Method for automating alignment of scan data and computer-readable recording medium in which program for executing same in computer is recorded

Abstract

The method for automating alignment of scan data comprises the steps of: determining a face vector indicating a direction in which a patient's face is located; and determining a reference surface and a facial side vector on the basis of the face vector.

Description

A computer-readable recording medium having recorded thereon a method for automating alignment of scan data and a program for executing the method on a computer

[0001] The present invention relates to an automated method for aligning scan data and a computer-readable recording medium having recorded thereon a program for executing the same on a computer, and more particularly, to an automated method for aligning scan data, which can automatically perform alignment of scan data and thereby reduce time and effort for matching three-dimensional volume data with the scan data, and a computer-readable recording medium having recorded thereon a program for executing the same on a computer.

[0002] Alignment refers to the process of adjusting or accurately aligning multiple data sets so they are consistent with each other. This alignment provides users with a wealth of information. It is used in autonomous vehicles, search engines, and artificial intelligence applications.

[0003] In particular, the above alignment can be important in dentistry. In dentistry, 3D patient medical image data, such as CT data, and 3D digital impression model scan data, such as facial scan data, are used for diagnosis, analysis, and prosthesis production. However, since the 3D patient medical image data and the 3D digital impression model scan data have different coordinate systems, a process for aligning the 3D patient medical image data and the 3D digital impression model scan data is necessary.

[0004] The above alignment includes initial alignment and fine alignment. After the initial alignment is performed, the fine alignment may be performed. The initial alignment refers to a task of roughly adjusting the data, and the fine alignment refers to a task of finely adjusting the data. Here, the accuracy of the fine alignment may be determined based on the accuracy of the initial alignment. Therefore, the accuracy of the initial alignment may be important. In particular, the process of aligning the 3D digital impression model scan data may be important.

[0005] The purpose of the present invention is to provide an automated method for aligning scan data, which can reduce the time and effort required for aligning three-dimensional volume data and scan data.

[0006] Another object of the present invention is to provide a computer-readable recording medium having recorded thereon a program for executing the above-described automated method for aligning scan data on a computer.

[0007] The automated alignment method of scan data according to embodiments for realizing the above-described object of the present invention includes a step of determining a face vector indicating a direction in which a patient's face is located, and a step of determining a reference plane and a face side vector based on the face vector.

[0008] In one embodiment, the automated alignment method of the scan data further includes a step of determining a uniform point and a feature point, and the reference plane and the face side vector can be determined based on the face vector, the uniform point, and the feature point.

[0009] In one embodiment, the face vector may be determined based on a normal vector of a mesh included in the scan data.

[0010] In one embodiment, the face vector may be an average vector of the normal vectors of the mesh.

[0011] In one embodiment, the face vector is x face When the normal vector of the above mesh is Mi and argmin(f(x)) is a minimum function that determines x such that the function f(x) has a minimum value, the face vector can be obtained using [Mathematical Formula 1].

[0012] [Mathematical Formula 1]

[0013]

[0014] In one embodiment, the uniform point can be determined to be spatially uniform from the image of the patient included in the scan data.

[0015] In one embodiment, the feature point can be determined based on the curvature of the mesh included in the scan data.

[0016] In one embodiment, the curvature of the mesh can be determined based on a normal vector of the mesh.

[0017] In one embodiment, the feature points may be determined to be spatially non-uniform from the image of the patient included in the scan data.

[0018] In one embodiment, the step of determining the face side vector may include the steps of determining a reference point, the step of moving the uniform point and the feature point in parallel based on the reference point, and the step of determining the reference plane and the face side vector based on the face vector, the moved uniform point in parallel, and the moved feature point in parallel.

[0019] In one embodiment, the reference point may be the center point of the uniform point.

[0020] In one embodiment, the uniform point and the feature point can be moved parallel to the difference between the reference point and the origin.

[0021] In one embodiment, the face side vector may be a normal vector of the reference surface.

[0022] In one embodiment, the reference plane may pass through the origin.

[0023] In one embodiment, the reference plane may vary depending on the feature point.

[0024] In one embodiment, the face side vector is x opt , and the vector of the uniform point that has been moved parallel to the above is , and the vector transposed from the above-mentioned parallel-translated uniform point is , and the weight of the vector of the uniform point that has been moved parallel to the above is , and the number of samples of the above uniform points is , and the vector obtained by transposing the above face vector is , and the weight of the above face vector is , and the vector of the feature point that has been moved in parallel is , and the vector obtained by transposing the vector of the feature point that has been moved in parallel is , and the weight of the vector of the feature point that has been moved in parallel is , and the number of samples of the above feature points is , and when argmin(f(x)) is a minimum function that determines x such that the function f(x) has a minimum value, the face side vector can be obtained using [Mathematical Formula 2].

[0025] [Equation 2]

[0026]

[0027] In one embodiment, the automated alignment method of the scan data may further include a step of determining a face upper vector based on the face vector and the face side vector.

[0028] In one embodiment, the upper face vector may be determined as either a first vector that is a vector obtained by cross-producting the face vector and the side face vector, or a second vector that is a vector in the opposite direction of the first vector.

[0029] In one embodiment, the upper face vector may be determined based on a Histogram of Oriented Gradients (HOG) algorithm.

[0030] In one embodiment of the present invention, a program for executing the above method for automating alignment of scan data on a computer can be recorded on a computer-readable recording medium.

[0031] According to a method for automating alignment of scan data according to the present invention and a computer-readable recording medium having recorded thereon a program for executing the same on a computer, the method for automating alignment of the scan data may include a step of determining a face vector and a step of determining a reference plane and a face side vector based on the face vector. Accordingly, the face vector, the face side vector, and the face upper vector may be determined for an image of a patient included in the scan data, and the image of the patient included in the scan data may be aligned based on the face vector, the face side vector, and the face upper vector.

[0032] Figure 1 is a drawing showing three-dimensional volume data and scan data.

[0033] FIGS. 2 and 3 are flowcharts illustrating an automated method for aligning scan data according to embodiments of the present invention.

[0034] Figures 4 to 8 are drawings explaining a step of determining a face vector, a step of determining a uniform point and a feature point, and a step of determining a reference plane and a face side vector based on the face vector.

[0035] Figure 9 is a drawing explaining a step of determining a face upper vector based on the face vector and the face side vector.

[0036] Figure 10 is a drawing showing the facial axis, the facial lateral axis, and the facial upper axis.

[0037] Figure 11 is a diagram showing complex data.

[0038] With respect to the embodiments of the present invention disclosed in the text, specific structural and functional descriptions are merely illustrative for the purpose of explaining the embodiments of the present invention, and the embodiments of the present invention may be implemented in various forms and should not be construed as being limited to the embodiments described in the text.

[0039] The present invention is susceptible to various modifications and takes various forms. Specific embodiments are illustrated in the drawings and described in detail herein. However, this is not intended to limit the present invention to specific disclosed forms, but rather to encompass all modifications, equivalents, and alternatives falling within the spirit and technical scope of the present invention.

[0040] While terms like "first" and "second" may be used to describe various components, these components should not be limited by these terms. These terms may be used to distinguish one component from another. For example, without departing from the scope of the present invention, a first component could be referred to as a "second component," and similarly, a second component could also be referred to as a "first component."

[0041] When a component is referred to as being "connected" or "connected" to another component, it should be understood that it may be directly connected or connected to that other component, but that there may be other components in between. Conversely, when a component is referred to as being "directly connected" or "directly connected" to another component, it should be understood that there are no other components in between. Other expressions that describe the relationship between components, such as "between" and "directly between" or "adjacent to" and "directly adjacent to", should be interpreted similarly.

[0042] The terminology used in this application is only used to describe specific embodiments and is not intended to limit the present invention. The singular expression includes the plural expression unless the context clearly indicates otherwise. In this application, it should be understood that the terms "comprise" or "have" indicate the presence of a described feature, number, step, operation, component, part, or combination thereof, but do not preclude the possibility of the presence or addition of one or more other features, numbers, steps, operations, components, parts, or combinations thereof.

[0043] Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by those of ordinary skill in the art to which this invention pertains. Terms defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and shall not be construed in an idealized or overly formal sense unless explicitly defined herein.

[0044] Meanwhile, if a particular embodiment can be implemented differently, the functions or operations specified within a particular block may occur in a different order than specified in the flowchart. For example, two consecutive blocks may actually be executed substantially simultaneously, or, depending on the related functions or operations, the blocks may be executed in reverse order.

[0045] Hereinafter, preferred embodiments of the present invention will be described in more detail with reference to the attached drawings. Identical components in the drawings are designated by the same reference numerals, and redundant descriptions of identical components are omitted.

[0046] Figure 1 is a diagram showing three-dimensional volume data (3VD) and scan data (SCD).

[0047] Referring to Fig. 1, 3D volume data (3VD) refers to data obtained by photographing a head and neck region including teeth and the oral cavity. For example, the 3D volume data (3VD) may be a CT (Computed Tomography) image. The 3D volume data (3VD) may include information about bones, hard tissues, soft tissues, etc. However, the 3D volume data (3VD) may have low color sensitivity. On the other hand, the scan data (SCD) may have high color sensitivity. However, the scan data (SCD) may not include information about the structure inside the patient's skin.

[0048] Each of the three-dimensional volume data (3VD) and the scan data (SCD) may include an x-axis, a y-axis, and a z-axis. In Fig. 1, the three-dimensional volume data (3VD) is expressed based on the x-axis and the z-axis, and the scan data (SCD) is expressed based on the x-axis and the y-axis. Here, the axes of each of the three-dimensional volume data (3VD) and the scan data (SCD) may be different from each other.

[0049] When the above 3D volume data (3VD) and the scan data (SCD) are aligned, composite data can be generated in which the 3D volume data (3VD) and the scan data (SCD) are overlapped. The composite data can be expressed by the information about the bone, the hard tissue, the soft tissue, etc. of the 3D volume data (3VD) and the color of the scan data (SCD). Accordingly, the composite data can have both the advantages of the 3D volume data (3VD) and the advantages of the scan data (SCD). When the composite data is used, the user can have advantages such as establishing a treatment strategy for the patient and obtaining a predicted shape of the patient after the treatment for the patient.

[0050] In order to align the three-dimensional volume data (3VD) and the scan data (SCD), a process of aligning the scan data (SCD) may be important. In order to align the scan data (SCD), an alignment axis of the scan data (SCD) may be determined. For example, the scan data (SCD) may include an image of the patient, and the alignment axis of the scan data (SCD) may be determined based on the image of the patient. The purpose of the automated alignment method of the scan data (SCD) according to the present embodiments is to determine a face direction axis, a face side axis, and a face upper axis. FIGS. 2 and 3 illustrate overall flowcharts of the automated alignment method of the scan data (SCD), and FIGS. 4 to 11 illustrate each step in detail.

[0051] Meanwhile, although the scan data (SCD) in FIG. 1 is expressed in one color, the number of colors included in the scan data (SCD) is not limited to one. The number of colors in the scan data (SCD) may be at least two or more. Accordingly, the composite data may have a richer sense of color.

[0052] FIGS. 2 and 3 are flowcharts illustrating an automated method for aligning scan data (SCD) according to embodiments of the present invention.

[0053] Referring to FIGS. 1 to 3, the automated alignment method of scan data (SCD) according to the present embodiment may include a step of determining a face vector indicating a direction in which a patient's face is located (step S100) and a step of determining a reference plane and a face side vector based on the face vector (step S300). The automated alignment method of the scan data (SCD) may further include a step of determining a uniform point and a feature point (step S200). The automated alignment method of the scan data (SCD) may further include a step of determining a face upper vector based on the face vector and the face side vector (step S400).

[0054] The step of determining the above-mentioned face side vector (step S300) may include a step of determining a reference point (step S310), a step of moving the uniform point and the feature point in parallel based on the reference point (step S320), and a step of determining the face side vector based on the face vector, the uniform point moved in parallel, and the feature point moved in parallel (step S330).

[0055] The above method for automating alignment of the above scan data (SCD) can be performed by a computing device.

[0056] Figures 4 to 8 show the face vector (x face) (step S100), the step of determining the uniform point (UP) and the feature point (FP) (step S200), and the face vector (x face ) based on the reference plane (RPN) and the face side vector (x opt ) are drawings explaining the step (step S300) of judging.

[0057] Referring to FIGS. 1 to 8, the automated alignment method of the scan data (SCD) is performed on the face vector (x face ) may include the step (step S100) of determining the above.

[0058] The above scan data (SCD) can be expressed as a mesh. For example, the mesh can be multiple and can have various shapes. For example, the shape of the mesh can be a triangle or a rectangle. In one embodiment, the face vector (x face ) can be determined based on the normal vector of the above mesh.

[0059] For example, the above face vector (x face ) may be the average vector of the normal vectors of the above mesh. Here, the face vector (x face ) may be all meshes included in the scan data (SCD).

[0060] For example, the above face vector (x face ) may be an optimization vector using the normal vector of the above mesh. Here, the face vector (x face ) may be all meshes included in the scan data (SCD). For example, the face vector (x face ) can be obtained using [Mathematical Formula 1].

[0061] [Mathematical Formula 1]

[0062]

[0063] Here, x face is the above face vector, and M i is the normal vector of the above mesh, and argmin is the minimum function. Here, argmin(f(x)) outputs x for which the function f(x) has a minimum value.

[0064] The larger the inner product of Mi and x, the larger x in [Mathematical Formula 1] face can be reduced. The inner product of Mi and x is the normal vector of the mesh and x face The smaller the angle between them, the larger it can be. Accordingly, x face The smaller the lens, the better the patient's face can be seen.

[0065] The above-described automated alignment method of the above-described scan data (SCD) may include a step (step S200) of determining the uniform point (UP) and the feature point (FP).

[0066] The above uniform point (UP) can be determined from among all points included in the scan data (SCD). For example, the uniform point (UP) can be determined to be spatially uniform from the image of the patient.

[0067] The above feature point (FP) can be determined from among all points included in the scan data (SCD). For example, the feature point (FP) can be determined to be spatially non-uniform from the image of the patient. The feature point (FP) can be determined using various methods. For example, the feature point (FP) can be determined using deep learning. For example, the feature point (FP) can be determined based on the curvature of the image of the patient. Specifically, when the curvature of a point included in the image of the patient is greater than a specific value, the point can be determined as the feature point (FP).

[0068] The above automated alignment method of the above scan data (SCD) is the face vector (x face ) based on the reference plane (RPN) and the face side vector (x opt ) may include the step (step S300) of determining the reference plane (RPN) and the face side vector (x opt ) is the face vector (x face ), can be judged based on the uniform point (UP) and the feature point (FP).

[0069] The above face side vector (x opt ) is determined (step S300), the step of determining a reference point (step S310), the step of moving the uniform point (UP) and the feature point (FP) in parallel based on the reference point (step S320), and the step of determining the face vector (x face ), and the step (step S330) of determining the face side vector based on the parallel-shifted uniform point (UP_TRANS) and the parallel-shifted feature point (FP_TRANS).

[0070] The above reference point (not shown) may be determined based on the uniform point (UP). The reference point may be a point that serves as a reference for parallel movement of the scan data (SCD). The uniform point (UP) may be uniformly distributed in space in the image of the patient. Therefore, when the reference point is determined based on the uniform point (UP), the reference point may well represent the reference of the image of the patient. For example, the reference point may be the center point of the uniform point (UP). In this case, the reference point may be located at the center of the image of the patient.

[0071] The scan data (SCD) can be translated in parallel based on the reference point. Accordingly, the uniform point (UP) and the feature point (FP) can be translated in parallel based on the reference point. For example, the uniform point (UP) and the feature point (FP) can be translated in parallel by the difference between the reference point and the origin (ORG). Here, the origin (ORG) may be a point where each of the x-axis, the y-axis, and the z-axis included in the scan data (SCD) intersects. Accordingly, as illustrated in FIG. 6, the image of the patient can be expressed based on the origin (ORG). For example, the uniform point (UP) can be expressed as the uniform point (UP_TRANS) translated in parallel based on the origin (ORG), and the feature point (FP) can be expressed as the feature point (FP_TRANS) translated in parallel based on the origin (ORG).

[0072] The above face side vector (x opt ) is the face vector (x face ), can be determined based on the parallel shifted uniform point (UP_TRANS), and the parallel shifted feature point (FP_TRANS). For example, the face side vector (x opt ) is the face vector (x face ), the above parallel shifted uniform point (UP_TRANS), and the above parallel shifted feature point (FP_TRANS) may be an optimization vector. For example, the face side vector (x opt ) can be obtained using [Mathematical Formula 2]. The face side vector (x) determined in [Mathematical Formula 2] opt ) can be a normal vector of the reference plane (RPN).

[0073] [Equation 2]

[0074]

[0075] Here, x opt is the face side vector, is the vector of the above parallel shifted uniform point (UP_TRANS), is a vector transposed from the above-mentioned parallel-translated uniform point, is the vector of the above parallel shifted uniform point (UP_TRANS) ) is the weight, is the number of samples of the above uniform point (UP), is the above face vector (x face ) is expressed differently, is the above face vector ( ) is a vector transposed, is the above face vector ( ) is the weight, is a vector of the above parallel shifted feature points (FP_TRANS), is a vector transposed from the above-mentioned vector of the feature point that has been moved in parallel, is the vector of the above parallel shifted feature point (FP_TRANS) ) is the weight, is the number of samples of the above feature point (FP), and argmin is the minimum function. Here, argmin(f(x)) outputs x that makes the function f(x) have a minimum value.

[0076] The smaller the inner product of and x, the smaller x in [Mathematical Formula 2] opt can become smaller. The inner product of x and x is the vector of the parallel-translated uniform point (UP_TRANS) ) and the reference plane (RPN) may be smaller.

[0077] The smaller the inner product of and x, the smaller x in [Mathematical Formula 2] opt can become smaller. The inner product of x and the face vector (x face ) and x opt The closer the angle between them is to 90 degrees, the smaller it can be.

[0078] The smaller the inner product of and x, the smaller x in [Mathematical Formula 2] opt can become smaller. The inner product of x and x is the vector of the parallel-translated feature point (FP_TRANS) ) and the reference plane (RPN) may be smaller.

[0079] Accordingly, the reference plane (RPN) and the face side vector (x opt ) can be determined. The reference plane (RPN) can be obtained as a symmetrical plane that passes through the origin (ORG) and divides the image of the patient into left and right, and the face side vector (x opt ) is the face vector (x face ) can form a 90 degree angle.

[0080] Meanwhile, the face side vector (x) determined using [Mathematical Formula 2] according to the feature point (FP) determined in the above drawing 5 opt ) may be different, so the reference plane (RPN) may be different depending on the feature point (FP) determined in FIG. 5. FIG. 8 illustrates these reference planes (RPN).

[0081] However, the above automated alignment method of the above scan data (SCD) is not applicable to the face side vector (x opt ) is performed, the image of the patient is not aligned vertically. Therefore, the image of the patient may be flipped. Therefore, in FIG. 9, it is determined whether the image of the patient is flipped, and the image of the patient can be aligned vertically.

[0082] Figure 9 shows the face vector (x face ) and the face side vector (x opt ) based on the upper face vector (x up) is a drawing explaining a step (step S400) of determining a face axis. Fig. 10 is a drawing showing a face axis, a face side axis, and a face upper axis. Fig. 11 is a drawing showing composite data.

[0083] Referring to FIGS. 1 to 11, the automated alignment method of the scan data (SCD) is performed on the face vector (x face ) and the face side vector (x opt ) based on the upper face vector (x up ) may include a step (step S400) of determining.

[0084] The upper face vector (x) up ) is the face vector (x face ) and the face side vector (x opt ) can be determined based on the face vector (x). For example, two images (I, I') can be obtained for the image of the patient by obtaining an image that is flipped upside down. In this case, the first image (I') is the face vector (x face ) and the above face side vector (x opt ) and externally "x face ×x opt " can be taken as an upper vector, and the second image (I) can have the face vector (x face ) and the above face side vector (x opt ) and reverse it to "-x face ×x opt " can be had as an upper vector.

[0085] Image face detection can be performed on the first image (I') and the second image (I). The image face detection can determine the upper or lower side of the image of the patient based on a confidence score. For example, the image face detection can use the HOG (Histogram of Oriented Gradients) algorithm. The HOG algorithm is widely used in object detection and recognition tasks. The HOG algorithm can divide the image of the patient into a plurality of cells and then obtain a score for each of the cells. For example, the scores of the eyes and nose of the image of the patient may be different, and the image face detection can determine the upper or lower side of the image of the patient based on the scores.

[0086] The above face vector (x face ), the face side vector (x opt ), and the upper face vector (x up ) can be determined based on the face axis, the face side axis, and the face upper axis. For example, the face axis can be determined based on the face vector (x face ) can be judged based on the face side axis, and the face side vector (x opt ) can be judged based on the face upper axis, and the face upper vector (x up ) can be judged based on. In Fig. 10, the reference plane (RPN), the face axis, the face lateral axis, and the face upper axis are shown for the image of the patient included in the scan data (SCD).

[0087] The alignment of the above scan data (SCD) and the three-dimensional volume data (3VD) can be performed based on the face axis, the face side axis, and the face upper axis of the scan data (SCD) and the axes of the three-dimensional volume data (3VD). Here, the alignment of the points of the scan data (SCD) and the points of the three-dimensional volume data (3VD) can be performed based on an ICP (Iterative Closest Point) algorithm. Here, the ICP algorithm is a nonlinear optimization algorithm that matches and aligns two point clouds for one object.

[0088] Figure 11 illustrates composite data, which is data obtained by combining the three-dimensional volume data (3VD) and the scan data (SCD). The composite data can be expressed in terms of information on bones, hard tissues, soft tissues, etc. of the three-dimensional volume data (3VD) and the colors of the scan data (SCD).

[0089] In this way, the above automated alignment method of the above scan data (SCD) is face ) (step S100), the step of determining the uniform point (UP) and the feature point (FP) (step S200), and the face vector (x face ), the face side vector (x) based on the uniform point (UP) and the feature point (FP) opt ) may include a step (step S300) of determining the face vector (x) of the patient's image included in the scan data (SCD). Accordingly, the face vector (x) of the patient's image included in the scan data (SCD) face ), the face side vector (x opt ), and the upper face vector (x up ) can be judged, and the face vector (x face ), the face side vector (x opt ), and the upper face vector (x up) can be aligned with the patient's image included in the scan data (SCD).

[0090] According to embodiments of the present invention, a computer-readable recording medium having recorded thereon a program for executing the above-described automated method for aligning scan data (SCD) on a computer can be provided. The above-described method can be written as a program that can be executed on a computer, and can be implemented in a general-purpose digital computer that executes the program using a computer-readable medium. In addition, the structure of the data used in the above-described method can be recorded on a computer-readable medium through various means. The computer-readable medium can include program commands, data files, data structures, etc., either singly or in combination. The program commands recorded on the medium may be those specially designed and configured for the present invention, or may be known and usable by those skilled in the art in the field of computer software. Examples of the computer-readable recording medium include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical recording media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and hardware devices specially configured to store and execute program commands such as ROMs, RAMs, and flash memories. Examples of program instructions include not only machine language codes, such as those generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the present invention.

[0091] Additionally, the above method for automating the alignment of the above scan data (SCD) can also be implemented in the form of a computer program or application executed by a computer and stored in a recording medium.

[0092] The present invention relates to a method for automating alignment of scan data and a computer-readable recording medium having recorded thereon a program for executing the method on a computer, which can reduce the effort and time for computational processing operations and improve accuracy and productivity.

[0093] Although the present invention has been described above with reference to preferred embodiments thereof, it will be understood by those skilled in the art that various modifications and changes may be made to the present invention without departing from the spirit and scope of the present invention as set forth in the claims below.

Claims

1. A step of determining a face vector indicating the direction in which the patient's face is located; and A method for automating alignment of scan data, comprising a step of determining a reference plane and a face side vector based on the above face vector.

2. In the first paragraph, further comprising a step of determining uniform points and characteristic points, An automated method for aligning scan data, characterized in that the reference plane and the face side vector are determined based on the face vector, the uniform point, and the feature point.

3. A method for automating alignment of scan data, characterized in that in the first paragraph, the face vector is determined based on a normal vector of a mesh included in the scan data.

4. A method for automating alignment of scan data, characterized in that in the third paragraph, the face vector is an average vector of the normal vectors of the mesh.

5. In the third paragraph, the face vector is x face A method for automating alignment of scan data, characterized in that the face vector is obtained using [Mathematical Formula 1] when the normal vector of the mesh is Mi and argmin(f(x)) is a minimum function that determines x such that the function f(x) has a minimum value. [Mathematical Formula 1] 6. A method for automating alignment of scan data, characterized in that in the second paragraph, the uniform point is determined to be spatially uniform from the image of the patient included in the scan data.

7. A method for automating alignment of scan data, characterized in that in the second paragraph, the feature point is determined based on the curvature of the mesh included in the scan data.

8. A method for automating alignment of scan data, characterized in that in the 7th paragraph, the curvature of the mesh is determined based on the normal vector of the mesh.

9. A method for automating alignment of scan data, characterized in that in the second paragraph, the feature points are determined to be spatially uneven from the image of the patient included in the scan data.

10. In the second paragraph, the step of determining the face side vector is, Step of determining the reference point; A step of moving the uniform point and the feature point in parallel based on the reference point; and A method for automating alignment of scan data, comprising a step of determining the reference plane and the face side vector based on the face vector, the parallel-shifted uniform point, and the parallel-shifted feature point.

11. A method for automating alignment of scan data, characterized in that in the 10th paragraph, the reference point is the center point of the uniform point.

12. A method for automating alignment of scan data, characterized in that in the 10th paragraph, the uniform point and the feature point are moved in parallel by the difference between the reference point and the origin.

13. A method for automating alignment of scan data, characterized in that in the 10th paragraph, the face side vector is a normal vector of the reference surface.

14. A method for automating alignment of scan data, characterized in that in the 13th paragraph, the reference plane passes through the origin.

15. A method for automating alignment of scan data, characterized in that in the 13th paragraph, the reference plane varies depending on the feature point.

16. In the 10th paragraph, the face side vector is x opt , and the vector of the uniform point that has been moved parallel to the above is , and the vector transposed from the above-mentioned parallel-translated uniform point is , and the weight of the vector of the uniform point that has been moved parallel to the above is , and the number of samples of the above uniform points is , and the vector obtained by transposing the above face vector is , and the weight of the above face vector is , and the vector of the feature point that has been moved in parallel is , and the vector obtained by transposing the vector of the feature point that has been moved in parallel is , and the weight of the vector of the feature point that has been moved in parallel is , and the number of samples of the above feature points is A method for automating alignment of scan data, characterized in that the face side vector is obtained using [Mathematical Formula 2] when argmin(f(x)) is a minimum function that determines x such that the function f(x) has a minimum value. [Equation 2] 17. A method for automating alignment of scan data, characterized in that it further comprises a step of determining an upper face vector based on the face vector and the face side vector in the first paragraph.

18. A method for automating alignment of scan data, characterized in that in the 17th paragraph, the upper face vector is determined as one of a first vector which is a vector obtained by cross-producting the face vector and the side face vector, and a second vector which is a vector in the opposite direction of the first vector.

19. A method for automating alignment of scan data, characterized in that in the 17th paragraph, the upper face vector is determined based on the HOG (Histogram of Oriented Gradients) algorithm.

20. A computer-readable recording medium having recorded thereon a program for executing the method of any one of claims 1 to 19 on a computer.

Images