CN115534567A - Preparation method of high-precision simulated figure sculpture - Google Patents
Preparation method of high-precision simulated figure sculpture Download PDFInfo
- Publication number
- CN115534567A CN115534567A CN202211261704.5A CN202211261704A CN115534567A CN 115534567 A CN115534567 A CN 115534567A CN 202211261704 A CN202211261704 A CN 202211261704A CN 115534567 A CN115534567 A CN 115534567A
- Authority
- CN
- China
- Prior art keywords
- sculpture
- outline
- dimensional
- standard
- mold
- 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.)
- Pending
Links
- 238000002360 preparation method Methods 0.000 title abstract description 15
- 238000010146 3D printing Methods 0.000 claims abstract description 32
- 238000000034 method Methods 0.000 claims abstract description 24
- 238000004519 manufacturing process Methods 0.000 claims abstract description 10
- 102000002067 Protein Subunits Human genes 0.000 claims abstract description 7
- 108010001267 Protein Subunits Proteins 0.000 claims abstract description 7
- 238000012545 processing Methods 0.000 claims abstract description 7
- 238000000465 moulding Methods 0.000 claims abstract description 5
- 238000004040 coloring Methods 0.000 claims abstract description 4
- 239000002994 raw material Substances 0.000 claims abstract description 4
- 238000001514 detection method Methods 0.000 claims description 41
- 238000011176 pooling Methods 0.000 claims description 9
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 238000005498 polishing Methods 0.000 claims description 4
- 230000001680 brushing effect Effects 0.000 claims description 2
- 238000004088 simulation Methods 0.000 abstract description 8
- 238000011031 large-scale manufacturing process Methods 0.000 abstract description 3
- 239000000463 material Substances 0.000 description 9
- 230000036544 posture Effects 0.000 description 8
- 229910052602 gypsum Inorganic materials 0.000 description 7
- 239000010440 gypsum Substances 0.000 description 7
- 238000007639 printing Methods 0.000 description 6
- 230000009286 beneficial effect Effects 0.000 description 5
- 239000011159 matrix material Substances 0.000 description 5
- 239000003795 chemical substances by application Substances 0.000 description 4
- 239000004927 clay Substances 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 239000002002 slurry Substances 0.000 description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 2
- VYPSYNLAJGMNEJ-UHFFFAOYSA-N Silicium dioxide Chemical compound O=[Si]=O VYPSYNLAJGMNEJ-UHFFFAOYSA-N 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 239000000919 ceramic Substances 0.000 description 2
- 238000012512 characterization method Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 229910052802 copper Inorganic materials 0.000 description 2
- 239000010949 copper Substances 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 238000005520 cutting process Methods 0.000 description 2
- 230000001066 destructive effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- AEQDJSLRWYMAQI-UHFFFAOYSA-N 2,3,9,10-tetramethoxy-6,8,13,13a-tetrahydro-5H-isoquinolino[2,1-b]isoquinoline Chemical compound C1CN2CC(C(=C(OC)C=C3)OC)=C3CC2C2=C1C=C(OC)C(OC)=C2 AEQDJSLRWYMAQI-UHFFFAOYSA-N 0.000 description 1
- 239000006004 Quartz sand Substances 0.000 description 1
- 239000003513 alkali Substances 0.000 description 1
- 239000004411 aluminium Substances 0.000 description 1
- 229910052782 aluminium Inorganic materials 0.000 description 1
- XAGFODPZIPBFFR-UHFFFAOYSA-N aluminium Chemical compound [Al] XAGFODPZIPBFFR-UHFFFAOYSA-N 0.000 description 1
- 238000005452 bending Methods 0.000 description 1
- 239000004568 cement Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 239000011152 fibreglass Substances 0.000 description 1
- 238000010304 firing Methods 0.000 description 1
- 239000010977 jade Substances 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 229910052751 metal Inorganic materials 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 239000004033 plastic Substances 0.000 description 1
- 229920003023 plastic Polymers 0.000 description 1
- 239000000843 powder Substances 0.000 description 1
- 239000011347 resin Substances 0.000 description 1
- 229920005989 resin Polymers 0.000 description 1
- -1 sandstone Chemical compound 0.000 description 1
- 229940005574 sodium gluconate Drugs 0.000 description 1
- 235000012207 sodium gluconate Nutrition 0.000 description 1
- 239000000176 sodium gluconate Substances 0.000 description 1
- 239000004575 stone Substances 0.000 description 1
- 239000002023 wood Substances 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B44—DECORATIVE ARTS
- B44C—PRODUCING DECORATIVE EFFECTS; MOSAICS; TARSIA WORK; PAPERHANGING
- B44C3/00—Processes, not specifically provided for elsewhere, for producing ornamental structures
- B44C3/04—Modelling plastic materials, e.g. clay
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B44—DECORATIVE ARTS
- B44C—PRODUCING DECORATIVE EFFECTS; MOSAICS; TARSIA WORK; PAPERHANGING
- B44C3/00—Processes, not specifically provided for elsewhere, for producing ornamental structures
- B44C3/06—Sculpturing
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B44—DECORATIVE ARTS
- B44C—PRODUCING DECORATIVE EFFECTS; MOSAICS; TARSIA WORK; PAPERHANGING
- B44C5/00—Processes for producing special ornamental bodies
-
- 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
-
- 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
- G06T17/30—Polynomial surface description
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- Computer Graphics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- Chemical & Material Sciences (AREA)
- Dispersion Chemistry (AREA)
- Algebra (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Mathematical Physics (AREA)
- Pure & Applied Mathematics (AREA)
- Image Processing (AREA)
Abstract
The invention relates to a preparation method of a high-precision simulated figure sculpture, which belongs to the technical field of sculpture manufacturing, and can construct a mould model according to a contour picture of a figure sculpture to be prepared so as to prepare a sculpture model, so that the large-scale production is facilitated while the simulation precision of the figure sculpture is improved; the method comprises the following steps: s1, obtaining pictures of the same person, the same posture and a plurality of directions; s2, respectively carrying out image processing on the obtained pictures to obtain a two-dimensional outline of a figure sculpture target in each picture; s3, correlating the two-dimensional outlines of all the figure sculpture targets to obtain a three-dimensional outline of the figure sculpture targets; s4, constructing a mould model by taking the obtained three-dimensional outline of the character sculpture target as an inner outline; s5, preparing a mold in a 3D printing mode according to the constructed mold model; s6, injecting a sculpture raw material into the inner cavity of the mold, and demolding after molding to obtain a sculpture protomer; and S7, coloring the sculpture protomer to obtain the final sculpture.
Description
Technical Field
The invention relates to the technical field of sculpture manufacturing, in particular to a preparation method of a high-precision simulated figure sculpture.
Background
Sculptures are important components of the traditional Chinese culture art, and have a long history. Especially human sculptures are most common. Sculpture is also called carving, which is a general name of three creating methods of carving, carving and moulding. The artistic picture is made of various plastic materials (such as gypsum, resin, clay, etc.) or hard materials (such as wood, stone, metal, jade block, agate, aluminium, glass fiber reinforced plastic, sandstone, copper, etc.) which can be carved and carved, and has a certain space and can be seen and touched, thereby reflecting the social life, expressing the aesthetic feeling, aesthetic feeling and aesthetic ideal art of artists.
The existing traditional sculpture process is based on clay sculpture, and needs to prepare clay sculpture small manuscripts firstly and then carve formal sculptures according to the small manuscripts so as to avoid losing direction in the manufacturing process. But later, the sculpture often needs to be repeatedly trimmed to obtain a more simulated character sculpture. The method is time-consuming and labor-consuming, and is not enough in simulation degree and not beneficial to large-scale development.
Along with the development of 3D printing technique, the sculpture field has also existed the mode of printing the sculpture with 3D printing technique, but this kind of mode does not have the advantage when large-scale volume production, and because 3D printing technique's restriction itself, the precision of its personage sculpture of printing out is not very good, often need carry out certain sculpture again and polish to each finished product sculpture and just can obtain qualified sculpture. In addition, the 3D modeling often requires destructive cutting of an existing sculpture, or also requires preparation of a small manuscript and then destructive cutting modeling, which is inconvenient.
Accordingly, there is a need to develop a method of manufacturing a high-precision simulated human sculpture that addresses the deficiencies of the prior art to solve or mitigate one or more of the problems set forth above.
Disclosure of Invention
In view of the above, the invention provides a method for preparing a high-precision simulated human sculpture, which can construct a mold model according to a contour picture of a human sculpture to be prepared, so as to prepare a sculpture model, and is convenient for large-scale production while improving the simulation precision of the human sculpture.
The invention provides a preparation method of a high-precision simulated figure sculpture, which comprises the following steps:
s1, obtaining pictures of the same person in the same posture and in a plurality of directions;
s2, respectively carrying out image processing on the obtained pictures to obtain a two-dimensional outline of a figure sculpture target in each picture;
s3, correlating the two-dimensional outlines of all the figure sculpture targets to obtain a three-dimensional outline of the figure sculpture targets;
s4, constructing a mould model by taking the obtained three-dimensional outline of the character sculpture target as an inner outline;
s5, preparing a mold by adopting a 3D printing mode according to the constructed mold model;
s6, injecting a sculpture raw material into the inner cavity of the mold, and demolding after molding to obtain a sculpture protomer;
and S7, coloring the sculpture protomer to obtain the final sculpture.
The above-described aspect and any possible implementation manner further provide an implementation manner, and the content of step S1 includes:
s1.1, shooting the same character target in the same posture in a surrounding mode, and selecting more than eight pictures with different angles as original pictures;
s1.2, detecting the original picture by adopting a contour detection model to obtain two-dimensional figure sculpture contours on all the original pictures;
and S1.3, associating all the obtained two-dimensional figure sculpture outlines by adopting a coordinate conversion mode to obtain a three-dimensional figure sculpture outline.
The above-described aspects and any possible implementations further provide an implementation in which the contour detection model includes:
the detection submodules are sequentially connected and are used for obtaining a two-dimensional figure sculpture outline on an original picture;
the comparison module is internally provided with a standard picture database and is used for comparing the obtained two-dimensional figure sculpture outline with a standard picture in the standard picture database, judging whether the figure sculpture outline belongs to the figure sculpture outline or not and finding a standard picture group with the highest similarity;
the standard picture database comprises a plurality of groups of standard picture groups, wherein each standard picture group is sculptured for the same person and comprises more than eight directions of profile data including right front, right back, right left, right front 45 degrees, left back 45 degrees and right back 45 degrees.
The above-described aspect and any possible implementation manner further provide an implementation manner, where each of the detection submodules includes six convolution units connected in sequence and a pooling unit disposed after the sixth convolution unit; the input end of the pooling unit is connected with the output end of the sixth convolution unit; the output end of the first convolution unit is also connected with the input end of the fifth convolution unit;
the output end of the pooling unit of the previous detection sub-module is connected with the input end of the first convolution unit of the next detection sub-module;
the number of the output characteristic graphs of each detection submodule is 30.
As for the above-described aspect and any possible implementation, there is further provided an implementation, where the step S1.3 includes:
s1.3.1 selecting the profile data in the four directions of right front, right back, right left and right from the corresponding standard picture group, and taking the four profile data as a standard coordinate system;
s1.3.2, selecting a plurality of important points from each selected standard picture as standard reference points;
s1.3.3 selecting a plurality of same important points from each original picture as actual reference points;
s1.3.4, obtaining the difference value coordinate of each original picture relative to the standard coordinate system according to the coordinate data of the actual reference point and the coordinate data of the standard reference point;
s1.3.5, traversing pixel points of the two-dimensional figure sculpture outline in each original picture, and obtaining coordinate data mapped to a standard coordinate system according to corresponding differential coordinates, thereby realizing the association of all the two-dimensional figure sculpture outlines and obtaining the three-dimensional outline of the figure sculpture.
The above-described aspect and any possible implementation manner further provide an implementation manner, and the content of step S4 includes:
s4.1, taking the obtained three-dimensional outline of the character sculpture target as an inner outline, and obtaining an outer outline of the mold according to the inner outline and the thickness of the mold;
s4.2, constructing a 3D printing model of the mold according to the inner contour and the outer contour;
the 3D printing model comprises a first 3D printing model and a second 3D printing model which are divided into a front part and a rear part or a left part and a right part.
As with the above-described aspect and any possible implementation, there is further provided an implementation in which the thickness of the mold in step S4.1 is of equal thickness.
As with the above-described aspect and any possible implementation, there is further provided an implementation in which the outer contour in step S4.1 is shaped like a corresponding figure sculpture or cube.
The above-described aspect and any possible implementation manner further provide an implementation manner, and the content of step S5 includes: respectively importing the first 3D printing model and the second 3D printing model into a 3D printer; and the 3D printer respectively prints and prepares a first mold half structure and a second mold half structure according to the 3D printing model.
The above-mentioned aspect and any possible implementation manner further provide an implementation manner, and the content of step S5 further includes: and (3) polishing and/or brushing a release agent on the inner walls of the manufactured first mold half structure and the second mold half structure.
In the above aspects and any possible implementation manners, an implementation manner is further provided, in which a standard picture that meets the requirements of the standard database is selected from all the original pictures and added to the standard database as a new standard picture group;
the meeting requirement means that: a group of pictures including eight pictures of the four-direction pictures overlapping with the standard coordinate system and the four-direction pictures whose difference coordinates satisfy 45 °.
Compared with the prior art, one of the technical schemes has the following advantages or beneficial effects: the invention can construct the three-dimensional outline of the character sculpture through the picture data of the character sculpture to be prepared, and the mould is printed by taking the three-dimensional outline as the inner outline in a 3D way, so that the character sculpture is prepared by pouring sculpture feed liquid into the inner cavity of the mould, and the preparation method can greatly improve the simulation precision of the character sculpture and is convenient for large-scale production;
another technical scheme among the above-mentioned technical scheme has following advantage or beneficial effect: the invention integrates the two-dimensional outlines of the figure sculpture in different directions by setting a standard coordinate system to form the three-dimensional outline of the figure sculpture, and the processing mode has ingenious conception, is simple and reliable, has small calculated amount under the condition of obtaining high-precision simulation effect, and is beneficial to improving the processing speed;
another technical scheme in the above technical scheme has the following advantages or beneficial effects: according to the sculpture preparation method, when a favorite sculpture or figure scene is met and the preparation of a sculpture thumbnail is inconvenient, the subsequent mould preparation and the sculpture preparation can be realized only by adopting a simple photographing or video recording mode to obtain initial data, so that the work of sculpture practitioners is greatly facilitated; the preparation method can simulate the original sculpture or scene with high precision, and the simulation precision is far higher than that of the traditional clay sculpture sample; compared with the traditional yolo network, the improved contour detection model can better detect the two-dimensional contour in the picture and further improve the simulation precision of the sculpture.
Of course, it is not necessary for any one product in which the invention is practiced to achieve all of the above-described technical effects simultaneously.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a flowchart of a method for manufacturing a high-precision simulated human sculpture according to an embodiment of the present invention.
Detailed Description
For better understanding of the technical solutions of the present invention, the following detailed descriptions of the embodiments of the present invention are provided with reference to the accompanying drawings.
It should be understood that the described embodiments are only some embodiments of the invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Aiming at the defects of the prior art, the invention provides a preparation method of a high-precision simulated figure sculpture, which comprises the following steps:
step 1, character outline simulation:
processing images in four directions, eight directions or more directions under the same posture of the same person to obtain a two-dimensional contour of a humanoid target in each picture, correlating the two-dimensional contours of the humanoid target in the four, eight or more pictures, and mainly realizing the correlation of contour coordinates among the pictures by adopting a coordinate conversion mode to obtain a three-dimensional contour of the humanoid target;
the specific content of the step comprises:
1.1, aiming at the same humanoid target in the same posture, performing circumferential shooting, selecting more than eight pictures from the pictures as original pictures for standby, and selecting more than eight pictures from different directions respectively so as to ensure that the pictures can better reflect the whole circumferential profile of the humanoid target;
1.2, carrying out contour detection on each picture to obtain a two-dimensional figure sculpture contour on the corresponding picture;
the step is realized by adopting a contour detection model, and the contour detection model is realized by adopting an improved yolo network structure. The structure comprises 10 detection submodules which are connected in sequence, each detection submodule comprises six convolution units which are connected in sequence and a pooling unit arranged behind the sixth convolution unit (the input end of the pooling unit is connected with the output end of the sixth convolution unit), and the output end of the first convolution unit is also connected with the input end of the fifth convolution unit. In two adjacent detection submodules, the output end of the pooling unit of the previous detection submodule is connected with the input end of the first convolution unit of the next detection submodule. The number of characteristic graphs output by each layer of detection sub-modules is 30, which is far less than that of the traditional 128-256 characteristic graphs, so that the detection efficiency can be improved, and the problem of low detection speed caused by increasing the number of detection sub-modules is solved. Compared with 3 or 5 detection sub-modules, the 10-layer detection sub-modules can show more excellent detection effect in the process of detecting the contour of a complex picture; experiments prove that the same training and testing are respectively carried out on the detection networks of the 3-layer, the 5-layer and the 10-layer by adopting the same 1000 groups of training data sets and 100 groups of testing data sets, and the detection accuracy of the detection network of the 10-layer to the human-shaped contour is more than 99.5 percent and is obviously higher than that of the detection network of the 3-layer and the 5-layer. In addition, the feature data processed by the 10 layers of detection sub-modules is enough for subsequent use, and the feature data is directly output without being processed by a feature enhancement processing module of the traditional yolo network structure.
The contour detection model comprises the improved yolo network structure and a comparison module, wherein a plurality of standard contours are stored in the comparison module, the detected contours are compared with the standard contours in a standard library, and whether the contours are human-shaped sculpture contours is judged. The standard profile is a human-shaped sculpture profile with different clothes, different postures and different angles. Different clothes specifically comprise trousers, various skirts, various antiques and other clothes types commonly used for sculpture; the different postures specifically comprise standing, sitting, bending, various semi-lying, squatting and standing postures which are commonly used by sculptures; different angles include front, back, left, right, front left, front right, back left, back right and other angles located in the middle of any two adjacent angles of the above eight angles, included angles between two adjacent angles are the same, and the sum of all included angles is 360 degrees. And the contour diagrams of all directions corresponding to the same humanoid target in the same posture of the same garment are used as a group of standard contours.
And detecting and comparing the outline of the outline detection model to obtain the two-dimensional human-shaped outline.
It should be noted that although the improved yolo network structure is used in the contour detection model of the present invention, this does not mean that other contour detection algorithms cannot be used, and as long as a contour detection structure with higher accuracy can be implemented on the sculpture target in the picture and contour data can be obtained, the contour detection model can be applied to the present invention in principle, and there is no problem in connection with the subsequent construction of the three-dimensional contour.
1.3, correlating the detected two-dimensional humanoid outline to obtain a three-dimensional outline of the humanoid target;
the invention mainly adopts a coordinate conversion mode to realize the association of the outline coordinates between the pictures.
Firstly, selecting contour diagrams in four directions of front, back, left and right from a standard contour group corresponding to the two-dimensional humanoid contour, and taking the four contour diagrams as standard coordinates;
when the standard contour group is selected, because the clothes action of the human-shaped target is not completely consistent with the pictures in the standard library, slight difference may exist, and the standard contour pictures compared with the contours at different angles are not always the same, four pictures in front of, behind, on the left of and on the right of one group of standard contours where the associated standard contours with the most occurrence times are located are selected as the standard coordinate picture group, namely the picture group formed by the pictures in four aspects in one group of standard contour groups with the most comparison times; or selecting front, back, left and right pictures in a standard contour group corresponding to the standard contour with the maximum similarity as a standard coordinate picture group.
Secondly, selecting several important points in each standard coordinate picture as standard reference points;
thirdly, comparing the same important points in the profile picture to be associated with the corresponding standard reference points in the standard coordinate picture to obtain difference value coordinates between the important points and the standard coordinates;
and finally, constructing the three-dimensional profile of the humanoid target according to the plurality of difference coordinates, the four standard coordinates and the plurality of two-dimensional humanoid profile data obtained in the previous step.
Let f (x, y) be the standard image, and g (u, v) be the image to be associated, i.e. the two-dimensional contour image corresponding to the original image. Wherein (x, y) and (u, v) respectively represent the coordinates of the pixel points at the same position in the standard image and the two-dimensional profile, and because of the distortion between the two, the two groups of coordinates are no longer equal, and the two groups of coordinates can be converted by a nonlinear transformation, namely:
(x,y)＝T[(u,v)]；
expressed in polynomial form is:
wherein a is ij ,b ij Is the undetermined coefficient and n is the degree of the polynomial. The coefficients of the polynomial are fitted using the coordinates of the known reference point pairs, and the resulting polynomial is used to recover other distortion points. The accuracy of the correction is related to the degree of the correction polynomial employed, with higher polynomial degrees being more accurate. However, as the degree of the polynomial increases, the number of coefficients increases accordingly, resulting in a drastic increase in the amount of calculation. When n =1, the amount of calculation is small, but only linear distortion can be characterized; when n =2, most geometric distortion can be represented, and the direction representation requirements of the two-dimensional profile image and the standard image can be met, so that a quadratic polynomial can be selected to represent the geometric distortionThe two-dimensional contour image of (1). The quadratic polynomial of the spatial coordinate transformation is then expressed as:
when fitting the polynomial using the reference point coordinate pairs, the sum of squares of the fitting errors for the x-axis and the y-axis is expressed as:
the sum of the squares of the fitting errors in the above formula should be minimized, i.e., ε in the formula x And ε y And is minimal. Wherein, L is the number of the reference point pairs.
When epsilon x And ε y At minimum, then there is a partial differential equation of 0, i.e.:
wherein n =0,1,2; m =0,1,2-n. The method further comprises the following steps:
the above formula can be expressed in a matrix manner as follows:
wherein:
the characterization coefficient matrix a, B is represented as:
A＝[a 00 a 01 a 02 a 10 a 11 a 20 ] T
B＝[b 00 b 01 b 02 b 10 b 11 b 20 ] T
from the coordinates of the reference point pairs, T, X, Y can be calculated. According to the operation rule of the matrix, the following formula can be obtained:
the quadratic polynomial in this embodiment has 12 unknowns in total, so at least 6 reference points need to be selected. The reference points are selected from the positions of side points, corner points and inflection points with obvious characteristics or large gray level difference. The method for selecting the reference point in the embodiment comprises the following steps: carrying out linear scanning on the binarized image of the standard image and the binarized image of the two-dimensional outline image, scanning upwards from the lower left corner of the image by using a straight line with the slope of-1, wherein the first pixel point tangent to the image is a reference point 2, and the last intersected pixel point is a reference point 6; scanning upwards from the lower right corner of the image by using a straight line with the slope of 1, wherein the first pixel point tangent to the image is a reference point 1, and the last intersected pixel point is a reference point 3; scanning downwards from the upper left corner of the image by using a straight line with the slope of 0.75, wherein the first pixel point tangent to the image is a reference point 4; the line with a slope of-0.75 is used to scan down from the top right corner of the image, with the first pixel point tangent to the image being the reference point 5. Thereby obtaining 6 reference point coordinates in each of the two images of the standard image and the two-dimensional outline image, namely 6 sets of reference coordinate pairs. And respectively substituting the coordinates of the reference points in the standard image and the two-dimensional contour image into the matrix T and the formula 1, solving the characterization coefficient matrixes A and B in a mode of solving the inverse of the matrix, and further obtaining the difference value coordinates of the two images.
Because the four standard pictures are in four directions of front, back, left and right, and the coordinate relation of the pixel points in the four pictures is determined in a known way, the difference value coordinate between a certain two-dimensional contour picture and a certain standard picture is obtained, and each pixel point in the two-dimensional contour picture can be mapped into a three-dimensional standard coordinate system.
During construction, because the two-dimensional humanoid outline and the standard outline are most likely to have the outline difference, all pixel points on the two-dimensional humanoid outline are mapped into the standard coordinate system in a traversal mode.
Step 2, 3D modeling:
constructing a 3D printing model of the mold meeting the size requirement according to the inner shape of the obtained three-dimensional profile of the humanoid target; the 3D printing model comprises a first 3D printing model and a second 3D printing model, wherein the first 3D printing model and the second 3D printing model respectively represent half of the three-dimensional outline of the humanoid target, and the first 3D printing model and the second 3D printing model are combined to form the mold printing model of the whole humanoid target three-dimensional outline.
The mould can be of a specific thickness, namely the same thickness, the outer contour of the mould is the same as the three-dimensional contour of the humanoid target, and the mould can also be of a non-uniform thickness, so that the outer contour is of a specific shape, such as a cube.
When constructing the equal thickness model: the method comprises the steps of collecting coordinate data of a current contour point and coordinate data of n contour points before and after the current contour point, determining the degree of tangency of the current contour point according to the coordinate data, and determining the coordinate data of a corresponding outer contour according to the degree of tangency and the thickness of a mold to be constructed. This is done for all contour points of the inner contour, so that coordinate data of the entire outer contour of the mold is obtained, and the 3D printing model to be constructed is obtained from the coordinate data of the inner and outer contours.
Step 3, manufacturing a die:
and importing the data of the two printing models constructed in the last step into a 3D printer, and respectively printing two mold half structures meeting the size requirement by the 3D printer according to the coordinate data required by printing obtained from the 3D printing models.
Polishing the inner wall of the finished mould to make the inner wall of the mould smoother; after polishing, the thin one-layer isolating agent is sprayed on the inner wall, the material of the isolating agent is determined according to the material of the mold and the material of the sculpture, or the isolating agent can not be used, the aim is to ensure that the inner wall of the mold can not be adhered to the sculpture material, and the demolding is convenient, so that the yield of the preparation of the sculpture is improved.
When the material of the mold is ceramic, a high-temperature firing step is added to obtain the ceramic mold. The material of the mold may also be other materials that can be used for 3D printing and meet the requirements of subsequent mold preparation, and the present invention is not limited to this.
When the mold is prepared by using the 3D printing technology, the size of the mold can be adjusted as required, so that the sculpture meeting the size requirement is prepared.
Step 4, manufacturing the sculpture:
pouring the sculpture raw materials, such as cement slurry or molten copper or gypsum water slurry, into a mold combined together, and demolding after molding to obtain the proto-sculpture to be obtained.
The gypsum water slurry is a mixture of gypsum and water, the gypsum being a gypsum mixture comprising: 77 parts by mass of gypsum powder, 22 parts by mass of quartz sand, 0.5 part by mass of sodium gluconate and 0.5 part by mass of alkali fiber.
And 5, coloring the sculpture protomer to obtain the final simulated character sculpture.
The above details describe the method for manufacturing a high-precision simulated human sculpture according to the embodiment of the present application. The above description of the embodiments is only for the purpose of helping to understand the method of the present application and its core ideas; meanwhile, for a person skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.
Claims (10)
1. A method for preparing a high-precision simulated character sculpture is characterized by comprising the following steps:
s1, obtaining pictures of a character sculpture to be prepared in a plurality of directions;
s2, respectively carrying out image processing on the obtained pictures to obtain a two-dimensional outline of a figure sculpture target in each picture;
s3, correlating the two-dimensional outlines of all the figure sculpture targets to obtain a three-dimensional outline of the figure sculpture target;
s4, constructing a mould model by taking the obtained three-dimensional outline of the character sculpture target as an inner outline;
s5, preparing a mold in a 3D printing mode according to the constructed mold model;
s6, injecting a sculpture raw material into the inner cavity of the mold, and demolding after molding to obtain a sculpture protomer;
and S7, coloring the sculpture protomer to obtain the final sculpture.
2. The method for preparing a high-precision simulated human sculpture according to claim 1, wherein the content of the step S1 includes:
s1.1, shooting the same character target in the same posture in a surrounding mode, and selecting more than eight pictures with different angles as original pictures;
s1.2, detecting the original picture by adopting a contour detection model to obtain two-dimensional figure sculpture contours on all the original pictures;
and S1.3, associating all the obtained two-dimensional figure sculpture outlines by adopting a coordinate conversion mode to obtain a three-dimensional figure sculpture outline.
3. The method of manufacturing a high-precision artificial human sculpture according to claim 2, wherein said contour detection model includes:
the detection submodules are sequentially connected and are used for obtaining a two-dimensional figure sculpture outline on an original picture;
the comparison module is internally provided with a standard picture database and is used for comparing the obtained two-dimensional figure sculpture outline with a standard picture in the standard picture database, judging whether the figure sculpture outline belongs to the figure sculpture outline or not and finding a standard picture group with the highest similarity;
the standard picture database comprises a plurality of standard picture groups, each standard picture group is sculptured for the same person and comprises more than eight directions of profile data including right front, right back, right left, right front, left front 45 degrees, right front 45 degrees, left back 45 degrees and right back 45 degrees.
4. The method for preparing a high-precision simulated human sculpture according to claim 3, wherein each of said detection submodules comprises six convolution units and a pooling unit disposed behind the sixth convolution unit, which are connected in sequence; the input end of the pooling unit is connected with the output end of the sixth convolution unit; the output end of the first convolution unit is also connected with the input end of the fifth convolution unit;
the output end of the pooling unit of the previous detection sub-module is connected with the input end of the first convolution unit of the next detection sub-module;
the number of the output characteristic graphs of each detection submodule is 30.
5. The method for preparing a high-precision simulated human sculpture according to claim 3, wherein the step of step S1.3 includes:
s1.3.1 selecting the profile data in the four directions of right front, right back, right left and right from the corresponding standard picture group, and taking the four profile data as a standard coordinate system;
s1.3.2, selecting a plurality of important points from each selected standard picture as standard reference points;
s1.3.3, selecting a plurality of same important points in each original picture as actual reference points;
s1.3.4, obtaining the difference value coordinate of each original picture relative to the standard coordinate system according to the coordinate data of the actual reference point and the coordinate data of the standard reference point;
s1.3.5, traversing pixel points of the two-dimensional figure sculpture outline in each original picture, and obtaining coordinate data mapped to a standard coordinate system according to corresponding differential coordinates, thereby realizing the association of all the two-dimensional figure sculpture outlines and obtaining the three-dimensional outline of the figure sculpture.
6. The method for preparing a high-precision simulated human sculpture according to claim 1, wherein the content of the step S4 includes:
s4.1, taking the obtained three-dimensional outline of the character sculpture target as an inner outline, and obtaining an outer outline of the mold according to the inner outline and the thickness of the mold;
s4.2, constructing a 3D printing model of the mold according to the inner contour and the outer contour;
the 3D printing model comprises a first 3D printing model and a second 3D printing model which are divided into a front part and a rear part or a left part and a right part.
7. The method for preparing a high-precision artificial human sculpture according to claim 6, wherein the thickness of the mold in step S4.1 is equal.
8. The method for preparing a high-precision simulated human sculpture according to claim 6, wherein the outer contour in step S4.1 is in the shape of a corresponding human sculpture or cube.
9. The method for preparing a high-precision simulated human sculpture according to claim 6, wherein the content of the step S5 includes: respectively importing the first 3D printing model and the second 3D printing model into a 3D printer; and the 3D printer respectively prints and prepares a first mold half structure and a second mold half structure according to the 3D printing model.
10. The method for preparing a high-precision simulated human sculpture according to claim 9, wherein the content of step S5 further includes: and (3) polishing the inner walls of the manufactured first mould half structure and the second mould half structure and/or brushing a separant.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211261704.5A CN115534567A (en) | 2022-10-14 | 2022-10-14 | Preparation method of high-precision simulated figure sculpture |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211261704.5A CN115534567A (en) | 2022-10-14 | 2022-10-14 | Preparation method of high-precision simulated figure sculpture |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115534567A true CN115534567A (en) | 2022-12-30 |
Family
ID=84734632
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211261704.5A Pending CN115534567A (en) | 2022-10-14 | 2022-10-14 | Preparation method of high-precision simulated figure sculpture |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115534567A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1482580A (en) * | 2002-09-15 | 2004-03-17 | �����з��ѿƼ�����˾ | Method for forming new three-dimensional model using a group of two-dimensional photos and three-dimensional library |
| CN101301161A (en) * | 2008-06-13 | 2008-11-12 | 贾凤忠 | Commemorate article with portrait and manufacture method thereof |
| CN101430798A (en) * | 2008-11-04 | 2009-05-13 | 曾文煌 | Three-dimensional colorful article production method |
| CN101786398A (en) * | 2010-04-01 | 2010-07-28 | 重庆大学 | Human body sculpture method through combination technology |
| KR20170090020A (en) * | 2016-01-27 | 2017-08-07 | 대진대학교 산학협력단 | System and method for manufacturing an ornament using converting 2-dimensional image to 3-dimensional image |
| US20200108655A1 (en) * | 2018-10-05 | 2020-04-09 | Lilah Jurgens | Method for Creating a Three-Dimensional Decorative Sculpture |
| CN112519470A (en) * | 2020-11-30 | 2021-03-19 | 华艺博展装饰有限公司 | Method for creating three-dimensional sculpture |
| CN115035267A (en) * | 2022-04-21 | 2022-09-09 | 武汉尉来科技有限责任公司 | Manufacturing method of large-scale sculpture digital 3D model |
-
2022
- 2022-10-14 CN CN202211261704.5A patent/CN115534567A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1482580A (en) * | 2002-09-15 | 2004-03-17 | �����з��ѿƼ�����˾ | Method for forming new three-dimensional model using a group of two-dimensional photos and three-dimensional library |
| CN101301161A (en) * | 2008-06-13 | 2008-11-12 | 贾凤忠 | Commemorate article with portrait and manufacture method thereof |
| CN101430798A (en) * | 2008-11-04 | 2009-05-13 | 曾文煌 | Three-dimensional colorful article production method |
| CN101786398A (en) * | 2010-04-01 | 2010-07-28 | 重庆大学 | Human body sculpture method through combination technology |
| KR20170090020A (en) * | 2016-01-27 | 2017-08-07 | 대진대학교 산학협력단 | System and method for manufacturing an ornament using converting 2-dimensional image to 3-dimensional image |
| US20200108655A1 (en) * | 2018-10-05 | 2020-04-09 | Lilah Jurgens | Method for Creating a Three-Dimensional Decorative Sculpture |
| CN112519470A (en) * | 2020-11-30 | 2021-03-19 | 华艺博展装饰有限公司 | Method for creating three-dimensional sculpture |
| CN115035267A (en) * | 2022-04-21 | 2022-09-09 | 武汉尉来科技有限责任公司 | Manufacturing method of large-scale sculpture digital 3D model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110757804B (en) | Full-color layered slicing algorithm based on texture mapping three-dimensional model | |
| CN104809755B (en) | Three-dimensional rebuilding method based on single image cultural relic ruins | |
| CN106846461B (en) | A kind of human body three-dimensional scan method | |
| CN109493422A (en) | A kind of substation's 3 D model construction method based on three-dimensional laser scanning technique | |
| CN105809733A (en) | SketchUp-based campus three-dimensional hand-drawn map construction method | |
| CN107730587A (en) | One kind is based on picture quick three-dimensional Interactive Modeling method | |
| CN110232738B (en) | Multi-view remote sensing image stereo reconstruction method based on disparity map and key points | |
| CN105205846A (en) | Water-and-ink animation production method | |
| CN104249221A (en) | Method of laser processing mold surface | |
| CN107564092A (en) | Method based on MATLAB according to picture quick Fabrication ceramic relief | |
| CN1814459A (en) | Method and device for making three-dimensional portrait | |
| CN104200525B (en) | Three-dimensional modeling method and system based on extrusion object images | |
| CN115534567A (en) | Preparation method of high-precision simulated figure sculpture | |
| CN110757806A (en) | 3D printing-oriented double-type-shape close-laying method and system | |
| CN107328371A (en) | Sub-pix contours extract based on Gaussian and the optimization using Softmax recurrence in the case where metal plate detects scene | |
| CN108724734A (en) | A kind of 3D printing pre-treatment hierarchical algorithm based on dense feature | |
| CN107856466A (en) | A kind of design method, mould and the flowerpot of Bark mark Mould for flower pot | |
| Xu et al. | Color 3D reverse engineering | |
| CN114781146A (en) | Ceramic product design system based on three-dimensional computer | |
| CN108763767A (en) | Big data quantity IGS industry pattern POLYGON conversion methods towards VR engines | |
| CN108712831A (en) | Back drill PCB crosssection micrographs are as technological parameter extracting method | |
| CN114049423A (en) | Automatic realistic three-dimensional model texture mapping method | |
| CN110176074B (en) | Quick modeling method for bas-relief model based on isogeometric matching method | |
| Lu | Modeling Design of Ceramic Products Based on Digital Image Processing Technology | |
| Furukawa et al. | Carved visual hulls for high-accuracy image-based modeling |
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 |