Image processing method, device, computed tomography equipment and storage medium

Abstract

The present application discloses an image processing method, device, computed tomography equipment, and storage medium, which are applied to a computed tomography equipment. The image processing method includes: determining a first image and a second image adjacent to a target image in a plurality of images; determining a rotated first image and a second image corresponding to the target image based on the first image and the second image; determining at least one abnormal pixel region in the target image; determining the pixel value of the center point of each abnormal pixel region based on the pixel value of each abnormal pixel region, the first abnormal region corresponding to each abnormal pixel region on the rotated first image, and the second abnormal region corresponding to each abnormal pixel region on the rotated second image, so as to determine the final target image. Thus, based on the first image and the second image adjacent to the target image, the pixel values of the pixels on the target image that do not conform to the actual situation are corrected, thereby obtaining a target image with higher accuracy.

Description

Technical Field

[0001] The present application relates to the technical field of industrial measurement, and more specifically, to an image processing method, apparatus, computer tomography equipment, and storage medium. Background Art

[0002] Industrial computerized tomography (CT) is a technology that uses X-rays to scan an object to generate a three-dimensional image of its internal structure. CT is widely used in nondestructive testing, materials analysis, quality control, and other fields.

[0003] However, during the scanning process of the target object using industrial computed tomography technology, its imaging quality may be affected by various interferences (for example, noise interference, multipath interference or scattering effects, etc.), resulting in a decrease in the clarity of the three-dimensional image and an increase in artifacts, which in turn affects the final three-dimensional reconstruction result of the target object, thereby affecting the imaging accuracy of industrial computed tomography technology. Summary of the Invention

[0004] In view of the above problems, the present application proposes an image processing method, device, computed tomography equipment and storage medium, which can effectively improve the imaging accuracy of industrial computed tomography technology.

[0005] In a first aspect, an embodiment of the present application provides an image processing method, which is applied to a computed tomography device, wherein the computed tomography device is used to rotate about a preset rotation axis and continuously obtain multiple images of the object to be detected at different angles around the object to be detected. The image processing method includes: determining a first image and a second image adjacent to a target image in the multiple images; the target image is any one of the multiple images; rotating the first image and the second image about the preset rotation axis respectively to obtain a rotated first image and a second image corresponding to the target image; determining at least one abnormal pixel area in the target image based on the rotated first image and the rotated second image; determining the pixel value of the center point of each abnormal pixel area based on the pixel value of each abnormal pixel area, the first abnormal area corresponding to each abnormal pixel area on the rotated first image, and the second abnormal area corresponding to each abnormal pixel area on the rotated second image; and determining the final target image based on the pixel value of the center point of each abnormal pixel area in at least one abnormal pixel area.

[0006] In a second aspect, an embodiment of the present application further provides an image processing device, which is applied to a computed tomography device, wherein the computed tomography device is used to rotate about a preset rotation axis and continuously obtain multiple images of the object to be detected at different angles around the object to be detected. The image processing device includes: a first determination module, used to determine the first image and the second image adjacent to the target image in the multiple images; the target image is any one of the multiple images; a rotation module, used to rotate the first image and the second image about the preset rotation axis respectively to obtain the rotated first image and the second image corresponding to the target image; a second determination module, used to determine at least one abnormal pixel area in the target image based on the rotated first image and the rotated second image; a first execution module, used to determine the pixel value of the center point of each abnormal pixel area based on the pixel value of each abnormal pixel area, the first abnormal area corresponding to each abnormal pixel area on the rotated first image, and the second abnormal area corresponding to each abnormal pixel area on the rotated second image; a second execution module, used to determine the final target image based on the pixel value of the center point of each abnormal pixel area in at least one abnormal pixel area.

[0007] In a third aspect, an embodiment of the present application further provides a computed tomography device comprising a processor, a memory, and one or more applications; the one or more applications are stored in the memory and configured to be executed by the processor to implement the above-mentioned image processing method.

[0008] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, in which a program code is stored, wherein the above-mentioned image processing method is executed when the program code is run by a processor.

[0009] The technical solution provided in the present application is applied to a computed tomography device, which is used to rotate about a preset rotation axis and continuously obtain multiple images of the object to be detected at different angles around the object to be detected. The image processing method includes: determining a first image and a second image adjacent to a target image in the multiple images; the target image is any one of the multiple images; rotating the first image and the second image about the preset rotation axis respectively to obtain a rotated first image and a rotated second image corresponding to the target image; determining at least one abnormal pixel area in the target image based on the rotated first image and the rotated second image; determining the pixel value of the center point of each abnormal pixel area based on the pixel value of each abnormal pixel area, the first abnormal area corresponding to each abnormal pixel area on the rotated first image, and the second abnormal area corresponding to each abnormal pixel area on the rotated second image; and determining the final target image based on the pixel value of the center point of each abnormal pixel area in at least one abnormal pixel area. Therefore, based on the first image and the second image adjacent to the target image, the pixel values of the pixel points on the target image that are inconsistent with the actual situation are corrected so that the pixel values of the pixel points on the target image are closer to the actual situation, thereby obtaining a target image with higher accuracy, thereby improving the imaging accuracy of industrial computed tomography technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of this application, the following is a brief introduction to the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments and drawings obtained by ordinary technicians in this field without creative work are within the scope of protection of this invention.

[0011] Figure 1 A flow chart of an image processing method provided in an embodiment of the present application is shown.

[0012] Figure 2 A structural diagram of an image provided in an embodiment of the present application is shown.

[0013] Figure 3 A schematic structural diagram of an abnormal pixel area provided in an embodiment of the present application is shown.

[0014] Figure 4 A schematic structural diagram of an image processing device provided in an embodiment of the present application is shown.

[0015] Figure 5 A structural schematic diagram of a computer tomography device provided in an embodiment of the present application is shown.

[0016] Figure 6 A schematic structural diagram of a computer-readable storage medium provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solutions and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limiting this application. All other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0018] In the following description, references to "some embodiments" describe a subset of all possible embodiments. However, it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict. In the following description, the term "plurality" refers to at least two.

[0019] In the following description, the terms "first\second" are only used to distinguish similar objects and do not represent a specific order for the objects. It can be understood that "first\second" can be interchanged with a specific order or sequence where permitted, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application pertains. The terms used herein are for the purpose of describing the embodiments of this application only and are not intended to limit this application.

[0021] Industrial computerized tomography (CT) is a technology that uses X-rays to scan an object to generate a three-dimensional image of its internal structure. CT is widely used in nondestructive testing, materials analysis, quality control, and other fields.

[0022] However, during the scanning process of the target object using industrial computed tomography technology, its imaging quality may be affected by various interferences (for example, noise interference, multipath interference or scattering effects, etc.), resulting in a decrease in the clarity of the three-dimensional image and an increase in artifacts, which in turn affects the final three-dimensional reconstruction result of the target object, thereby affecting the imaging accuracy of industrial computed tomography technology.

[0023] Noise interference refers to random noise introduced during the image acquisition and transmission of the target object. This random noise primarily originates from electronic noise in the equipment itself (for example, the detector), instability in the radiation source, and electromagnetic interference in the environment. Noise interference reduces image contrast, making it difficult to discern important structural details.

[0024] Multipath interference occurs when a beam of light passes through an object and some of the signal travels through multiple paths to the detector due to reflection, refraction, and other factors. These multipath signals are superimposed on the main path signal, causing artifacts and blur in the image.

[0025] Scattering is caused by the interaction of radiation with atoms within an object. Scattering can cause radiation to deviate from its original path during transmission, weakening or shifting the received signal, leading to image blur and distortion. In other words, noise, multipath interference, and scattering can affect the imaging accuracy of industrial computed tomography.

[0026] In related technologies, filtering techniques are used to sort local areas of an image and replace the central pixel value with the median value, effectively removing isolated noise points while preserving edge details. Gaussian filtering can also be used to perform convolution operations on the image to reduce high-frequency noise. Deep learning methods can also be used to produce high-quality denoised images. For example, convolutional neural networks (CNNs) are used. Specifically, CNNs are trained using a large number of noisy and denoised images. CNNs can automatically learn the characteristics of noise and effectively remove it. Their generative adversarial networks consist of a generator and a discriminator. The generator is responsible for generating the denoised image, while the discriminator determines the image's authenticity. Through adversarial training between the generator and the discriminator, high-quality denoised images can be generated.

[0027] The above-mentioned method is used to reduce the impact of noise interference on industrial computed tomography imaging, thereby improving the imaging effect of industrial computed tomography. However, while reducing image noise, the above-mentioned method can also lead to the loss of some image details, low adaptability, and high sample requirements or equipment performance requirements. For example, detail loss is more likely to occur in the edge areas of the image. For another example, manual adjustment of parameters is required to better reduce image noise under different image and noise conditions, making it difficult for the above-mentioned method to automatically adapt to complex noise patterns. For another example, a large amount of labeled data is required for training. If the training data is insufficient or unrepresentative, the denoising effect may be significantly reduced. For another example, due to the high computational complexity of the above-mentioned method, especially when processing high-resolution CT images, high-performance computing resources may be required in practical applications, increasing the complexity and cost of the system.

[0028] Among other related technologies, multipath interference suppression can be achieved using blind equalization techniques, such as constant modulus algorithms and particle filters. The constant modulus algorithm does not rely on prior signal information. It adjusts the filter coefficients to keep the modulus of the filter's output signal constant, thereby suppressing multipath interference. The minimum mean square error algorithm can be used to minimize the mean square error between the received signal and the desired signal, and the multipath effect can be gradually eliminated by continuously adjusting the filter parameters. Particle filtering, on the other hand, is suitable for nonlinear and non-Gaussian systems. It generates a series of particles and updates the particle weights based on the observed signal to estimate the most likely true signal, thereby reducing the impact of multipath interference.

[0029] While blind equalization algorithms, such as the constant modulus algorithm (CMA) and the least mean square error (LMS) algorithm, perform well in mitigating multipath interference, they can face convergence and stability issues in practical applications. These algorithms are sensitive to the initial conditions of the signal, potentially leading to unstable results. Furthermore, while particle filtering performs well in dealing with complex multipath interference, it suffers from particle degradation. As the filtering process progresses, the weights of some particles gradually decrease or even disappear, resulting in an insufficient number of effective particles, affecting filtering accuracy and, consequently, the imaging precision of industrial computed tomography.

[0030] In other related technologies, scattering effect suppression can be achieved through scattering compensation or compensation based on the Bayesian method. Specifically, Monte Carlo simulation corrects the distortion in the image caused by scattering by simulating the propagation path of rays inside the object, including the scattering and absorption processes. Compensation based on the Bayesian method calculates the most likely scattering effect and corrects it based on prior information and observation data. In addition, the scattering effect on the imaging accuracy of industrial computed tomography technology can be reduced through multi-view imaging and image fusion. Through multi-view imaging and image fusion, CT images of the target object are obtained from multiple perspectives, and image fusion technology is used to reduce the impact of scattering effects, thereby effectively enhancing the contrast and clarity of the image.

[0031] However, while these methods can provide highly accurate compensation, they are computationally complex, especially when processing large 3D data sets. This makes real-time processing impractical. Furthermore, Bayesian-based compensation requires accurate prior information; insufficient or incorrect prior information can introduce new errors. Furthermore, the image fusion algorithms used in multi-view imaging and image fusion must be efficient and accurate to ensure accurate registration and fusion between images from different viewpoints, placing high demands on hardware.

[0032] In summary, the imaging accuracy of industrial CT can be improved by reducing the effects of noise, multipath interference, or scattering on the imaging results of industrial CT. However, due to the limitations or high hardware requirements of the above methods, the imaging accuracy of industrial CT is relatively low.

[0033] In order to improve the above-mentioned problems, the present application provides an image processing method, device, computed tomography equipment and storage medium, which are applied to a computed tomography equipment, wherein the computed tomography equipment is used to rotate about a preset rotation axis and continuously obtain multiple images of the object to be detected at different angles around the object to be detected. The image processing method includes: determining a first image and a second image adjacent to a target image in multiple images; the target image is any one of the multiple images; rotating the first image and the second image about a preset rotation axis respectively to obtain a rotated first image and a second image corresponding to the target image; determining at least one abnormal pixel area in the target image based on the rotated first image and the rotated second image; determining the pixel value of the center point of each abnormal pixel area based on the pixel value of each abnormal pixel area, the first abnormal area corresponding to each abnormal pixel area on the rotated first image, and the second abnormal area corresponding to each abnormal pixel area on the rotated second image; and determining the final target image based on the pixel value of the center point of each abnormal pixel area in at least one abnormal pixel area.

[0034] Therefore, based on the first image and the second image adjacent to the target image, the pixel values of the pixel points on the target image that are inconsistent with the actual situation are corrected so that the pixel values of the pixel points on the target image are closer to the actual situation, thereby obtaining a target image with higher accuracy, thereby improving the imaging accuracy of industrial computed tomography technology.

[0035] In order to enable people skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0036] See also Figure 1 , Figure 1 FIG. 1 shows a flow chart of an image processing method provided by an embodiment of the present application. Figure 1 As shown, the image processing method is applied to a computed tomography device, which is used to rotate about a preset rotation axis and continuously obtain multiple images of the object to be detected at different angles around the object to be detected. The image processing method may include steps 110 to 150.

[0037] In step 110 , a first image and a second image adjacent to a target image in a plurality of images are determined.

[0038] A computed tomography (CT) scanner may include a workbench, a scanning module, and a processing module. The workbench may be used to support an object to be inspected. The scanning module may be configured to rotate about a predetermined axis, surround the object to be inspected, and emit X-rays toward the object to obtain multiple images of the object at different angles. For example, the scanning module may rotate about a predetermined axis and capture an image of the object at predetermined angles, thereby obtaining multiple images of the object.

[0039] In some embodiments, the scanning module rotates about a predetermined rotation axis, capturing an image of the object to be detected at every angle, thereby obtaining 360 images of the object to be detected. For ease of explanation, this application assumes that the scanning module captures an image of the object to be detected at every angle, thereby obtaining 360 images of the object to be detected. It will be understood that any one of the 360 images is separated from its adjacent image by one angle.

[0040] The processing module can be used to process the image information collected by the scanning module to obtain a clearer image. That is, the processing module executes the image processing method of the present application to obtain the final target image.

[0041] In some embodiments, the coordinate system corresponding to the computed tomography device includes an X-axis, a Y-axis, and a Z-axis. The computed tomography device is specifically configured to rotate around the object to be inspected and acquire an image of the object to be inspected at predetermined angles, thereby acquiring multiple images.

[0042] In other embodiments, the computed tomography device is specifically configured to acquire an image of the object to be detected at every preset angle around the object to be detected using the Y-axis of the computed tomography device as a rotation axis to obtain multiple images.

[0043] In other embodiments, the computed tomography device is specifically configured to acquire an image of the object to be detected once at every preset angle around the object to be detected, using the Z axis of the computed tomography device as a rotation axis, so as to acquire multiple images.

[0044] For ease of explanation, this application uses the X-axis of the computed tomography device as the rotation axis, and obtains an image of the object to be detected once at a preset angle around the object to be detected, taking obtaining multiple images as an example for specific explanation.

[0045] The target image is any one of the multiple images. The multiple images are sorted according to the order in which they were acquired by the scanning module, i.e., they are ordered according to the acquisition time corresponding to each of the multiple images. In other words, there is a difference in the angle of the scanning module between any one of the multiple images and its two adjacent images, i.e., there is a preset angle between any one of the multiple images and its two adjacent images.

[0046] After determining the target image, the processing module determines, from the plurality of images sorted in the order of image acquisition, images adjacent to the target image as the first image and the second image, respectively. For example, if the plurality of images includes image A, image B, and image C, arranged in the order of image acquisition, and image B is determined as the target image, then image A is the first image and image C is the second image.

[0047] For example, please refer to Figure 2 , Figure 2 A schematic diagram of the structure of an image provided by an embodiment of the present application is shown in FIG. Figure 2 The computer tomography device is used to scan multiple images of the object to be detected. Figure 2 2A in is the first image, Figure 2 2B in is the target image, Figure 2 2C in the figure is the second image.

[0048] After determining that the target image is adjacent to the first and second images in the plurality of images, the first and second images are processed in subsequent steps to reconfirm the pixel values corresponding to the pixels on the target image based on the processed first and second images, thereby reducing the impact of factors such as interference on the target image, thereby improving the imaging accuracy of the computed tomography device. Specifically:

[0049] In step 120 , the first image and the second image are respectively rotated about a preset rotation axis to obtain the rotated first image and the second image corresponding to the target image.

[0050] As can be seen from the above description, the first image differs from the target image by a preset angle, and the target image differs from the second image by a preset angle. The processing module rotates the first image about the X-axis toward the angle corresponding to the target image, so that the rotated first image and the target image have the same angle. The processing module also rotates the second image about the X-axis toward the angle corresponding to the target image, so that the rotated second image and the target image have the same angle.

[0051] Since the CT scanner rotates on the X-axis, the pixels corresponding to a point on the object to be detected in multiple images can form a circle. By calculating the specific position information of each point on the circle, the specific position information of the pixel point in each image can be determined.

[0052] Specifically, in some embodiments, the step of rotating the first image and the second image respectively about a preset rotation axis to obtain the rotated first image and the second image corresponding to the target image may include the following steps:

[0053] (1) Determine the first rotation point corresponding to each pixel point on the X-axis in the first image.

[0054] (2) Determine the coordinate information of each pixel in the first image after rotation based on the coordinate information of each pixel in the first image, the coordinate information of the first rotation point corresponding to each pixel in the first image, and the preset angle, so as to determine the rotated first image.

[0055] (3) Determine the second rotation point corresponding to each pixel point on the X-axis in the second image.

[0056] (4) Determine the coordinate information of each pixel in the second image after rotation based on the coordinate information of each pixel in the second image, the coordinate information of the second rotation point corresponding to each pixel in the second image, and the preset angle to determine the rotated second image.

[0057] The first rotation point corresponding to each pixel in the first image is the center of the circle corresponding to each pixel in the first image. For example, assuming there is pixel A in the first image, pixel A can form a circle with its center on the x-axis across multiple images. This center is determined as the first rotation point corresponding to pixel A.

[0058] The processing module can determine the radius of the circle corresponding to each pixel in the first image based on the coordinate information of each pixel in the first image and the first rotation point corresponding to each pixel. Thus, based on the radius information of the circle corresponding to each pixel in the first image, the first rotation point corresponding to each pixel, and the preset angle, a first set of equations corresponding to the circle (i.e., the parametric equation of the circle) can be determined. Based on the parametric equation of the circle, the coordinate information corresponding to the pixel in the first image on the target image can be determined. This allows the pixel in the first image to be rotated to obtain the coordinate information of the corresponding pixel on the target image. Each pixel in the first image is rotated in the manner described above to obtain the position information corresponding to the pixel in the first image on the target image, thereby obtaining the rotated first image.

[0059] Exemplarily, the first image includes pixel A, and the center of the circle formed by pixel A on multiple images is circle center A. Based on the coordinate information of pixel A and the coordinate information of circle center A, the distance between pixel A and circle center A can be determined, that is, the radius of the circle formed by pixel A on multiple images can be determined. Based on the coordinate information of circle center A, the radius of the circle formed by pixel A on multiple images, and a preset angle, the coordinate information of pixel A on the target image can be determined. The corresponding coordinate information of each pixel in the first image on the target image is determined in the above manner, thereby determining the corresponding coordinate information of each pixel in the first image on the target image to obtain the rotated first image.

[0060] It will be appreciated that the second rotation point corresponding to each pixel in the second image is the center of the circle corresponding to each pixel in the second image. Similarly, the processing module determines the coordinate information of each pixel in the second image after rotation to obtain the rotated second image. The aforementioned processing module determines the coordinate information of each pixel in the first image after rotation to obtain the corresponding description of the rotated first image, and will not be further described here.

[0061] More specifically, in some embodiments, the step of determining the coordinate information of each pixel in the first image after rotation based on the coordinate information of each pixel in the first image, the coordinate information of the first rotation point corresponding to each pixel in the first image, and a preset angle may include the following steps:

[0062] (1) Determine a first distance value between each pixel point in the first image and a first rotation point corresponding to each pixel point in the first image.

[0063] (2) Determine the coordinate information of each pixel point in the first image after rotation based on the coordinate information of the first rotation point corresponding to each pixel point in the first image, the preset angle, and the first distance value corresponding to each pixel point in the first image.

[0064] The first distance value may be the radius of the circle corresponding to each pixel in the first image. That is, the first distance value is the distance between each pixel in the first image and the center of the circle corresponding to it. For example, assuming there is pixel A in the first image, and the center of the circle formed by pixel A across multiple images is circle center A, the first distance value corresponding to pixel A is the distance between the coordinate information of pixel A and the coordinate information of circle center A.

[0065] Based on the coordinate information of the center of the circle corresponding to each pixel point in the first image, the radius of the circle corresponding to each pixel point in the first image, and the angle difference between the first image and the target image, the coordinate information of the pixel point corresponding to each pixel point in the first image in the target image can be determined, so as to correspond each pixel point in the first image with each pixel point on the target image.

[0066] In a specific embodiment, the step of determining the coordinate information of each pixel point in the first image after rotation based on the coordinate information of the first rotation point corresponding to each pixel point in the first image, a preset angle, and a first distance value corresponding to each pixel point in the first image may include: determining the coordinate information of each pixel point in the first image after rotation through a first set of equations.

[0067] The expression of the first set of equations is:

[0068] ;

[0069] Among them, the coordinate information (x(t), y(t)) is the coordinate information of each pixel point in the first image after rotation, the coordinate information (h, k) is the coordinate information of the first rotation point corresponding to each pixel point in the first image, r is the first distance value corresponding to each pixel point in the first image, and t is the preset angle.

[0070] Here, t can be expressed in radians. To determine the pixel corresponding to a point on the object to be detected across all 360 images, t can be varied from 0 to 2π, incremented by the scanning angle. For example, the first image corresponds to t 0, the second image to t (0 + the preset angle), and so on.

[0071] In some embodiments, the step of determining the coordinate information of each pixel in the first image after rotation based on the coordinate information of each pixel in the first image, the coordinate information of the first rotation point corresponding to each pixel in the first image, and the preset angle may include the following steps:

[0072] (1) Determine a second distance value between each pixel point in the second image and a second rotation point corresponding to each pixel point in the second image.

[0073] (2) Determine the coordinate information of each pixel point in the second image after rotation based on the coordinate information of the second rotation point corresponding to each pixel point in the second image, the preset angle, and the second distance value corresponding to each pixel point in the second image.

[0074] The second distance value may be the radius of the circle corresponding to each pixel in the second image. That is, the second distance value is the distance between each pixel in the second image and the center of the circle corresponding to it. For example, assuming there is pixel A in the second image, and the center of the circle formed by pixel A across multiple images is circle center A, the second distance value corresponding to pixel A is the distance between the coordinate information of pixel A and the coordinate information of circle center A.

[0075] Based on the coordinate information of the center of the circle corresponding to each pixel point in the second image, the radius of the circle corresponding to each pixel point in the second image, and the angle difference between the second image and the target image, the coordinate information of the pixel point corresponding to each pixel point in the second image in the target image can be determined, so as to correspond each pixel point in the second image with each pixel point on the target image.

[0076] In a specific embodiment, the step of determining the coordinate information of each pixel point in the second image after rotation based on the coordinate information of the second rotation point corresponding to each pixel point in the second image, a preset angle, and a second distance value corresponding to each pixel point in the second image may include: determining the coordinate information of each pixel point in the second image after rotation through a first set of equations.

[0077] Among them, the coordinate information (x(t), y(t)) is the coordinate information of each pixel point in the second image after rotation, the coordinate information (h, k) is the coordinate information of the second rotation point corresponding to each pixel point in the second image, r is the second distance value corresponding to each pixel point in the second image, and t is the preset angle.

[0078] By rotating the first image and the second image respectively about a preset rotation axis, the rotated first image and the second image corresponding to the target image are obtained, so that the pixel points on the first image are corresponded to the pixel points on the target image, and the pixel points on the second image are corresponded to the pixel points on the target image, so that the pixel value corresponding to the corresponding pixel point of a certain pixel point on the target image in the first image and the pixel value corresponding to the corresponding pixel point of a certain pixel point on the target image in the second image can be determined, and then according to the pixel value corresponding to the pixel point on the target image, the pixel value corresponding to the corresponding pixel point of the pixel point in the first image and the pixel value corresponding to the corresponding pixel point of the pixel point in the second image, it is determined whether the pixel point is affected by interference and other factors.

[0079] When it is determined that the pixel point is affected by interference and other factors and is inaccurate, the pixel value corresponding to the pixel point is corrected to reduce the impact of interference and other factors on the imaging accuracy of the computer tomography device. Specifically:

[0080] In step 130 , at least one abnormal pixel region in the target image is determined based on the rotated first image and the rotated second image.

[0081] The abnormal pixel area is a pixel value corresponding to a pixel point at the center of the abnormal pixel area that is different from or has a large difference from the pixel value corresponding to the pixel point corresponding to the pixel point on the first image, or the pixel value corresponding to the pixel point at the center of the abnormal pixel area is different from or has a large difference from the pixel value corresponding to the pixel point on the second image.

[0082] Specifically, in one embodiment, the step of determining at least one abnormal pixel region in the target image based on the rotated first image and the rotated second image may include the following steps:

[0083] (1) When a pixel value of a pixel point on the target image is different from a pixel value of a corresponding pixel point on the rotated first image, the pixel point is determined to be a first abnormal pixel point on the target image.

[0084] (2) When the pixel value of the pixel point on the target image is different from the pixel value of the corresponding pixel point on the rotated second image, the pixel point is determined to be a second abnormal pixel point on the target image.

[0085] (3) Determine the final abnormal pixel point in the target image based on the first abnormal pixel point and the second abnormal pixel point.

[0086] (4) Determine at least one abnormal pixel region based on each final abnormal pixel point and the pixels adjacent to each final abnormal pixel point.

[0087] The processing module determines the pixel point with the same coordinate information as the pixel point on the rotated first image based on the coordinate information of the pixel point on the target image, and can determine the pixel value of the pixel point corresponding to the pixel point on the first image, thereby determining whether the pixel value corresponding to the pixel point on the target image is the same as the pixel value corresponding to the pixel point on the target image on the first image.

[0088] For example, the target image includes pixel A. Based on the coordinate information of pixel A, pixel B with the same coordinate information as pixel A is determined on the rotated first image. That is, pixel B is the pixel corresponding to pixel A on the first image. By comparing the pixel value corresponding to pixel A with the pixel value corresponding to pixel B, it can be determined whether pixel A is inaccurate due to factors such as interference.

[0089] The processing module determines the pixel point with the same coordinate information as the pixel point on the rotated second image based on the coordinate information of the pixel point on the target image, and can determine the pixel value of the corresponding pixel point on the second image of the pixel point on the target image, thereby determining whether the corresponding pixel value of the pixel point on the target image is the same as the pixel value of the corresponding pixel point on the second image of the pixel point on the target image.

[0090] For example, the target image includes pixel A. Based on the coordinate information of pixel A, pixel B with the same coordinate information as pixel A is determined on the rotated second image. That is, pixel B is the pixel corresponding to pixel A on the second image. By comparing the pixel value corresponding to pixel A with the pixel value corresponding to pixel B, it can be determined whether pixel A is inaccurate due to factors such as interference.

[0091] The processing module determines the pixel values of the corresponding pixels on the first image and the second image of the pixel points on the target image, so as to determine the pixel points on the target image that are inaccurate due to factors such as interference as final abnormal pixel points, and then determines at least one abnormal pixel area by combining each final abnormal pixel point and the pixels adjacent to each final abnormal pixel point.

[0092] For example, the final abnormal pixel points include a final abnormal pixel point A and a final abnormal pixel point B. The final abnormal pixel point A and the pixels adjacent to the final abnormal pixel point A are determined as an abnormal pixel region. The final abnormal pixel point B and the pixels adjacent to the final abnormal pixel point B are determined as an abnormal pixel region. In this way, multiple abnormal pixel regions are determined in the target image.

[0093] For example, please refer to Figure 3 , Figure 3 FIG. 1 shows a schematic structural diagram of an abnormal pixel region provided by an embodiment of the present application, such as Figure 3 As shown, the processing module determines the pixel points adjacent to the final abnormal pixel point A as an abnormal pixel area in the at least one abnormal pixel area.

[0094] In another embodiment, the step of determining at least one abnormal pixel region in the target image based on the rotated first image and the rotated second image may include the following steps:

[0095] (1) When a difference between a pixel value of a pixel point on the target image and a pixel value of a corresponding pixel point on the rotated first image is greater than a first preset threshold, the pixel point is determined to be a third abnormal pixel point on the target image.

[0096] (2) When the difference between the pixel value of the pixel point on the target image and the pixel value of the corresponding pixel point on the rotated second image is greater than a second preset threshold, the pixel point is determined to be a fourth abnormal pixel point on the target image.

[0097] (3) Determine the final abnormal pixel point in the target image according to the third abnormal pixel point and the fourth abnormal pixel point.

[0098] (4) Determine at least one abnormal pixel region based on each final abnormal pixel point and the pixels adjacent to each final abnormal pixel point.

[0099] The processing module determines a pixel point on the rotated first image with the same coordinate information as the pixel point based on the coordinate information of the pixel point on the target image, and can determine the pixel value of the pixel point on the target image corresponding to the pixel point on the first image, thereby determining whether the difference between the pixel value corresponding to the pixel point on the target image and the pixel value of the pixel point on the target image corresponding to the pixel point on the first image is greater than a first preset threshold, thereby determining the third abnormal pixel point.

[0100] For example, the target image includes pixel A. Based on the coordinate information of pixel A, pixel B having the same coordinate information as pixel A is determined on the rotated first image. That is, pixel B is the pixel corresponding to pixel A on the first image. Thus, by comparing the difference between the pixel values corresponding to pixel A and the pixel values corresponding to pixel B with a first preset threshold, it can be determined whether pixel A is inaccurate due to factors such as interference.

[0101] The processing module determines a pixel point on the rotated second image with the same coordinate information as the pixel point based on the coordinate information of the pixel point on the target image, and can determine the pixel value of the pixel point corresponding to the pixel point on the second image, thereby determining whether the difference between the pixel value corresponding to the pixel point on the target image and the pixel value of the pixel point corresponding to the pixel point on the target image on the second image is greater than the second preset threshold, thereby determining the fourth abnormal pixel point.

[0102] For example, the target image includes pixel A. Based on the coordinate information of pixel A, pixel B with the same coordinate information as pixel A is determined on the rotated second image. That is, pixel B is the pixel corresponding to pixel A on the second image. By comparing the difference between the pixel values corresponding to pixel A and pixel B with a second preset threshold, it can be determined whether pixel A is inaccurate due to interference or other factors.

[0103] The processing module determines the pixel values of the corresponding pixels on the first image and the second image of the pixel points on the target image, so as to determine the pixel points on the target image that are inaccurate due to factors such as interference as final abnormal pixel points, and then determines at least one abnormal pixel area by combining each final abnormal pixel point and the pixels adjacent to each final abnormal pixel point.

[0104] Among them, the specific values of the first preset threshold and the second preset threshold can be flexibly set according to actual conditions. If the imaging quality requirements for the target image are high, the specific values of the first preset threshold and the second preset threshold can be set to be smaller.

[0105] After determining at least one abnormal pixel region, the processing module determines the pixel value of the pixel at the center of the abnormal pixel region based on the pixel values corresponding to the first abnormal pixel region corresponding to the at least one abnormal pixel region on the first image and the second abnormal pixel region corresponding to the at least one abnormal pixel region on the second image, so as to complete the correction of the pixels in the abnormal pixel region, thereby obtaining a more accurate target image. Specifically:

[0106] In step 140, the pixel value of the center point of each abnormal pixel area is determined based on the pixel value of each pixel point in each abnormal pixel area, the first abnormal area corresponding to each abnormal pixel area on the rotated first image, and the second abnormal area corresponding to each abnormal pixel area on the rotated second image.

[0107] Exemplarily, at least one abnormal pixel area includes an abnormal pixel area A, a first abnormal area B corresponding to the abnormal pixel area A on the first image, and a second abnormal area C corresponding to the abnormal pixel area A on the second image. Based on the pixel values corresponding to the pixel points contained in the abnormal pixel area A, the first abnormal area B, and the second abnormal area C, the pixel value of the center point of the abnormal pixel area A is determined to complete the correction of the pixel value of the center point of the abnormal pixel area A, thereby reducing the inaccuracy caused by the influence of interference and other factors on the center point of the abnormal pixel area A.

[0108] Through the above method, the pixel value of the center point of each abnormal pixel area is determined in turn to complete the correction of the pixel value of the center point of each abnormal pixel area, reducing the influence of factors such as interference on the target image and resulting in low imaging quality, so as to obtain a target image with higher accuracy.

[0109] Further, in some embodiments, the step of determining the pixel value of the center point of each abnormal pixel region based on the pixel value of each abnormal pixel region, the first abnormal region corresponding to each abnormal pixel region on the rotated first image, and the second abnormal region corresponding to each abnormal pixel region on the rotated second image may include the following steps:

[0110] (1) Determine the pixel range corresponding to the center point of each abnormal pixel area based on the pixel value of each pixel point in each abnormal pixel area, the pixel value of each pixel point in the first abnormal area corresponding to each abnormal pixel area on the rotated first image, and the pixel value of each pixel point in the second abnormal area corresponding to each abnormal pixel area on the rotated second image.

[0111] (2) The median of the pixel range corresponding to the center point of each abnormal pixel area is determined as the pixel value of the center point of each abnormal pixel area.

[0112] The processing module can determine the pixel point with the same coordinate information as the center point on the rotated first image based on the coordinate information of the center point of each abnormal pixel area, thereby determining the pixel point corresponding to the center point on the first image, and then determine the first abnormal pixel area corresponding to the abnormal pixel area based on the pixel point corresponding to the center point on the first image and its adjacent pixel points.

[0113] The processing module can determine the pixel point with the same coordinate information as the center point on the rotated second image based on the coordinate information of the center point of each abnormal pixel area, thereby determining the pixel point corresponding to the center point on the second image, and then determine the second abnormal pixel area corresponding to the abnormal pixel area based on the pixel point corresponding to the center point on the second image and its adjacent pixel points.

[0114] The processing module then determines the pixel range of the center point of each abnormal pixel area according to each abnormal pixel area, the first abnormal pixel area corresponding to each abnormal pixel area, and the second abnormal pixel area corresponding to each abnormal pixel area.

[0115] Exemplarily, at least one abnormal pixel area includes an abnormal pixel area A, a first abnormal area B corresponding to the abnormal pixel area A on the first image, and a second abnormal area C corresponding to the abnormal pixel area A on the second image. The pixel range corresponding to the center point of the abnormal pixel area A is determined based on the pixel values corresponding to the pixel points contained in the abnormal pixel area A, the first abnormal area B, and the second abnormal area C.

[0116] That is to say, the pixel range corresponding to a certain abnormal pixel area is a pixel interval composed of the pixel value corresponding to each pixel point in the abnormal pixel area, the pixel value corresponding to each pixel point in the first abnormal area corresponding to the abnormal pixel area on the first image, and the pixel value corresponding to each pixel point in the second abnormal area corresponding to the abnormal pixel area on the second image.

[0117] That is, the processing module determines the pixel value corresponding to each pixel point in the abnormal pixel area, the pixel value corresponding to each pixel point in the first abnormal area corresponding to the abnormal pixel area on the first image, and each pixel point in the second abnormal area corresponding to the abnormal pixel area on the second image, and determines the pixel range corresponding to the abnormal pixel area by the minimum pixel value and the maximum pixel value among these pixel values.

[0118] It is understandable that since a pixel point in an abnormal pixel area may be affected by factors such as interference and undergo large changes, the pixel point may be determined as the minimum pixel value or the maximum pixel value. In this case, the median of the pixel range corresponding to the abnormal pixel area is determined based on the minimum pixel value and the maximum pixel value to determine the pixel value corresponding to the center point of the abnormal pixel area. This situation will cause the pixel value corresponding to the corrected pixel point to differ greatly from the actual value.

[0119] Similarly, a pixel point in the first abnormal pixel area and the second abnormal pixel area may also be affected by factors such as interference and undergo significant changes. These abnormal pixel points may be determined as the minimum pixel value and the maximum pixel value, so that the pixel value corresponding to the corrected pixel point is significantly different from the actual value.

[0120] Based on the above situation, the step of determining the pixel value of the center point of each abnormal pixel area according to the pixel value of each abnormal pixel area, the first abnormal area corresponding to each abnormal pixel area on the rotated first image, and the second abnormal area corresponding to each abnormal pixel area on the rotated second image may include the following steps:

[0121] (1) Determine the median corresponding to each abnormal pixel area according to the pixel value of each pixel point in each abnormal pixel area, the pixel value of each pixel point in the first abnormal area corresponding to each abnormal pixel area on the rotated first image, and the pixel value of each pixel point in the second abnormal area corresponding to each abnormal pixel area on the rotated second image.

[0122] (2) Determine the pixel range corresponding to each abnormal pixel area based on the median and the third preset threshold.

[0123] (3) The median of the pixel range corresponding to the center point of each abnormal pixel area is determined as the pixel value of the center point of each abnormal pixel area.

[0124] The processing module determines the median of these pixel values by determining the pixel value corresponding to each pixel point in a certain abnormal pixel area, the pixel value corresponding to each pixel point in a first abnormal area corresponding to the abnormal pixel area on the first image, and the pixel value corresponding to each pixel point in a second abnormal area corresponding to the abnormal pixel area on the second image.

[0125] The processing module then screens out pixel values whose difference from the median is greater than a third preset threshold value to determine pixel values closer to the median, thereby re-determining the pixel range corresponding to the abnormal pixel area based on the screened pixel values, and then determines the median of the pixel range as the pixel value of the center point of the abnormal pixel area, so as to eliminate interference in confirming the pixel value of the pixel point of the center point of the abnormal pixel area caused by pixel points in the abnormal pixel area, a first abnormal pixel area corresponding to the abnormal pixel area, and a second abnormal pixel area corresponding to the abnormal pixel area that differ greatly from the actual value, so as to obtain a more accurate pixel value of the pixel point of the center point of the abnormal pixel area.

[0126] It is understandable that the pixel values of the pixel points at the center points of other abnormal pixel areas can also be determined one by one in the above manner, thereby correcting the pixel values of the pixel points at the center points of each abnormal pixel area on the target image to obtain a target image that is more in line with reality.

[0127] In step 150, a final target image is determined based on the pixel value of the center point of each abnormal pixel region in at least one abnormal pixel region.

[0128] The processing module corrects the pixel values of the center points of the abnormal pixel area one by one to obtain the final target image. This allows the inaccurate pixels in the target image initially captured by the CT scanner to be filtered out due to factors such as interference and corrected to obtain a target image that is closer to reality, thereby improving the imaging quality of the CT scanner.

[0129] From the above description, it can be seen that by comparing the pixel values corresponding to the pixel points on the target image with the pixel values corresponding to the pixel points on the target image in the first image, and comparing the pixel values corresponding to the pixel points on the target image with the pixel values corresponding to the pixel points on the target image in the second image, the pixel points on the target image whose values are different from the actual values due to interference and other factors are determined.

[0130] Since there are many pixels on the target image, it is necessary to rotate the pixels on the first image and the pixels on the second image to determine the pixels on the first image and the corresponding pixels on the target image, as well as the pixels on the second image and the corresponding pixels on the target image.

[0131] Furthermore, the number of images acquired by the computed tomography device is also large, and each image acquired by the computed tomography device is corrected using the above method, resulting in a large number of the above calculation processes of the computed tomography device, which will occupy a large amount of computing resources.

[0132] Based on the above situation, the computed tomography equipment in this application rotates around a preset rotation axis, and continuously obtains multiple images of the object to be detected at different angles around the object to be detected. The scanning module obtains the image of the object to be detected twice every degree to obtain 720 images of the object to be detected.

[0133] That is to say, when the scanning module obtains an image of the object to be detected at a certain angle, the scanning module obtains two images of the object to be detected at the same angle.

[0134] The processing module determines any one of the two images of the object to be detected at a certain angle as the target image. Before correcting the corresponding pixel points in the target image through the above-mentioned scheme, the processing module compares the pixel values corresponding to the pixel points in the target image with the pixel values corresponding to the pixel points in the other image corresponding to the target image. If the pixel values corresponding to the pixel points in the target image are significantly different from the pixel values corresponding to the pixel points in the other image corresponding to the target image, the pixel points corresponding to the pixel points in the target image with the larger difference on the first image and the pixel points corresponding on the second image are determined, and then the pixel values corresponding to the pixel points in the target image with the larger difference are corrected through the above-mentioned method.

[0135] Therefore, there is no need to rotate all the pixels on the first image or the second image. Instead, the pixels in the target image corresponding to the larger gap need only be rotated to the angles corresponding to the first and second images to determine the corresponding pixels on the first and second images. This allows the user to determine whether the pixels in the target image corresponding to the larger gap are inconsistent with the actual situation and whether to perform subsequent correction steps for the pixel values corresponding to the pixels in the target image corresponding to the larger gap. This effectively reduces the computational burden on the computed tomography scanner.

[0136] See also Figure 4 , Figure 4 A schematic structural diagram of an image processing device provided in an embodiment of the present application is shown, which is applied to a computed tomography device. The computed tomography device is used to rotate about a preset rotation axis to continuously acquire multiple images of the object to be detected at different angles. The image processing device 200 includes: a first determination module 210, a rotation module 220, a second determination module 230, a first execution module 240, and a second execution module 250. Specifically:

[0137] A first determining module 210 is configured to determine a first image and a second image that are adjacent to a target image in a plurality of images; the target image is any one of the plurality of images;

[0138] The rotation module 220 is configured to rotate the first image and the second image respectively about a preset rotation axis to obtain the rotated first image and the second image corresponding to the target image;

[0139] A second determining module 230 is configured to determine at least one abnormal pixel region in the target image based on the rotated first image and the rotated second image;

[0140] A first execution module 240 is configured to determine a pixel value of a center point of each abnormal pixel region based on the pixel value of each abnormal pixel region, the first abnormal region corresponding to each abnormal pixel region on the rotated first image, and the second abnormal region corresponding to each abnormal pixel region on the rotated second image;

[0141] The second execution module 250 is configured to determine a final target image according to the pixel value of the center point of each abnormal pixel area in the at least one abnormal pixel area.

[0142] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and modules can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0143] In several embodiments provided in this application, the coupling or direct coupling or communication connection between the modules shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or modules, which can be electrical, mechanical or other forms.

[0144] In addition, the functional modules in the various embodiments of the present application may be integrated into a processing module, or each module may exist physically separately, or two or more modules may be integrated into a single module. The above-mentioned integrated modules may be implemented in the form of hardware or software functional modules.

[0145] See also Figure 5 , Figure 5 A structural schematic diagram of a computed tomography device provided in an embodiment of the present application is shown. The computed tomography device 300 in the present application may include one or more of the following components: a processor 310, a memory 320, and one or more application programs, wherein the one or more application programs may be stored in the memory 320 and configured to be executed by the one or more processors 310, and the one or more programs are configured to execute the image processing method described in the aforementioned method embodiment.

[0146] The processor 310 may include one or more processing cores. The processor 310 connects various components of the terminal device 300 using various interfaces and circuits. It executes instructions, programs, code sets, or instruction sets stored in the memory 320 and accesses data stored in the memory 320 to perform various functions and process data for the terminal device 300. Optionally, the processor 310 may be implemented using at least one of the following hardware forms: a digital signal processing (DSP), a field-programmable gate array (FPGA), or a programmable logic array (PLA). The processor 310 may integrate one or a combination of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. The CPU primarily processes the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing display content; and the modem handles wireless communications. It is understood that the modem may also be implemented independently of the processor 310 via a separate communications chip.

[0147] The memory 320 may include random access memory (RAM) or read-only memory (ROM). The memory 320 may be used to store instructions, programs, code, code sets, or instruction sets. The memory 320 may include a program storage area and a data storage area. The program storage area may store instructions for implementing an operating system, instructions for implementing at least one function, and instructions for implementing the various method embodiments described below. The data storage area may also store data created by the terminal device 300 during use.

[0148] See also Figure 6 , Figure 6 A schematic structural diagram of a computer-readable storage medium provided in an embodiment of the present application is shown. The computer-readable medium 400 stores program code, which can be called by a processor to execute the image processing method described in the above method embodiment.

[0149] Computer-readable storage medium 400 may be an electronic memory such as flash memory, EEPROM (Electrically Erasable Programmable Read-Only Memory), EPROM, a hard disk, or ROM. Alternatively, computer-readable storage medium 300 may comprise a non-transitory computer-readable storage medium. Computer-readable storage medium 400 has storage space for program code 410 for executing any of the method steps described above. This program code can be read from or written to one or more computer program devices. Program code 410 may be compressed, for example, in a suitable format.

[0150] The technical solution provided in the present application is applied to a computed tomography device, which is used to rotate about a preset rotation axis and continuously obtain multiple images of the object to be detected at different angles around the object to be detected. The image processing method includes: determining a first image and a second image adjacent to a target image in the multiple images; the target image is any one of the multiple images; rotating the first image and the second image about the preset rotation axis respectively to obtain a rotated first image and a rotated second image corresponding to the target image; determining at least one abnormal pixel area in the target image based on the rotated first image and the rotated second image; determining the pixel value of the center point of each abnormal pixel area based on the pixel value of each abnormal pixel area, the first abnormal area corresponding to each abnormal pixel area on the rotated first image, and the second abnormal area corresponding to each abnormal pixel area on the rotated second image; and determining the final target image based on the pixel value of the center point of each abnormal pixel area in at least one abnormal pixel area. Thus, based on the adjacent first and second images of the target image, pixel values on the target image that do not match the actual values are corrected to bring the pixel values on the target image closer to the actual values, thereby obtaining a more accurate target image and improving the imaging accuracy of industrial computed tomography technology.

[0151] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. An image processing method, characterized in that: The method is applied to a computer tomography device, wherein the computer tomography device is used to rotate about a preset rotation axis and continuously acquire multiple images of the object to be detected at different angles around the object to be detected. The method includes: Determine a first image and a second image that are adjacent to a target image in the plurality of images; the target image is any one of the plurality of images; Rotating the first image and the second image respectively about the preset rotation axis to obtain the rotated first image and the second image corresponding to the target image; The computed tomography device is specifically configured to obtain an image of the object to be detected once at a preset angle around the object to be detected, using the X-axis of the computed tomography device as a rotation axis, so as to obtain the multiple images; The step of rotating the first image and the second image respectively about the preset rotation axis to obtain the rotated first image and the second image corresponding to the target image includes: Determine a first rotation point corresponding to each pixel point in the first image on the X-axis; determining, based on the coordinate information of each pixel in the first image, the coordinate information of the first rotation point corresponding to each pixel in the first image, and the preset angle, the coordinate information of each pixel in the first image after rotation, so as to determine the rotated first image; Determine a second rotation point corresponding to each pixel point in the second image on the X-axis; determining the coordinate information of each pixel in the second image after rotation based on the coordinate information of each pixel in the second image, the coordinate information of the second rotation point corresponding to each pixel in the second image, and the preset angle, so as to determine the rotated second image; determining at least one abnormal pixel region in the target image according to the rotated first image and the rotated second image; Determine the pixel value of the center point of each abnormal pixel region according to the pixel value of each abnormal pixel region, the first abnormal region corresponding to each abnormal pixel region on the rotated first image, and the second abnormal region corresponding to each abnormal pixel region on the rotated second image; The final target image is determined according to the pixel value of the center point of each abnormal pixel area in the at least one abnormal pixel area.

2. The image processing method according to claim 1, wherein: The determining, based on the coordinate information of each pixel in the first image, the coordinate information of the first rotation point corresponding to each pixel in the first image, and the preset angle, coordinate information of each pixel in the first image after rotation includes: Determining a first distance value between each pixel point in the first image and the first rotation point corresponding to each pixel point in the first image; Determining the coordinate information of each pixel in the first image after rotation according to the coordinate information of the first rotation point corresponding to each pixel in the first image, the preset angle, and the first distance value corresponding to each pixel in the first image; And / or, determining the coordinate information of each pixel in the second image after rotation based on the coordinate information of each pixel in the second image, the coordinate information of the second rotation point corresponding to each pixel in the second image, and the preset angle includes: Determining a second distance value between each pixel point in the second image and the second rotation point corresponding to each pixel point in the second image; The coordinate information of each pixel in the second image after rotation is determined according to the coordinate information of the second rotation point corresponding to each pixel in the second image, the preset angle, and the second distance value corresponding to each pixel in the second image.

3. The image processing method according to claim 1, wherein: The determining, based on the coordinate information of the first rotation point corresponding to each pixel in the first image, the preset angle, and the first distance value corresponding to each pixel in the first image, coordinate information of each pixel in the first image after rotation includes: The coordinate information of each pixel in the first image after rotation is determined by a first set of equations, where the expression of the first set of equations is: Wherein, the coordinate information (x(t), y(t)) is the coordinate information of each pixel in the first image after rotation, the coordinate information (h, k) is the coordinate information of the first rotation point corresponding to each pixel in the first image, r is the first distance value corresponding to each pixel in the first image, and t is the preset angle; The determining, based on the coordinate information of the second rotation point corresponding to each pixel in the second image, the preset angle, and the second distance value corresponding to each pixel in the second image, coordinate information of each pixel in the second image after rotation includes: The coordinate information of each pixel point in the second image after rotation is determined by the first set of equations.

4. The image processing method according to claim 1, wherein: The determining of at least one abnormal pixel region in the target image according to the rotated first image and the rotated second image includes: When a pixel value of a pixel point on the target image is different from a pixel value of a corresponding pixel point of the pixel point on the rotated first image, determining the pixel point as a first abnormal pixel point on the target image; When a pixel value of a pixel point on the target image is different from a pixel value of a corresponding pixel point on the rotated second image, determining that the pixel point is a second abnormal pixel point on the target image; Determine a final abnormal pixel in the target image according to the first abnormal pixel and the second abnormal pixel; The at least one abnormal pixel region is determined according to each of the final abnormal pixel points and the pixel points adjacent to each of the final abnormal pixel points.

5. The image processing method according to claim 1, wherein: The determining of at least one abnormal pixel region in the target image according to the rotated first image and the rotated second image includes: When a difference between a pixel value of a pixel point on the target image and a pixel value of a corresponding pixel point of the pixel point on the rotated first image is greater than a first preset threshold, determining that the pixel point is a third abnormal pixel point on the target image; When a difference between a pixel value of a pixel point on the target image and a pixel value of a corresponding pixel point of the pixel point on the rotated second image is greater than a second preset threshold, determining that the pixel point is a fourth abnormal pixel point on the target image; Determine a final abnormal pixel in the target image according to the third abnormal pixel and the fourth abnormal pixel; The at least one abnormal pixel region is determined according to each of the final abnormal pixel points and the pixel points adjacent to each of the final abnormal pixel points.

6. The image processing method according to claim 1, wherein: Determining the pixel value of the center point of each abnormal pixel region according to the pixel value of each abnormal pixel region, the first abnormal region corresponding to each abnormal pixel region on the rotated first image, and the second abnormal region corresponding to each abnormal pixel region on the rotated second image includes: Determine a pixel range corresponding to a center point of each abnormal pixel region according to a pixel value of each pixel point in each abnormal pixel region, a pixel value of each pixel point in a first abnormal region corresponding to each abnormal pixel region on the rotated first image, and a pixel value of each pixel point in a second abnormal region corresponding to each abnormal pixel region on the rotated second image; The median of the pixel range corresponding to the center point of each abnormal pixel area is determined as the pixel value of the center point of each abnormal pixel area.

7. An image processing device, characterized in that Applied to a computer tomography device, the computer tomography device is used to rotate about a preset rotation axis and continuously acquire multiple images of the object to be detected at different angles around the object to be detected, the device comprising: A first determining module is configured to determine a first image and a second image that are adjacent to a target image in the plurality of images; the target image is any one of the plurality of images; a rotation module, configured to rotate the first image and the second image respectively about the preset rotation axis to obtain the rotated first image and the second image corresponding to the target image; The computed tomography device is specifically configured to obtain an image of the object to be detected once at a preset angle around the object to be detected, using the X-axis of the computed tomography device as a rotation axis, so as to obtain the multiple images; The step of rotating the first image and the second image respectively about the preset rotation axis to obtain the rotated first image and the second image corresponding to the target image includes: Determine a first rotation point corresponding to each pixel point in the first image on the X-axis; determining, based on the coordinate information of each pixel in the first image, the coordinate information of the first rotation point corresponding to each pixel in the first image, and the preset angle, the coordinate information of each pixel in the first image after rotation, so as to determine the rotated first image; Determine a second rotation point corresponding to each pixel point in the second image on the X-axis; determining the coordinate information of each pixel in the second image after rotation based on the coordinate information of each pixel in the second image, the coordinate information of the second rotation point corresponding to each pixel in the second image, and the preset angle, so as to determine the rotated second image; a second determining module, configured to determine at least one abnormal pixel region in the target image based on the rotated first image and the rotated second image; a first execution module, configured to determine a pixel value of a center point of each abnormal pixel region based on the pixel value of each abnormal pixel region, the first abnormal region corresponding to each abnormal pixel region on the rotated first image, and the second abnormal region corresponding to each abnormal pixel region on the rotated second image; The second execution module is configured to determine the final target image according to the pixel value of the center point of each abnormal pixel area in the at least one abnormal pixel area.

8. A computer tomography device, characterized in that: include: one or more processors; Memory; One or more application programs, wherein the one or more application programs are stored in the memory and are configured to execute the image processing method according to any one of claims 1 to 6 by the one or more processors.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores program code, and the program code can be called by a processor to execute the image processing method according to any one of claims 1 to 6.

Images