Digital radiographic image processing method, device, equipment, and storage medium

Abstract

The present application discloses a digital radiographic image processing method, apparatus, equipment, and storage medium, which relate to the field of industrial image detection technology and are applied to industrial detection equipment, including: determining a current Gaussian filter based on the signal-to-noise ratio of the digital radiographic image to be processed; the current Gaussian filter includes a first parameter for controlling high-frequency enhancement and a second parameter for controlling low-frequency suppression; using the current Gaussian filter to filter the frequency domain decomposition result of the digital radiographic image to be processed to obtain corresponding filtered image information; converting the filtered image information to the spatial domain to obtain a processed image corresponding to the digital radiographic image to be processed, so as to use the processed image to perform relevant industrial detection operations. It can be seen that the present application determines a Gaussian filter that meets the current image processing requirements based on the signal-to-noise ratio of the digital radiographic image to be processed, which can suppress low-frequency noise while retaining high-frequency details, and can improve the enhancement effect of the digital radiographic image.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial image detection, and in particular to a digital radiographic image processing method, device, equipment and storage medium. Background Art

[0002] Among the methods used to process high-resolution digital radiographic images for industrial inspection, commonly used image enhancement methods, such as histogram equalization, spatial filtering, and the Mexican Hat algorithm, primarily improve image quality by directly adjusting pixel values. However, these methods exhibit significant issues when processing high-frequency details, such as amplifying noise while enhancing high-frequency details and losing detail due to a lack of processing of frequency domain characteristics. In frequency domain processing, commonly used methods, such as Fourier transforms and wavelet transforms, can separate high- and low-frequency components by converting images from the spatial domain to the frequency domain, providing new insights for image enhancement. However, existing frequency domain processing methods still suffer from poor adaptability to the local features of different image regions, resulting in uneven enhancement effects. Digital radiographic images processed in this manner can further impact the accuracy of image recognition during subsequent industrial inspections.

[0003] It can be seen that how to improve the processing effect of digital radiographic images is a problem to be solved in this field. Summary of the Invention

[0004] In view of this, the present invention aims to provide a digital radiographic image processing method, apparatus, device, and storage medium. This method determines a Gaussian filter suitable for the current image processing based on the signal-to-noise ratio of the digital radiographic image to be processed. This method can suppress low-frequency noise while preserving high-frequency details, thereby improving the enhancement effect of digital radiographic images. The specific implementation is as follows:

[0005] In a first aspect, the present application provides a digital radiographic image processing method, which is applied to industrial inspection equipment, comprising:

[0006] Determining a current Gaussian filter according to a signal-to-noise ratio of the digital radiographic image to be processed; the current Gaussian filter includes a first parameter for controlling high-frequency enhancement and a second parameter for controlling low-frequency suppression;

[0007] Using the current Gaussian filter to filter the frequency domain decomposition result of the digital radiographic image to be processed to obtain corresponding filtered image information;

[0008] The filtered image information is converted into a spatial domain to obtain a processed image corresponding to the digital radiographic image to be processed, so as to perform relevant industrial detection operations using the processed image.

[0009] Optionally, determining the current Gaussian filter according to the signal-to-noise ratio of the digital radiographic image to be processed includes:

[0010] Determining a digital radiographic image to be processed, and displaying, through a preset parameter interactive interface, several sets of filter parameter information that match the signal-to-noise ratio of the digital radiographic image to be processed; each set of filter parameter information includes a first parameter and a corresponding second parameter;

[0011] Obtaining selection instructions for several groups of filter parameter information through the preset parameter interaction interface;

[0012] A parameter adjustment operation is performed on a preset Gaussian filter based on the target filter parameter information corresponding to the selection instruction to obtain a current Gaussian filter corresponding to the digital radiographic image to be processed.

[0013] Optionally, the filtering process of the frequency domain decomposition result of the digital radiographic image to be processed by using the current Gaussian filter includes:

[0014] Performing a logarithmic transformation operation on the digital radiographic image to be processed using a preset logarithmic transformation formula to obtain corresponding transformed image information; the preset logarithmic transformation formula is a formula constructed based on a sixteen-bit depth image;

[0015] Performing a frequency domain decomposition operation on the transformed image information based on a fast Fourier transform to obtain a corresponding frequency domain decomposition result;

[0016] The frequency domain decomposition result is filtered using the current Gaussian filter.

[0017] Optionally, performing a logarithmic transformation operation on the digital radiographic image to be processed using a preset logarithmic transformation formula includes:

[0018] Based on the weighted average method, the color channel of the digital radiographic image to be processed is converted into a single-channel grayscale value to obtain a corresponding grayscale image;

[0019] A logarithmic transformation operation is performed on the grayscale image using a preset logarithmic transformation formula.

[0020] Optionally, converting the filtered image information into a spatial domain to obtain a processed image corresponding to the digital radiographic image to be processed includes:

[0021] Converting the filtered image information into a spatial domain based on an inverse fast Fourier transform to obtain a corresponding converted image;

[0022] Determining a current image processing strategy corresponding to the digital radiographic image to be processed; the current image processing strategy is a processing strategy constructed based on a bilinear interpolation algorithm and / or a contrast-limited adaptive equalization technique;

[0023] If the current image processing strategy only includes the bilinear interpolation algorithm or the limited contrast adaptive equalization technique, the converted image is processed using the bilinear interpolation algorithm or the limited contrast adaptive equalization technique to obtain a first processed image corresponding to the digital radiographic image to be processed;

[0024] If the current image processing strategy includes the bilinear interpolation algorithm and the contrast-limited adaptive equalization technique, performing a first processing on the converted image using a first processing method, and performing a second processing on the image obtained by the first processing using a second processing method, to obtain a second processed image corresponding to the digital radiographic image to be processed;

[0025] The first processing method is any one of the bilinear interpolation algorithm and the limited contrast adaptive equalization technology, and the second processing method is another processing method of the bilinear interpolation algorithm and the limited contrast adaptive equalization technology except the first processing method.

[0026] Optionally, the method further includes:

[0027] The fast Fourier transform or the inverse fast Fourier transform process is accelerated by a pre-set computer vision and machine learning library to obtain the frequency domain decomposition result or convert the filtered image information into the spatial domain.

[0028] Optionally, performing relevant industrial inspection operations using the processed image includes:

[0029] Determining the type of image visual effect corresponding to the industrial inspection equipment according to a pre-constructed correspondence table representing the correspondence between the industrial inspection equipment and the image visual effect;

[0030] Displaying several groups of visual parameter information matching the image visual effect type through a preset parameter interaction interface, and obtaining operation instructions for the several groups of visual parameter information;

[0031] A linear adjustment operation is performed on the processed image based on the target visual parameter information corresponding to the operation instruction, so as to use the linearly adjusted image to perform relevant industrial detection operations.

[0032] In a second aspect, the present application provides a digital radiographic image processing device for use in industrial inspection equipment, comprising:

[0033] A filter determination module, configured to determine a current Gaussian filter according to a signal-to-noise ratio of the digital radiographic image to be processed; the current Gaussian filter includes a first parameter for controlling high-frequency enhancement and a second parameter for controlling low-frequency suppression;

[0034] a filtering module, configured to filter the frequency domain decomposition result of the digital radiographic image to be processed using the current Gaussian filter to obtain corresponding filtered image information;

[0035] The conversion module is used to convert the filtered image information into the spatial domain to obtain a processed image corresponding to the digital radiographic image to be processed, so as to use the processed image to perform relevant industrial detection operations.

[0036] In a third aspect, the present application provides an electronic device, comprising:

[0037] Memory, used to store computer programs;

[0038] A processor is used to execute the computer program to implement the digital radiographic image processing method as described above.

[0039] In a fourth aspect, the present application provides a computer-readable storage medium for storing a computer program, which, when executed by a processor, implements the digital radiographic image processing method as described above.

[0040] It can be seen that when the industrial inspection equipment in this application processes digital radiographic images, it first determines the current Gaussian filter based on the signal-to-noise ratio of the digital radiographic image to be processed; the current Gaussian filter includes a first parameter for controlling high-frequency enhancement and a second parameter for controlling low-frequency suppression; the frequency domain decomposition result of the digital radiographic image to be processed is then filtered using the current Gaussian filter to obtain corresponding filtered image information; the filtered image information is then converted to the spatial domain to obtain a processed image corresponding to the digital radiographic image to be processed, so that the processed image can be used to perform relevant industrial inspection operations. In this way, when processing digital radiographic images, the present application can determine a Gaussian filter that meets the current image processing requirements based on the signal-to-noise ratio of the digital radiographic image to be processed, and achieve concurrent high-frequency enhancement and low-frequency suppression with the help of the first parameter and the second parameter for controlling high-frequency enhancement and low-frequency suppression, thereby suppressing low-frequency noise while retaining high-frequency details, solving problems such as detail loss, noise amplification, and artifact generation, and improving the enhancement effect of digital radiographic images. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0042] Figure 1This is a flow chart of a digital radiographic image processing method disclosed in this application;

[0043] Figure 2 This is a flow chart of a specific digital radiographic image processing method disclosed in this application;

[0044] Figure 3 This is a structural diagram of a digital radiographic image processing device disclosed in this application;

[0045] Figure 4 This is a structural diagram of an electronic device disclosed in this application. DETAILED DESCRIPTION

[0046] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0047] See also Figure 1 As shown, an embodiment of the present invention discloses a digital radiographic image processing method, which is applied to industrial detection equipment, comprising:

[0048] Step S11 : determining a current Gaussian filter according to the signal-to-noise ratio of the digital radiographic image to be processed; the current Gaussian filter includes a first parameter for controlling high-frequency enhancement and a second parameter for controlling low-frequency suppression.

[0049] In the present application, when the industrial inspection equipment obtains the digital radiographic image to be processed, the signal-to-noise ratio of the digital radiographic image to be processed can be calculated, and the current Gaussian filter to be used for the digital radiographic image to be processed can be determined based on the signal-to-noise ratio of the image. It is understandable that the signal-to-noise ratios of different images are different, and when the Gaussian filter is used to enhance the image, the processing effect on images with different signal-to-noise ratios is also different. Furthermore, the present application can determine a filter that is more suitable for processing the current image based on the signal-to-noise ratio of the digital radiographic image to be processed. It should be pointed out that the current Gaussian filter includes a pre-set first parameter for controlling high-frequency enhancement and a second parameter for controlling low-frequency suppression. Combining these two parameters with the signal-to-noise ratio of the image, a suitable filter can be determined for filtering the current digital radiographic image to be processed.

[0050] In a specific embodiment, determining the current Gaussian filter based on the signal-to-noise ratio of the digital radiographic image to be processed may include: determining the digital radiographic image to be processed, and displaying several groups of filter parameter information matching the signal-to-noise ratio of the digital radiographic image to be processed through a preset parameter interaction interface; a single group of the filter parameter information includes a first parameter and a corresponding second parameter; obtaining selection instructions for several groups of the filter parameter information through the preset parameter interaction interface; and performing parameter adjustment operations on the preset Gaussian filter based on the target filter parameter information corresponding to the selection instruction to obtain the current Gaussian filter corresponding to the digital radiographic image to be processed. Specifically, in the process of determining the current Gaussian filter based on the signal-to-noise ratio of the digital radiographic image to be processed, it is first necessary to determine the image to be processed, that is, the digital radiographic image to be processed, and then calculate the signal-to-noise ratio of the image, and display several groups of filter parameter information that match the calculated signal-to-noise ratio through a preset parameter interactive interface; it can be understood that, based on the signal-to-noise ratio, several groups of filter parameter information can be screened out, and a group of parameters specifically includes a first parameter and a corresponding second parameter; further, relevant staff can select a suitable set of parameters according to actual needs, that is, issue a selection instruction for several groups of filter parameters, and then use the target filter parameter information corresponding to the selection instruction to adjust the parameters of the pre-set Gaussian filter, which can also obtain a Gaussian filter that is adapted to the current signal-to-noise ratio of the digital radiographic image to be processed and suitable for current actual needs.

[0051] Step S12: Filter the frequency domain decomposition result of the digital radiographic image to be processed using the current Gaussian filter to obtain corresponding filtered image information.

[0052] In this application, the above steps can be used to determine a suitable current Gaussian filter based on the signal-to-noise ratio of the digital radiographic image to be processed; then, the current Gaussian filter can be used to filter the frequency domain decomposition results of the digital radiographic image to be processed. It can be understood that by combining the first parameter for controlling high-frequency gain and the second parameter for controlling low-frequency suppression in the current Gaussian filter, a balance between high-frequency enhancement and low-frequency suppression can be achieved in the current digital radiographic image to be processed, ultimately obtaining the corresponding filtered image information. Furthermore, the Gaussian filter Z(D) is specifically as follows:

[0053] ;

[0054] in, Indicates the distance between the frequency point and the center of the spectrum, M and N are the image sizes, d0 is the cutoff frequency, and Control the high-frequency gain and low-frequency attenuation rate respectively, and c adjusts the steepness of the transition band. The exponential attenuation characteristic preserves high-frequency details while suppressing low-frequency noise; and It can be dynamically and adaptively adjusted according to the signal-to-noise ratio of the image.

[0055] In another specific embodiment, performing a logarithmic transformation on the digital radiographic image to be processed using a preset logarithmic transformation formula may include: converting the color channels of the digital radiographic image to be processed into single-channel grayscale values ​​based on a weighted average method to obtain a corresponding grayscale image; and performing a logarithmic transformation on the grayscale image using a preset logarithmic transformation formula. Specifically, during the logarithmic transformation of the digital radiographic image to be processed, the digital radiographic image to be processed may first be converted into a grayscale image, thereby reducing computational complexity and preserving key structural information; wherein, a weighted average method may be used to convert the color channels of the digital radiographic image to be processed into single-channel grayscale values ​​to obtain a corresponding grayscale image. Subsequently, the grayscale image may be logarithmically transformed using the preset logarithmic transformation formula.

[0056] In a specific embodiment, the method may further include accelerating the Fast Fourier Transform (FFT) or Inverse Fast Fourier Transform (IFFT) process using a pre-configured computer vision and machine learning library to obtain the frequency domain decomposition result or convert the filtered image information into the spatial domain. Specifically, to increase the speed of image processing, the FFT and IFFT processes in the above embodiment may be accelerated using a computer vision and machine learning library. For large-scale image processing tasks, parallel acceleration optimization may be performed to increase image processing speed.

[0057] Step S13: convert the filtered image information into a spatial domain to obtain a processed image corresponding to the digital radiographic image to be processed, so as to perform relevant industrial inspection operations using the processed image.

[0058] In this application, the above steps can be used to filter the current digital radiographic image to be processed using a suitable current Gaussian filter to obtain corresponding filtered image information. Furthermore, the filtered image information in the frequency domain can be converted to the spatial domain to obtain a processed image that has been filtered to perform high-frequency gain and low-frequency suppression. Furthermore, this processed image can be used for subsequent industrial inspection operations.

[0059] In a specific embodiment, converting the filtered image information to the spatial domain to obtain a processed image corresponding to the digital radiographic image to be processed may include: converting the filtered image information to the spatial domain based on inverse fast Fourier transform to obtain a corresponding converted image; determining a current image processing strategy corresponding to the digital radiographic image to be processed; the current image processing strategy is a processing strategy constructed based on a bilinear interpolation algorithm and / or a limited contrast adaptive equalization technology; if the current image processing strategy only includes the bilinear interpolation algorithm or the limited contrast adaptive equalization technology, then using the bilinear interpolation algorithm or the limited contrast adaptive equalization technology to process the converted image to obtain to a first processed image corresponding to the digital radiographic image to be processed; if the current image processing strategy includes the bilinear interpolation algorithm and the limited contrast adaptive equalization technology, the converted image is processed for the first time using the first processing method, and the image obtained by the corresponding first processing is processed for the second time using the second processing method to obtain a second processed image corresponding to the digital radiographic image to be processed; wherein the first processing method is any one of the bilinear interpolation algorithm and the limited contrast adaptive equalization technology, and the second processing method is another processing method of the bilinear interpolation algorithm and the limited contrast adaptive equalization technology other than the first processing method. Specifically, the filtered image information can be converted to the spatial domain by inverse fast Fourier transform to obtain the corresponding converted image. It is understandable that in order to enhance local features, the converted image can be further processed. First, the current image processing strategy needs to be determined. For example, the image can be optimized by performing feature fusion processing based on the bilinear interpolation algorithm and / or the limited contrast adaptive equalization technology. Different actual usage scenarios require different corresponding image processing strategies. For resolution optimization, the bilinear interpolation algorithm can be used, and for local grayscale distribution, the limited contrast adaptive equalization technology can be used. Accordingly, if the current image processing strategy indicates that one of the bilinear interpolation algorithm and the limited contrast adaptive equalization technology is used to optimize the converted image, image feature fusion optimization can be performed directly. If the current image processing strategy indicates that both the bilinear interpolation algorithm and the limited contrast adaptive equalization technology are used to optimize the image, either of the two methods can be used to process the converted image first, and then the corresponding processed image can be processed again using the other method. It is understandable that in specific embodiments, the bilinear interpolation algorithm and the limited contrast adaptive equalization technology are used in no particular order, and both can be used to perform feature fusion optimization on the converted image.

[0060] In a specific embodiment, the frequency domain signal Transform to the spatial domain through inverse Fourier transform, where (u, v) represents the frequency domain coordinates, F filered (u,v) is the image spectrum; the formula involved is as follows:

[0061] ;

[0062] Furthermore, the image is optimized for feature fusion by combining the bilinear interpolation algorithm and / or the contrast-limited adaptive equalization technology. The formula involved is as follows:

[0063] ;

[0064] In another specific embodiment, performing relevant industrial inspection operations using the processed image may include: determining the type of image visual effect corresponding to the industrial inspection device based on a pre-established correspondence table representing the relationship between industrial inspection devices and image visual effects; displaying multiple sets of visual parameter information matching the image visual effect type through a preset parameter interactive interface, and obtaining operation instructions for the multiple sets of visual parameter information; performing a linear adjustment operation on the processed image based on the target visual parameter information corresponding to the operation instructions, so as to perform relevant industrial inspection operations using the linearly adjusted image. Specifically, it is understood that different industrial inspection devices have different requirements for the format of output images. In other words, the visual effects of images output by different industrial inspection devices are different. Here, a relationship table between industrial inspection devices and image visual effects can be pre-established. Then, when the industrial inspection device processes the image, it can determine the type of visual effect of the image currently to be output based on the relationship table. The corresponding visual effect type may correspond to multiple visual parameters. The interactive interface can further display multiple sets of visual parameter information matching the visual effect type, and the parameters can be arbitrarily selected by the relevant work. Then, using the selected target visual parameter information, the processed image is linearly adjusted so that the visual effect of the final output image meets the actual requirements. In a specific embodiment, when the industrial inspection equipment outputs an image, the linear adjustment formula is as follows:

[0065] ;

[0066] in, and It can be adjusted according to different industrial testing equipment.

[0067] It can be seen that when processing digital X-ray images, the present application can determine a Gaussian filter that meets the current image processing based on the signal-to-noise ratio of the digital X-ray image to be processed, and achieve concurrent high-frequency enhancement and low-frequency suppression with the help of the first parameter and the second parameter for controlling high-frequency enhancement and low-frequency suppression, thereby suppressing low-frequency noise while retaining high-frequency details; through frequency domain decomposition, the high-frequency features of tiny defects such as cracks and pores can be significantly enhanced, and combined with subsequent feature fusion optimization, the image information can be enhanced to meet the strict industry standards of high-end manufacturing, and can provide high-quality data processing for subsequent industrial image detection, thereby improving the accuracy of detection image evaluation.

[0068] like Figure 2 As shown, the embodiment of the present application discloses a digital radiographic image processing method, which is applied to industrial detection equipment, including:

[0069] Step S21 : determining a current Gaussian filter according to the signal-to-noise ratio of the digital radiographic image to be processed; the current Gaussian filter includes a first parameter for controlling high-frequency enhancement and a second parameter for controlling low-frequency suppression.

[0070] Step S22: performing a logarithmic transformation operation on the digital radiographic image to be processed using a preset logarithmic transformation formula to obtain corresponding transformed image information; the preset logarithmic transformation formula is a formula constructed based on a sixteen-bit depth image.

[0071] In this embodiment, during the filtering process of the frequency domain decomposition results of the digital radiographic image to be processed, the digital radiographic image to be processed must first be converted to the frequency domain. A logarithmic transformation operation can be performed on the digital radiographic image to be processed using a preset logarithmic transformation formula. This logarithmic transformation can separate the illumination and reflection components, enhancing the processability of high-frequency details. It should be noted that the logarithmic transformation formula used here is constructed for a 16-bit depth image, which effectively avoids precision loss compared to 8-bit processing. Furthermore, for the input digital radiographic image I to be processed, the logarithmic transformation formula is as follows:

[0072] ;

[0073] Among them, I+1 avoids the invalidity of logarithmic operation for zero value and is normalized to the range of [0,1] to adapt to 16-bit depth image.

[0074] Step S23: performing a frequency domain decomposition operation on the transformed image information based on fast Fourier transform to obtain a corresponding frequency domain decomposition result.

[0075] Furthermore, the corresponding transformed image information can be obtained through logarithmic transformation, and then the transformed image information can be converted to the frequency domain through fast Fourier transform, that is, the frequency domain decomposition operation can be performed through fast Fourier transform to obtain the corresponding frequency domain decomposition result, so that the frequency domain decomposition result can be filtered using the current Gaussian filter to enhance the image information. Furthermore, the frequency domain decomposition operation of the transformed image information based on fast Fourier transform involves the following formula:

[0076] ;

[0077] Among them, F(u, v) is the frequency domain representation, the high-frequency components are concentrated in the periphery of the spectrum center, and the low-frequency components are concentrated in the central area, laying the foundation for subsequent image enhancement.

[0078] Step S24: Utilize the current Gaussian filter to filter the frequency domain decomposition result.

[0079] Step S25 : converting the filtered image information into a spatial domain to obtain a processed image corresponding to the digital radiographic image to be processed, so as to perform relevant industrial inspection operations using the processed image.

[0080] For more specific processing procedures of the above steps S21, S24 and S25, reference may be made to the corresponding contents disclosed in the aforementioned embodiments, which will not be described in detail here.

[0081] It can be seen that when processing digital X-ray images, the present application can determine a Gaussian filter that meets the current image processing requirements based on the signal-to-noise ratio of the digital X-ray image to be processed, and achieve concurrent high-frequency enhancement and low-frequency suppression with the help of the first parameter and the second parameter for controlling high-frequency enhancement and low-frequency suppression. While retaining high-frequency details, low-frequency noise is suppressed, which can solve problems such as detail loss, noise amplification, and artifact generation, thereby improving the enhancement effect of digital X-ray images.

[0082] like Figure 3 As shown, the embodiment of the present application discloses a digital radiographic image processing device, which is applied to industrial detection equipment, including:

[0083] A filter determination module 11 is configured to determine a current Gaussian filter according to a signal-to-noise ratio of the digital radiographic image to be processed; the current Gaussian filter includes a first parameter for controlling high-frequency enhancement and a second parameter for controlling low-frequency suppression;

[0084] A filtering module 12 is configured to filter the frequency domain decomposition result of the digital radiographic image to be processed using the current Gaussian filter to obtain corresponding filtered image information;

[0085] The conversion module 13 is used to convert the filtered image information into a spatial domain to obtain a processed image corresponding to the digital radiographic image to be processed, so as to perform relevant industrial detection operations using the processed image.

[0086] It can be seen that when processing digital X-ray images, the present application can determine a Gaussian filter that meets the current image processing requirements based on the signal-to-noise ratio of the digital X-ray image to be processed, and achieve concurrent high-frequency enhancement and low-frequency suppression with the help of the first parameter and the second parameter for controlling high-frequency enhancement and low-frequency suppression. While retaining high-frequency details, low-frequency noise is suppressed, which can solve problems such as detail loss, noise amplification, and artifact generation, thereby improving the enhancement effect of digital X-ray images.

[0087] In a specific embodiment, the filter determination module 11 may include:

[0088] A first display unit is used to determine a digital radiographic image to be processed and display, through a preset parameter interactive interface, a plurality of sets of filter parameter information that match the signal-to-noise ratio of the digital radiographic image to be processed; each set of filter parameter information includes a first parameter and a corresponding second parameter;

[0089] A first instruction acquisition unit, configured to acquire selection instructions for several groups of filter parameter information through the preset parameter interaction interface;

[0090] The first adjustment unit is configured to perform a parameter adjustment operation on a preset Gaussian filter based on target filter parameter information corresponding to the selection instruction, so as to obtain a current Gaussian filter corresponding to the digital radiographic image to be processed.

[0091] In a specific embodiment, the filtering module 12 may include:

[0092] a logarithmic transformation submodule, configured to perform a logarithmic transformation operation on the digital radiographic image to be processed using a preset logarithmic transformation formula to obtain corresponding transformed image information; the preset logarithmic transformation formula is a formula constructed based on a 16-bit depth image;

[0093] A frequency domain decomposition unit, configured to perform a frequency domain decomposition operation on the transformed image information based on a fast Fourier transform to obtain a corresponding frequency domain decomposition result;

[0094] A filtering processing unit is used to perform filtering processing on the frequency domain decomposition result using the current Gaussian filter.

[0095] In another specific embodiment, the logarithmic transformation submodule may include:

[0096] A color channel conversion unit is used to convert the color channel of the digital radiographic image to be processed into a single-channel grayscale value based on a weighted average method to obtain a corresponding grayscale image;

[0097] The logarithmic transformation unit is used to perform a logarithmic transformation operation on the grayscale image using a preset logarithmic transformation formula.

[0098] In a specific embodiment, the conversion module 13 may include:

[0099] An image information conversion unit, configured to convert the filtered image information into a spatial domain based on an inverse fast Fourier transform to obtain a corresponding converted image;

[0100] a strategy determination unit, configured to determine a current image processing strategy corresponding to the digital radiographic image to be processed; the current image processing strategy being a processing strategy constructed based on a bilinear interpolation algorithm and / or a contrast-limited adaptive equalization technique;

[0101] a first processing unit configured to, when the current image processing strategy only includes the bilinear interpolation algorithm or the limited contrast adaptive equalization technique, process the converted image using the bilinear interpolation algorithm or the limited contrast adaptive equalization technique to obtain a first processed image corresponding to the digital radiographic image to be processed;

[0102] a second processing unit configured to, when the current image processing strategy includes the bilinear interpolation algorithm and the limited contrast adaptive equalization technique, perform a first processing on the converted image using a first processing method, and perform a second processing on the image obtained by the corresponding first processing using a second processing method, to obtain a second processed image corresponding to the digital radiographic image to be processed; wherein the first processing method is any one of the bilinear interpolation algorithm and the limited contrast adaptive equalization technique, and the second processing method is another processing method of the bilinear interpolation algorithm and the limited contrast adaptive equalization technique other than the first processing method.

[0103] In a specific embodiment, the device may further include:

[0104] A transformation acceleration unit is used to accelerate the fast Fourier transform or the inverse fast Fourier transform process through a pre-set computer vision and machine learning library to obtain the frequency domain decomposition result or convert the filtered image information into the spatial domain.

[0105] In a specific embodiment, the conversion module 13 may include:

[0106] A visual effect type determination unit, configured to determine the image visual effect type corresponding to the industrial inspection equipment according to a pre-constructed correspondence table representing the correspondence between the industrial inspection equipment and the image visual effects;

[0107] A second display unit is used to display several groups of visual parameter information matching the image visual effect type through a preset parameter interaction interface;

[0108] A second instruction acquisition unit is used to acquire operation instructions for several groups of visual parameter information;

[0109] a second adjustment unit, configured to perform a linear adjustment operation on the processed image based on target visual parameter information corresponding to the operation instruction;

[0110] The industrial inspection unit is used to perform relevant industrial inspection operations using the linearly adjusted image.

[0111] Furthermore, the embodiment of the present application also discloses an electronic device, Figure 4 This is a structural diagram of an electronic device 20 according to an exemplary embodiment. The content in the diagram should not be considered as any limitation to the scope of application of the present application.

[0112] Figure 4 This is a schematic diagram of the structure of an electronic device 20 provided in an embodiment of the present application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 is used to store a computer program, which is loaded and executed by the processor 21 to implement the relevant steps of the digital radiographic image processing method disclosed in any of the aforementioned embodiments. Furthermore, the electronic device 20 in this embodiment may specifically be an electronic computer.

[0113] In this embodiment, the power supply 23 is used to provide operating voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and the external device. The communication protocol it follows is any communication protocol that can be applied to the technical solution of this application and is not specifically limited here; the input and output interface 25 is used to obtain external input data or output data to the outside world. Its specific interface type can be selected according to specific application needs and is not specifically limited here.

[0114] In addition, the memory 22, as a carrier for resource storage, can be a read-only memory, random access memory, disk or CD, etc. The resources stored thereon can include an operating system 221, a computer program 222, etc., and the storage method can be temporary storage or permanent storage.

[0115] The operating system 221 is used to manage and control the hardware devices and computer program 222 on the electronic device 20, and can be Windows Server, Netware, Unix, Linux, etc. In addition to including a computer program capable of implementing the digital radiographic image processing method performed by the electronic device 20 disclosed in any of the aforementioned embodiments, the computer program 222 may further include a computer program capable of implementing other specific tasks.

[0116] Furthermore, this application also discloses a computer-readable storage medium for storing a computer program; wherein, when executed by a processor, the computer program implements the aforementioned digital radiographic image processing method. The specific steps of this method can be referred to the corresponding contents disclosed in the aforementioned embodiments and will not be repeated here.

[0117] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from the other embodiments. Reference can be made to the descriptions of the identical or similar parts between the various embodiments. For the devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple, and the relevant parts can be referred to the descriptions of the methods.

[0118] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the above description has generally described the components and steps of each example according to their functions. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0119] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0120] Finally, it should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or device comprising the element.

[0121] The above is a detailed introduction to the technical solution provided by the present application. Specific examples are used herein to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea. At the same time, for those skilled in the art, according to the ideas of the present application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A digital radiographic image processing method, characterized in that: Used in industrial testing equipment, including: Determining a current Gaussian filter according to a signal-to-noise ratio of the digital radiographic image to be processed; the current Gaussian filter includes a first parameter for controlling high-frequency enhancement and a second parameter for controlling low-frequency suppression; Using the current Gaussian filter to filter the frequency domain decomposition result of the digital radiographic image to be processed to obtain corresponding filtered image information; Converting the filtered image information into a spatial domain to obtain a processed image corresponding to the digital radiographic image to be processed, so as to perform relevant industrial inspection operations using the processed image; The performing of relevant industrial inspection operations using the processed image includes: Determining the type of image visual effect corresponding to the industrial inspection equipment according to a pre-constructed correspondence table representing the correspondence between the industrial inspection equipment and the image visual effect; Displaying several groups of visual parameter information matching the image visual effect type through a preset parameter interaction interface, and obtaining operation instructions for the several groups of visual parameter information; A linear adjustment operation is performed on the processed image based on the target visual parameter information corresponding to the operation instruction, so as to use the linearly adjusted image to perform relevant industrial detection operations.

2. The digital radiographic image processing method according to claim 1, wherein: The determining of the current Gaussian filter according to the signal-to-noise ratio of the digital radiographic image to be processed comprises: Determining a digital radiographic image to be processed, and displaying, through a preset parameter interactive interface, several sets of filter parameter information that match the signal-to-noise ratio of the digital radiographic image to be processed; each set of filter parameter information includes a first parameter and a corresponding second parameter; Obtaining selection instructions for several groups of filter parameter information through the preset parameter interaction interface; A parameter adjustment operation is performed on a preset Gaussian filter based on the target filter parameter information corresponding to the selection instruction to obtain a current Gaussian filter corresponding to the digital radiographic image to be processed.

3. The digital radiographic image processing method according to claim 1, wherein: The filtering process of the frequency domain decomposition result of the digital radiographic image to be processed by using the current Gaussian filter includes: Performing a logarithmic transformation operation on the digital radiographic image to be processed using a preset logarithmic transformation formula to obtain corresponding transformed image information; the preset logarithmic transformation formula is a formula constructed based on a sixteen-bit depth image; Performing a frequency domain decomposition operation on the transformed image information based on a fast Fourier transform to obtain a corresponding frequency domain decomposition result; The frequency domain decomposition result is filtered using the current Gaussian filter.

4. The digital radiographic image processing method according to claim 3, wherein: The logarithmic transformation operation is performed on the digital radiographic image to be processed using a preset logarithmic transformation formula, including: Based on the weighted average method, the color channel of the digital radiographic image to be processed is converted into a single-channel grayscale value to obtain a corresponding grayscale image; A logarithmic transformation operation is performed on the grayscale image using a preset logarithmic transformation formula.

5. The digital radiographic image processing method according to claim 3, wherein: The step of converting the filtered image information into a spatial domain to obtain a processed image corresponding to the digital radiographic image to be processed includes: Converting the filtered image information into a spatial domain based on an inverse fast Fourier transform to obtain a corresponding converted image; Determining a current image processing strategy corresponding to the digital radiographic image to be processed; the current image processing strategy is a processing strategy constructed based on a bilinear interpolation algorithm and / or a contrast-limited adaptive equalization technique; If the current image processing strategy only includes the bilinear interpolation algorithm or the limited contrast adaptive equalization technique, the converted image is processed using the bilinear interpolation algorithm or the limited contrast adaptive equalization technique to obtain a first processed image corresponding to the digital radiographic image to be processed; If the current image processing strategy includes the bilinear interpolation algorithm and the contrast-limited adaptive equalization technique, performing a first processing on the converted image using a first processing method, and performing a second processing on the image obtained by the first processing using a second processing method, to obtain a second processed image corresponding to the digital radiographic image to be processed; The first processing method is any one of the bilinear interpolation algorithm and the limited contrast adaptive equalization technology, and the second processing method is another processing method of the bilinear interpolation algorithm and the limited contrast adaptive equalization technology except the first processing method.

6. The digital radiographic image processing method according to claim 5, wherein: Also includes: The fast Fourier transform or the inverse fast Fourier transform process is accelerated by a pre-set computer vision and machine learning library to obtain the frequency domain decomposition result or convert the filtered image information into the spatial domain.

7. A digital radiographic image processing device, characterized in that: Used in industrial testing equipment, including: A filter determination module, configured to determine a current Gaussian filter according to a signal-to-noise ratio of the digital radiographic image to be processed; the current Gaussian filter includes a first parameter for controlling high-frequency enhancement and a second parameter for controlling low-frequency suppression; a filtering module, configured to filter the frequency domain decomposition result of the digital radiographic image to be processed using the current Gaussian filter to obtain corresponding filtered image information; a conversion module, configured to convert the filtered image information into a spatial domain to obtain a processed image corresponding to the digital radiographic image to be processed, so as to perform relevant industrial inspection operations using the processed image; Among them, the process of performing relevant industrial inspection operations through the conversion module includes: determining the image visual effect type corresponding to the industrial inspection equipment based on a pre-constructed correspondence table representing the correspondence between industrial inspection equipment and image visual effects; displaying several groups of visual parameter information matching the image visual effect type through a preset parameter interactive interface, and obtaining operation instructions for several groups of visual parameter information; performing a linear adjustment operation on the processed image based on the target visual parameter information corresponding to the operation instruction, so as to use the linearly adjusted image to perform relevant industrial inspection operations.

8. An electronic device, characterized in that: include: Memory, used to store computer programs; A processor, configured to execute the computer program to implement the digital radiographic image processing method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that Used to store a computer program, which, when executed by a processor, implements the digital radiographic image processing method according to any one of claims 1 to 6.

Images