Terahertz image denoising method and device for oral cariogenic microorganisms and electronic equipment

Abstract

The invention provides a terahertz image denoising method and device for oral cariogenic microorganisms and electronic equipment. A specific embodiment of the method comprises the following steps: acquiring a terahertz image of the oral cariogenic microorganisms; the terahertz image comprises a phase image and an amplitude image; filtering high-frequency noise in the phase image through Fourier transform to obtain a first de-noised phase image; performing dual-core Gaussian filtering processing on the first de-noised phase image to obtain a second de-noised phase image; obtaining a target phase image according to the first de-noised phase image and the second de-noised phase image; performing dual-core Gaussian filtering processing on the amplitude image to obtain a target amplitude image; and obtaining a target terahertz image of the oral cariogenic microorganisms according to the target phase image and the target amplitude image. According to the method, accurate structure and form information of oral cariogenic microorganisms can be obtained through the target terahertz image.

Description

Technical Field

[0001] The present application relates to the field of image processing, and in particular to a terahertz image denoising method, device and electronic device for oral caries-causing microorganisms. Background Art

[0002] Terahertz (THz) refers to electromagnetic waves with a radiation frequency of 0.1-10THz and a wavelength of 30-3000μm. The radiation frequency range is 0.1-10THz, which proves that it is between the electronics and optics frequencies, so it can have many unique optoelectronic properties.

[0003] In addition, THz radiation has a penetration similar to that of microwaves and can be used to detect the internal information of most dielectric materials. Furthermore, the photon energy of THz radiation is low and will not cause ionization damage to biological tissues, so it is suitable for biological tissue detection.

[0004] In the related art, a terahertz image can be obtained by THz imaging technology. Among them, the terahertz image includes multiple images (such as phase images and amplitude images). However, in the related art, when denoising the terahertz image, a unified denoising method is used to denoise the multiple images included in the terahertz image, which makes the processed terahertz image unable to reflect more details and has low clarity, so the image effect is not good. Summary of the invention

[0005] The purpose of the embodiments of the present application is to provide a method, device and electronic device for denoising a terahertz image of oral caries-causing microorganisms, so as to obtain relatively accurate structural and morphological information of oral caries-causing microorganisms through processed target terahertz images.

[0006] In the first aspect, the embodiment of the present application provides a terahertz image denoising method of oral caries-causing microorganisms, the method comprising: obtaining a terahertz image of oral caries-causing microorganisms; the terahertz image comprises a phase image and an amplitude image; filtering out high-frequency noise in the phase image by Fourier transform to obtain a first denoised phase image; performing dual-core Gaussian filtering on the first denoised phase image to obtain a second denoised phase image; obtaining a target phase image according to the first denoised phase image and the second denoised phase image; performing dual-core Gaussian filtering on the amplitude image to obtain a target amplitude image; obtaining a target terahertz image of the oral caries-causing microorganism according to the target phase image and the target amplitude image. In this way, the phase image and the amplitude image of the caries-causing microorganisms are adaptively denoised, thereby obtaining a relatively clear target terahertz image that retains more details, and then being able to obtain relatively accurate structural and morphological information of the oral caries-causing microorganisms, providing a high reference value for diagnosing and treating oral caries.

[0007] Optionally, filtering out high-frequency noise in the phase image by Fourier transform to obtain the first denoised phase image includes: converting the phase image from the spatial domain to the frequency domain by Fourier transform to obtain a frequency domain image; transferring the low-frequency components in the frequency domain image to the central area of ​​the image; inputting the frequency domain image with the transferred low-frequency components into a high-frequency filter to filter out high-frequency noise; and converting the frequency domain image with the filtered high-frequency noise to the spatial domain by inverse Fourier transform to obtain the first denoised phase image. In this way, the frequency domain image can be spectrally centered to move the low-frequency components to the central position of the image, thereby reducing artifacts that may be introduced during the filtering process.

[0008] Optionally, the step of performing dual-core Gaussian filtering on the first denoised phase image to obtain the second denoised phase image includes: performing convolution operations on the first denoised phase image with two Gaussian kernels of a dual-core Gaussian filter respectively to obtain two convolution results; the two Gaussian filters in the dual-core Gaussian filter have different standard deviations; and obtaining the second denoised phase image according to the difference between the two convolution results. In this way, the first denoised phase image can be smoothed using two Gaussian filters with different standard deviations, and then the image details can be enhanced by determining their difference. Thus, important detail information in the phase image can be retained while denoising, improving the situation where details are lost due to over-smoothing.

[0009] Optionally, obtaining the target phase image according to the first denoised phase image and the second denoised phase image includes: performing weighted superposition of the first denoised phase image and the second denoised phase image to obtain the target phase image. In this way, since there is no high-frequency noise in the first denoised phase image, and the second denoised phase image is a smoothed image after dual-core Gaussian filtering, with less medium and low-frequency noise, the target phase image obtained based on the two can complement each other in different frequency ranges, thereby more comprehensively removing noise and improving detail expression capabilities.

[0010] Optionally, the subjecting the amplitude image to dual-core Gaussian filtering to obtain a target amplitude image includes: convolving the amplitude image with two Gaussian kernels of a dual-core Gaussian filter to obtain two convolution results; the two Gaussian filters in the dual-core Gaussian filter have different standard deviations; and obtaining the target amplitude image according to the difference between the two convolution results and the pixel average of the amplitude image. Here, considering that the filtering process may cause the overall brightness of the amplitude image to decrease, by adding the pixel average of the amplitude image, its global brightness and contrast can be restored, so that the filtered image will not be too dark or too bright.

[0011] Optionally, the oral cariogenic microorganisms include one or more of Streptococcus sanguinis, Candida albicans, Streptococcus sobrinus, Streptococcus salivarius, Streptococcus oralis, and Streptococcus mutans.

[0012] In the second aspect, the embodiment of the present application provides a terahertz image denoising device for oral caries-causing microorganisms, the device comprising: an acquisition module, used to acquire a terahertz image of oral caries-causing microorganisms; the terahertz image comprises a phase image and an amplitude image; a phase image denoising module, used to filter out high-frequency noise in the phase image by Fourier transform to obtain a first denoised phase image; the first denoised phase image is subjected to dual-core Gaussian filtering to obtain a second denoised phase image; a target phase image is obtained according to the first denoised phase image and the second denoised phase image; an amplitude image denoising module, used to perform dual-core Gaussian filtering on the amplitude image to obtain a target amplitude image; a joint module, used to obtain a target terahertz image of the oral caries-causing microorganism according to the target phase image and the target amplitude image. In this way, more accurate structural and morphological information of oral caries-causing microorganisms can be obtained, which provides a higher reference value for the diagnosis and treatment of oral caries.

[0013] In a third aspect, an embodiment of the present application provides an electronic device, comprising a processor and a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the steps in the method provided in the first aspect are performed.

[0014] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps in the method provided in the first aspect are performed.

[0015] In a fifth aspect, an embodiment of the present application provides a computer program product, which includes a computer program or instructions, and when the computer program or instructions are executed by a processor, the method described in the first aspect is performed.

[0016] Other features and advantages of the present application will be described in the following description, and partly become apparent from the description, or be understood by practicing the embodiments of the present application. The purpose and other advantages of the present application can be realized and obtained by the structures specifically pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 A flowchart of a terahertz image denoising method for oral caries-causing microorganisms provided in an embodiment of the present application;

[0019] Figure 2 A terahertz image of a standard strain of oral mutans Streptococcus UA159 provided in an embodiment of the present application;

[0020] Figure 3 A target terahertz image of an oral mutans Streptococcus UA159 standard strain provided in an embodiment of the present application;

[0021] Figure 4 A terahertz image of an oral mutans Streptococcus rnc gene deletion strain provided in an embodiment of the present application;

[0022] Figure 5 A target terahertz image of an oral mutans Streptococcus rnc gene deletion strain provided in an embodiment of the present application;

[0023] Figure 6 A terahertz image of an oral mutans Streptococcus rnc gene overexpressing strain provided in an embodiment of the present application;

[0024] Figure 7 A target terahertz image of an oral mutans Streptococcus rnc gene overexpression strain provided in an embodiment of the present application;

[0025] Figure 8 A terahertz image of an oral mutans Streptococcus smc gene deletion strain provided in an embodiment of the present application;

[0026] Fig. 9 A target terahertz image of an oral mutans Streptococcus smc gene deletion strain provided in an embodiment of the present application;

[0027] Fig.10 A terahertz image of an oral mutans Streptococcus smc gene overexpressing strain provided in an embodiment of the present application;

[0028] Fig.11 A target terahertz image of an oral mutans Streptococcus smc gene overexpression strain provided in an embodiment of the present application;

[0029] Fig.12A structural block diagram of a terahertz image denoising device for oral caries-causing microorganisms provided in an embodiment of the present application;

[0030] Fig.13 A schematic diagram of the structure of an electronic device for executing a terahertz image denoising method for oral caries-causing microorganisms provided in an embodiment of the present application. DETAILED DESCRIPTION

[0031] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0032] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0033] It should be noted that the embodiments in this application or the technical features in the embodiments may be combined if there is no conflict.

[0034] In the related art, there is a problem that terahertz images cannot reflect many details and have low clarity, resulting in poor image effects; in order to solve this problem, the present application provides a terahertz image denoising method, device and electronic device for oral caries-causing microorganisms; further, by denoising the phase image and amplitude image in the terahertz image respectively, the image details are enhanced and the clarity is improved.

[0035] In some application scenarios, the terahertz image denoising method of oral caries-causing microorganisms can be applied to terminal devices such as computers and mobile phones. In other application scenarios, it can also be applied to service terminals such as servers, server clusters or cloud platforms, which are not limited in this application. For example, this application is described below by applying to a server.

[0036] The defects existing in the solutions in the above-mentioned related technologies are the results obtained by the inventor after practice and careful research. Therefore, the discovery process of the above-mentioned problems and the solutions proposed in the embodiments of the present invention below for the above-mentioned problems should all be the contributions made by the inventor to the present invention during the process of the present invention.

[0037] The following text of this application aims to explain the terahertz image denoising method of oral caries-causing microorganisms. This is because the inventors have found in long-term practice that the incidence of oral caries is high, but currently it is impossible to obtain relatively accurate structural and morphological information of oral caries-causing microorganisms, thereby failing to provide a high reference value for the diagnosis and treatment of oral caries.

[0038] Please refer to Figure 1 , which shows a flow chart of a terahertz image denoising method for oral caries-causing microorganisms provided in an embodiment of the present application. Figure 1 As shown, the terahertz image denoising method for oral caries-causing microorganisms includes the following steps 101 to 106.

[0039] Step 101, obtaining a terahertz image of oral caries-causing microorganisms; the terahertz image includes a phase image and an amplitude image;

[0040] The above-mentioned oral caries-causing microorganisms include one or more of Streptococcus sanguinis, Candida albicans, Streptococcus sobrinus, Streptococcus salivarius, Streptococcus oralis, and Streptococcus mutans.

[0041] It should be noted that any of the above-mentioned oral cariogenic microorganisms is a relatively common cariogenic microorganism. In addition to the above-mentioned cariogenic microorganisms, there are other cariogenic microorganisms, which are not listed one by one in this application.

[0042] The above phase image can reflect the fine structure inside the microorganism. Specifically, the differences in the cell wall, cell membrane and internal structure of the microorganism will lead to changes in phase information, so the internal structural information of the microorganism can be obtained through the phase image.

[0043] The above amplitude image can reflect the absorption and scattering characteristics of microorganisms to terahertz radiation, which is closely related to the absorption characteristics of the morphology, size and composition of the microorganisms. Therefore, the amplitude image can better show the edge contour, size and distribution of the microorganisms, so that the morphological information of the microorganisms can be obtained through the amplitude image.

[0044] Step 102, filtering out high-frequency noise in the phase image by Fourier transform to obtain a first denoised phase image;

[0045] In some application scenarios, the phase image can be converted from the spatial domain to the frequency domain through Fourier transform, so as to filter out high-frequency noise in the frequency domain and obtain a first denoised phase image.

[0046] Step 103, performing dual-core Gaussian filtering on the first denoised phase image to obtain a second denoised phase image;

[0047] The above dual-core Gaussian filtering process can be implemented by a dual-core Gaussian filter. In some application scenarios, the calculation formula of the dual-core Gaussian filter can be, for example: Wherein, x and y represent the pixel coordinates of the image (here, the first denoised phase image), and σ represents the standard deviation of the Gaussian filter.

[0048] It should be noted that when the server uses the dual-core Gaussian filter to process the first denoised phase image, the two standard deviations of the dual-core Gaussian filter may be the same or different, and there is no limitation here.

[0049] Step 104, obtaining a target phase image according to the first denoised phase image and the second denoised phase image;

[0050] In some application scenarios, the server may fuse the first denoised phase image and the second denoised phase image to obtain a target phase image.

[0051] In these application scenarios, for example, a feature-based method can be used for fusion. Specifically, since the first denoised phase image has filtered out high-frequency noise, its low-frequency features (such as edges, contours, etc.) can be extracted. Since the second denoised phase image is processed by a dual-core Gaussian filter, it retains more details and is relatively smooth, so its intermediate frequency features (such as texture features) can be extracted. Then, the extracted features can be matched, and the matched features can be fused to obtain the target phase image.

[0052] Step 105, performing dual-core Gaussian filtering on the amplitude image to obtain a target amplitude image;

[0053] It should be noted that this process is similar to the process of obtaining the target phase image and will not be described in detail here.

[0054] Step 106: Obtain a target terahertz image of the oral caries-causing microorganisms according to the target phase image and the target amplitude image.

[0055] It should be noted that the terahertz image includes a phase image and an amplitude image. After the phase image and the amplitude image are denoised respectively, a target terahertz image including a target phase image and a target amplitude image can be obtained.

[0056] Furthermore, the main noise sources of terahertz images include Gaussian noise, speckle noise, Poisson noise and impulse noise, Rayleigh noise, Irish (gamma) noise, uniform noise, exponential distribution noise, etc. Since oral caries-causing microorganisms are collected in an indoor environment, electromagnetic interference and electronic noise of the sensor are more significant, so Gaussian noise has a greater impact on the phase image corresponding to oral caries-causing microorganisms. Therefore, after the phase image is processed based on Fourier transform and dual-core Gaussian filtering, Gaussian noise can be effectively eliminated to obtain a clearer target phase image with more details, while the amplitude image is used to reflect the morphological information of the microorganism. Without Fourier transform, its surface information can be effectively retained. Only dual-core Gaussian filtering can be performed on it to retain more detailed information.

[0057] Therefore, in this implementation, the phase image and amplitude image of cariogenic microorganisms are adaptively denoised, thereby obtaining a relatively clear target terahertz image with more details. In this way, relatively accurate structural and morphological information of oral cariogenic microorganisms can be obtained, providing a high reference value for the diagnosis and treatment of oral caries.

[0058] In some optional implementations, filtering out high-frequency noise in the phase image by Fourier transform in step 102 to obtain a first denoised phase image includes:

[0059] Sub-step 1021, converting the phase image from the spatial domain to the frequency domain by Fourier transform to obtain a frequency domain image;

[0060] Sub-step 1022, transferring the low-frequency components in the frequency domain image to the central area of ​​the image;

[0061] Sub-step 1023, inputting the frequency domain image with the low frequency components transferred into a high frequency filter to filter out high frequency noise;

[0062] Sub-step 1024, converting the frequency domain image from which high-frequency noise has been filtered out to the spatial domain through inverse Fourier transform to obtain the first denoised phase image.

[0063] For example, the server can convert the phase image f(x, y) in the spatial domain into the frequency domain through Fourier transform to obtain the frequency domain image F(u, v). Specifically, the calculation formula The frequency domain image F(u, v) is obtained; wherein u and v represent the frequency coordinates of the pixel in the frequency domain; and x and y represent the pixel coordinates of the phase image.

[0064] Furthermore, since the result of Fourier transform usually makes the low-frequency components concentrated in the image angle, the low-frequency components in the frequency domain image F(u, v) can be transferred to the central area of ​​the image to facilitate filtering operations. Specifically, it can be calculated by Transfer, where M represents the image width, N represents the image height, and F centered (u,v) represents the frequency domain image with the low frequency components shifted.

[0065] Then, the server can input the frequency domain image with the low-frequency components transferred into the high-frequency filter H(u,v) to retain the low-frequency components such as the basic structure and shape and filter out the high-frequency noise. Specifically, the calculation formula G(u,v)=F centered (u,v)·H(u,v) filters out high frequency noise. D0 represents the radius of the high-frequency filter H(u,v), (u0,v0) represents the central pixel coordinates of the frequency domain image F(u,v), and G(u,v) represents the frequency domain image after high-frequency noise is filtered out.

[0066] Then, the server can calculate the inverse Fourier transform The frequency domain image G(u,v) with high-frequency noise filtered out is converted to the spatial domain to obtain the first denoised phase image g(x,y).

[0067] In this implementation, the frequency domain image may be subjected to spectrum centering processing so as to move the low-frequency components to the center of the image, thereby reducing artifacts that may be introduced during the filtering process.

[0068] In some optional implementations, the step 103 of performing dual-kernel Gaussian filtering on the first denoised phase image to obtain a second denoised phase image includes:

[0069] Sub-step 1031, performing convolution operations on the first denoised phase image and two Gaussian kernels of a dual-kernel Gaussian filter respectively to obtain two convolution results; the standard deviations of the two Gaussian filters in the dual-kernel Gaussian filter are different;

[0070] That is, a dual-core Gaussian filter can be constructed using two Gaussian filters with different standard deviations.

[0071] In some application scenarios, the first denoised phase image is more sensitive to noise, so a larger standard deviation is needed to smooth the noise. If the two standard deviations are σ1 and σ2, then σ1∈[1.0,3.0], σ2∈[1.0,3.0].

[0072] It should be noted that the standard deviation can affect the width of the Gaussian filter and its response to frequency components, so the server can subsequently adjust the standard deviation through image effects to obtain a denoising effect that meets actual requirements.

[0073] Sub-step 1032: obtaining the second denoised phase image according to the difference between the two convolution results.

[0074] For ease of understanding, continuing the above example, after obtaining the first denoised phase image g(x, y), the server can calculate it through formula (1): And calculation formula (2): Perform convolution operations on the first denoised phase image g(x,y) to obtain a smooth image and images (That is, the convolution result).

[0075] Then, according to the calculation formula Get the image and images The difference image g detail (x,y), the difference image g detail (x,y) is also the second denoised phase image.

[0076] In this implementation, two Gaussian filters with different standard deviations can be used to smooth the first denoised phase image, and then the image details can be enhanced by determining their differences, so that important detail information in the phase image can be retained while denoising, improving the situation where details are lost due to over-smoothing.

[0077] In some optional implementations, obtaining a target phase image based on the first denoised phase image and the second denoised phase image in the above step 104 includes: performing weighted superposition of the first denoised phase image and the second denoised phase image to obtain the target phase image.

[0078] For example, the server may pre-process the first denoised phase image g(x, y) and the second denoised phase image g detail (x, y) are assigned corresponding weights, and then the two are weighted fused, so that the calculation formula g final (x,y)=g(x,y)+g detail (x,y), get the target phase image g final (x,y).

[0079] In this implementation, the target phase image can be obtained by weighted superposition. In this way, since there is no high-frequency noise in the first denoised phase image, and the second denoised phase image is a smoothed image after dual-core Gaussian filtering, there is less medium and low-frequency noise. Therefore, the target phase images obtained based on the two can complement each other in different frequency ranges, thereby more comprehensively removing noise and improving the ability to express details.

[0080] In some optional implementations, the step 105 of performing dual-core Gaussian filtering on the amplitude image to obtain a target amplitude image includes:

[0081] Sub-step 1051, performing convolution operations on the amplitude image and two Gaussian kernels of a dual-kernel Gaussian filter respectively to obtain two convolution results; the standard deviations of the two Gaussian filters in the dual-kernel Gaussian filter are different;

[0082] In some application scenarios, since amplitude images usually have a higher dynamic range and more edge details, a smaller standard deviation can be used to retain these features. In these application scenarios, if the two standard deviations are σ3 and σ4, then σ3∈[0.5,2.0], σ4∈[0.5,2.0].

[0083] Sub-step 1052, obtaining the target amplitude image according to the difference between the two convolution results and the pixel average value of the amplitude image.

[0084] For example, the server may input the amplitude image A into a dual-core Gaussian filter to perform a convolution operation on the amplitude image A through the dual-core Gaussian filter to obtain two convolution results. The convolution process here may be the same or similar to the convolution process of the first denoised phase image in the previous text, and will not be repeated here.

[0085] Furthermore, the dual-core Gaussian filter can be calculated by the formula F(A)=GaussianBlur(A,k1,σ3)-GaussianBlur(A,k2,σ4)+μ A , and get the target amplitude image F(A). Where k1 represents the kernel of the first Gaussian filter; k2 represents the kernel of the second Gaussian filter; σ3 represents the standard deviation of the first Gaussian filter; σ4 represents the standard deviation of the second Gaussian filter. μ A Characterizes the pixel average value of the amplitude image A.

[0086] In this implementation, considering that the filtering process may cause the overall brightness of the amplitude image to decrease, the global brightness and contrast of the amplitude image can be restored by adding the pixel average value of the amplitude image, so that the filtered image will not be too dark or too bright.

[0087] In some application scenarios, since oral mutans Streptococcus is the main caries-causing microorganism, the present application performs denoising on the terahertz image of oral mutans Streptococcus through the denoising method in any of the above implementations.

[0088] See also Figure 2-Figure 11 In this application, terahertz images corresponding to the standard strain of oral mutans Streptococcus UA159, the rnc gene deletion strain of oral mutans Streptococcus, the rnc gene overexpression strain of oral mutans Streptococcus, the smc gene deletion strain of oral mutans Streptococcus, and the smc gene overexpression strain of oral mutans Streptococcus were denoised, and the target terahertz image of the corresponding oral caries-causing microorganisms after denoising was obtained. Through the target terahertz image, relatively accurate structural and morphological information of the corresponding oral caries-causing microorganisms can be obtained, which provides a high reference value for the diagnosis and treatment of oral caries.

[0089] Those skilled in the art will appreciate that, in the above method of a specific embodiment, the order in which the steps are written does not imply a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of the steps should be determined by their functions and possible internal logic.

[0090] Please refer to Fig.12 , which shows a structural block diagram of a terahertz image denoising device for oral caries-causing microorganisms provided in an embodiment of the present application. The terahertz image denoising device for oral caries-causing microorganisms may be a module, program segment or code on an electronic device. It should be understood that the device is similar to the above-mentioned Figure 1 The method embodiment corresponds to and can be executed Figure 1 The method embodiment involves various steps.

[0091] Optionally, the terahertz image denoising device of the oral caries-causing microorganisms comprises an acquisition module 1201, a phase image denoising module 1202, an amplitude image denoising module 1203 and a combination module 1204. The acquisition module 1201 is used to acquire a terahertz image of the oral caries-causing microorganisms; the terahertz image comprises a phase image and an amplitude image; the phase image denoising module 1202 is used to filter out high-frequency noise in the phase image by Fourier transform to obtain a first denoised phase image; the first denoised phase image is subjected to dual-core Gaussian filtering to obtain a second denoised phase image; a target phase image is obtained according to the first denoised phase image and the second denoised phase image; the amplitude image denoising module 1203 is used to perform dual-core Gaussian filtering on the amplitude image to obtain a target amplitude image; and the combination module 1204 is used to obtain a target terahertz image of the oral caries-causing microorganisms according to the target phase image and the target amplitude image.

[0092] Optionally, the phase image denoising module 1202 is further used to: convert the phase image from the spatial domain to the frequency domain through Fourier transform to obtain a frequency domain image; transfer the low-frequency components in the frequency domain image to the central area of ​​the image; input the frequency domain image with the transferred low-frequency components into a high-frequency filter to filter out high-frequency noise; and convert the frequency domain image with the high-frequency noise filtered out to the spatial domain through inverse Fourier transform to obtain the first denoised phase image.

[0093] Optionally, the phase image denoising module 1202 is further used to: perform convolution operations on the first denoised phase image with two Gaussian kernels of a dual-core Gaussian filter, respectively, to obtain two convolution results; the standard deviations of the two Gaussian filters in the dual-core Gaussian filter are different; and based on the difference between the two convolution results, obtain the second denoised phase image.

[0094] Optionally, the phase image denoising module 1202 is further used to: perform weighted superposition on the first denoised phase image and the second denoised phase image to obtain the target phase image.

[0095] Optionally, the amplitude image denoising module 1203 is further used to: perform convolution operations on the amplitude image with two Gaussian kernels of a dual-core Gaussian filter respectively to obtain two convolution results; the standard deviations of the two Gaussian filters in the dual-core Gaussian filter are different; and obtain the target amplitude image based on the difference between the two convolution results and the pixel average value of the amplitude image.

[0096] Optionally, the oral cariogenic microorganisms include one or more of Streptococcus sanguinis, Candida albicans, Streptococcus sobrinus, Streptococcus salivarius, Streptococcus oralis, and Streptococcus mutans.

[0097] It should be noted that those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0098] Please refer to Fig.13 , Fig.13A schematic diagram of the structure of an electronic device for executing a terahertz image denoising method for oral caries-causing microorganisms provided in an embodiment of the present application, the electronic device may include: at least one processor 1301, such as a CPU, at least one communication interface 1302, at least one memory 1303 and at least one communication bus 1304. Among them, the communication bus 1304 is used to realize direct connection and communication between these components. Among them, the communication interface 1302 of the device in the embodiment of the present application is used to communicate signaling or data with other node devices. The memory 1303 can be a high-speed RAM memory or a non-volatile memory (non-volatile memory), such as at least one disk storage. The memory 1303 can optionally also be at least one storage device located away from the aforementioned processor. The memory 1303 stores computer-readable instructions. When the computer-readable instructions are executed by the processor 1301, the electronic device can execute the above-mentioned Figure 1 The method process is shown.

[0099] Understandably, Fig.13 The structure shown is for illustration only, and the electronic device may also include Fig.13 More or fewer components as shown, or with Fig.13 Different configurations are shown. Fig.13 Each component shown in the figure can be implemented by hardware, software or a combination thereof.

[0100] The present application embodiment provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the following can be performed: Figure 1 The method process in the method embodiment shown is executed by the electronic device.

[0101] An embodiment of the present application provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the methods provided by the above-mentioned method embodiments. For example, the method may include: acquiring a terahertz image of oral caries-causing microorganisms; the terahertz image includes a phase image and an amplitude image; filtering out high-frequency noise in the phase image by Fourier transform to obtain a first denoised phase image; performing dual-kernel Gaussian filtering on the first denoised phase image to obtain a second denoised phase image; obtaining a target phase image based on the first denoised phase image and the second denoised phase image; performing dual-kernel Gaussian filtering on the amplitude image to obtain a target amplitude image; and obtaining a target terahertz image of the oral caries-causing microorganism based on the target phase image and the target amplitude image.

[0102] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0103] In addition, the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple 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.

[0104] Furthermore, the functional modules in the various embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

[0105] In this document, relational terms such as first and second, etc. are used merely to distinguish one entity or operation from another entity or operation, but do not necessarily require or imply any such actual relationship or order between these entities or operations.

[0106] The above description is only an embodiment of the present application and is not intended to limit the protection scope of the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A terahertz image denoising method for oral caries-causing microorganisms, characterized in that: include: Acquire terahertz images of oral cariogenic microorganisms; The terahertz image includes a phase image and an amplitude image; By Fourier transform, high-frequency noise in the phase image is filtered out to obtain a first denoised phase image; Performing dual-kernel Gaussian filtering on the first denoised phase image to obtain a second denoised phase image; Obtaining a target phase image according to the first denoised phase image and the second denoised phase image; Performing dual-core Gaussian filtering on the amplitude image to obtain a target amplitude image; A target terahertz image of the oral caries-causing microorganisms is obtained according to the target phase image and the target amplitude image.

2. The method according to claim 1, characterized in that The step of filtering out high frequency noise in the phase image by Fourier transform to obtain a first denoised phase image comprises: Convert the phase image from the spatial domain to the frequency domain by Fourier transform to obtain a frequency domain image; Transferring low-frequency components in the frequency domain image to a central area of ​​the image; The frequency domain image with the low-frequency components shifted is input into a high-frequency filter to filter out high-frequency noise; The frequency domain image from which high-frequency noise has been filtered out is converted to the spatial domain through inverse Fourier transform to obtain the first denoised phase image.

3. The method according to any one of claims 1 or 2, characterized in that: The step of performing dual-core Gaussian filtering on the first denoised phase image to obtain a second denoised phase image includes: Convolving the first denoised phase image with two Gaussian kernels of a dual-kernel Gaussian filter respectively to obtain two convolution results; the two Gaussian filters in the dual-kernel Gaussian filter have different standard deviations; The second denoised phase image is obtained according to the difference between the two convolution results.

4. The method according to claim 3, characterized in that The step of obtaining a target phase image according to the first denoised phase image and the second denoised phase image comprises: The first denoised phase image and the second denoised phase image are weightedly superimposed to obtain the target phase image.

5. The method according to any one of claims 1-2 and 4, characterized in that: The step of performing dual-core Gaussian filtering on the amplitude image to obtain a target amplitude image includes: The amplitude image is convolved with two Gaussian kernels of a dual-core Gaussian filter to obtain two convolution results; the two Gaussian filters in the dual-core Gaussian filter have different standard deviations; The target amplitude image is obtained according to the difference between the two convolution results and the pixel average value of the amplitude image.

6. The method according to any one of claims 1-2 and 4, characterized in that: The oral caries-causing microorganisms include one or more of Streptococcus sanguinis, Candida albicans, Streptococcus sobrinus, Streptococcus salivarius, Streptococcus oralis, and Streptococcus mutans.

7. A terahertz image denoising device for oral caries-causing microorganisms, characterized in that: include: An acquisition module, used for acquiring terahertz images of oral cariogenic microorganisms; The terahertz image includes a phase image and an amplitude image; A phase image denoising module is used to filter out high-frequency noise in the phase image by Fourier transform to obtain a first denoised phase image; perform dual-core Gaussian filtering on the first denoised phase image to obtain a second denoised phase image; and obtain a target phase image based on the first denoised phase image and the second denoised phase image; An amplitude image denoising module, used for performing dual-core Gaussian filtering on the amplitude image to obtain a target amplitude image; A combined module is used to obtain a target terahertz image of the oral caries-causing microorganisms according to the target phase image and the target amplitude image.

8. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, the method according to any one of claims 1 to 6 is executed.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is executed.

10. A computer program product comprising a computer program or instructions, characterized in that When the computer program or instruction is executed by a processor, the method according to any one of claims 1 to 6 is performed.

Images