CN111354057A - Bone fracture line map drawing method based on image deformation technology - Google Patents
Bone fracture line map drawing method based on image deformation technology Download PDFInfo
- Publication number
- CN111354057A CN111354057A CN202010162209.3A CN202010162209A CN111354057A CN 111354057 A CN111354057 A CN 111354057A CN 202010162209 A CN202010162209 A CN 202010162209A CN 111354057 A CN111354057 A CN 111354057A
- Authority
- CN
- China
- Prior art keywords
- triangle
- image
- deformation
- fracture
- outer contour
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/20—Drawing from basic elements, e.g. lines or circles
- G06T11/203—Drawing of straight lines or curves
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
- G06T17/20—Finite element generation, e.g. wire-frame surface description, tesselation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10081—Computed x-ray tomography [CT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30008—Bone
Abstract
The invention discloses a fracture line map drawing method based on an image deformation technology, which comprises the steps of preprocessing input fracture CT data; extracting an outer contour from the preprocessed image, dividing fracture blocks, extracting fracture lines and determining outer contour feature points; performing triangulation according to the characteristic points to generate a triangular network and adjusting an image area; traversing the whole triangular network and carrying out separate adjustment and scaling adjustment on each triangle; and (3) carrying out image deformation on the anisotropic skeleton sample based on the outer contour under the condition of ensuring that the internal skeleton line characteristics are not changed, so as to unify the abnormal skeleton sample to a standard skeleton template and finish the drawing of a skeleton line map. The method can be used for rapidly drawing the fracture line map, and is high in reliability and good in accuracy.
Description
Technical Field
The invention belongs to the field of image processing, and particularly relates to a bone fracture line map drawing method based on an image deformation technology.
Background
Fracture injury is the most common bone injury, and the main reason is high-energy injury caused by external force to bones, and the physiological manifestations are fracture, bone fracture and the like. After the fracture occurs, if the diagnosis and treatment or nursing are not proper, a plurality of complications are easy to cause. The fracture forms of various parts have close relationship with the clinical treatment effect. Therefore, the fracture line map can provide a comprehensive and intuitive fracture characteristic description. The fracture line mapping technique is a method of superimposing fracture lines of a plurality of cases on one bone model by computer image simulation to redisplay the fracture form. The fracture model is characterized in that 'big data' of a certain fracture can be visually displayed, and the fracture model comprises information such as fracture line starting and stopping, trend, distribution, fracture type, crushing degree, joint surface defect and the like, so that people can more visually and three-dimensionally know the whole form of the fracture, and more abundant information is provided for doctors.
At present, the common method for drawing the fracture line map is still a manual hand-drawing mode: the method is characterized in that abundant doctors use image processing software (such as Photoshop) to process each picture one by one, and the pictures are superposed on a standard template one by one to obtain a corresponding fracture line map. However, obviously, the current manual processing and drawing method is time-consuming, labor-consuming, complex in process, extremely dependent on the manual experience of the processor, and poor in consistency.
Disclosure of Invention
The invention aims to provide a bone fracture line map drawing method based on an image deformation technology, which has high reliability, high accuracy, high speed and good effect.
The invention provides a bone fracture line map drawing method based on an image deformation technology, which comprises the following steps:
s1, preprocessing input fracture CT data to obtain a preprocessed image;
s2, aiming at the preprocessed image obtained in the step S1, extracting an outer contour, finishing the division of fracture blocks, extracting fracture lines and determining outer contour feature points;
s3, performing triangulation according to the characteristic points acquired in the step S2 to generate a triangular network, and adjusting image areas;
s4, traversing the whole triangular network obtained in the step S3, and separately adjusting and zooming each triangle;
s5, carrying out image deformation based on the outer contour on the condition that the characteristic of the internal fracture line is not changed by the anisotropic bone sample, so that the bone samples are unified to a standard bone template, and drawing of a fracture line map is completed.
The step S1 is to preprocess the input fracture CT data to obtain a preprocessed image, specifically, to model, reset, render and convert the input fracture CT data into a two-dimensional image, so as to extract the outer contour and the fracture line features.
The step S2 is to extract the outer contour, complete the division of the fracture block, the extraction of the fracture line, and the determination of the outer contour feature point for the preprocessed image obtained in the step S1, specifically, extract the outer contour on the image by using an edge detection algorithm, then complete the division of the fracture block and the extraction of the fracture line by using a clustering algorithm, and finally sample the outer contour by using a sine function sampling algorithm to determine the feature point.
When the outer contour and the fracture line are extracted, the Canny operator is adopted to extract the edge contour, and then the principal component analysis method is adopted to smooth the line.
The triangulation is performed according to the feature points acquired in the step S2 to generate a triangulation network, and the image region is adjusted in the step S3, specifically, a Delaunay triangulation method is adopted, triangulation is performed based on the feature points sampled in the step S2 to generate the triangulation network, and the deformation image partial region is manually adjusted, so that the problem of local distortion in the modeling and resetting process is solved.
The manual adjustment of the partial area of the deformed image is specifically to measure the error of a certain vertex of a single triangle before and after deformation by adopting a least square method and ensure the similarity before and after deformation by utilizing the local relative coordinates of the triangle.
The method adopts least square method to measure the error of a certain vertex of a single triangle before and after deformation, specifically the vertex V of the triangle2Relative to vertex V0And V1The local coordinates of (a) are expressed as follows:
in the formula V2Is the vertex to be deformed; v0V1Two vertexes of a triangle which is not changed; x01Is a V2Projection on the X-axis of the local coordinate system; y is01Is a V2Projection on the Y-axis of the local coordinate system; r90Convert matrices for local coordinates and
the above formula for calculating the local coordinates is complex and affects the time complexity of the overall algorithm, so the triangle can be set as an equilateral triangle, in which the local coordinates are expressed as follows:
wherein V2Is the vertex to be deformed; v0V1Two vertexes of a triangle which is not changed; r60Convert matrix for equilateral triangle local coordinates and
step S4, traversing the entire triangle network obtained in step S3, separately adjusting and scaling each triangle, specifically traversing the entire triangle network, separately adjusting each triangle to minimize the miscut deformation energy of the total triangle, and then scaling each triangle with the centroid coordinates of the triangles as the scaling origin.
Traversing the whole triangular network, and separately adjusting each triangle to minimize the miscut deformation energy of the total triangle, wherein the triangular deformation energy function in the fitting stage is as follows:
in the formulaThe vertex coordinates of the fitted triangle are obtained, and the following formula is satisfied:
i=1,2,3;the coordinates of the vertex of the fitted triangle are obtained; and then calculating the partial derivative of the triangular deformation energy function in the fitting stage, thereby obtaining the parameter when the deformation energy is minimized.
And S5, performing image deformation based on the outer contour, so as to unify the image into a standard skeleton template and finish drawing a fracture line map, wherein an energy calculation formula of any point P on the contour line before and after deformation is as follows:
the ith base coordinate of point P before deformationThe center coordinate isPoint on the deformed corresponding position P' is at the ith base coordinateHas the coordinates ofWherein P and P' are both two-bit column vectors; r isiIs a scaling ratio andliis corresponding to LiEnd unitized vector of, kiIs corresponding to KiThe end unitized vector of (a); omegaiα is a user-controlled distortion parameter for adjusting the scale in the vertical direction, and α∈ [0,1 ]]。
The method for drawing the bone fracture line map based on the image deformation technology can unify a plurality of pictures to a standard template at one time according to the standard of outline anastomosis, has high calculation speed and accurate result, and is suitable for statistical analysis of fracture of each part; and a target energy function is established by using a moving least square method, and deformation is completed in an error driving mode by using the constraint condition of local coordinates of an equilateral triangle in the iteration process; in order to ensure the integral deformation effect, the error of each equilateral triangle is minimized to achieve the best deformation effect; after the energy minimization of a single triangle is ensured, traversing the whole triangular mesh to achieve the energy minimization of the whole error; therefore, the method has high reliability, good accuracy, high speed and good effect.
Drawings
FIG. 1 is a schematic flow chart of the method of the present invention.
FIG. 2 is a diagram of input data and preprocessing according to the present invention.
Fig. 3 is a schematic diagram of the transformation process of the present invention.
FIG. 4 is a schematic diagram of the fracture line and contour extracted from the test case of the present invention.
Detailed Description
FIG. 1 is a schematic flow chart of the method of the present invention: the invention provides a bone fracture line map drawing method based on an image deformation technology, which comprises the following steps:
s1, preprocessing input fracture CT data to obtain a preprocessed image; specifically, modeling, resetting, rendering and converting input CT data into a two-dimensional image so as to extract the outer contour and the fracture line characteristics; as shown in fig. 2;
s2, aiming at the preprocessed image obtained in the step S1, extracting an outer contour, finishing the division of fracture blocks, extracting fracture lines and determining outer contour feature points; specifically, an outer contour is extracted on an image by using an edge detection algorithm, then a clustering algorithm is adopted to complete the division of fracture blocks and the extraction of fracture lines, and finally a sine function sampling algorithm is adopted to sample the outer contour so as to determine feature points;
in specific implementation, when the outer contour and the fracture line are extracted, the Canny operator can be used for extracting the edge contour, and then the main component analysis method is used for smoothing the line;
s3, performing triangulation according to the characteristic points acquired in the step S2 to generate a triangular network, and adjusting image areas; specifically, a Delaunay triangulation method is adopted, triangulation is carried out based on the characteristic points obtained by sampling in the step S2, a triangular network is generated, and partial areas of a deformation image are manually adjusted, so that the problem of local distortion in the modeling resetting process is solved;
in specific implementation, a least square method is adopted to measure the error of a certain vertex of a single triangle before and after deformation, and local relative coordinates of the triangle are utilized to ensure the similarity before and after deformation, as shown in fig. 3 (a);
wherein, the least square method is adopted to measure the error of a certain vertex of a single triangle before and after deformation (as shown in figure 3 (b)), specifically the vertex V of the triangle2Relative to vertex V0And V1Local coordinates ofIs represented as follows:
in the formula V2Is the vertex to be deformed; v0V1Two vertexes of a triangle which is not changed; x01Is a V2Projection on the X-axis of the local coordinate system; y is01Is a V2Projection on the Y-axis of the local coordinate system; r90Convert matrices for local coordinates and
the above formula for calculating the local coordinates is complex and affects the time complexity of the overall algorithm, so the triangle can be set as an equilateral triangle, in which the local coordinates are expressed as follows:
wherein V2Is the vertex to be deformed; v0V1Two vertexes of a triangle which is not changed; r60Convert matrix for equilateral triangle local coordinates and
s4, traversing the whole triangular network obtained in the step S3, and separately adjusting and zooming each triangle; specifically, the whole triangle network is traversed, each triangle is separately adjusted, so that the miscut deformation energy of the total triangle is minimized, and then each triangle is scaled and adjusted by taking the barycentric coordinates of the triangles as the scaling origin (as shown in fig. 3 (c));
in specific implementation, the triangle deformation energy function in the fitting stage is:
in the formulaThe vertex coordinates of the fitted triangle are obtained, and the following formula is satisfied:
i=1,2,3;the coordinates of the vertex of the fitted triangle are obtained; then, calculating partial derivatives of the triangular deformation energy function in the fitting stage, thereby obtaining parameters when the deformation energy is minimized;
s5, carrying out image deformation based on the outer contour under the condition that the characteristic of the internal fracture line is not changed by using the anisotropic bone samples, so that a standard bone template is unified, and drawing of a fracture line map is completed; specifically, the energy calculation formula of any point P on the contour line before and after deformation is as follows:
the ith base coordinate of point P before deformationThe center coordinate isPoint on the deformed corresponding position P' is at the ith base coordinateHas the coordinates ofWherein P and P' are both two-bit column vectors; r isiIs a scaling ratio andliis a pair ofShould LiEnd unitized vector of, kiIs corresponding to KiThe end unitized vector of (a); omegaiα is a user-controlled distortion parameter for adjusting the scale in the vertical direction, and α∈ [0,1 ]]。
FIG. 4 is a diagram illustrating the effect of one embodiment of the method of the present invention. As can be seen from FIG. 4, the method of the present invention can reliably and clearly draw the fracture line, and the effect is good.
Claims (10)
1. A bone fracture line map drawing method based on image deformation technology comprises the following steps:
s1, preprocessing input fracture CT data to obtain a preprocessed image;
s2, aiming at the preprocessed image obtained in the step S1, extracting an outer contour, finishing the division of fracture blocks, extracting fracture lines and determining outer contour feature points;
s3, performing triangulation according to the characteristic points acquired in the step S2 to generate a triangular network, and adjusting image areas;
s4, traversing the whole triangular network obtained in the step S3, and separately adjusting and zooming each triangle;
s5, carrying out image deformation based on the outer contour on the condition that the characteristic of the internal fracture line is not changed by the anisotropic bone sample, so that the bone samples are unified to a standard bone template, and drawing of a fracture line map is completed.
2. The method for drawing a bone fracture line map based on image deformation technology as claimed in claim 1, wherein the step S1 is performed by preprocessing the input fracture CT data to obtain a preprocessed image, specifically, the inputted fracture CT data is modeled, reset, rendered and converted into a two-dimensional image, so as to extract the outer contour and the bone fracture line features.
3. The method for drawing a bone fracture line map based on an image deformation technology as claimed in claim 2, wherein the step S2 is to extract the outer contour, complete the division of the bone fracture blocks, the extraction of the bone fracture lines and the determination of the outer contour feature points for the preprocessed image obtained in the step S1, specifically, the outer contour is extracted by using an edge detection algorithm on the image, then the division of the bone fracture blocks and the extraction of the bone fracture lines are completed by using a clustering algorithm, and finally the outer contour is sampled by using a sine function sampling algorithm to determine the feature points; when the outer contour and the fracture line are extracted, the Canny operator is adopted to extract the edge contour, and then the principal component analysis method is adopted to smooth the line.
4. The method for drawing a bone fracture line map based on image deformation technology as claimed in claim 3, wherein in step S3, triangulation is performed according to the feature points obtained in step S2 to generate a triangulation network, and image area adjustment is performed, specifically, a Delaunay triangulation method is employed, triangulation is performed based on the feature points sampled in step S2 to generate a triangulation network, and a deformation image partial area is manually adjusted, so as to solve the problem of local distortion during modeling and resetting.
5. The method according to claim 4, wherein the distortion image portion is manually adjusted, specifically, a least square method is used to measure the error of a vertex of a single triangle before and after distortion, and local relative coordinates of the triangle are used to ensure the similarity before and after distortion.
6. The method of claim 5, wherein the error of a vertex of a triangle before and after deformation is measured by least squares method, specifically, the vertex V of the triangle2Relative to vertex V0And V1Is represented by the following formula:
7. the method of claim 6, wherein the triangle is an equilateral triangle, and the corresponding local coordinates are represented by the following formula:
8. the method for bone fracture line mapping based on image morphing technique of claim 7, wherein step S4 is to traverse the entire triangle network obtained in step S3, and perform separate adjustment and scaling adjustment on each triangle, specifically traverse the entire triangle network, perform separate adjustment on each triangle to minimize the energy of the total triangle caused by miscut deformation, and then perform scaling adjustment on each triangle with the coordinates of the center of gravity of the triangle as the scaling origin.
9. The method according to claim 8, wherein the entire network of triangles is traversed, and each triangle is separately adjusted so that the miscut deformation energy of the total triangle is minimized, and specifically the triangle deformation energy function in the fitting stage is:
in the formulaThe vertex coordinates of the fitted triangle are obtained, and the following formula is satisfied:
i is 1,2, 3; and then calculating the partial derivative of the triangular deformation energy function in the fitting stage, thereby obtaining the parameter when the deformation energy is minimized.
10. The method for drawing a bone fracture line map based on image deformation technology as claimed in claim 9, wherein the step S5 is performed to perform image deformation based on the outer contour, so as to unify to the standard skeleton template, and complete the drawing of the bone fracture line map, specifically, the energy calculation formula of any point P on the contour line before and after deformation is:
the ith base coordinate of point P before deformationThe center coordinate isPoint on the deformed corresponding position P' is at the ith base coordinateHas the coordinates ofWherein P and P' are both two-bit column vectors; r isiIs a scaling ratio andliis corresponding to LiEnd unitized vector of, kiIs corresponding to KiThe end unitized vector of (a); omegaiα is a user-controlled distortion parameter for adjusting the scale in the vertical direction, and α∈ [0,1 ]]。
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010162209.3A CN111354057B (en) | 2020-03-10 | 2020-03-10 | Bone fracture line map drawing method based on image deformation technology |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010162209.3A CN111354057B (en) | 2020-03-10 | 2020-03-10 | Bone fracture line map drawing method based on image deformation technology |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111354057A true CN111354057A (en) | 2020-06-30 |
CN111354057B CN111354057B (en) | 2022-07-08 |
Family
ID=71196031
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010162209.3A Active CN111354057B (en) | 2020-03-10 | 2020-03-10 | Bone fracture line map drawing method based on image deformation technology |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111354057B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113298784A (en) * | 2021-05-25 | 2021-08-24 | 中南大学 | Bone fracture line extraction and mapping method based on visual angle |
CN117218091A (en) * | 2023-09-19 | 2023-12-12 | 徐州医科大学 | Fracture line extraction method for fracture map construction |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040167625A1 (en) * | 1999-01-27 | 2004-08-26 | Disc-O-Tech Orthopedic Technologies Inc. | Spacer filler |
CN101276482A (en) * | 2008-05-12 | 2008-10-01 | 北京理工大学 | Simplifying method for rendering three-dimensional scene based on dynamic Billboard technique |
CN106600683A (en) * | 2016-11-28 | 2017-04-26 | 淮阴工学院 | Bone CT sequence image oriented grid model adaptive reconstruction method |
CN108491770A (en) * | 2018-03-08 | 2018-09-04 | 李书纲 | A kind of data processing method based on fracture image |
CN110522501A (en) * | 2019-08-09 | 2019-12-03 | 常州市第二人民医院 | The building of 3D printing personalization orthopedic implant and biomethanics optimized treatment method |
CN110570430A (en) * | 2019-09-16 | 2019-12-13 | 中南大学 | orbital bone tissue segmentation method based on body registration |
-
2020
- 2020-03-10 CN CN202010162209.3A patent/CN111354057B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040167625A1 (en) * | 1999-01-27 | 2004-08-26 | Disc-O-Tech Orthopedic Technologies Inc. | Spacer filler |
CN101276482A (en) * | 2008-05-12 | 2008-10-01 | 北京理工大学 | Simplifying method for rendering three-dimensional scene based on dynamic Billboard technique |
CN106600683A (en) * | 2016-11-28 | 2017-04-26 | 淮阴工学院 | Bone CT sequence image oriented grid model adaptive reconstruction method |
CN108491770A (en) * | 2018-03-08 | 2018-09-04 | 李书纲 | A kind of data processing method based on fracture image |
CN110522501A (en) * | 2019-08-09 | 2019-12-03 | 常州市第二人民医院 | The building of 3D printing personalization orthopedic implant and biomethanics optimized treatment method |
CN110570430A (en) * | 2019-09-16 | 2019-12-13 | 中南大学 | orbital bone tissue segmentation method based on body registration |
Non-Patent Citations (2)
Title |
---|
廖胜辉等: "基于Mean Shift 和插值图像修复算法的CT图像金属伪影消除方法", 《电子学报》 * |
张英琪等: "股骨近端外侧壁的骨折特征地图研究", 《中国临床解剖学杂志》 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113298784A (en) * | 2021-05-25 | 2021-08-24 | 中南大学 | Bone fracture line extraction and mapping method based on visual angle |
CN117218091A (en) * | 2023-09-19 | 2023-12-12 | 徐州医科大学 | Fracture line extraction method for fracture map construction |
CN117218091B (en) * | 2023-09-19 | 2024-03-29 | 徐州医科大学 | Fracture line extraction method for fracture map construction |
Also Published As
Publication number | Publication date |
---|---|
CN111354057B (en) | 2022-07-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106780619B (en) | Human body size measuring method based on Kinect depth camera | |
WO2021169191A1 (en) | Fast ct scanning method and system based on virtual stereoscopic positioned image | |
CN106249881A (en) | Augmented reality view field space and virtual three-dimensional target dynamic method for registering | |
CN111354057B (en) | Bone fracture line map drawing method based on image deformation technology | |
CN110930374A (en) | Acupoint positioning method based on double-depth camera | |
CN111179321B (en) | Point cloud registration method based on template matching | |
CN112057107A (en) | Ultrasonic scanning method, ultrasonic equipment and system | |
CN109118455B (en) | Ancient human skull craniofacial interactive restoration method based on modern soft tissue distribution | |
CN112330813A (en) | Wearing three-dimensional human body model reconstruction method based on monocular depth camera | |
CN114066953A (en) | Three-dimensional multi-modal image deformable registration method for rigid target | |
Shao et al. | Augmented reality calibration using feature triangulation iteration-based registration for surgical navigation | |
CN114581632A (en) | Method, equipment and device for detecting assembly error of part based on augmented reality technology | |
EP3801201A1 (en) | Measuring surface distances on human bodies | |
AU2020101643A4 (en) | Method for automatically constructing patient-specific anatomic model based on statistical shape model (SSM) | |
JP5526401B2 (en) | Ventricular wall information extraction device | |
CN109087357A (en) | Scan orientation method, apparatus, computer equipment and computer readable storage medium | |
WO2023188671A1 (en) | Inspection assistance system, inspection assistance method, and inspection assistance program | |
CN109740458B (en) | Method and system for measuring physical characteristics based on video processing | |
CN114187252B (en) | Image processing method and device, and method and device for adjusting detection frame | |
CN113298784B (en) | Bone fracture line extraction and mapping method based on visual angle | |
Kashihara | An intelligent computer assistance system for artifact restoration based on genetic algorithms with plane image features | |
JPH09204532A (en) | Image recognition method and image display method | |
Cheng et al. | Ground truth delineation for medical image segmentation based on Local Consistency and Distribution Map analysis | |
Villa-Uriol et al. | Automatic creation of three-dimensional avatars | |
CN107451610B (en) | Image detection method for improving feature matching precision |
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 |