Dental arch line extraction method based on morphology and binary image thinning and related device

Abstract

The application discloses a kind of based on morphology and binary image thinning dental arch line extraction method and related device, first obtain three-dimensional dental grid model, the projection of the center point of the triangular mesh that each dental crown contains in dental crown area is made in occlusal surface direction;Ellipse structural element is selected to do morphological filtering inflation operation to two-dimensional projection image;Inflation projection image is handled with gray scale, and binary image is obtained by handling with gray scale projection image;Binary image is operated, and each connected component of binary image is thinned to single-pixel width skeleton;The skeleton line obtained is smoothed using high-order polynomial spline curve fitting method, and after scale reduction, the dental arch line required to be extracted is obtained.The present application can accurately extract dental arch line from three-dimensional model automatically through morphological inflation operation and binary image thinning, without human intervention, improve the precision and efficiency of dental arch line extraction.

Description

Technical Field

[0001] This invention belongs to the field of three-dimensional medical image processing technology, and relates to a method and related apparatus for extracting dental arch lines based on morphology and binary image refinement. Background Technology

[0002] With the development of computer-aided design and manufacturing, and 3D imaging technologies such as laser technology, digital technology has begun to be widely applied in medical fields, including oral disease diagnosis and treatment, orthodontics, and cosmetic dentistry. In the process of using digital technology to reconstruct virtual models of the jaw and jaw, and to customize orthodontic appliances and treatment tools, the dental arch line, as a key parameter defining the position of the upper and lower jaw teeth, provides a basis for diagnostic analysis, planning of dental implants, and orthodontic treatment. By delineating the dental arch line, the position and alignment of teeth can be more accurately confirmed, which helps to formulate more precise treatment plans. The accuracy of extracting the dental arch line directly affects the quality of the design and manufacturing of archwires or invisible orthodontic brackets; therefore, accurate extraction of the dental arch line is of great significance.

[0003] Traditional methods for extracting dental arch lines typically involve manually selecting arch feature points such as molar cusps, canine cusps, and incisor midpoints, then manually drawing the arch curve using geometric methods and calculating its length; or fitting the arch curve by connecting feature points using a specific curve function, and finally calculating the arch length based on the curve function's equation. These methods have the following significant drawbacks: ① Firstly, the basic arch feature points are greatly affected by malformed teeth. For dental models with many malformed teeth, the accuracy of arch line extraction is relatively low, requiring high model quality. ② Secondly, while these methods are simple and intuitive, they demand a certain level of operator skill and experience, resulting in high manual intervention and low extraction efficiency. In summary, the above methods cannot simultaneously achieve both accuracy and efficiency in arch line extraction. Summary of the Invention

[0004] The purpose of this invention is to solve the problems in the prior art and provide a method and related device for extracting dental arch lines based on morphology and binary image thinning. By extracting the skeleton lines of the three-dimensional dental model projection through morphological dilation operation and binary image thinning, the dental arch lines can be extracted accurately and effectively, avoiding the complex operation brought about by traditional extraction methods. It has good robustness for the extraction of highly personalized dental arch lines.

[0005] To achieve the above objectives, the present invention employs the following technical solution:

[0006] In a first aspect, the present invention provides a method for extracting dental arch lines based on morphology and binary image thinning, comprising the following steps:

[0007] Based on the three-dimensional dental mesh model data, the center point of the triangular mesh is projected onto the occlusal surface direction to obtain a two-dimensional projection point set, which constitutes a two-dimensional projection map.

[0008] A morphological dilation operation is performed on a two-dimensional projection image to obtain a dilated projection image;

[0009] The dilatation projection image is binarized to obtain a binarized projection image;

[0010] A thinning operation is performed on the binarized projected image to obtain a two-dimensional skeleton line;

[0011] The two-dimensional skeleton lines were smoothed by using a high-order polynomial spline curve fitting method to obtain the dental arch lines.

[0012] Secondly, the present invention provides a dental arch line extraction system based on morphology and binary image refinement, comprising:

[0013] The two-dimensional projection point set calculation module is used to project the center point of the triangular mesh in the occlusal direction based on the three-dimensional dental mesh model data to obtain a two-dimensional projection point set, which constitutes a two-dimensional projection map.

[0014] The dilation module is used to perform morphological dilation operations on two-dimensional projected images to obtain dilated projected images.

[0015] The binarization processing module is used to binarize the dilatation projection image to obtain a binarized projection image;

[0016] The thinning operation module is used to perform thinning operations on the binary projection image to obtain two-dimensional skeleton lines;

[0017] The smoothing module is used to smooth the two-dimensional skeleton lines using a high-order polynomial spline curve fitting method to obtain the dental arch lines.

[0018] Thirdly, the present invention provides an electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method described above.

[0019] Fourthly, the present invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the method described above.

[0020] Compared with the prior art, the present invention has the following beneficial effects:

[0021] This invention utilizes the two-dimensional projection of a three-dimensional dental mesh model as the data basis for extracting the arch line. At the same time, it eliminates the interference of malformed teeth through morphological dilation operations, thereby improving the anti-interference ability of the arch line extraction method and reducing the requirements for model quality. The binary image thinning method extracts the arch line, which can accurately express the topological features of the arch line in the dental model and enhance the accuracy of the method in extracting the arch line. Attached Figure Description

[0022] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a flowchart of the method of the present invention.

[0024] Figure 2 This is a schematic diagram of the system of the present invention.

[0025] Figure 3 This is a flowchart of the dental arch line extraction method based on morphology and binary image thinning according to an embodiment of the present invention.

[0026] Figure 4 This is a two-dimensional projection of the mandibular mesh model according to an embodiment of the present invention.

[0027] Figure 5 This is a morphological dilation calculation image of the mandibular model projection in an embodiment of the present invention.

[0028] Figure 6 This refers to the 8-neighbor connected region of a pixel in an embodiment of the present invention.

[0029] Figure 7 The image shows the refined skeleton lines of the mandibular model projection in this embodiment of the invention.

[0030] Figure 8 This is a schematic diagram comparing the projection of the mandibular model with the extracted skeleton lines and dental arch lines in an embodiment of the present invention. Detailed Implementation

[0031] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0032] Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0033] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0034] In the description of the embodiments of the present invention, it should be noted that if terms such as "upper," "lower," "horizontal," or "inner" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, or the orientation or positional relationship commonly used when the product of the invention is in use, they are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention. Furthermore, terms such as "first" and "second" are only used to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0035] Furthermore, the use of the term "horizontal" does not imply that the component must be absolutely horizontal, but rather that it can be slightly tilted. For example, "horizontal" simply means that its direction is more horizontal than "vertical," and does not mean that the structure must be completely horizontal, but can be slightly tilted.

[0036] In the description of the embodiments of the present invention, it should also be noted that, unless otherwise explicitly specified and limited, the terms "set," "install," "connect," and "link" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in the present invention according to the specific circumstances.

[0037] The present invention will now be described in further detail with reference to the accompanying drawings:

[0038] See Figure 3 This invention discloses a method for extracting dental arch lines based on morphology and binary image thinning, comprising the following steps:

[0039] S1 projects the center point of the triangular mesh onto the occlusal plane direction based on the three-dimensional dental mesh model data, and obtains a two-dimensional projection point set to form a two-dimensional projection map.

[0040] Specifically: Project the center point of the triangular mesh in each crown region of the 3D dental mesh model data onto the occlusal plane to obtain a 2D projection point set.

[0041] Where i is the grid number, m is the number of crowns, and N is the number of teeth. m The number of grids contained in each crown.

[0042] S2 performs morphological dilation on the two-dimensional projection image to obtain a dilated projection image;

[0043] Specifically: Take the maximum value within an elliptical neighborhood of each position and use it as the output value for that position.

[0044] [δ g (X g )](x,y)=max(X g )

[0045] Among them, [δ g (X g )](x) represents the process of the structuring element g performing a dilation operation on the sub-elements x within the set X; after the iterative dilation operation, the dilated projection image is obtained.

[0046] S3 performs binarization processing on the dilatation projection image to obtain a binarized projection image;

[0047] Specifically:

[0048] S3-1 performs grayscale processing on the image, converting each pixel from RGB mode to grayscale mode to obtain a grayscale projection image:

[0049]

[0050] in, The R value of a pixel. The G value of a pixel. N is the B value of a pixel. p This represents the number of pixels in the dilated projection image.

[0051] S3-2 performs binarization on the obtained grayscale projection image, setting it to 127. Pixels with grayscale values ​​greater than the pixel grayscale threshold will be set to 1, otherwise to 0; thus obtaining the binarized projection image I, where each pixel I(i,j) is 0 or 1.

[0052] S4 performs a thinning operation on the binary projection image to obtain a two-dimensional skeleton line;

[0053] Specifically: each connected component of the binarized projected image is thinned to a skeleton of one pixel width, all contour points other than the skeleton points are removed, and then a binary matrix M containing the thinned image is output.

[0054] The thinning algorithm employs two sub-loops to maintain the connectivity of the skeleton; in the first sub-loop, the condition for deleting target pixel P1 is:

[0055] Condition (1): 2 ≤ B(P1) ≤ 6

[0056] Condition (2): A(P1) = 1

[0057] Condition (3): P2×P4×P6=0

[0058] Condition (4): P4×P6×P8=0

[0059] Where B(P1) is the number of non-zero adjacent pixels of P1, and A(P1) is the number of 01 patterns in the ordered set {P2,P3,P4,...,P8,P9}, where the ordered set is the 8 adjacent pixels of P1.

[0060] In the second sub-loop, the condition for deleting target pixel P1 is:

[0061] Condition (1): 2 ≤ B(P1) ≤ 6

[0062] Condition (2): A(P1) = 1

[0063] Condition (3): P2×P4×P8=0

[0064] Condition (4): P2×P6×P8=0

[0065] If the condition is met, then the target pixel P1 is a deletable pixel; traverse all pixels and refine the skeleton line of the binary image after thinning:

[0066]

[0067] Where, N s This represents the number of skeleton points.

[0068] S5 uses a high-order polynomial spline curve fitting method to smooth the two-dimensional skeleton lines, thus obtaining the dental arch lines.

[0069] Specifically:

[0070] S5-1 uses a high-order polynomial spline curve fitting method to smooth the skeleton line of the binary image, obtaining the smoothed curve U, whose expression is:

[0071] U(x,w)=w0+w1x+w2x 2 +…+wβ x β

[0072] Where β is the order of the polynomial, w β These are the coefficients of the polynomial;

[0073] S5-2 performs a scaling reduction on the smoothed curve U. The maximum lengths of the curve and the two-dimensional projection in the x and y directions are taken respectively. The average of the x and y ratios is the scaling reduction ratio μ. The scaled-down curve is the desired dental archline. The dental archline length l is calculated by accumulating the point distances.

[0074]

[0075] Where, N s For the number of skeleton points,

[0076] like Figure 2 As shown, this embodiment of the invention provides a dental arch line extraction system based on morphology and binary image thinning, comprising:

[0077] The two-dimensional projection point set calculation module is used to project the center point of the triangular mesh in the occlusal direction based on the three-dimensional dental mesh model data to obtain a two-dimensional projection point set, which constitutes a two-dimensional projection map.

[0078] The dilation module is used to perform morphological dilation operations on two-dimensional projected images to obtain dilated projected images.

[0079] The binarization processing module is used to binarize the dilatation projection image to obtain a binarized projection image;

[0080] The thinning operation module is used to perform thinning operations on the binary projection image to obtain two-dimensional skeleton lines;

[0081] The smoothing module is used to smooth the two-dimensional skeleton lines using a high-order polynomial spline curve fitting method to obtain the dental arch lines.

[0082] Example:

[0083] like Figure 3 As shown, this embodiment provides a method for extracting dental arch lines based on morphology and binary image thinning, comprising the following steps:

[0084] Step 1: Obtain 3D dental mesh model data, including the crown and gingival regions. Project the center point of the triangular mesh contained in each crown onto the occlusal plane to obtain a 2D projection point set. like Figure 4 The image shown is a two-dimensional projection of a mandibular model.

[0085] Step 2: Perform morphological dilation on the two-dimensional projection of the dental model to expand the target area and fill cracks or holes caused by dental deformities or missing teeth in the image. In the dilation operation, different shapes and sizes of structuring elements have different effects. To eliminate sharp edges, an elliptical structuring element g is selected, and its size is set to (30, 30) based on experience. The dilation operation takes the maximum value within the neighborhood of an elliptical structure at each location and uses it as the output value for that location. The formula is expressed as follows:

[0086] [δ g (X g )](x,y)=max(X g )

[0087] Where [δ g (X g )](x) represents the process of the expansion operation of the structuring element g on the sub-element x in the set X.

[0088] The dilated projection image is obtained after iterative dilation operations.

[0089] Step 3: Binarize the obtained dilated projection image. First, perform grayscale processing on the image, converting each pixel from RGB mode to grayscale mode to obtain a grayscale projection image:

[0090]

[0091] in, The R value of a pixel. The G value of a pixel. N is the B value of a pixel. p This represents the number of pixels in the dilated projection image.

[0092] The resulting grayscale projection image is binarized by setting the pixel grayscale threshold to 127. Pixels with a grayscale value greater than 127 are set to 1, and others are set to 0. This yields a binarized projection image I, where each pixel I(i,j) is either 0 or 1.

[0093] Step 4: Perform a thinning operation on the binarized projection image, thinning each connected component of the binarized projection image to a skeleton of one pixel width, removing all contour points other than the skeleton points, and then outputting a binary matrix M containing the thinned image.

[0094] The thinning algorithm employs two sub-loops to maintain the connectivity of the skeleton. In the first sub-loop: the condition for deleting target pixel P1 is:

[0095]

[0096] Where B(P1) is the number of non-zero adjacent pixels of P1, and A(P1) is the number of 01 patterns in the ordered set {P2,P3,P4,…,P8,P9}, where the ordered set consists of the 8 adjacent pixels of P1, as shown below. Figure 6 As shown.

[0097] In the second sub-loop, conditions (3) and (4) above are changed to:

[0098]

[0099] If the condition is met, then the target pixel P1 is a deletable pixel. Traverse all pixels and refine the skeleton lines of the resulting binary image. N s For the number of skeleton points, such as Figure 7 As shown.

[0100] Step 5: The skeleton line obtained after the refinement calculation is quite curved, making it difficult to calculate its length through curve fitting. Therefore, the cumulative point distance calculation method is used. The point distance between each point and its two adjacent points is calculated separately, the adjacent point distances of all points are accumulated, and the result is scaled down proportionally to obtain an approximate skeleton line length.

[0101] Specifically: After the thinning operation, a high-order polynomial spline curve fitting method is used to smooth the skeleton line of the binary image, obtaining the smoothed curve U, whose expression is:

[0102] U(x,w)=w0+w1x+w2x 2 +…+w β x β

[0103] Where β is the order of the polynomial, here we take β = 7 based on experience, w0…w β These are the coefficients of the polynomial.

[0104] The smoothed curve U is scaled down proportionally. The maximum lengths of the curve and its two-dimensional projection in the x and y directions are taken respectively. The average of these ratios in the x and y directions is the scaling factor μ. The scaled-down curve is the desired dental archline. The archline length l is calculated by accumulating the distances between points, as shown in the following expression:

[0105]

[0106] like Figure 8 As shown, the dental arch line extracted by this invention accurately represents the topological structure of the dental model.

[0107] A computer device is provided according to an embodiment of the present invention. This computer device includes a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps in the various method embodiments described above. Alternatively, when the processor executes the computer program, it implements the functions of each module / unit in the various device embodiments described above.

[0108] The computer program can be divided into one or more modules / units, which are stored in the memory and executed by the processor to complete the present invention.

[0109] The computer device may be a desktop computer, laptop, handheld computer, or cloud server, etc. The computer device may include, but is not limited to, a processor and memory.

[0110] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0111] The memory can be used to store the computer program and / or module, and the processor implements various functions of the computer device by running or executing the computer program and / or module stored in the memory, and by calling the data stored in the memory.

[0112] If the modules / units integrated into the computer device are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electrical carrier signals and telecommunication signals.

[0113] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for extracting dental arch lines based on morphology and binary image thinning, characterized in that, Includes the following steps: Based on the 3D dental mesh model data, the center points of the triangular mesh are projected onto the occlusal plane to obtain a 2D projection point set, which constitutes a 2D projection map; the specific method is as follows: Projecting the center point of the triangular mesh in each crown region of the 3D dental mesh model data onto the occlusal plane direction yields a 2D projection point set. ; in, For grid numbering, Number of crowns The number of grids contained in each crown; A dilated projection image is obtained by performing morphological dilation on a two-dimensional projection image; the specific method is as follows: Take the maximum value within an elliptical neighborhood of each location and use it as the output value for that location: in, Represents elliptical structural elements For sets child elements The process of dilation operation; after iterative dilation operation, the dilated projected image is obtained; The dilatation projection image is binarized to obtain a binary projection image; the specific method is as follows: To process an image into grayscale, convert each pixel from RGB mode to grayscale mode to obtain a grayscale projection image. in, For the first The R value of each pixel For the first The G value of each pixel For the first The B value of each pixel, The number of pixels in the dilated projection image; The resulting grayscale projection image is binarized. Pixels with grayscale values ​​greater than a pixel grayscale threshold are set to 1, and others are set to 0; this yields the binarized projection image. Each pixel It can be 0 or 1; A thinning operation is performed on the binarized projected image to obtain a two-dimensional skeleton line; The two-dimensional skeleton lines were smoothed by fitting high-order polynomial spline curves to obtain the dental arch lines; The skeleton lines of the binary image are smoothed by fitting high-order polynomial spline curves to obtain the smoothed curves. Its expression is: in, It is the order of the polynomial. These are the coefficients of the polynomial; For the smoothed curve After scaling down, take the curve and the two-dimensional projection respectively. Find the maximum length in the direction. The reduction ratio is obtained by taking the average of the directional proportions. The required arch line is obtained after scaling down; the arch line length is calculated by accumulating the distance between points. : in, This represents the number of skeleton points.

2. The method for extracting dental arch lines based on morphology and binary image thinning according to claim 1, characterized in that, The grayscale threshold for the pixel is 127.

3. The method for extracting dental arch lines based on morphology and binary image thinning according to claim 1, characterized in that, The process of thinning the binarized projected image to obtain a two-dimensional skeleton line includes: Each connected component of the binarized projected image is thinned to a skeleton of one pixel width. All contour points other than the skeleton points are removed, and a binary matrix containing the thinned image is then output. ; The thinning algorithm employs two sub-loops to maintain the connectivity of the skeleton; in the first sub-loop, the target pixel... The conditions for deletion are: Condition (1): Condition (2): Condition (3): Condition (4): in, yes The number of non-zero adjacent pixels, It is in an ordered set The number of 01 patterns in the ordered set is 8 adjacent pixels; In the second sub-loop, the target pixel The conditions for deletion are: Condition (1): Condition (2): Condition (3): Condition (4): If the condition is met, then the target pixel For deletable pixels; iterate through all pixels and refine the skeleton lines of the resulting binary image: in, This represents the number of skeleton points.

4. A dental arch line extraction system based on morphology and binary image thinning for implementing the method of claim 1, characterized in that, include: The two-dimensional projection point set calculation module is used to project the center point of the triangular mesh in the occlusal direction based on the three-dimensional dental mesh model data to obtain a two-dimensional projection point set, which constitutes a two-dimensional projection map. The dilation module is used to perform morphological dilation operations on two-dimensional projected images to obtain dilated projected images. The binarization processing module is used to binarize the dilatation projection image to obtain a binarized projection image; The thinning operation module is used to perform thinning operations on the binary projection image to obtain two-dimensional skeleton lines; The smoothing module is used to smooth the two-dimensional skeleton lines using a high-order polynomial spline curve fitting method to obtain the dental arch lines.

5. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1-3.

6. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1-3.

Images