not described or illustrated in any particular embodiment, reference is made to the related descriptions of other embodiments.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus/network device and method may be implemented in other manners. For example, the apparatus/network device embodiments described above are merely illustrative, e.g., the division of the modules or units is merely a logical functional division, and there may be additional divisions in actual implementation, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection via interfaces, devices or units, which may be in electrical, mechanical or other forms.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
The above embodiments are only for illustrating the technical solution of the present application, and are not limiting; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application, and are intended to be included in the scope of the present application.
Claims (9)
1. A method of obtaining a generator network for interference fringe pattern filtering, comprising:
acquiring a plurality of groups of training sample graphs; each group of training sample images comprises an interference fringe image and a label image corresponding to the interference fringe image, wherein the label image is an image obtained by filtering the background of the interference fringe image;
training a generated countermeasure network to be trained according to the plurality of groups of training sample graphs to obtain a trained generated countermeasure network, wherein the trained generated countermeasure network is used for carrying out background filtering on the interference fringe graph, and comprises a generated countermeasure network and a discriminator network;
the obtaining a plurality of sets of training sample graphs includes:
obtaining N groups of training sample graphs by a simulation method, wherein N is a positive integer; the light intensity expressions of the N interference fringe patterns are as follows:
the light intensity expressions of the N label patterns corresponding to the N interference fringe patterns are as follows: />
Where n=1, 2, …, N is the phase shift order of the interference fringe pattern, N is the total number of steps of the phase shift, (x, y) represents the position in the interference fringe pattern, a (x, y) and B (x, y) represent the background light intensity and fringe modulation amplitude distribution of the interference fringe pattern, respectively>
Representing the measured phase distribution, θ n The phase shift amount corresponding to the nth frame of interference fringe pattern;
in analog computation, the measured phase distribution
Satisfy->
Wherein, the value of r is related to the density program of the interference fringes, and the larger the value of r is, the denser the interference fringes are; (a, b) represents the interference fringeThe heart coordinates, the phase objects G (x, y) conform to the distribution of the two-dimensional gaussian function; the background light intensity a (x, y) is represented by formula (2), and the fringe modulation amplitude distribution B (x, y) is represented by formula (3);
the formula (2) is:
the formula (3) is:
wherein a is 1 、a 2 、b 1 、b 2 、x 1 、y 2 Are random numbers; the noise is a normal distribution with the mean value equal to 0 and the standard deviation equal to 1
The random matrix is used for carrying out point-by-point random number superposition on the interference fringe pattern; phase shift amount theta n Randomly distributed within a preset range.
2. The method of claim 1, wherein training the generated countermeasure network to be trained according to the plurality of sets of training sample patterns to obtain the trained generated countermeasure network, comprises:
using a plurality of the label graphs as real samples to primarily train a discriminator network, and obtaining the primarily trained discriminator network; the output of the discriminator network is used for representing the probability that the input graph is a true graph;
generating: taking the interference fringe pattern as input of a generator network to obtain a pseudo pattern corresponding to the interference fringe pattern; the generator network is used for carrying out background filtering on the interference fringe pattern;
and an identification step: respectively inputting the pseudo graph and the label graph corresponding to the interference fringe graph into the identifier network after preliminary training, and outputting a first probability value corresponding to the pseudo graph and a second probability value corresponding to the label graph;
optimizing: generating a loss function according to the first probability value and the second probability value, and optimizing parameters of the generated countermeasure network based on the loss function;
and repeating the generating step, the identifying step and the optimizing step until the optimized generating countermeasure network meets a first preset condition, so as to obtain the trained generating countermeasure network.
3. The acquisition method of claim 2, wherein the loss function is a cross entropy loss function.
4. An interference fringe pattern filtering method based on a generator network, comprising the steps of:
obtaining an interference fringe pattern to be filtered;
filtering the interference fringe pattern to be filtered by using the generator network acquired by the acquisition method of any one of claims 1 to 3 to generate an interference fringe pattern with the background filtered.
5. The interference fringe pattern filtering method of claim 4, further comprising:
and calculating the phase information of the interference fringe pattern after the background is filtered by a two-step phase shift method.
6. An acquisition device for a generator network for interference fringe pattern filtering, comprising:
the acquisition unit is used for acquiring a plurality of groups of training sample graphs; each group of training sample images comprises an interference fringe image and a label image corresponding to the interference fringe image, wherein the label image is an image of the interference fringe image subjected to background filtering;
the training unit is used for training the generated countermeasure network to be trained according to the plurality of groups of training sample graphs to obtain a trained generated countermeasure network, the trained generated countermeasure network is used for carrying out background filtering on the interference fringe graph, and the generated countermeasure network comprises a generated network and a discriminator network;
the acquisition unit is specifically configured to:
obtaining N groups of training sample graphs by a simulation method, wherein N is a positive integer; the light intensity expressions of the N interference fringe patterns are as follows:
the light intensity expressions of the N label patterns corresponding to the N interference fringe patterns are as follows: />
Where n=1, 2, …, N is the phase shift order of the interference fringe pattern, N is the total number of steps of the phase shift, (x, y) represents the position in the interference fringe pattern, a (x, y) and B (x, y) represent the background light intensity and fringe modulation amplitude distribution of the interference fringe pattern, respectively>
Representing the measured phase distribution, θ n The phase shift amount corresponding to the nth frame of interference fringe pattern;
in analog computation, the measured phase distribution
Satisfy->
Wherein, the value of r is related to the density program of the interference fringes, and the larger the value of r is, the denser the interference fringes are; (a, b) represents the center coordinates of the interference fringes, and the phase object G (x, y) conforms to the distribution of a two-dimensional gaussian function; the background light intensity a (x, y) is represented by formula (2), and the fringe modulation amplitude distribution B (x, y) is represented by formula (3);
the formula (2) is:
the formula (3) is:
wherein a is 1 、a 2 、b 1 、b 2 、x 1 、y 2 Are random numbers; the noise is a normal distribution with the mean value equal to 0 and the standard deviation equal to 1
The random matrix is used for carrying out point-by-point random number superposition on the interference fringe pattern; phase shift amount theta n Randomly distributed within a preset range.
7. An interference fringe pattern filtering apparatus based on a generator network, comprising:
the acquisition unit is used for acquiring an interference fringe pattern to be filtered;
the filtering unit is configured to filter the interference fringe pattern to be filtered by using the generator network acquired by the acquiring device of claim 6, and generate an interference fringe pattern with the background filtered.
8. An electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any one of claims 1 to 5 when the computer program is executed.
9. A computer readable storage medium storing a computer program, characterized in that the computer program when executed by a processor implements the steps of the method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911069537.2A CN111079893B (en) | 2019-11-05 | 2019-11-05 | Acquisition method and device for generator network for interference fringe pattern filtering |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911069537.2A CN111079893B (en) | 2019-11-05 | 2019-11-05 | Acquisition method and device for generator network for interference fringe pattern filtering |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111079893A CN111079893A (en) | 2020-04-28 |
| CN111079893B true CN111079893B (en) | 2023-05-09 |
Family
ID=70310657
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911069537.2A Active CN111079893B (en) | 2019-11-05 | 2019-11-05 | Acquisition method and device for generator network for interference fringe pattern filtering |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111079893B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112381731B (en) * | 2020-11-12 | 2021-08-10 | 四川大学 | Single-frame stripe image phase analysis method and system based on image denoising |
| CN112545532B (en) * | 2020-11-26 | 2023-05-16 | 中国人民解放军战略支援部队信息工程大学 | Data enhancement method and system for electroencephalogram signal classification and identification |
| CN112985300B (en) * | 2021-02-24 | 2022-03-25 | 中国科学院长春光学精密机械与物理研究所 | Optical element contour detection method and device based on stripe tracking and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103954238A (en) * | 2014-04-17 | 2014-07-30 | 天津工业大学 | Method for carrying out bias light compensation on optical fiber interference fringe image based on Gaussian function |
| CN104236452A (en) * | 2014-07-17 | 2014-12-24 | 华南师范大学 | Single-monochrome-CCD phase shift dual-wavelength interferometry method based on specific phase shift amount |
| CN105091781A (en) * | 2015-05-21 | 2015-11-25 | 中国科学院光电技术研究所 | Optical surface measuring method and apparatus using single-frame interference fringe pattern |
| CN108805188A (en) * | 2018-05-29 | 2018-11-13 | 徐州工程学院 | A kind of feature based recalibration generates the image classification method of confrontation network |
| CN110097103A (en) * | 2019-04-22 | 2019-08-06 | 西安电子科技大学 | Based on the semi-supervision image classification method for generating confrontation network |
| CN110163813A (en) * | 2019-04-16 | 2019-08-23 | 中国科学院深圳先进技术研究院 | A kind of image rain removing method, device, readable storage medium storing program for executing and terminal device |
-
2019
- 2019-11-05 CN CN201911069537.2A patent/CN111079893B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103954238A (en) * | 2014-04-17 | 2014-07-30 | 天津工业大学 | Method for carrying out bias light compensation on optical fiber interference fringe image based on Gaussian function |
| CN104236452A (en) * | 2014-07-17 | 2014-12-24 | 华南师范大学 | Single-monochrome-CCD phase shift dual-wavelength interferometry method based on specific phase shift amount |
| CN105091781A (en) * | 2015-05-21 | 2015-11-25 | 中国科学院光电技术研究所 | Optical surface measuring method and apparatus using single-frame interference fringe pattern |
| CN108805188A (en) * | 2018-05-29 | 2018-11-13 | 徐州工程学院 | A kind of feature based recalibration generates the image classification method of confrontation network |
| CN110163813A (en) * | 2019-04-16 | 2019-08-23 | 中国科学院深圳先进技术研究院 | A kind of image rain removing method, device, readable storage medium storing program for executing and terminal device |
| CN110097103A (en) * | 2019-04-22 | 2019-08-06 | 西安电子科技大学 | Based on the semi-supervision image classification method for generating confrontation network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111079893A (en) | 2020-04-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111079893B (en) | Acquisition method and device for generator network for interference fringe pattern filtering | |
| US11475593B2 (en) | Methods and apparatus for processing image data for machine vision | |
| US11657630B2 (en) | Methods and apparatus for testing multiple fields for machine vision | |
| Yoshizawa et al. | Fast gauss bilateral filtering | |
| US10846563B2 (en) | Methods and apparatus for generating a dense field of three dimensional data for machine vision | |
| CN112435193B (en) | Method and device for denoising point cloud data, storage medium and electronic equipment | |
| CN112336342B (en) | Hand key point detection method and device and terminal equipment | |
| CN112950685B (en) | Infrared and visible light image registration method, system and storage medium | |
| CN113848550A (en) | Ground radar adaptive threshold permanent scatterer identification method, device and storage medium | |
| Feng et al. | BM3D‐GT&AD: an improved BM3D denoising algorithm based on Gaussian threshold and angular distance | |
| CN111277809A (en) | Image color correction method, system, device and medium | |
| CN112381731B (en) | Single-frame stripe image phase analysis method and system based on image denoising | |
| CN110210279A (en) | Object detection method, device and computer readable storage medium | |
| Kim et al. | ADOM: ADMM-based optimization model for stripe noise removal in remote sensing image | |
| Zhang et al. | Research on chips’ defect extraction based on image-matching | |
| CN115689947A (en) | Image sharpening method, system, electronic device and storage medium | |
| Wang et al. | An Improved Canny‐Zernike Subpixel Detection Algorithm | |
| CN110335219B (en) | Correction method and correction device for pixel distortion and terminal | |
| CN110310312B (en) | Image registration method, image registration device and terminal | |
| Salloum et al. | Efficient image splicing localization via contrastive feature extraction | |
| CN114066749A (en) | Phase-dependent anti-noise displacement estimation method, equipment and storage medium | |
| EP3624062A1 (en) | Methods and apparatus for processing image data for machine vision | |
| Cicconet et al. | Complex-valued hough transforms for circles | |
| CN113962877B (en) | Pixel distortion correction method, correction device and terminal | |
| CN113962876B (en) | Pixel distortion correction method, correction device and terminal |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |