CN107085838B - Method and device for removing hologram noise - Google Patents
Method and device for removing hologram noise Download PDFInfo
- Publication number
- CN107085838B CN107085838B CN201710408021.0A CN201710408021A CN107085838B CN 107085838 B CN107085838 B CN 107085838B CN 201710408021 A CN201710408021 A CN 201710408021A CN 107085838 B CN107085838 B CN 107085838B
- Authority
- CN
- China
- Prior art keywords
- hologram
- image
- denoising
- noise
- preset
- 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
- 238000000034 method Methods 0.000 title claims abstract description 65
- 238000001914 filtration Methods 0.000 claims abstract description 49
- 238000012545 processing Methods 0.000 claims abstract description 33
- 238000013528 artificial neural network Methods 0.000 claims abstract description 29
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 21
- 238000001228 spectrum Methods 0.000 claims description 10
- 238000005070 sampling Methods 0.000 claims description 4
- 238000004458 analytical method Methods 0.000 claims description 3
- 230000008878 coupling Effects 0.000 claims description 3
- 238000010168 coupling process Methods 0.000 claims description 3
- 238000005859 coupling reaction Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims 3
- 238000000605 extraction Methods 0.000 claims 1
- 230000006870 function Effects 0.000 description 23
- 238000010586 diagram Methods 0.000 description 10
- 238000003860 storage Methods 0.000 description 9
- 238000004590 computer program Methods 0.000 description 8
- 230000000007 visual effect Effects 0.000 description 8
- 230000003287 optical effect Effects 0.000 description 6
- 230000008901 benefit Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000009826 distribution Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000007796 conventional method Methods 0.000 description 2
- 238000001093 holography Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000013441 quality evaluation Methods 0.000 description 2
- GGCZERPQGJTIQP-UHFFFAOYSA-N sodium;9,10-dioxoanthracene-2-sulfonic acid Chemical compound [Na+].C1=CC=C2C(=O)C3=CC(S(=O)(=O)O)=CC=C3C(=O)C2=C1 GGCZERPQGJTIQP-UHFFFAOYSA-N 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 238000005312 nonlinear dynamic Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- G06T5/70—
Abstract
The invention discloses a method and a device for removing hologram noise, relates to the field of image processing, and mainly aims to solve the problem that the quality of an image is reduced because the detail information in the image is damaged when the noise in the hologram is directly filtered to reproduce the image of the hologram in the prior art. The technical scheme comprises the following steps: acquiring a hologram to be processed, wherein the hologram is a hologram containing speckle noise; denoising the hologram according to a neural network method with an image denoising function; carrying out preset reconstruction processing on the denoised hologram to obtain a reconstructed image of the hologram; and filtering and denoising the reproduced image according to a preset filtering algorithm. The method is mainly used for removing the hologram noise.
Description
Technical Field
The present invention relates to the field of image processing, and in particular, to a method and an apparatus for removing hologram noise.
Background
Holography is a technical means capable of simultaneously recording all information of object light wave front, such as amplitude and phase information, and with the development of computer technology, an optical sensor CCD is used instead of a silver salt dry plate to obtain a digitized hologram, then the data of the obtained hologram is stored in a computer, and the computer reproduces the hologram according to a light wave diffraction model to realize digital holography. The digital holographic imaging is divided into two processes of optical recording and numerical value reproduction, the numerical value reproduction process is a reproduction process of simulating optical holographic by a computer, the complex amplitude distribution of an image light wave field is obtained through numerical value calculation, and the obtained intensity distribution and phase distribution are displayed on a display, so that a morphological structure image (namely a reproduced image) of a sample can be obtained. During the collection, storage, processing, transmission, display, etc. of the digital hologram, various degrees of distortion, such as various types of noise pollution, are often generated, thereby affecting the quality of the digital hologram. Such as speckle noise, which can affect the quality of the image and reduce the signal-to-noise ratio.
At present, the existing method for removing noise in the hologram is to remove noise by using filtering, but the image reconstructed by directly using filtering on the hologram destroys detailed information in the image, so that the quality of the image is reduced.
Disclosure of Invention
In view of the above, the present invention has been made to provide a hologram noise removing method and apparatus that overcomes or at least partially solves the above problems.
By the technical scheme, the method for removing the hologram noise provided by the invention comprises the following steps:
acquiring a hologram to be processed, wherein the hologram is a hologram containing speckle noise;
denoising the hologram according to a neural network method with an image denoising function;
carrying out preset reconstruction processing on the denoised hologram to obtain a reconstructed image of the hologram;
and filtering and denoising the reproduced image according to a preset filtering algorithm.
By the above technical solution, the hologram noise removing apparatus provided by the present invention includes:
the acquisition unit is used for acquiring a hologram to be processed, wherein the hologram is a hologram containing speckle noise;
the first denoising unit is used for denoising the hologram according to a neural network method with an image denoising function;
the processing unit is used for carrying out preset reproduction processing on the denoised hologram to obtain a reproduced image of the hologram;
and the second denoising unit is used for filtering and denoising the reproduced image according to a preset filtering algorithm.
The embodiment of the invention provides a method and a device for removing hologram noise, which comprises the steps of firstly obtaining a hologram to be processed, wherein the hologram is a hologram containing speckle noise, then denoising the hologram according to a neural network method with an image denoising function, then performing preset reconstruction processing on the denoised hologram to obtain a reconstructed image of the hologram, and finally performing filtering denoising on the reconstructed image according to a preset filtering algorithm, compared with the conventional method for removing the noise in the hologram, the method and the device for removing the hologram noise have the advantages that the noise is removed by filtering, the embodiment of the invention firstly denoises the hologram by adopting the neural network, then re-phenomena the denoised hologram, and then performs filtering denoising on the reconstructed image to realize secondary denoising, so that a higher peak signal-to-noise ratio is obtained, the visual effect of the reconstructed image containing the noise is improved, and the efficiency of removing the hologram noise is improved, the quality of the image is improved. The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
FIG. 1 is a flow chart of a method for removing hologram noise according to an embodiment of the present invention;
FIG. 2 is a flow chart of another hologram noise removing method provided by the embodiment of the invention;
fig. 3 is a block diagram illustrating an apparatus for removing hologram noise according to an embodiment of the present invention;
fig. 4 is a block diagram illustrating another hologram noise removing apparatus according to an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
The embodiment of the invention provides a method for removing hologram noise, as shown in fig. 1, the method comprises the following steps:
101. and acquiring the hologram to be processed.
The hologram is a hologram containing speckle noise, and the hologram is shot by a CCD optical sensor instead of a silver salt dry plate, so that the hologram is converted into a digital hologram and can be stored in a computer so as to reproduce the hologram according to a light wave diffraction model. The speckle noise is generated because the high-correlation laser light is reflected on the surface of an object and is coherently superposed to form granular noise on the hologram.
Since digital holograms are different from general images, it is difficult to directly apply an algorithm for restoring an image using a digital image method to a hologram, and thus it is necessary to use a method suitable for processing a digital hologram. For example, a hologram of an image may be acquired using a bosch code approach.
102. And denoising the hologram according to a neural network method with an image denoising function.
The neural network method with the image denoising function can adopt a pulse coupling neural network PCNN for effectively removing the noise of the high-frequency part of the image and reserving and removing the edge part of the image.
It should be noted that PCNN is used as a third-generation artificial neural network, and is mainly used for image denoising, image segmentation, and image enhancement in image processing, and since PCNN is a network model of a continuous domain, a complex nonlinear dynamic system is formed by a feedback neural network formed by interconnecting a plurality of neurons.
103. And carrying out preset reproduction processing on the denoised hologram to obtain a reproduced image of the hologram.
The preset recurrence processing is used for processing the hologram reconstruction image, and the specific method may be to perform inverse discrete fourier transform on the hologram to obtain the hologram reconstruction image.
In the method of converting an image into a hologram, a discretized object function is obtained by sampling an actual object picture as object light, a fourier transform spectrum is obtained by performing a discrete fourier transform, and a hologram is obtained by encoding.
104. And filtering and denoising the reproduced image according to a preset filtering algorithm.
The speckle noise is multiplicative noise, so the preset filtering algorithm is a filtering algorithm for removing the multiplicative noise, and may be Lee filtering. Lee filtering is a spatial domain filtering method, and the filtering result can be adjusted according to the statistical characteristics of the image in a given window, so that the effect of removing noise can be greatly improved.
It should be noted that the Lee filtering needs to minimize the mean square error on the basis of considering multiplicative noise, and therefore, when selecting the mean square error, the theoretical mode of the speckle noise is generally considered together.
Compared with the conventional method for removing the noise in the hologram by filtering, the method for removing the noise in the hologram provided by the embodiment of the invention has the advantages that the neural network is adopted to remove the noise firstly, then the phenomenon is carried out on the denoised hologram, and then the filtering and denoising are carried out on the reconstructed image, so that the secondary denoising is realized, the higher peak signal-to-noise ratio is obtained, the visual effect of the reconstructed image of the noise-containing hologram is improved, the efficiency of removing the noise in the hologram is improved, and the quality of the image is improved.
The embodiment of the present invention provides another method for removing hologram noise, as shown in fig. 2, the method includes:
201. and generating a hologram of the image to be processed according to the preset speckle noise parameters.
In order to clearly display the noise-containing hologram re-phenomenon in the generated hologram, a preset speckle noise parameter, such as the intensity of speckle noise, needs to be set when the hologram is generated, and the preset speckle noise parameter may be set by a technician when the program is edited. For example, the preset speckle noise intensity may be 0.01. In addition, the picture taken with the CDD camera may also be subjected to a grayscale process before the hologram is generated.
For the embodiment of the present invention, step 201 may specifically include: extracting an object function after sampling of an image to be processed, performing discrete Fourier transform on the object function to obtain a Fourier transform spectrum, and encoding the Fourier transform spectrum through a preset hologram encoding mode and speckle noise determined according to preset speckle noise parameters to obtain a hologram of the image to be processed.
The preset hologram encoding mode is used for encoding a fourier transform spectrum after discrete fourier transform into a digital hologram, and may be a bosch code.
202. And acquiring the hologram to be processed.
This step is the same as step 101 shown in fig. 1, and is not described herein again.
203. And denoising the hologram according to a neural network method with an image denoising function.
This step is the same as step 102 shown in fig. 1, and is not described herein again.
204. And carrying out preset reproduction processing on the denoised hologram to obtain a reproduced image of the hologram.
This step is the same as step 103 shown in fig. 1, and is not described herein again.
205. And filtering and denoising the reproduced image according to a preset filtering algorithm.
This step is the same as step 104 shown in fig. 1, and will not be described herein again.
206. Analyzing the quality index parameters of the re-phenomenon after denoising, and adjusting the parameters in the neural network method with the image denoising function and the preset filtering algorithm according to the quality index parameters.
The quality index parameters include a peak signal-to-noise ratio, an equivalent visual number, and a speckle index, and the parameters of the neural network method are parameters in a neural network model, such as MATLAB, which can be set by a technician when data simulation is performed by using computer software, and the embodiment of the present invention is not particularly limited. The parameters in the preset filtering algorithm are parameters when the Lee filter performs filtering, and may be specifically set by a technician, and the embodiment of the present invention is not specifically limited. And analyzing the quality index parameters of the re-phenomenon after the de-noising to realize the quality evaluation after the de-noising.
The analysis quality index parameter is a parameter for identifying various parameters that determine a peak signal-to-noise ratio, an equivalent view, and a speckle index, for example, the peak signal-to-noise ratio can well evaluate the intensity of noise in an image, and the formula (1) is as follows:
PSNR＝10log10(2552/MSE) (1)；
wherein MSE represents the mean square error of the image, and the larger the peak signal-to-noise ratio, the smaller the noise of the image. The equivalent view is an objective index for measuring the smoothness of an image, and the mathematical formula (2) is as follows:
wherein, mu and sigma are the mean value and standard deviation of the whole image respectively, and the larger the equivalent view is, the smoother the image is. The speckle index measures the intensity of speckle noise in an image, and mathematical formula (3) is as follows:
where N denotes the size of the image, σ (i, j) and μ (i, j) are the standard deviation and mean of the grey values of the elements in the window, and the smaller the speckle index, the sharper the image.
207. The adjusted parameters are marked as default parameters for removing hologram noise.
For the embodiment of the invention, when the hologram noise is removed again, the default parameters are directly adopted for denoising. The mark may be a symbol mark or a memory mark, and the embodiment of the present invention is not particularly limited. In order to ensure that the best denoising effect can be achieved in each denoising, the adjusted parameters are marked as default parameters, and the denoising is carried out by the optimal parameters.
For example, after analyzing the peak signal-to-noise ratio, the equivalent visual number, and the speckle index, parameters in the peak signal-to-noise ratio, the equivalent visual number, and the speckle index with the best quality can be determined to be a, b, and c, respectively, and are marked as default parameters, and when denoising is performed next time, denoising is performed directly by using a, b, and c.
For the embodiment of the present invention, specific application scenarios may be as follows, but are not limited to the following scenarios, including: the method comprises the steps of taking an apple picture by using a CCD camera, generating a hologram of the apple image, performing reconstruction processing after performing first denoising by using a PCNN neural network to obtain a reconstructed image of the hologram, performing secondary filtering denoising on the reconstructed image of the apple image by using a Lee filter, and finally obtaining the denoised reconstructed image.
According to the method for removing the noise of the hologram, the hologram is generated according to the preset speckle noise parameters, then the PCNN is adopted to denoise the hologram, then the denoised hologram is subjected to re-phenomenon, then the reproduced image is subjected to filtering denoising, secondary denoising is achieved, the quality index parameters of the denoised reproduced image are analyzed, and the parameters of the optimal denoising method are obtained, so that when denoising is performed again, the optimal parameters are directly used, the high peak signal-to-noise ratio is achieved, the visual effect of the reproduced image of the hologram with the noise is improved, the efficiency of removing the noise of the hologram is improved, and the quality of the image is improved.
Further, as a specific implementation of the method shown in fig. 1, an embodiment of the present invention provides an apparatus for removing hologram noise, where as shown in fig. 3, the apparatus may include: the device comprises an acquisition unit 31, a first denoising unit 32, a processing unit 33 and a second denoising unit 34.
The acquiring unit 31 is configured to acquire a hologram to be processed, where the hologram is a hologram containing speckle noise; the acquiring unit 31 executes a function module for acquiring a hologram to be processed for the hologram noise removing apparatus.
A first denoising unit 32, configured to denoise the hologram according to a neural network method having an image denoising function; the first denoising unit 32 is a functional module of a hologram noise removing apparatus for performing denoising of the hologram according to a neural network method having an image denoising function.
A processing unit 33, configured to perform preset reconstruction processing on the denoised hologram to obtain a reconstructed image of the hologram; the processing unit 33 is a functional module for executing preset reproduction processing on the de-noised hologram by the hologram noise removing device to obtain a reproduced image of the hologram.
And a second denoising unit 34, configured to filter and denoise the reproduced image according to a preset filtering algorithm. The second denoising unit 34 is a functional module for the hologram noise removing apparatus to perform filtering and denoising on the reproduced image according to a preset filtering algorithm. Compared with the existing method for removing the noise in the hologram by filtering, the device for removing the hologram noise provided by the embodiment of the invention firstly removes the noise in the hologram by adopting the neural network, then carries out re-phenomenon on the de-noised hologram, and then carries out filtering de-noising on the reproduced image, thereby realizing secondary de-noising, obtaining higher peak signal-to-noise ratio, improving the visual effect of the reproduced image of the noise-containing hologram, improving the efficiency of removing the hologram noise and improving the quality of the image.
The embodiment of the apparatus corresponds to the embodiment of the method, and for convenience of reading, details in the embodiment of the apparatus are not repeated one by one, but it should be clear that the apparatus in the embodiment can correspondingly implement all the contents in the embodiment of the method.
Further, as a specific implementation of the method shown in fig. 2, an embodiment of the present invention provides another apparatus for removing hologram noise, where as shown in fig. 4, the apparatus may include: the device comprises an acquisition unit 41, a first denoising unit 42, a processing unit 43, a second denoising unit 44, a generation unit 45, an analysis unit 46 and a marking unit 47.
An obtaining unit 41, configured to obtain a hologram to be processed, where the hologram is a hologram containing speckle noise;
a first denoising unit 42, configured to denoise the hologram according to a neural network method having an image denoising function;
a processing unit 43, configured to perform preset reconstruction processing on the denoised hologram to obtain a reconstructed image of the hologram;
and a second denoising unit 44, configured to filter and denoise the reproduced image according to a preset filtering algorithm.
Further, in order to clearly present a noise-containing hologram reproduction phenomenon in the generated hologram, when the hologram is generated, a preset speckle noise parameter needs to be set, and the apparatus further includes:
and the generating unit 45 is used for generating the hologram of the image to be processed according to the preset speckle noise parameters.
Further, in order to facilitate performing a discrete fourier transform, thereby obtaining a digital hologram, the generating unit 45 includes:
an extracting module 4501, configured to extract an object function after sampling an image to be processed;
a transform module 4502, configured to perform discrete fourier transform on the object function to obtain a fourier transform spectrum;
and an encoding module 4503, configured to encode the fourier transform spectrum according to a preset hologram encoding mode and speckle noise determined according to a preset speckle noise parameter, so as to obtain a hologram of the image to be processed.
Further, for the quality evaluation after denoising, the apparatus further comprises:
and the analyzing unit 46 is configured to analyze a quality index parameter of the denoised reproduced image, and adjust parameters in the neural network method with the image denoising function and the preset filtering algorithm according to the quality index parameter.
Further, in order to ensure that the best denoising effect can be achieved in each denoising, the adjusted parameters are marked as default parameters, and the denoising with the optimal parameters is realized, the apparatus further includes:
and a marking unit 47, configured to mark the adjusted parameter as a default parameter for removing the hologram noise, so that when the hologram noise is removed again, the default parameter is directly used for denoising.
The embodiment of the apparatus corresponds to the embodiment of the method, and for convenience of reading, details in the embodiment of the apparatus are not repeated one by one, but it should be clear that the apparatus in the embodiment can correspondingly implement all the contents in the embodiment of the method.
According to the device for removing the noise of the hologram, which is provided by the embodiment of the invention, the hologram is generated according to the preset speckle noise parameters, then the PCNN is adopted to remove the noise of the hologram, then the phenomenon is reproduced on the de-noised hologram, then the filtering and de-noising are carried out on the reproduced image, the secondary de-noising is realized, and the quality index parameters of the de-noised reproduced image are analyzed to obtain the parameters of the optimal de-noising method, so that when the de-noising is carried out again, the optimal parameters are directly used, the higher peak signal-to-noise ratio is realized, the visual effect of the reproduced image of the noise-containing hologram is improved, the efficiency of removing the noise of the hologram is.
The hologram noise removing device comprises a processor and a memory, wherein the acquiring unit, the first denoising unit, the processing unit, the second denoising unit and the like are stored in the memory as program units, and the processor executes the program units stored in the memory to realize corresponding functions.
The processor comprises a kernel, and the kernel calls the corresponding program unit from the memory. One or more than one kernel can be set, and the problem that the quality of an image is reduced because the detail information in the image is damaged by directly using filtering on the noise in the hologram to reproduce the image of the hologram in the prior art is solved by adjusting the parameters of the kernels.
The memory may include volatile memory in a computer readable medium, Random Access Memory (RAM) and/or nonvolatile memory such as Read Only Memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip.
The present application further provides a computer program product adapted to perform program code for initializing the following method steps when executed on a data processing device: acquiring a hologram to be processed, wherein the hologram is a hologram containing speckle noise; denoising the hologram according to a neural network method with an image denoising function; carrying out preset reconstruction processing on the denoised hologram to obtain a reconstructed image of the hologram; and filtering and denoising the reproduced image according to a preset filtering algorithm.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). The memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (2)
1. A method for removing hologram noise, comprising:
acquiring a hologram to be processed, wherein the hologram is a hologram containing speckle noise;
denoising the hologram according to a neural network method with an image denoising function, wherein the neural network method with the image denoising function is a pulse coupling neural network PCNN and is used for removing noise of a high-frequency part of an image and reserving an image edge part;
carrying out preset reconstruction processing on the denoised hologram to obtain a reconstructed image of the hologram;
filtering and denoising the reproduced image according to a preset filtering algorithm;
before the acquiring the hologram to be processed, the method further comprises:
generating a hologram of an image to be processed according to a preset speckle noise parameter;
the generating the hologram of the image to be processed according to the preset speckle noise parameter includes:
extracting an object function after sampling of an image to be processed;
performing discrete Fourier transform on the objective function to obtain a Fourier transform spectrum;
encoding the Fourier transform spectrum by a preset hologram encoding mode and speckle noise determined according to preset speckle noise parameters to obtain a hologram of an image to be processed;
after the filtering and denoising the reproduced image according to a preset filtering algorithm, the method further comprises:
analyzing the quality index parameter of the re-phenomenon after denoising, and adjusting the parameters in the neural network method with the image denoising function and the preset filtering algorithm according to the quality index parameter;
and marking the adjusted parameters as default parameters for removing the hologram noise so as to directly adopt the default parameters for denoising when the hologram noise is removed again.
2. An apparatus for removing hologram noise, comprising:
the acquisition unit is used for acquiring a hologram to be processed, wherein the hologram is a hologram containing speckle noise;
the first denoising unit is used for denoising the hologram according to a neural network method with an image denoising function, wherein the neural network method with the image denoising function is a pulse coupling neural network PCNN and is used for removing noise of a high-frequency part of an image and reserving an image edge part;
the processing unit is used for carrying out preset reproduction processing on the denoised hologram to obtain a reproduced image of the hologram;
the second denoising unit is used for filtering and denoising the reproduced image according to a preset filtering algorithm;
the device further comprises:
the generating unit is used for generating a hologram of an image to be processed according to a preset speckle noise parameter;
the generation unit includes:
the extraction module is used for extracting the sampled object function of the image to be processed;
the transformation module is used for carrying out discrete Fourier transformation on the objective function to obtain a Fourier transformation spectrum;
the encoding module is used for encoding the Fourier transform spectrum through a preset hologram encoding mode and speckle noise determined according to preset speckle noise parameters to obtain a hologram of an image to be processed;
the device further comprises:
the analysis unit is used for analyzing the quality index parameters of the reproduced image after denoising and adjusting the parameters in the neural network method with the image denoising function and the preset filtering algorithm according to the quality index parameters;
and the identification unit is used for marking the adjusted parameters as default parameters for removing the hologram noise so as to directly adopt the default parameters for denoising when the hologram noise is removed again.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710408021.0A CN107085838B (en) | 2017-06-02 | 2017-06-02 | Method and device for removing hologram noise |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710408021.0A CN107085838B (en) | 2017-06-02 | 2017-06-02 | Method and device for removing hologram noise |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107085838A CN107085838A (en) | 2017-08-22 |
| CN107085838B true CN107085838B (en) | 2021-02-26 |
Family
ID=59609108
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710408021.0A Active CN107085838B (en) | 2017-06-02 | 2017-06-02 | Method and device for removing hologram noise |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107085838B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108267945B (en) * | 2018-01-16 | 2019-08-09 | 电子科技大学 | A method of the elimination optical scanner holography defocus noise based on self-organizing map neural network |
| CN108089425B (en) * | 2018-01-16 | 2019-09-24 | 电子科技大学 | A method of the elimination optical scanner holography defocus noise based on deep learning |
| CN109978782A (en) * | 2019-03-18 | 2019-07-05 | 新疆大学 | The minimizing technology and device of speckle noise in a kind of Reconstructed Image of Digital Holography |
| CN110097518B (en) * | 2019-04-28 | 2022-12-27 | 东软医疗系统股份有限公司 | Image denoising method and device and terminal equipment |
| CN114384780B (en) * | 2020-10-16 | 2024-02-09 | 深圳大学 | Method, apparatus, computer device and storage medium for imaging through scattering medium |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106067026B (en) * | 2016-05-30 | 2020-01-31 | 天水师范学院 | Characteristic extraction, identification and retrieval method of traditional Chinese medicine microscopic images |
| CN106228523A (en) * | 2016-07-28 | 2016-12-14 | 新疆大学 | A kind of method improving noisy digital hologram quality reproduction |
-
2017
- 2017-06-02 CN CN201710408021.0A patent/CN107085838B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN107085838A (en) | 2017-08-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107085838B (en) | Method and device for removing hologram noise | |
| CN107958235B (en) | Face image detection method, device, medium and electronic equipment | |
| JP2010003347A5 (en) | ||
| Li et al. | Deep DIH: single-shot digital in-line holography reconstruction by deep learning | |
| CN114677300A (en) | Hyperspectral image depth noise reduction method and system based on two-stage learning framework | |
| CN114926374B (en) | Image processing method, device and equipment based on AI and readable storage medium | |
| KR102190773B1 (en) | Apparatus and method for speckle removal in hologram using light field conversion and deep learning | |
| CN115640506B (en) | Magnetic particle distribution model reconstruction method and system based on time-frequency spectrum signal enhancement | |
| Madsen et al. | On-axis digital holographic microscopy: Current trends and algorithms | |
| CN110352387B (en) | System and method for reconstructing holographic lensless images by multi-depth sparse phase recovery | |
| CN112950731B (en) | Transparent scattering medium imaging method under single-frame strong background interference | |
| CN114384780B (en) | Method, apparatus, computer device and storage medium for imaging through scattering medium | |
| CN112288633B (en) | Novel sub-pixel resolution diffraction imaging method | |
| CN113554555B (en) | Phase distortion compensation method, apparatus, computer device and storage medium | |
| Maycock et al. | Speckle reduction of reconstructions of digital holograms using three dimensional filtering | |
| CN111176091A (en) | 3D holographic animal model projection method | |
| CN111722513B (en) | Holographic display method, system, equipment and storage medium based on frequency decomposition | |
| AKINTOYE et al. | COMPOSITE MEDIAN WIENER FILTER BASED TECHNIQUE FOR IMAGE ENHANCEMENT. | |
| Sharma et al. | SVD Based Noise Removal Technique: An Experimental Analysis. | |
| Gavet et al. | Image Processing Tutorials with Python® | |
| Proppe et al. | 3d-2d neural nets for phase retrieval in noisy interferometric imaging | |
| EP3318932B1 (en) | System and method for the removal of twin-image artifact in lens free imaging | |
| Agrawal et al. | K-means clustering for adaptive wavelet based image denoising | |
| Papachary et al. | DLCNN Model with Multi-exposure Fusion for Underwater Image Enhancement | |
| Oroumchian | ECEI Spectrogram Denoising and Feature Extraction Using a Multi-Wavelet Convolutional Neural Network Model |
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 |