CN115880173A - Image processing method, image processing apparatus, and computer-readable storage medium - Google Patents
Image processing method, image processing apparatus, and computer-readable storage medium Download PDFInfo
- Publication number
- CN115880173A CN115880173A CN202211576532.0A CN202211576532A CN115880173A CN 115880173 A CN115880173 A CN 115880173A CN 202211576532 A CN202211576532 A CN 202211576532A CN 115880173 A CN115880173 A CN 115880173A
- Authority
- CN
- China
- Prior art keywords
- frequency component
- image
- low
- image processing
- processing method
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Image Processing (AREA)
Abstract
The application provides an image processing method, an image processing apparatus, and a computer-readable storage medium. The image processing method comprises the following steps: acquiring an image to be processed; acquiring a high-frequency component and a low-frequency component of the image to be processed; according to a nonlinear stretching rule, increasing the pixel value of the low-frequency component to obtain the low-frequency component with enhanced contrast; performing noise reduction processing on the high-frequency component to obtain a noise-reduced high-frequency component; and performing image reconstruction by using the low-frequency component after contrast enhancement and the high-frequency component after noise reduction to obtain a contrast enhanced image. Through the mode, the image processing device decomposes the image to be processed, reduces high-frequency noise while enhancing the contrast in a low-frequency nonlinear mode, reconstructs the image and enhances the contrast of the image.
Description
Technical Field
The present disclosure relates to the field of image processing technologies, and in particular, to an image processing method, an image processing apparatus, and a computer-readable storage medium.
Background
In order to solve the problem of image noise, many image noise reduction algorithms are presented in the industry, such as: a window filtering method irrelevant to the image content, a Non-local Means algorithm based on image structure similarity analysis, and the like.
The window filtering method irrelevant to the image content has small calculated amount, but the detail loss of the image is serious; the Non-local Means algorithm based on image structure similarity analysis is good in detail keeping and color protection, but the algorithm is high in complexity and low in efficiency. The contradiction between the noise reduction effect and the efficiency is more prominent.
Disclosure of Invention
The application provides an image processing method, an image processing apparatus, and a computer-readable storage medium.
The application provides an image processing method, which comprises the following steps:
acquiring an image to be processed;
acquiring a high-frequency component and a low-frequency component of the image to be processed;
according to a nonlinear stretching rule, increasing the pixel value of the low-frequency component to obtain the low-frequency component with enhanced contrast;
performing noise reduction processing on the high-frequency component to obtain a noise-reduced high-frequency component;
and carrying out image reconstruction by using the low-frequency component after contrast enhancement and the high-frequency component after noise reduction to obtain a contrast enhancement image.
Wherein the acquiring the high frequency component and the low frequency component of the image to be processed includes:
performing wavelet decomposition on the image to be processed to obtain a low-frequency component and a high-frequency component of the image to be processed;
the increasing the pixel value of the low-frequency component according to the nonlinear stretching rule to obtain the low-frequency component with enhanced contrast includes:
determining a low-frequency stretching range based on the wavelet coefficient range of the low-frequency component;
and performing stretching processing on the wavelet coefficients of the low-frequency component in the low-frequency stretching range to update the wavelet coefficients of the low-frequency component.
Wherein the stretching processing of the wavelet coefficients of the low frequency component in the low frequency stretching range includes:
acquiring the maximum value and the minimum value of the wavelet coefficient of the low-frequency component;
acquiring a first difference value of a wavelet coefficient of a low-frequency component in the low-frequency stretching range and the wavelet coefficient minimum value, and a second difference value of the wavelet coefficient maximum value and the wavelet coefficient minimum value;
and determining the wavelet coefficient after the stretching treatment according to the first difference and the second difference.
Wherein, the denoising processing is performed on the high-frequency component to obtain a denoised high-frequency component, and the denoising processing includes:
and denoising the wavelet coefficient of the high-frequency component by using a denoising threshold value so as to update the wavelet coefficient of the high-frequency component.
Wherein the denoising the wavelet coefficient of the high frequency component with the denoising threshold to update the wavelet coefficient of the high frequency component comprises:
updating the wavelet coefficient of the high-frequency component with the absolute value smaller than the denoising threshold value to a preset value;
performing, on wavelet coefficients of the high-frequency component whose absolute value is equal to or greater than the denoising threshold: acquiring a difference value between the absolute value of the wavelet coefficient and the denoising threshold value, wherein the positive sign and the negative sign of the difference value are the positive sign and the negative sign of the wavelet coefficient; and taking the difference value as a wavelet coefficient after denoising treatment.
Wherein the high frequency components include a horizontal high frequency component, a vertical high frequency component, and a diagonal high frequency component; and the noise reduction threshold corresponding to the horizontal high-frequency component, the noise reduction threshold corresponding to the vertical high-frequency component and the noise reduction threshold corresponding to the diagonal high-frequency component are different.
Wherein the image processing method further comprises:
acquiring the standard deviation of the wavelet coefficient of the high-frequency component;
and determining the noise reduction threshold according to the standard deviation.
Before the obtaining of the high-frequency component and the low-frequency component of the image to be processed, the image processing method further includes:
and converting multiplicative noise in the image to be processed into additive noise by using a noise transformation algorithm.
Wherein the image to be processed is an X-ray image;
before the obtaining of the high frequency component and the low frequency component of the image to be processed, the image processing method further includes:
acquiring a pixel maximum value and a pixel minimum value of the X-ray image;
and calculating the pixel value of each pixel point after the X-ray image is stretched by utilizing the pixel maximum value, the pixel minimum value and a preset pixel threshold value.
Wherein before the obtaining of the maximum pixel value and the minimum pixel value of the X-ray image, the image processing method further comprises:
performing a histogram equalization operation on the X-ray image.
The present application also provides an image processing apparatus comprising a processor and a memory, the memory having stored therein program data, the processor being configured to execute the program data to implement the image processing method as described above.
The present application also provides a computer-readable storage medium for storing program data which, when executed by a processor, is used to implement the image processing method described above.
The beneficial effect of this application is: the image processing device acquires an image to be processed; acquiring a high-frequency component and a low-frequency component of the image to be processed; according to a nonlinear stretching rule, increasing the pixel value of the low-frequency component to obtain the low-frequency component with enhanced contrast; performing noise reduction processing on the high-frequency component to obtain a noise-reduced high-frequency component; and carrying out image reconstruction by using the low-frequency component after contrast enhancement and the high-frequency component after noise reduction to obtain a contrast enhancement image. Through the mode, the image processing device decomposes the image to be processed, reduces high-frequency noise while enhancing the contrast in a low-frequency nonlinear way, and finally reconstructs the image to realize the enhancement of the image contrast.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts. Wherein:
FIG. 1 is a schematic representation of an X-ray image of a standard provided herein;
FIG. 2 is a schematic flowchart of an embodiment of an image processing method provided in the present application;
FIG. 3 is a schematic overall flowchart of an image processing method provided in the present application;
FIG. 4 is a schematic illustration of the detection area of an X-ray image of a standard provided herein;
FIG. 5 is a diagram illustrating the effect of histogram equalization of the detection region in FIG. 4;
FIG. 6 is a schematic diagram of a wavelet decomposition process provided herein;
FIG. 7 is a schematic diagram of a wavelet reconstruction process provided herein;
FIG. 8 is a schematic diagram of a pre-image processing detection region provided herein;
FIG. 9 is a schematic illustration of a detection region after image processing as provided herein;
FIG. 10 is a schematic structural diagram of an embodiment of an image processing apparatus provided in the present application;
FIG. 11 is a schematic structural diagram of an embodiment of a computer-readable storage medium provided in the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be described clearly and completely with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only some embodiments of the present application, and not all embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present application without making any creative effort belong to the protection scope of the present application.
With the development and popularization of intelligent security, more and more scenes provide higher requirements for security inspection. The X-ray security check instrument is an indispensable important component, and plays a great role in entrances and exits of important public places such as airports, subways and the like. The X-ray security check instrument can detect various dangerous articles such as cutters and explosives in the package, and greatly guarantees the environmental safety of public places.
In the use process of the X-ray security check instrument, due to the influence of the imaging principle and the environment, the overall contrast of an X-ray picture is very low, and the noise is too large, so that the details of an object are lost, and the judgment of security check service personnel is influenced. Due to the particularity of the imaging principle of the X-ray security check instrument, the noise component is complex and is not easy to estimate. Especially, in the current large environment of intelligent security inspection, the contrast and imaging quality of images greatly influence the effect of subsequent intelligent identification. Therefore, the problem to be solved by the application is to improve the contrast of the X-ray image, reduce noise and develop an X-ray image contrast enhancement algorithm.
It should be noted that the present application provides an image processing method applicable to images of all imaging principles, such as infrared images, X-ray images, ultrasound images, and the like. The following describes the image processing method provided by the present application with an X-ray image as a specific embodiment.
The main reasons for the low contrast of X-ray images are: the image dynamic range is large, the noise is large, and the types are complex. Fig. 1 shows an X-ray image of a standard piece, in which the two black bars above and below the standard piece are actually objects, but cannot be observed due to their low contrast.
Aiming at the problem of low imaging contrast in the prior art, the method for enhancing the X-ray image contrast is designed, firstly, noise analysis and pretreatment are carried out on an X-ray image, then, the X-ray image is decomposed, noise reduction and low-frequency contrast enhancement are respectively carried out on high frequency, and finally, the image is restored, so that the purpose of enhancing the X-ray image contrast is achieved.
Referring to fig. 2 and fig. 3 in detail, fig. 2 is a schematic flowchart of an embodiment of an image processing method provided by the present application, and fig. 3 is a schematic flowchart of an entire image processing method provided by the present application.
The image processing method is applied to an image processing device, wherein the image processing device can be a server, and can also be a system in which the server and a terminal device are matched with each other. Accordingly, the image processing apparatus may include various parts, such as various units, sub-units, modules, and sub-modules, which are all disposed in the server, or may be disposed in the server and the terminal device, respectively.
Further, the server may be hardware or software. When the server is hardware, it may be implemented as a distributed server cluster formed by multiple servers, or may be implemented as a single server. When the server is software, it may be implemented as a plurality of software or software modules, for example, software or software modules for providing distributed servers, or as a single software or software module, and is not limited herein. In some possible implementations, the image processing method of the embodiments of the present application may be implemented by a processor calling a computer readable instruction stored in a memory.
As shown in fig. 3, an X-ray image is input, histogram equalization and linear stretching are performed on the X-ray image, noise conversion is performed after noise in the image is estimated, the image is decomposed based on wavelet transform, different strategies are applied to high and low frequency images to perform noise suppression and contrast enhancement, and finally the image is restored by wavelet reconstruction and noise inverse transformation.
Specifically, as shown in fig. 2, the image processing method according to the embodiment of the present application specifically includes the following steps:
step S11: and acquiring an image to be processed.
In the embodiment of the present application, the image processing apparatus acquires an image to be processed by an imaging instrument, for example, acquires an X-ray image by an X-ray security check instrument.
Since the X-ray image pixels are 16 bits (0-65535), the pixel values of most effective pixels are not high, and most effective pixels are concentrated in a low-brightness range; therefore, the image processing apparatus performs histogram equalization on the X-ray image first, and the main purpose is to increase the contrast between pixels.
Specifically, taking the white frame area in fig. 4 as an example, the pixel distribution histogram is as the left diagram in fig. 5, and the pixel values of most of the pixels are lower. After histogram equalization, the pixels are distributed as uniformly as possible, and the histogram is converted to the right-hand graph of fig. 5. Comparing the left and right images of fig. 5 shows that the contrast of the X-ray image is significantly improved.
The histogram equalization comprises the following specific steps: sequentially scanning each pixel of the original gray image, and calculating a gray histogram of the image; calculating a cumulative distribution function of the gray level histogram; obtaining a mapping relation between input and output according to a cumulative distribution function and a histogram equalization principle; and finally, carrying out image transformation according to the result obtained by the mapping relation.
For the X-ray image, the number of bits of the X-ray image is 16, and the pixel value range is 0 to 255 when the display is displayed, that is, an 8-bit image, and therefore, the image processing apparatus also needs to linearly stretch the X-ray image. The main purpose of linear stretching is to stretch the pixel values distributed in the range of 0-65535 to 0-255, i.e. to change the 16-bit image into 8-bit image, so as to reduce the amount of calculation and facilitate the subsequent processing and display.
Specifically, the image processing apparatus acquires a pixel maximum value and a pixel minimum value of an X-ray image; and calculating the pixel value of each pixel point after the X-ray image is stretched by utilizing the maximum pixel value, the minimum pixel value and a preset pixel threshold value. The specific linear stretching formula is embodied as follows:
wherein p is str Is the pixel value after stretching, p is the pixel value before stretching, p max Is the regional pixel maximum, p min Is the regional pixel minimum.
In order to improve the noise processing of the subsequent steps, the application also provides an image processing scheme of noise transformation. Specifically, according to the imaging principle of the X-ray security inspection apparatus, the noise in the X-ray image includes additive gaussian noise and multiplicative poisson noise. Noise aliasing increases the difficulty of noise processing, and multiplicative noise is more difficult to remove, so that the image processing device can convert multiplicative noise such as Poisson Gaussian mixed noise, poisson noise and the like in an image into Gaussian noise by using an Anscombe transformation algorithm for subsequent processing. The specific noise transformation formula is embodied as follows:
wherein p is vst To the post-conversion pixel value, p is the pre-conversion pixel value.
Step S12: and acquiring high-frequency components and low-frequency components of the image to be processed.
In this embodiment, the image processing apparatus may perform wavelet decomposition on the image to be processed to obtain a low frequency component and a high frequency component of the image to be processed. In other embodiments, the image processing apparatus may also use other image high-frequency and low-frequency extraction methods, such as fourier transform, discrete Cosine Transform (DCT), and the like.
In the embodiment of the application, the image processing device performs wavelet decomposition on the image to be processed to obtain the low-frequency component and the high-frequency component of the image to be processed. Because noise often exists in the high-frequency components of the image, the effect of extracting the high-frequency parts of the image for individual noise reduction is better.
Specifically, the image processing apparatus divides an image into a low frequency component and a high frequency component using a two-dimensional wavelet transform, wherein the high frequency component includes a horizontal high frequency, a vertical high frequency, and a diagonal high frequency. Therefore, as shown in fig. 6, the image processing apparatus can divide the original image into four parts of a low-frequency component, a horizontal high-frequency, a vertical high-frequency, and a diagonal high-frequency. The image processing device carries out wavelet base decomposition on line pixels of an original image to obtain a horizontal low frequency and a horizontal high frequency; the vertical low frequency and the vertical high frequency can be obtained by decomposing the column pixels of the original image through wavelet basis; diagonal low frequency and diagonal high frequency can be obtained by decomposing diagonal pixels of the original image through wavelet base. The horizontal low frequency, the vertical low frequency, and the diagonal low frequency of the original image constitute low frequency components, and as shown in fig. 6, the size of the low frequency components is half the size of the original image.
Wherein, the wavelet base can be haar wavelet or db2 wavelet, and the decomposition layer number can be freely set. As shown in fig. 6, the original image is subjected to a one-layer wavelet decomposition, and if a two-layer wavelet decomposition is required, that is, a low-frequency component is taken as an input to be subjected to a secondary wavelet decomposition.
Step S13: and according to a nonlinear stretching rule, increasing the pixel value of the low-frequency component to obtain the low-frequency component after the contrast is enhanced.
Specifically, the image processing apparatus increases the pixel value of the low-frequency component by a preset non-linear stretching rule to enhance the contrast of the low-frequency component. The non-linear stretching rule may be to increase all pixel values in the low frequency component, or may be to increase some pixel values in the low frequency component.
In one embodiment, the image processing apparatus determines a low-frequency stretching range based on a wavelet coefficient range of a low-frequency component; then, the wavelet coefficients of the low frequency component in the low frequency stretching range are subjected to stretching processing to update the wavelet coefficients of the low frequency component.
In the embodiment of the application, the image processing device realizes low-frequency contrast enhancement aiming at low-frequency components. The low-frequency component after wavelet decomposition represents the contour information of the image and can also be regarded as effective information, so that the image processing apparatus can further enhance the contrast of the low-frequency component.
The application designs a nonlinear stretching method to process the low-frequency wavelet coefficient: specifically, the image processing apparatus acquires a wavelet coefficient maximum value and a wavelet coefficient minimum value of the low-frequency component; acquiring a first difference value of a wavelet coefficient of a low-frequency component in the low-frequency stretching range and the wavelet coefficient minimum value, and a second difference value of the wavelet coefficient maximum value and the wavelet coefficient minimum value; and determining the wavelet coefficient after the stretching treatment according to the first difference and the second difference.
The specific low frequency contrast enhancement formula is embodied as follows:
wherein, c str Is wavelet coefficient after stretching, c is wavelet coefficient before stretching, c min Is the minimum of the wavelet coefficients before stretching, c max Is the maximum value of the wavelet coefficient before stretching. Used here as 0.1 min 、0.1 max For the boundary, the wavelet coefficients at the head and the tail are removed, that is, the wavelet coefficients of the part are not processed, and only the part with more middle section information is stretched, so that the purpose of enhancing the contrast is achieved.
Step S14: and carrying out noise reduction processing on the high-frequency component to obtain a noise-reduced high-frequency component.
Specifically, the image processing apparatus may perform denoising processing on the wavelet coefficients of the high frequency components using a denoising threshold value to update the wavelet coefficients of the high frequency components. In other embodiments, the image processing apparatus may also perform noise reduction on the high frequency component by using other noise reduction algorithms, which are not listed here.
In the embodiment of the present application, the image processing apparatus realizes high-frequency noise suppression for high-frequency components. Taking a layer of wavelet decomposition as an example, the decomposed wavelet coefficients of three high frequency components, namely horizontal high frequency, vertical high frequency and diagonal high frequency, all contain a large amount of noise, and the image processing device needs to perform soft threshold denoising on the wavelet coefficients of the high frequency components.
The specific high-frequency noise suppression formula is embodied as follows:
wherein, c dn For the denoised wavelet coefficients, c for the pre-denoised coefficientsWavelet coefficient, sgn (×) is sign function, c is greater than 0 and takes 1, c is less than 0 and takes-1, and λ is noise reduction threshold. The larger the numerical value of the noise reduction threshold value is, the higher the degree of high-frequency noise suppression is, and the better the suppression effect is.
The image processing apparatus may perform noise suppression on the wavelet coefficients of the three high frequency components of the horizontal high frequency, the vertical high frequency and the diagonal high frequency by using the high frequency noise suppression formula, where the noise reduction threshold used may be the same or different.
In addition, the numerical value of the noise reduction threshold value can be set manually or can be set in a self-adaptive mode according to the image to be processed. For example, the image processing apparatus may acquire the standard deviation of the wavelet coefficients of the high frequency components and then determine the denoising threshold value based on the standard deviation, e.g., the image processing apparatus may take 2.5 to 3.5 times the standard deviation of the wavelet coefficients before denoising as the denoising threshold value. Wherein the standard deviation may represent a fluctuation state of wavelet coefficients of the high frequency component. In other embodiments, calculation methods such as variance and average may be used, which are not listed here.
Step S15: and performing image reconstruction by using the low-frequency component after contrast enhancement and the high-frequency component after noise reduction to obtain a contrast enhanced image.
In the embodiment of the present application, the wavelet reconstruction process is the reverse of the wavelet decomposition process, i.e. it can be regarded as the inverse process of the wavelet decomposition process, and the purpose is to reconstruct the updated wavelet coefficients into the contrast-enhanced image. Specifically, as shown in fig. 7, fig. 7 is a schematic diagram of a wavelet reconstruction process provided in the present application.
With respect to the noise transformation process in step S11, the image processing apparatus of the present application may further perform inverse noise transformation on the reconstructed image after wavelet reconstruction. This is because the noise conversion is performed in step S11 and the non-noise signal is also converted at the same time, so that the signal needs to be restored.
The specific noise inverse transformation formula is embodied as follows:
wherein p is re P is the pixel value after the inverse transformation and p is the pixel value before the inverse transformation.
Through the steps, the noise of the contrast enhanced image is reduced, the contrast is enhanced, taking the white area of fig. 8 as an example, the contrast of the object in the area is greatly enhanced, that is, the effect graph of fig. 9 is formed, and a foundation is laid for the subsequent security inspection identification.
In the embodiment of the application, an image processing device acquires an image to be processed; acquiring a high-frequency component and a low-frequency component of the image to be processed; according to a nonlinear stretching rule, increasing the pixel value of the low-frequency component to obtain the low-frequency component with enhanced contrast; performing noise reduction processing on the high-frequency component to obtain a noise-reduced high-frequency component; and carrying out image reconstruction by using the low-frequency component after contrast enhancement and the high-frequency component after noise reduction to obtain a contrast enhancement image. Through the mode, the image processing device decomposes the image to be processed, reduces high-frequency noise while enhancing the contrast in a low-frequency nonlinear way, and finally reconstructs the image to realize the enhancement of the image contrast.
By designing a noise transformation method suitable for an X-ray image, the application can greatly increase the applicability of a noise reduction algorithm on the X-ray image by carrying out conversion post-processing aiming at the noise characteristic of the X-ray.
According to the method, an X-ray contrast enhancement algorithm is designed, the X-ray image is decomposed, high-frequency noise is reduced while the low-frequency nonlinear contrast is enhanced, and the image is reconstructed finally to achieve enhancement of the X-ray image contrast.
It will be understood by those skilled in the art that in the method of the present invention, the order of writing the steps does not imply a strict order of execution and any limitations on the implementation, and the specific order of execution of the steps should be determined by their function and possible inherent logic.
To implement the image processing method of the above embodiment, the present application further provides an image processing apparatus, and specifically please refer to fig. 10, where fig. 10 is a schematic structural diagram of an embodiment of the image processing apparatus provided in the present application.
The image processing apparatus 300 of the embodiment of the present application includes a memory 31 and a processor 32, wherein the memory 31 and the processor 32 are coupled.
The memory 31 is used for storing program data, and the processor 32 is used for executing the program data to realize the image processing method according to the above-mentioned embodiment.
In the present embodiment, the processor 32 may also be referred to as a CPU (Central Processing Unit). The processor 32 may be an integrated circuit chip having signal processing capabilities. The processor 32 may also be a general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components. A general purpose processor may be a microprocessor or the processor 32 may be any conventional processor or the like.
To implement the image processing method of the above embodiment, the present application further provides a computer-readable storage medium, as shown in fig. 11, the computer-readable storage medium 400 is used for storing program data 41, and the program data 41 is used for implementing the image processing method of the above embodiment when being executed by a processor.
The present application also provides a computer program product, wherein the computer program product comprises a computer program operable to cause a computer to execute the image processing method according to the embodiments of the present application. The computer program product may be a software installation package.
The image processing method according to the above embodiment of the present application may be stored in a device, for example, a computer readable storage medium, when the image processing method is implemented in the form of a software functional unit and sold or used as a stand-alone product. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) or a processor (processor) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above description is only an embodiment of the present application, and is not intended to limit the scope of the present application, and all equivalent structures or equivalent processes performed by the present application and the contents of the attached drawings, which are directly or indirectly applied to other related technical fields, are also included in the scope of the present application.
Claims (12)
1. An image processing method, characterized in that the image processing method comprises:
acquiring an image to be processed;
acquiring a high-frequency component and a low-frequency component of the image to be processed;
according to a nonlinear stretching rule, increasing the pixel value of the low-frequency component to obtain the low-frequency component with enhanced contrast;
performing noise reduction processing on the high-frequency component to obtain a noise-reduced high-frequency component;
and carrying out image reconstruction by using the low-frequency component after contrast enhancement and the high-frequency component after noise reduction to obtain a contrast enhancement image.
2. The image processing method according to claim 1,
the acquiring the high-frequency component and the low-frequency component of the image to be processed comprises:
performing wavelet decomposition on the image to be processed to obtain a low-frequency component and a high-frequency component of the image to be processed;
the increasing the pixel value of the low-frequency component according to the nonlinear stretching rule to obtain the low-frequency component with enhanced contrast includes:
determining a low-frequency stretching range based on the wavelet coefficient range of the low-frequency component;
and performing stretching processing on the wavelet coefficients of the low-frequency component in the low-frequency stretching range to update the wavelet coefficients of the low-frequency component.
3. The image processing method according to claim 2,
the stretching processing of the wavelet coefficients of the low-frequency component in the low-frequency stretching range comprises:
acquiring the maximum value and the minimum value of the wavelet coefficient of the low-frequency component;
acquiring a first difference value of a wavelet coefficient of a low-frequency component in the low-frequency stretching range and a minimum value of the wavelet coefficient, and a second difference value of a maximum value of the wavelet coefficient and a minimum value of the wavelet coefficient;
and determining the wavelet coefficient after the stretching treatment according to the first difference and the second difference.
4. The image processing method according to claim 2,
the performing noise reduction processing on the high-frequency component to obtain a noise-reduced high-frequency component includes:
and performing denoising processing on the wavelet coefficient of the high-frequency component by using a denoising threshold so as to update the wavelet coefficient of the high-frequency component.
5. The image processing method according to claim 4,
the denoising processing on the wavelet coefficient of the high-frequency component by using the denoising threshold to update the wavelet coefficient of the high-frequency component comprises:
updating the wavelet coefficient of the high-frequency component with the absolute value smaller than the denoising threshold value to a preset value;
performing, on wavelet coefficients of the high-frequency component whose absolute value is equal to or greater than the denoising threshold: acquiring a difference value between the absolute value of the wavelet coefficient and the denoising threshold value, wherein the positive sign and the negative sign of the difference value are the positive sign and the negative sign of the wavelet coefficient; and taking the difference value as a wavelet coefficient after the noise reduction processing.
6. The image processing method according to claim 4 or 5,
the high frequency components include a horizontal high frequency component, a vertical high frequency component, and a diagonal high frequency component; and the noise reduction threshold corresponding to the horizontal high-frequency component, the noise reduction threshold corresponding to the vertical high-frequency component and the noise reduction threshold corresponding to the diagonal high-frequency component are different.
7. The image processing method according to claim 4 or 5, characterized in that the image processing method further comprises:
acquiring the standard deviation of the wavelet coefficient of the high-frequency component;
and determining the noise reduction threshold according to the standard deviation.
8. The image processing method according to claim 1,
before the obtaining of the high frequency component and the low frequency component of the image to be processed, the image processing method further includes:
and converting multiplicative noise in the image to be processed into additive noise by using a noise transformation algorithm.
9. The image processing method according to claim 1 or 8,
the image to be processed is an X-ray image;
before the obtaining of the high frequency component and the low frequency component of the image to be processed, the image processing method further includes:
acquiring a pixel maximum value and a pixel minimum value of the X-ray image;
and calculating the pixel value of each pixel point after the X-ray image is stretched by utilizing the pixel maximum value, the pixel minimum value and a preset pixel threshold value.
10. The image processing method according to claim 9,
before the obtaining of the maximum pixel value and the minimum pixel value of the X-ray image, the image processing method further includes:
performing a histogram equalization operation on the X-ray image.
11. An image processing apparatus, characterized in that the image processing apparatus comprises a processor and a memory, the memory having stored therein program data, the processor being configured to execute the program data to implement the image processing method according to any one of claims 1 to 10.
12. A computer-readable storage medium for storing program data which, when executed by a processor, is adapted to implement the image processing method of any one of claims 1 to 10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211576532.0A CN115880173A (en) | 2022-12-08 | 2022-12-08 | Image processing method, image processing apparatus, and computer-readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211576532.0A CN115880173A (en) | 2022-12-08 | 2022-12-08 | Image processing method, image processing apparatus, and computer-readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115880173A true CN115880173A (en) | 2023-03-31 |
Family
ID=85766706
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211576532.0A Pending CN115880173A (en) | 2022-12-08 | 2022-12-08 | Image processing method, image processing apparatus, and computer-readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115880173A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116523810A (en) * | 2023-07-04 | 2023-08-01 | 深圳开立生物医疗科技股份有限公司 | Ultrasonic image processing method, device, equipment and medium |
-
2022
- 2022-12-08 CN CN202211576532.0A patent/CN115880173A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116523810A (en) * | 2023-07-04 | 2023-08-01 | 深圳开立生物医疗科技股份有限公司 | Ultrasonic image processing method, device, equipment and medium |
| CN116523810B (en) * | 2023-07-04 | 2023-11-17 | 深圳开立生物医疗科技股份有限公司 | Ultrasonic image processing method, device, equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Chandel et al. | Image filtering algorithms and techniques: A review | |
| Singh et al. | Various image enhancement techniques-a critical review | |
| Xu et al. | Image inpainting by patch propagation using patch sparsity | |
| US8731323B2 (en) | General banding and codec banding artifact removal | |
| Hossain et al. | Medical image enhancement based on nonlinear technique and logarithmic transform coefficient histogram matching | |
| JP5250465B2 (en) | Threshold function control type wavelet shrinkage denoising device and program | |
| CN115880173A (en) | Image processing method, image processing apparatus, and computer-readable storage medium | |
| CN111415317B (en) | Image processing method and device, electronic equipment and computer readable storage medium | |
| Kumari et al. | Fast single image and video deweathering using look-up-table approach | |
| US10229479B2 (en) | Image signal processing apparatus, image signal processing method and image signal processing program | |
| US11915392B2 (en) | Image enhancement method and apparatus | |
| Ahn et al. | Flat-region detection and false contour removal in the digital TV display | |
| Pandey et al. | A fast and effective vision enhancement method for single foggy image | |
| CN111192204A (en) | Image enhancement method, system and computer readable storage medium | |
| Panetta et al. | Parameterization of logarithmic image processing models | |
| CN111383299B (en) | Image processing method and device and computer readable storage medium | |
| CN114648469B (en) | Video image denoising method, system, device and storage medium thereof | |
| Adhikari et al. | Image enhancement using successive mean quantization transform and homomorphic filtering | |
| Parihar | Histogram modification and DCT based contrast enhancement | |
| CN107871311A (en) | A kind of image enhaucament and fusion method applied to cmos image sensor | |
| US8180169B2 (en) | System and method for multi-scale sigma filtering using quadrature mirror filters | |
| Tyagi et al. | Comparative study of image enhancement and analysis of thermal images using image processing and wavelet techniques | |
| US20230099539A1 (en) | Methods and devices for image restoration using sub-band specific transform domain learning | |
| Xu et al. | Color enhancement algorithm for visual communication posters based on homomorphic filtering | |
| Buades et al. | Dual domain video denoising with optical flow estimation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |