CN114298934B - Cheek clamp developing weakening method and device based on pixel adjustment - Google Patents
Cheek clamp developing weakening method and device based on pixel adjustmentDownload PDFInfo
- Publication number
- CN114298934B CN114298934BCN202111608572.4ACN202111608572ACN114298934BCN 114298934 BCN114298934 BCN 114298934BCN 202111608572 ACN202111608572 ACN 202111608572ACN 114298934 BCN114298934 BCN 114298934B
- Authority
- CN
- China
- Prior art keywords
- cheek
- pixel
- value
- clamp
- boundary
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034methodMethods0.000titleclaimsabstractdescription49
- 230000003313weakening effectEffects0.000titleclaimsabstractdescription33
- 238000011161developmentMethods0.000claimsabstractdescription24
- 238000012545processingMethods0.000claimsabstractdescription19
- 230000015654memoryEffects0.000claimsdescription18
- 238000004590computer programMethods0.000claimsdescription3
- 238000004364calculation methodMethods0.000description8
- 238000001514detection methodMethods0.000description3
- 230000000007visual effectEffects0.000description3
- 238000004422calculation algorithmMethods0.000description2
- 238000010586diagramMethods0.000description2
- 230000000694effectsEffects0.000description2
- 238000001914filtrationMethods0.000description2
- 238000012986modificationMethods0.000description2
- 230000004048modificationEffects0.000description2
- 239000007787solidSubstances0.000description2
- 238000005481NMR spectroscopyMethods0.000description1
- 239000000654additiveSubstances0.000description1
- 230000000996additive effectEffects0.000description1
- 238000003491arrayMethods0.000description1
- 238000002591computed tomographyMethods0.000description1
- 230000007547defectEffects0.000description1
- 238000003745diagnosisMethods0.000description1
- 201000010099diseaseDiseases0.000description1
- 208000037265diseases, disorders, signs and symptomsDiseases0.000description1
- 238000005516engineering processMethods0.000description1
- 230000001815facial effectEffects0.000description1
- 230000006870functionEffects0.000description1
- 238000003384imaging methodMethods0.000description1
- 238000010295mobile communicationMethods0.000description1
- 230000000877morphologic effectEffects0.000description1
- 230000003287optical effectEffects0.000description1
- 238000004445quantitative analysisMethods0.000description1
Images
Landscapes
- Image Processing (AREA)
Abstract
Description
Technical Field
The invention relates to the technical field of image denoising, in particular to a cheek clamp developing weakening method and device based on pixel adjustment.
Background
In recent years, computer and medical technology have been rapidly developed, and medical images of various modalities can be acquired by using an electronic computer tomography, nuclear magnetic resonance and other influencing equipment. Improving the quality of medical images helps to improve the accuracy and objectivity of computer-aided clinical medical diagnosis and quantitative analysis of diseases, and thus it is necessary to improve the quality of medical images. Noise is an important factor affecting image quality, and common denoising methods are classified into spatial domain and frequency domain methods. The method for denoising the spatial domain image in the prior art comprises the following steps: the method for removing the random impulse noise by the switch median and the morphological filtering, the algorithm for removing the random impulse noise by the self-adaptive double threshold, the algorithm for removing the random impulse noise based on the iteration method and the like. The method for denoising a frequency domain image in the prior art comprises the following steps: the method comprises the steps of denoising a singular detection image based on wavelet and multi-fractal, denoising the image by applying double-layer mixed wavelet transform of wiener filtering, denoising the image by applying even complex wavelet transform, and the like.
In the process of shooting the panoramic picture, a cheek clamp is needed to fix the head position of the patient, so that the shaking phenomenon is avoided as far as possible in the process of shooting the panoramic picture. The panoramic view appears discontinuous at the cheek clip location, since the cheek clip may attenuate the X-rays to some extent, while the cheek clip portion may be considered to be affected by additive noise. The object of the cheek clip development weakening is to reduce the degree to which the cheek clip portion is affected by noise, making the cheek clip portion and other portions appear as one whole in the panoramic image. When the existing method is applied to the problem of weakening of cheek clamp development, the blurring phenomenon of the non-cheek clamp part of the panoramic image can occur, or the effect that the cheek clamp part and other parts look into a whole cannot be achieved.
Disclosure of Invention
Therefore, the technical problem to be solved by the invention is to overcome the defect that the blurring phenomenon occurs in the non-cheek clamp part of a panoramic image when the existing method is applied to the cheek clamp developing weakening problem, so that the cheek clamp developing weakening method and device based on pixel adjustment are provided.
According to a first aspect, an embodiment of the present invention discloses a pixel adjustment-based cheek clamp development weakening method, including: acquiring a panoramic image to be weakened; carrying out image binarization processing by using a target network to obtain a cheek clamp boundary part; determining a fitting boundary corresponding to each cheek clamp boundary region in the cheek clamp boundary part and determining a boundary expression of each fitting boundary; determining a pixel set of each cheek clamp region and a pixel set of a non-cheek clamp image portion according to a boundary expression of the fitting boundary, wherein the pixel sets comprise position coordinates and pixel values of each pixel; determining each column of pixel adjustment values for each cheek clamp region from the set of pixels for the cheek clamp region and the set of pixels for the non-cheek clamp region portion; and adjusting the pixel value of the corresponding cheek clamp region by using each column of pixel adjustment values of each cheek clamp region.
Optionally, the determining each column of pixel adjustment values for each cheek clip region from the set of pixels for the cheek clip region and the set of pixels for the non-cheek clip region portion comprises: acquiring an expected value of each column of pixels in the cheek clamp area; acquiring a pixel mean value of each column in the cheek clamp area; and obtaining the pixel adjustment value of each column of each cheek clamp region according to the pixel expected value of each column of the cheek clamp region and the pixel average value of each column.
Optionally, obtaining an expected value of each column of pixels in the cheek clamp region includes: respectively obtaining a first pixel mean value of the preset column number of non-cheek clamp areas on the left side of the left boundary of each cheek clamp area; respectively obtaining a second pixel mean value of the preset column number of non-cheek clamp areas on the right side of the right boundary of each cheek clamp area; respectively acquiring a third pixel mean value of each cheek clamp region except the cheek clamp boundary part; and determining the expected value of each column of pixels in each cheek clamp area according to the first pixel mean value, the second pixel mean value and the third pixel mean value.
Optionally, after the image binarization processing is performed by using the target network to obtain the cheek clamp boundary portion, before determining one fitting boundary corresponding to each cheek clamp region in the cheek clamp boundary portion and determining a boundary expression of each fitting boundary, the method further includes: acquiring the number of detected fitting boundaries; and when the number of the fitting boundaries is the same as the preset number of the cheek clamp boundaries, executing a subsequent step of adjusting the pixel values of the cheek clamp region.
According to a second aspect, embodiments of the present invention also disclose a pixel-adjustment based cheek clip development weakening device, comprising: the first acquisition module is used for acquiring a panoramic image to be weakened; the processing module is used for carrying out image binarization processing by using a target network to obtain a cheek clamp boundary part; the first determining module is used for determining a fitting boundary corresponding to each cheek clamp boundary area in the cheek clamp boundary part and determining a boundary expression of each fitting boundary; a second determining module, configured to determine, according to a boundary expression of the fitting boundary, a pixel set of each cheek clamp region and a pixel set of a non-cheek clamp region portion, where the pixel set includes a position coordinate and a pixel value of each pixel; a third determining module that determines each column of pixel adjustment values for each cheek clip region from the set of pixels for the cheek clip region and the set of pixels for the non-cheek clip region portion; and the adjusting module is used for adjusting the pixel value of the corresponding cheek clamp region by using each column of pixel adjusting value of each cheek clamp region.
Optionally, the second determining module includes: the second acquisition submodule is used for acquiring the expected value of each row of pixels in the cheek clamp area; the third acquisition submodule is used for acquiring the pixel mean value of each row of the cheek clamp area; and the second determining submodule is used for obtaining each column of pixel adjustment value of each cheek clamp region according to the pixel expectation value of each column of the cheek clamp region and the pixel mean value of each column.
Optionally, the second obtaining sub-module includes: the fourth obtaining submodule is used for respectively obtaining a first pixel mean value of the preset column number of the non-cheek clamp area on the left side of the left boundary of each cheek clamp area; the fifth obtaining submodule is used for respectively obtaining a second pixel mean value of the preset column number of the non-cheek clamp area on the right side of the right boundary of each cheek clamp area; a sixth obtaining submodule, configured to obtain a third pixel mean of each cheek clamp region except for a cheek clamp boundary portion; and the third determining submodule is used for determining the expected value of each column of pixels of each cheek clamp area according to the first pixel average value, the second pixel average value and the third pixel average value.
Optionally, the apparatus further comprises: the second acquisition module is used for acquiring the number of the detected fitting boundaries; and the judging module is used for executing the subsequent step of adjusting the pixel values of the cheek clamp area when the number of the fitting boundaries is the same as the preset number of the cheek clamp boundaries.
According to a third aspect, an embodiment of the present invention further discloses an electronic device, including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to cause the at least one processor to perform the steps of the pixel adjusted cheek clip development weakening method according to the first aspect or any one of the optional embodiments of the first aspect.
According to a fourth aspect, embodiments of the present invention further disclose a computer-readable storage medium, on which a computer program is stored, which, when executed by a processor, implements the steps of the pixel-based adjusted cheek clip development weakening method as described in the first aspect or any one of the optional embodiments of the first aspect.
The technical scheme of the invention has the following advantages:
the invention provides a pixel adjustment-based cheek clamp development weakening method/device, which is used for acquiring a panoramic image to be weakened; carrying out image binarization processing by using a target network to obtain a cheek clamp image part; determining a fitting boundary corresponding to each cheek clamp boundary region in the cheek clamp boundary part and determining a boundary expression of each fitting boundary; determining a pixel set of each cheek clamp region and a pixel set of a non-cheek clamp image portion according to a boundary expression of the fitting boundary, wherein the pixel sets comprise position coordinates and pixel values of each pixel; determining each column of pixel adjustment values for each cheek clamp region from the set of pixels for the cheek clamp region and the set of pixels for the non-cheek clamp region portion; and adjusting the pixel value of the corresponding cheek clamp region by using each column of pixel adjustment values of each cheek clamp region. According to the cheek clamp developing weakening method based on pixel adjustment, only the pixel adjustment is carried out on the cheek clamp area, the definition of the non-cheek area is guaranteed, meanwhile, the pixel values of the cheek clamp and the neighborhood non-cheek clamp portion are considered, the row pixel adjustment is carried out according to the pixels of each row, and the visual effect of a panoramic image is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a flowchart of a specific example of a cheek clip development weakening method based on pixel adjustment in an embodiment of the present invention;
fig. 2 is an overall view of a cheek portion to be weakened according to a specific example of a method for weakening cheek clamp development based on pixel adjustment in the embodiment of the present invention;
fig. 3 is an overall view of a weakened cheek portion of a specific example of a pixel-adjustment-based cheek clip development weakening method in an embodiment of the present invention;
FIG. 4 is a functional block diagram of one specific example of a pixel adjustment based cheek clip development weakening device in an embodiment of the present invention;
fig. 5 is a diagram of a specific example of an electronic device in an embodiment of the invention.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the accompanying drawings, and it should be understood that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience of description and simplicity of description, but do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus, should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
In the description of the present invention, it should be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; can be mechanically or electrically connected; the two elements may be directly connected or indirectly connected through an intermediate medium, or may be communicated with each other inside the two elements, or may be wirelessly connected or wired connected. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
In addition, the technical features involved in the different embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
The embodiment of the invention discloses a pixel adjustment-based cheek clamp development weakening method, which comprises the following steps of:
Illustratively, the panoramic image to be weakened may be a medical image of multiple modalities acquired by an imaging device such as an electronic computer, magnetic resonance, or the like; in this embodiment, a method for weakening a cheek clamp development based on pixel adjustment described in the present application is described by taking a facial CT image with a cheek clamp development as an example, and fig. 2 is a panoramic view of a portion of a cheek to be weakened, where (1) indicates a left cheek clamp region and (2) indicates a right cheek clamp region.
And 102, carrying out image binarization processing by using a target network to obtain a cheek clamp boundary part.
Illustratively, the U-Net network is applied to divide the panoramic image to be weakened into a cheek clip boundary portion and a non-cheek clip boundary portion, so as to obtain a binary image, wherein the pixel value of the cheek clip boundary region is 1, and the pixel value of the non-cheek clip boundary region is 0.
Exemplarily, detecting cheek clamp boundary regions in the binary image, performing fitting boundary straight line operation by adopting a least square method according to pixels of each cheek clamp boundary region, and determining a boundary expression of each fitting boundary; in this specific embodiment, the to-be-weakened panoramic image has two cheek clamps for development, 4 fitting boundaries in total, the size of the to-be-weakened image is h × w (height × width), and the boundary expression of the obtained 4 fitting boundaries may be x = f1 (y)，x＝f2 (y)，x＝f3 (y)，x＝f4 (y) left cheek clip left boundary, left cheek clip right boundary, right cheek clip left boundary, and right cheek clip right boundary, respectively, where y is the ordinate of the point on the fitted boundary, where y =1,2, · h, x = fi (y) is the abscissa of the boundary point, where i =1,2,3,4.
Andstep 104, determining a pixel set of each cheek clamp region and a pixel set of a non-cheek clamp region part according to the boundary expression of the fitting boundary, wherein the pixel set comprises the position coordinate and the pixel value of each pixel.
Illustratively, since the fitting boundary is an approximate boundary of the cheek clamp region, the two boundaries of one cheek clamp are not in parallel relationship with each other, so the width of the cheek clamp needs to be calculated, and thus the cheek clamp region expression is obtained. In this embodiment, let p (x, y) denote a pixel with coordinates (x, y), and the left cheek width is wL ＝max(f2 (1)-f1 (1)，f2 (2)-f1 (2)，...，f2 (h)-f1 (h) Left cheek clamp area expression is left)1 ＝{p(x，y)|1≤y≤h，f1 (y)≤x＜f1 (y)+wL 2 and left2 ＝{p(x，y)|1≤y≤h，f2 (y)-wL /2≤x＜f2 (y) } two moieties; the width of the right cheek clamp is wR ＝max(f4 (1)-f3 (1)，f4 (2)-f3 (2)，...，f4 (h)-f3 (h) Then the right cheek clamp region is denoted right)1 ＝{p(x，y)|1≤y≤h，f3 (y)≤x＜f1 (y)+wR 2 and left2 ＝{p(x，y)|1≤y≤h，f4 (y)-wR /2≤x＜f4 (y) } two parts.
For example, each column of pixel adjustment values for each cheek clip region may be jointly determined by the set of pixels for the cheek clip region and the set of pixels for the non-cheek clip region.
Andstep 106, adjusting the pixel value of the corresponding cheek clamp region by using each column of pixel adjustment values of each cheek clamp region.
Illustratively, the pixels of each column of the cheek clamp region are adjusted by using the obtained pixel adjustment value of each column of each cheek clamp region, and a development weakening panoramic image after adjustment of the cheek clamp region is obtained, as shown in fig. 3.
The invention provides a cheek clamp developing weakening method based on pixel adjustment, which comprises the following steps: acquiring a panoramic image to be weakened; carrying out image binarization processing by using a target network to obtain a cheek clamp image part; determining a fitting boundary corresponding to each cheek clamp boundary region in the cheek clamp boundary part and determining a boundary expression of each fitting boundary; determining a pixel set of each cheek clamp region and a pixel set of a non-cheek clamp image portion according to a boundary expression of the fitting boundary, wherein the pixel sets comprise position coordinates and pixel values of each pixel; determining each column of pixel adjustment values for each cheek clamp region from the set of pixels for the cheek clamp region and the set of pixels for the non-cheek clamp region portion; and adjusting the pixel value of the corresponding cheek clamp region by using each column of pixel adjustment values of each cheek clamp region. According to the cheek clamp developing weakening method based on pixel adjustment, only the pixel adjustment is carried out on the cheek clamp area, the definition of the non-cheek area is guaranteed, meanwhile, the pixel values of the cheek clamp and the neighborhood non-cheek clamp portion are considered, the row pixel adjustment is carried out according to the pixels of each row, and the visual effect of a panoramic image is improved.
As an optional embodiment of the present invention, the determining each column of pixel adjustment values for each cheek clip region according to the set of pixels for the cheek clip region and the set of pixels for the non-cheek clip region portion includes: acquiring an expected value of each column of pixels in the cheek clamp area; acquiring a pixel mean value of each column of the cheek clamp area; and obtaining the pixel adjustment value of each column of each cheek clamp region according to the pixel expected value of each column of the cheek clamp region and the pixel average value of each column.
For example, each column of pixel adjustment values of each cheek clamp region may be obtained from a corresponding column-average pixel estimation value and a corresponding column-average pixel mean value, where the column-average pixel estimation value is an expected value of the column of pixels; in this embodiment, left can be set1 The row-to-row pixel estimate for the jth row in (j) is right1Estj Column pixel Mean left1Meanj Wherein the abscissa of the j-th column of pixels satisfies x = f1 (y) + j; let a (x, y) be the pixel adjustment value at coordinate (x, y), then set left1 Of column jThe pixel adjustment calculation process is shown as the following formula, where T is a threshold, and in this embodiment, T is 10:
next adjust left2 The pixel in (1) can be left2 The row-by-row pixel estimate for the jth row in (j) is right2Estj Column pixel Mean left2Meanj Wherein the abscissa of the j-th column of pixels satisfies x = f2 (y)+j-wL /2+1; let a (x, y) be the pixel adjustment value at coordinate (x, y), then set left2 The pixel adjustment calculation procedure for column j is shown as follows, where T is the threshold:
next adjust right1 The pixel in (1) can be set to right1 The row-to-row pixel estimate for the kth column is right1Estk The Mean value of the column pixels is right1Meank Wherein the abscissa of the k-th column of pixels satisfies x = f3 (y) + k; let a (x, y) be the pixel adjustment value at coordinate (x, y), then right is collected1 The pixel adjustment calculation procedure for the kth column is shown as follows, where T is the threshold:
next adjust right2 The pixel in (1) can be set to right2 The column-average pixel estimate for the kth column is right2Estk The Mean value of the column pixels is right2Meank Wherein the abscissa of the kth column of pixels satisfies x = f4 (y)+k-wR /2+1; let a (x, y) be the pixel adjustment value at coordinate (x, y), then right is collected2 The pixel adjustment calculation procedure for the kth column is shown as follows, where T is the threshold:
as an alternative embodiment of the present invention, acquiring the expected value of each column of pixels in the cheek clamp region includes: respectively obtaining a first pixel mean value of the preset column number of non-cheek clamp areas on the left side of the left boundary of each cheek clamp area; respectively obtaining a second pixel mean value of the preset column number of non-cheek clamp areas on the right side of the right boundary of each cheek clamp area; respectively acquiring a third pixel mean value of each cheek clamp region except the cheek clamp boundary part; and determining the expected value of each column of pixels in each cheek clamp area according to the first pixel mean value, the second pixel mean value and the third pixel mean value.
Exemplarily, in the present specific embodiment, let parallel to x = f1 (y) and is located at x = f1 (y) the pixel mean of the 5 left non-cheek clamp portions is leftL Parallel to x = f2 (y) and is located at x = f2 (y) mean value of non-cheek clamp portion of right 5 columns leftR . The mean pixel value of the middle part of the left cheek clamp is leftM Since the left and right borders of the cheek clip are not in parallel relationship, the left and right borders of the cheek clip are required to jointly determine leftM 。leftL ，leftR ，leftM Is shown in the following equation, where g (x, y) represents a pixel value with coordinates (x, y), and col represents a column offset:
left1 the horizontal and vertical coordinates of the j th row of pixels satisfy x = f1 (y) + j, then the column mean of the columnThe estimation value calculation process is shown in the following formula:
left2 the horizontal and vertical coordinates of the j-th row of pixels satisfy x = f2 (y)+j-wL /2+1, the column mean estimate calculation for this column is shown in the following equation:
let parallel to x = f3 (y) and is located at x = f3 (y) the average of the pixels of the left 5 columns of non-cheek clip portions is rightL Parallel to x = f4 (y) and is located at x = f4 (y) Right 5 columns of non-cheek clip portions mean rightR . The mean of the pixels in the middle of the left cheek clamp is rightM Since the left and right borders of the cheek clip are not in parallel relationship, the left and right borders of the cheek clip are required to jointly determine leftM ，rightL ，rightR ，rightM Is shown in the following formula, where g (x, y) represents a pixel value with coordinates (x, y):
right1 the horizontal and vertical coordinates of the k-th row of pixels satisfy x = f3 (y) + k, then the column mean estimate calculation for this column is shown in the following equation:
right2 the horizontal and vertical coordinates of the k-th row of pixels satisfy x = f4 (y)+k-wR /2+1, the column mean estimate calculation for this column is shown in the following equation:
as an optional embodiment of the present invention, before determining a fitting boundary corresponding to each cheek clip boundary region in the cheek clip boundary portion and determining a boundary expression of each fitting boundary after performing image binarization processing by using a target network to obtain a cheek clip image portion, the method further includes: acquiring the number of detected fitting boundaries; and when the number of the fitting boundaries is the same as the preset number of the cheek clamp boundaries, executing a subsequent step of adjusting the pixel values of the cheek clamp region.
Exemplarily, detecting a boundary region of a cheek clamp in the obtained binary image so as to obtain a connected region of the detected boundary region, obtaining a fitting boundary straight line of the cheek clamp according to pixels of each connected region, performing a subsequent step of adjusting pixel values of the cheek clamp region when the number of the fitting boundaries is the same as a preset number, and directly exiting when the number of the fitting boundaries is different from the preset number, wherein the boundary detection is wrong; in this embodiment, two cheek clamps are present in the to-be-weakened panorama, and there are four borders in total, and when the number of the fitting borders is not 4, it is indicated that there is a mistake in detecting the cheek clamp border region, and the detection is directly exited, and when the number of the fitting borders is equal to 4, the subsequent operation is performed.
The embodiment of the invention also discloses a cheek clamp developing weakening device based on pixel adjustment, which comprises the following components in percentage by weight as shown in fig. 4: a first obtaining module 201, configured to obtain a panoramic image to be weakened; the processing module 202 is configured to perform image binarization processing by using a target network to obtain a cheek clamp boundary portion; the first determining module 203 is configured to determine one fitting boundary corresponding to each cheek clip boundary region in the cheek clip boundary portion and determine a boundary expression of each fitting boundary; a second determining module 204, configured to determine, according to the boundary expression of the fitted boundary, a pixel set of each cheek clamp region and a pixel set of a non-cheek clamp region portion, where the pixel set includes a position coordinate and a pixel value of each pixel; a third determining module 205 for determining each column of pixel adjustment values for each cheek clip region from the set of pixels for the cheek clip region and the set of pixels for the non-cheek clip region portion; and the adjusting module 206 adjusts the pixel value of the corresponding cheek clamp region by using each column of pixel adjustment values of each cheek clamp region.
The invention provides a pixel adjustment-based cheek clamp developing weakening device which comprises a first obtaining module, a second obtaining module and a third obtaining module, wherein the first obtaining module is used for obtaining a panoramic image to be weakened; the processing module is used for carrying out image binarization processing by using a target network to obtain a cheek clamp image part; the first determining module is used for determining two fitting boundaries corresponding to each cheek clamp boundary area in the cheek clamp boundary part and determining a boundary expression of each fitting boundary; a second determining module, configured to determine, according to a boundary expression of the fitting boundary, a pixel set of each cheek clamp region and a pixel set of a non-cheek clamp image portion, where the pixel set includes a position coordinate and a pixel value of each pixel; a third determining module for determining each column of pixel adjustment values for each cheek clip region from the set of pixels for the cheek clip region and the set of pixels for the non-cheek clip region portion; and the adjusting module is used for adjusting the pixel value of the corresponding cheek clamp region by using each column of pixel adjusting value of each cheek clamp region. According to the cheek clamp developing weakening device based on pixel adjustment, only the pixel adjustment is carried out on the cheek clamp area, the definition of the non-cheek area is guaranteed, meanwhile, the pixel values of the cheek clamp and the neighborhood non-cheek clamp portion are considered, the row pixel adjustment is carried out according to the pixels in each row, and the visual effect of a panoramic image is improved.
As an optional implementation manner of the present invention, the second determining module includes: the second acquisition submodule is used for acquiring the expected value of each row of pixels in the cheek clamp area; the third acquisition submodule is used for acquiring the pixel mean value of each row in the cheek clamp area; and the second determining submodule is used for obtaining each column of pixel adjustment value of each cheek clamp region according to the pixel expected value of each column of the cheek clamp region and the pixel average value of each column.
As an optional embodiment of the present invention, the second obtaining sub-module includes: the fourth obtaining submodule is used for respectively obtaining a first pixel mean value of the preset column number of the non-cheek clamp area on the left side of the left boundary of each cheek clamp area; a fifth obtaining sub-module, configured to respectively obtain second pixel mean values of preset column numbers of non-cheek clamp regions on a right boundary of each cheek clamp region; a sixth obtaining submodule, configured to obtain a third pixel mean of each cheek clamp region except for a cheek clamp boundary portion; and the third determining submodule is used for determining the expected value of each column of pixels of each cheek clamp area according to the first pixel mean value, the second pixel mean value and the third pixel mean value.
As an optional embodiment of the present invention, the apparatus further comprises: the second acquisition module is used for acquiring the number of the detected fitting boundaries; and the judging module is used for executing the subsequent step of adjusting the pixel values of the cheek clamp area when the number of the fitting boundaries is the same as the preset number of the cheek clamp boundaries.
An embodiment of the present invention further provides an electronic device, as shown in fig. 5, the electronic device may include aprocessor 401 and amemory 402, where theprocessor 401 and thememory 402 may be connected through a bus or in another manner, and fig. 5 takes the connection through the bus as an example.
Thememory 402 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created by theprocessor 401, and the like. Further, thememory 402 may include high speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments,memory 402 may optionally include memory located remotely fromprocessor 401, which may be connected toprocessor 401 via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The one or more modules are stored in thememory 402 and when executed by theprocessor 401 perform the pixel-based adjusted cheek clip development weakening method as in the embodiment shown in fig. 1.
The details of the electronic device may be understood with reference to the corresponding related description and effects in the embodiment shown in fig. 1, and are not described herein again.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic Disk, an optical Disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a Flash Memory (Flash Memory), a Hard Disk (Hard Disk Drive, abbreviated as HDD), a Solid State Drive (SSD), or the like; the storage medium may also comprise a combination of memories of the kind described above.
Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations fall within the scope defined by the appended claims.
Claims (6)
1. A method of pixel-based adjustment of cheek clip development weakening, comprising:
acquiring a panoramic image to be weakened;
carrying out image binarization processing by using a target network to obtain a cheek clamp boundary part;
determining a fitting boundary corresponding to each cheek clamp boundary region in the cheek clamp boundary part and determining a boundary expression of each fitting boundary;
determining a pixel set of each cheek clamp region and a pixel set of a non-cheek clamp region part according to a boundary expression of the fitting boundary, wherein the pixel set comprises a position coordinate where each pixel is located and a pixel value;
determining each column of pixel adjustment values for each cheek clip region from the set of pixels for the cheek clip region and the set of pixels for the non-cheek clip region portion, comprising:
acquiring an expected value of each column of pixels in the cheek clamp area;
acquiring a pixel mean value of each column of the cheek clamp area;
obtaining each column of pixel adjustment value of each cheek clamp area according to the pixel expected value of each column of the cheek clamp area and the pixel mean value of each column;
acquiring an expected value of each column of pixels in the cheek clamp area, wherein the expected value comprises the following steps:
respectively obtaining a first pixel mean value of the preset column number of non-cheek clamp areas on the left side of the left boundary of each cheek clamp area;
respectively obtaining a second pixel mean value of the preset column number of non-cheek clamp areas on the right side of the right boundary of each cheek clamp area;
respectively acquiring a third pixel mean value of each cheek clamp region except the cheek clamp boundary part;
determining an expected value of each row of pixels in each cheek clamp area according to the first pixel mean value, the second pixel mean value and the third pixel mean value;
each column of pixel adjustment values for each of the cheek clip regions is determined by:
wherein left1 is the left half area of the left cheek clamp, y is the ordinate, f1 (y) is the left border of the left cheek clamp, a (f)1 (y) + j, y) represents left1 Middle coordinate (f)1 Pixel adjustment value at (y) + j, y), g (f)1 (y) + j, y) represents the coordinate (f)1 Pixel value at (y) + j, y), left1Estj Represents left1 Expected value of pixel in the j-th column, left1Meanj Represents left1 The mean value of the pixels of the j-th row, T is a threshold value;
wherein left2 is the right half area of the left cheek clamp, y is the ordinate, f2 (y) is the right border of the left cheek clip,
represents left2 Middle coordinate
Pixel adjustment of (2)Value of,
representing coordinates
Pixel value of (2 Est), left2j Represents left2 Expected pixel value of the j-th column, left2Meanj Represents left2 Mean value of the pixels of the j-th column, wL Represents the width of the left cheek clip, T being the threshold;
wherein right1 is the left half area of the right cheek clamp, y is the ordinate, f3 (y) is the left border of the right cheek clip, a (f)3 (y) + k, y) representing right1 Middle coordinate (f)3 Pixel adjustment value at (y) + k, y), g (f)3 (y) + k, y) represents the coordinate (f)3 The pixel value at (y) + k, y), right1Estk Representing right1 Expected value of pixel in the k-th column, right1Meank Representing right1 The average pixel mean value of the rows of the kth row is T, and T is a threshold value;
wherein right2 is the right half area of the right cheek clamp, y is the ordinate, f4 (y) is the right boundary of the right cheek clip,
representing right2 Middle coordinate
The pixel adjustment value of (a) is,
representing coordinates
The pixel value of (1), right2Estk Representing right2 Expected value of pixel in the k-th column, right2Meank Representing right2 Column-average pixel mean, w, of the k-th columnR Represents the width of the left cheek clip, T being the threshold;
and adjusting the pixel value of the corresponding cheek clamp region by using each column of pixel adjustment values of each cheek clamp region.
2. The method according to claim 1, wherein after the image binarization processing by using the target network obtains the cheek clip image portion, before the determining a fitting boundary corresponding to each cheek clip boundary area in the cheek clip boundary portion and determining a boundary expression of each fitting boundary, the method further comprises:
acquiring the number of detected fitting boundaries;
and when the number of the fitting boundaries is the same as the preset number of the cheek clamp boundaries, executing a subsequent step of adjusting the pixel values of the cheek clamp region.
3. A pixel adjustment based cheek clip development weakening apparatus, comprising:
the first acquisition module is used for acquiring a panoramic image to be weakened;
the processing module is used for carrying out image binarization processing by using a target network to obtain a cheek clamp boundary part;
the first determining module is used for determining a fitting boundary corresponding to each cheek clamp boundary area in the cheek clamp boundary part and determining a boundary expression of each fitting boundary;
a second determining module, configured to determine, according to a boundary expression of the fitting boundary, a pixel set of each cheek clamp region and a pixel set of a non-cheek clamp region portion, where the pixel set includes a position coordinate and a pixel value of each pixel;
a third determining module, configured to determine each column of pixel adjustment values for each cheek clamp region according to the set of pixels of the cheek clamp region and the set of pixels of the non-cheek clamp region portion, including:
the second acquisition submodule is used for acquiring the expected value of each row of pixels in the cheek clamp area;
the third acquisition submodule is used for acquiring the pixel mean value of each row of the cheek clamp area;
the second determining submodule is used for obtaining each row of pixel adjustment values of each cheek clamp region according to the pixel expected value of each row of the cheek clamp region and the pixel mean value of each row;
the second obtaining sub-module includes:
the fourth acquiring submodule is used for respectively acquiring a first pixel mean value of the preset column number of the non-cheek clamp area on the left side of the left boundary of each cheek clamp area;
the fifth obtaining submodule is used for respectively obtaining a second pixel mean value of the preset column number of the non-cheek clamp area on the right side of the right boundary of each cheek clamp area;
a sixth obtaining submodule, configured to obtain a third pixel mean of each cheek clamp region except for a cheek clamp boundary portion;
the third determining submodule is used for determining the expected value of each column of pixels of each cheek clamp area according to the first pixel average value, the second pixel average value and the third pixel average value;
each column of pixel adjustment values for each of the cheek clip regions is determined by:
wherein left1 is the left half area of the left cheek clamp, y is the ordinate, f1 (y) is the left boundary of the left cheek clip, a (f)1 (y) + j, y) denotes left1 Middle coordinate (f)1 Pixel adjustment value at (y) + j, y), g (f)1 (y) + j, y) represents the coordinate (f)1 Pixel value at (y) + j, y), left1Estj Represents left1 Expected value of pixel in the j-th column, left1Meanj Represents left1 The mean value of the pixels of the j-th row, T is a threshold value;
wherein left2 is the right half area of the left cheek clamp, y is the ordinate, f2 (y) is the right boundary of the left cheek clip,
represents left2 Middle coordinate
The pixel adjustment value of (a) is,
representing coordinates
At a pixel value of left2Estj Represents left2 Expected pixel value of the j-th column, left2Meanj Represents left2 Mean value of the pixels of the j-th column, wL Represents the width of the left cheek clip, T being the threshold;
wherein right1 is the left half area of the right cheek clamp, y is the ordinate, f3 (y) is the left border of the right cheek clip, a (f)3 (y) + k, y) representing right1 Middle coordinate (f)3 Pixel adjustment value at (y) + k, y), g (f)3 (y) + k, y) represents the coordinate (f)3 The pixel value at (y) + k, y), right1Estk Representing right1 Middle k columnPixel expected value of, right1Meank Representing right1 The average pixel mean value of the rows of the kth row is T, and T is a threshold value;
wherein right2 is the right half area of the right cheek clamp, y is the ordinate, f4 (y) is the right boundary of the right cheek clip,
representing right2 Middle coordinate
The pixel adjustment value of (a) is,
representing coordinates
The pixel value of (1), right2Estk Representing right2 Expected value of pixel in the k-th column, right2Meank Representing right2 Column-average pixel mean, w, of the k-th columnR Represents the width of the left cheek clip, T being the threshold;
and the adjusting module is used for adjusting the pixel value of the corresponding cheek clamp region by using each column of pixel adjusting value of each cheek clamp region.
4. The apparatus of claim 3, further comprising:
the second acquisition module is used for acquiring the number of the detected fitting boundaries;
and the judging module is used for executing the subsequent step of adjusting the pixel values of the cheek clamp area when the number of the fitting boundaries is the same as the preset number of the cheek clamp boundaries.
5. An electronic device, comprising: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to cause the at least one processor to perform the steps of the pixel based adjusted cheek clip development weakening method as defined in any one of claims 1-2.
6. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the pixel-based adjusted cheek clip development weakening method according to any one of the claims 1-2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111608572.4ACN114298934B (en) | 2021-12-24 | 2021-12-24 | Cheek clamp developing weakening method and device based on pixel adjustment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111608572.4ACN114298934B (en) | 2021-12-24 | 2021-12-24 | Cheek clamp developing weakening method and device based on pixel adjustment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114298934A CN114298934A (en) | 2022-04-08 |
| CN114298934Btrue CN114298934B (en) | 2022-12-09 |
Family
ID=80970182
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111608572.4AActiveCN114298934B (en) | 2021-12-24 | 2021-12-24 | Cheek clamp developing weakening method and device based on pixel adjustment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114298934B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013055707A1 (en)* | 2011-10-09 | 2013-04-18 | Clear Guide Medical, Llc | Interventional in-situ image-guidance by fusing ultrasound video |
| CN105741239A (en)* | 2014-12-11 | 2016-07-06 | 合肥美亚光电技术股份有限公司 | Method and apparatus for generating tooth panorama image, and panorama machine for shooting teeth |
| CN109145866A (en)* | 2018-09-07 | 2019-01-04 | 北京相貌空间科技有限公司 | Determine the method and device of side face tilt angle |
| CN111476791A (en)* | 2019-05-21 | 2020-07-31 | 北京昆仑医云科技有限公司 | Image processing method, image processing apparatus, and non-transitory computer-readable medium |
| CN112105312A (en)* | 2018-07-03 | 2020-12-18 | 柯惠Lp公司 | Systems, methods, and computer-readable media for detecting image degradation during a surgical procedure |
| CN112634235A (en)* | 2020-12-24 | 2021-04-09 | 深圳艾灵网络有限公司 | Product image boundary detection method and electronic equipment |
| CN113100805A (en)* | 2021-05-10 | 2021-07-13 | 蒋蔚 | A method to reduce the influence of the movement of the scanned object and improve the imaging quality of cone beam CT |
| CN113160248A (en)* | 2021-04-22 | 2021-07-23 | 浙江明峰智能医疗科技有限公司 | Image processing method, device and equipment and readable storage medium |
| CN113509198A (en)* | 2021-08-24 | 2021-10-19 | 深圳市菲森科技有限公司 | X-ray oral cavity panoramic scanning device and image reconstruction method |
| CN113687434A (en)* | 2021-09-29 | 2021-11-23 | 北京航星机器制造有限公司 | Object scanning position determining method and device for security check CT image reconstruction |
| CN113749692A (en)* | 2021-09-03 | 2021-12-07 | 中国科学院长春光学精密机械与物理研究所 | Pharyngeal swab collection method based on image recognition and positioning |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7801344B2 (en)* | 2006-12-01 | 2010-09-21 | Carestream Health, Inc. | Edge boundary definition for radiographic detector |
| BR112014026073A2 (en)* | 2012-04-23 | 2017-06-27 | Koninklijke Philips Nv | medical imaging system and image processing method |
| CN102831606B (en)* | 2012-08-01 | 2014-10-22 | 中国科学院自动化研究所 | Method for acquiring vocal organ profile in medical image |
| CN107920869B (en)* | 2016-08-09 | 2020-09-15 | 堤欧股份有限公司 | Manufacturing method of digital bracket for orthodontics using digital database |
| CN113375555A (en)* | 2018-07-02 | 2021-09-10 | 广西电网有限责任公司北海供电局 | Power line clamp measuring method and system based on mobile phone image |
| CN108986023A (en)* | 2018-08-03 | 2018-12-11 | 北京字节跳动网络技术有限公司 | Method and apparatus for handling image |
| CN109584147B (en)* | 2018-11-27 | 2023-06-30 | 东莞信大融合创新研究院 | Dental panorama generation method based on cone beam CT |
| CN112957005A (en)* | 2021-02-01 | 2021-06-15 | 山西省眼科医院(山西省红十字防盲流动眼科医院、山西省眼科研究所) | Automatic identification and laser photocoagulation region recommendation algorithm for fundus contrast image non-perfusion region |
- 2021
- 2021-12-24CNCN202111608572.4Apatent/CN114298934B/enactiveActive
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013055707A1 (en)* | 2011-10-09 | 2013-04-18 | Clear Guide Medical, Llc | Interventional in-situ image-guidance by fusing ultrasound video |
| CN105741239A (en)* | 2014-12-11 | 2016-07-06 | 合肥美亚光电技术股份有限公司 | Method and apparatus for generating tooth panorama image, and panorama machine for shooting teeth |
| CN112105312A (en)* | 2018-07-03 | 2020-12-18 | 柯惠Lp公司 | Systems, methods, and computer-readable media for detecting image degradation during a surgical procedure |
| CN109145866A (en)* | 2018-09-07 | 2019-01-04 | 北京相貌空间科技有限公司 | Determine the method and device of side face tilt angle |
| CN111476791A (en)* | 2019-05-21 | 2020-07-31 | 北京昆仑医云科技有限公司 | Image processing method, image processing apparatus, and non-transitory computer-readable medium |
| CN112634235A (en)* | 2020-12-24 | 2021-04-09 | 深圳艾灵网络有限公司 | Product image boundary detection method and electronic equipment |
| CN113160248A (en)* | 2021-04-22 | 2021-07-23 | 浙江明峰智能医疗科技有限公司 | Image processing method, device and equipment and readable storage medium |
| CN113100805A (en)* | 2021-05-10 | 2021-07-13 | 蒋蔚 | A method to reduce the influence of the movement of the scanned object and improve the imaging quality of cone beam CT |
| CN113509198A (en)* | 2021-08-24 | 2021-10-19 | 深圳市菲森科技有限公司 | X-ray oral cavity panoramic scanning device and image reconstruction method |
| CN113749692A (en)* | 2021-09-03 | 2021-12-07 | 中国科学院长春光学精密机械与物理研究所 | Pharyngeal swab collection method based on image recognition and positioning |
| CN113687434A (en)* | 2021-09-29 | 2021-11-23 | 北京航星机器制造有限公司 | Object scanning position determining method and device for security check CT image reconstruction |
Non-Patent Citations (3)
| Title |
|---|
| "CT图像中牙齿的半自动分割及应用";吴琳;《中国硕士学位论文全文数据库 （医药卫生科技）》;20160715(第（2016）07期);E076-4* |
| "Image-guided removal of deeply impacted mandibular third molar using a navigation system";Atsushi Takeda 等;《 Journal of Oral and Maxillofacial Surgery, Medicine, and Pathology》;20200101;1-9* |
| "基于深度神经网络的医疗图像分割算法研究";甄辉;《中国硕士学位论文全文数据库 （医药卫生科技）》;20200715(第（2020）07期);E080-20* |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114298934A (en) | 2022-04-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP5315157B2 (en) | Information processing apparatus, line noise reduction processing method, and program | |
| CN103026379B (en) | Method for Estimating Image Noise Level | |
| Ikhsan et al. | An analysis of x-ray image enhancement methods for vertebral bone segmentation | |
| WO2022057897A1 (en) | Referenceless image evaluation method for capsule endoscope, electronic device, and medium | |
| WO2019037676A1 (en) | Image processing method and device | |
| CN105894574A (en) | Binocular three-dimensional reconstruction method | |
| JP2014045488A (en) | Method for substantially removing dot noise and image processing system | |
| CN109509186A (en) | Cerebral arterial thrombosis lesion detection method and device based on brain CT image | |
| WO2007142682A2 (en) | Method for detecting streaks in digital images | |
| JP4938427B2 (en) | Cerebral hemorrhage volume calculator | |
| DE112021001373B4 (en) | REAL-TIME DETECTION AND CORRECTION OF SHADOWS IN HYPERSPECTRAL RETINAL IMAGES | |
| CN117036310A (en) | DICOM image peripheral outline identification and extraction method | |
| CN114092405A (en) | Retina layer automatic segmentation method for macular edema OCT image | |
| CN114299081B (en) | Maxillary sinus CBCT image segmentation method, maxillary sinus CBCT image segmentation device, maxillary sinus CBCT storage medium and electronic equipment | |
| CN115100217B (en) | Method, device, equipment and medium for extracting brain area from head and neck CT images | |
| CN116012322A (en) | Camera dirt detection method, device, equipment and medium | |
| CN118887136B (en) | Method, device and computer equipment for removing smoke from endoscope images | |
| CN115294166A (en) | Image edge extraction method and device | |
| CN114298934B (en) | Cheek clamp developing weakening method and device based on pixel adjustment | |
| JP2000126150A (en) | Setting of interest region, image processing device, and image processing device for medical purpose | |
| CN118071686B (en) | Medical equipment operation status monitoring method and system based on artificial intelligence | |
| JP2023522818A (en) | Image optimization method, related model training method, apparatus, apparatus and program | |
| US20150139522A1 (en) | Statistical property preserved bad line correction | |
| CN116681715B (en) | Blood vessel segmentation method, device, equipment and storage medium based on pixel value change | |
| WO2023138273A1 (en) | Image enhancement method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |