CN116342908A - Similarity matching search method and system based on geometric shape features of three-dimensional model - Google Patents
Similarity matching search method and system based on geometric shape features of three-dimensional model Download PDFInfo
- Publication number
- CN116342908A CN116342908A CN202310330609.4A CN202310330609A CN116342908A CN 116342908 A CN116342908 A CN 116342908A CN 202310330609 A CN202310330609 A CN 202310330609A CN 116342908 A CN116342908 A CN 116342908A
- Authority
- CN
- China
- Prior art keywords
- model
- feature
- similarity
- geometric
- dimensional model
- 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
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000000605 extraction Methods 0.000 claims abstract description 29
- 238000004364 calculation method Methods 0.000 claims abstract description 7
- 239000013598 vector Substances 0.000 claims description 16
- 230000005484 gravity Effects 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 4
- 238000011524 similarity measure Methods 0.000 description 3
- 238000012512 characterization method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/761—Proximity, similarity or dissimilarity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/51—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration using histogram techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
- G06V10/765—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects using rules for classification or partitioning the feature space
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/771—Feature selection, e.g. selecting representative features from a multi-dimensional feature space
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Computing Systems (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Image Analysis (AREA)
Abstract
The present disclosure provides a similarity matching search method and system based on geometric shape characteristics of a three-dimensional model, comprising: extracting features of the three-dimensional model to be searched by using a preset geometric feature extraction model to obtain geometric features of the model to be searched; calculating the similarity between the geometric shape features and a three-dimensional model in a pre-constructed feature index library based on the geometric shape features, and obtaining a model corresponding to the model to be searched based on a similarity calculation result; the feature index library stores a plurality of three-dimensional models and geometric feature extracted by a preset geometric feature extraction model corresponding to the three-dimensional models.
Description
Technical Field
The disclosure belongs to the technical field of three-dimensional model retrieval, and particularly relates to a similarity matching search method and system based on geometric shape characteristics of a three-dimensional model.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
With the development of computer software and hardware technology, three-dimensional models are widely applied in the fields of animation, machinery, medical treatment and the like, the number of the three-dimensional models is increased, and the three-dimensional model retrieval field also faces more challenges. At present, text searching is mostly used for searching a three-dimensional model, the method has poor performance and low matching degree, and the model searched according to the text is single in class and lacks diversity; there are also some methods that use image similarity to match and find out the corresponding model, if a single image feature is used, it often cannot well represent the external shape feature of the whole model, and a multi-view image is used to describe the model feature, so that the functional structure is complex and the cost is high; meanwhile, a method based on model geometric features exists, and the inventor discovers that most of the existing methods are to construct the similarity of the model by utilizing the point, side and surface data of the three-dimensional model, and the method can seriously influence the feature matching precision of the model under the condition that the number of the points, the sides and the surfaces of the model is different, namely, the fineness of the model is different.
Disclosure of Invention
In order to solve the problems, the present disclosure provides a similarity matching search method and system based on geometric shape features of a three-dimensional model, where the method uses a center of gravity of a plane in the model as a feature point of a triangular plane and a normal direction of the plane as a normal direction of the feature point, and classifies distances between the feature points by using a normal direction relationship between the feature points, thereby forming a histogram; in addition, a histogram is formed by utilizing the distance ratio between the feature points and the origin of the model, and the histogram is used as the feature of the three-dimensional model, so that the difference of concave-convex forms among the models can be effectively highlighted, the characterization accuracy of the extracted feature to the model is higher, and the accuracy of model searching can be further effectively improved.
According to a first aspect of the embodiments of the present disclosure, there is provided a similarity matching search method based on geometric shape features of a three-dimensional model, including:
extracting features of the three-dimensional model to be searched by using a preset geometric feature extraction model to obtain geometric features of the model to be searched;
calculating the similarity between the geometric shape features and a three-dimensional model in a pre-constructed feature index library based on the geometric shape features, and obtaining a model corresponding to the model to be searched based on a similarity calculation result;
wherein, the feature index library stores a plurality of three-dimensional models and geometric feature extracted by a preset geometric feature extraction model corresponding to the three-dimensional models; the geometric feature extraction model specifically performs the following processing procedures: acquiring point and surface data of a three-dimensional model; selecting a preset number of faces, and constructing a feature point set by taking the gravity center of each face as a feature point of the face; constructing a distance set based on the distances between every two feature points in the feature point set; calculating the distance ratio corresponding to every two feature points based on the distance from each feature point to the origin of the model, and constructing a distance ratio set; dividing the distance set and the distance ratio set into a plurality of subsets according to a preset rule, and forming a corresponding histogram for each subset; the obtained histogram and the number of elements in the subset are taken as the characteristics of the three-dimensional model.
Further, the dividing the distance set and the distance ratio set into a plurality of subsets according to a preset rule specifically includes: and calculating an included angle between a line segment formed by every two feature points in the feature point set and normal vectors of the two feature points, dividing the distance set and the distance ratio set into a plurality of subsets based on the included angle, and counting the number of elements in each subset.
Further, the calculating the included angle between the line segment formed by every two feature points in the feature point set and the normal vector of the two feature points specifically includes: for the characteristic points P1 and P2, calculating a first included angle between the line segment P1P2 and the normal vector of the characteristic point P1, and calculating a second included angle between the line segment P2P1 and the normal vector of the characteristic point P2; and dividing the distance set and the distance ratio set into subsets according to the first included angle and the second included angle and a preset angle threshold.
Further, the obtaining of the normal vector of the feature point specifically includes: the surface of the three-dimensional model adopts a triangular surface, the normal vector of the triangular surface is calculated based on three vertex data of the triangular surface, and the normal vector of the triangular surface is used as the normal vector of the corresponding characteristic point of the current triangular surface.
Further, for the distance ratio corresponding to every two feature points, when the distance ratio between two feature points is greater than 1, the reciprocal is taken as the final distance ratio.
Further, the calculating the similarity between the geometric shape feature and the three-dimensional model in the pre-constructed feature index library based on the geometric shape feature specifically comprises the following steps: calculating a similarity value of a histogram corresponding to a distance set in the model geometric shape features of the model to be searched and the model geometric shape features in the feature index library, and taking the similarity value as a first similarity; calculating a similarity value of a histogram corresponding to a distance ratio set in the geometric shape features of the model to be searched and the model in the feature index library, and taking the similarity value as a second similarity; and obtaining the final similarity through weighted summation of the first similarity and the second similarity.
Further, traversing all models in the feature index library, calculating the similarity between each model and the model to be searched, sorting the models from large to small based on the similarity, and selecting a preset number of models with the front sorting for display.
According to a second aspect of embodiments of the present disclosure, there is provided a similarity matching search system based on geometric features of a three-dimensional model, comprising:
the feature extraction unit is used for extracting features of the three-dimensional model to be searched by using a preset geometric feature extraction model to obtain geometric features of the model to be searched;
the model searching unit is used for calculating the similarity between the geometric shape characteristics and the three-dimensional model in the characteristic index library constructed in advance and obtaining a model corresponding to the model to be searched based on the similarity calculation result;
wherein, the feature index library stores a plurality of three-dimensional models and geometric feature extracted by a preset geometric feature extraction model corresponding to the three-dimensional models; the geometric feature extraction model specifically performs the following processing procedures: acquiring point and surface data of a three-dimensional model; selecting a preset number of faces, and constructing a feature point set by taking the gravity center of each face as a feature point of the face; constructing a distance set based on the distances between every two feature points in the feature point set; calculating the distance ratio corresponding to every two feature points based on the distance from each feature point to the origin of the model, and constructing a distance ratio set; dividing the distance set and the distance ratio set into a plurality of subsets according to a preset rule, and forming a corresponding histogram for each subset; the obtained histogram and the number of elements in the subset are taken as the characteristics of the three-dimensional model.
According to a third aspect of the embodiments of the present disclosure, there is provided an electronic device, including a memory, a processor, and a computer program running on the memory, where the processor implements the similarity matching search method based on geometric features of a three-dimensional model when executing the program.
According to a fourth aspect of embodiments of the present disclosure, there is provided a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the described similarity matching search method based on geometric features of a three-dimensional model.
Compared with the prior art, the beneficial effects of the present disclosure are:
(1) The scheme is characterized in that the difference of concave-convex forms between models is highlighted by utilizing normal information of a middle plane of a three-dimensional model and the distance ratio of a feature point to an origin of the model, so that the extracted model feature has higher accuracy; meanwhile, the gravity center of the surface in the model is used as a characteristic point of the triangular surface and the normal direction of the surface is used as the normal direction of the characteristic point, and the distance between the characteristic points is classified by utilizing the normal direction relation between every two characteristic points, so that a histogram is formed; and correspondingly, a histogram is formed by utilizing the distance ratio of the feature points to the origin of the model, and the histogram is used as the feature of the three-dimensional model together, so that the difference of concave-convex forms between the models can be effectively highlighted, the extracted feature has higher characterization accuracy on the model, and the accuracy of model searching can be further effectively improved.
(2) According to the scheme, matching search is performed based on the characteristics of the model, matching is performed according to the geometric shape characteristic information of the model, the matching degree is high, and the searched model diversity is not limited to a certain model; meanwhile, when the model feature library is created, view extraction of the model is not needed, and the method is simple to operate and low in cost.
Additional aspects of the disclosure will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the disclosure.
Drawings
The accompanying drawings, which are included to provide a further understanding of the disclosure, illustrate and explain the exemplary embodiments of the disclosure and together with the description serve to explain the disclosure, and do not constitute an undue limitation on the disclosure.
FIG. 1 is a process flow diagram of a method for performing a similarity matching search based on geometric features of a three-dimensional model according to an embodiment of the present disclosure;
fig. 2 is a feature extraction flow diagram of a geometric feature extraction model described in an embodiment of the disclosure.
Detailed Description
The disclosure is further described below with reference to the drawings and examples.
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the present disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments in accordance with the present disclosure. As used herein, the singular is also intended to include the plural unless the context clearly indicates otherwise, and furthermore, it is to be understood that the terms "comprises" and/or "comprising" when used in this specification are taken to specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof.
Embodiments of the present disclosure and features of embodiments may be combined with each other without conflict.
Embodiment one:
the embodiment aims to provide a similarity matching search method based on geometric shape characteristics of a three-dimensional model.
As shown in fig. 1, a similarity matching search method based on geometric shape features of a three-dimensional model includes:
extracting features of the three-dimensional model to be searched by using a preset geometric feature extraction model to obtain geometric features of the model to be searched;
calculating the similarity between the geometric shape features and a three-dimensional model in a pre-constructed feature index library based on the geometric shape features, and obtaining a model corresponding to the model to be searched based on a similarity calculation result;
wherein, the feature index library stores a plurality of three-dimensional models and geometric feature extracted by a preset geometric feature extraction model corresponding to the three-dimensional models; the geometric feature extraction model specifically performs the following processing procedures: acquiring point and surface data of a three-dimensional model; selecting a preset number of faces, and constructing a feature point set by taking the gravity center of each face as a feature point of the face; constructing a distance set based on the distances between every two feature points in the feature point set; calculating the distance ratio corresponding to every two feature points based on the distance from each feature point to the origin of the model, and constructing a distance ratio set; dividing the distance set and the distance ratio set into a plurality of subsets according to a preset rule, and forming a corresponding histogram for each subset; the obtained histogram and the number of elements in the subset are taken as the characteristics of the three-dimensional model.
In an implementation, as shown in fig. 2, the geometric feature extraction model specifically includes the following processing procedures:
step (1): reading a three-dimensional model file, and obtaining model point and surface (adopting triangular surface storage) data;
step (2): n faces are fixedly selected (can be set according to actual requirements), the gravity center of each triangular face is calculated and used as a characteristic point of the face, each triangular face is provided with three vertex data (P1 (x 1, y1, z 1), P2 (x 2, y2, z 3), P3 (x 3, y3, z 3)), P0=1/3 (P1+P2+P3), and P0 is used as the characteristic point of the face; constructing a three-dimensional model feature point set;
step (3): calculating Euclidean distance between every two feature points, e.g. feature point P0 (x 1 ,y 1 ,z 1 ),P1(x 2 ,y 2 ,z 2 ) The Euclidean distance between:
constructing a three-dimensional model distance set;
step (4): calculating the distance between each feature point P (x, y, z) and the origin (0, 0) of the model:
then calculate the pairwise distance ratio: r=l 1 /l 2 If R is>1, then: r=l 2 /l 1 The method comprises the steps of carrying out a first treatment on the surface of the Realizing the distance of a three-dimensional modelConstructing a ratio set;
step (5): dividing the distance set and the distance ratio set into a plurality of subsets according to a preset rule, wherein the distance set and the distance ratio set are specifically as follows:
step (6): and respectively calculating the included angles between the line segments formed by the characteristic points P1 and P2 and the normal directions n1 and n2 of the characteristic points, namely the cosine of the included angle between the directed line segments P1P2 and n 1: cos theta 1 ＝(P 1 P 2 ·n 1 )/(|P 1 P 2 |×|n 1 |) the angle cosine of the directed line segment P2P1 with n 2: cos theta 2 ＝(P 2 P 1 ·n 2 )/(|P 2 P 1 |×|n 2 |) is provided; θ in the formula 1 ，θ 2 The range of the angle is [0, pi ]]。
Step (7): according to theta 1 ，θ 2 The angle will be the line segment distance L, when 1 ，θ 2 The angles are all classified into one type when they are greater than pi/2, and the angles are all classified into one type when they are less than pi/2, and the rest are classified into one type. Three sets are ultimately formed: v (V) 1 ，V 2 ，V 3 And count the number W in each class 1 ,W 2 ,W 3 。
Step (8) classifying the distance ratio R as θ 1 ，θ 2 The angles are all classified into one type when they are greater than pi/2, and the angles are all classified into one type when they are less than pi/2, and the rest are classified into one type. Three sets are ultimately formed: q (Q) 1 ，Q 2 ，Q 33 And count the number W in each class 1 ,W 2 ,W 3 。
Step (9): first three sets of line segment distances V 1 ，V 2 ，V 3 Forming histograms respectively, wherein the maximum value in each set is max, the minimum value is min, the number of each histogram interval is fixed to 64, and the length unit of the horizontal axis of the histogram is as follows: bin= (max-min)/64,
step (10) three sets of ratios Q 1 ，Q 2 ，Q 3 Three histograms are also generated.
Step (11): will V 1 ，V 2 ，V 3 ，Q 1 ，Q 2 ，Q 3 Six sets ofSeparately generated histograms, and quantity W 1 ,W 2 ,W 3 The three values are used as the characteristic values of the three-dimensional model.
In specific implementation, extracting features of a model to be searched based on the geometric feature extraction model, and constructing a feature index library in advance based on the geometric feature extraction model; and then, by traversing the feature index library, carrying out similarity measurement between the model to be searched and each model feature in the feature index library, wherein the method specifically comprises the following steps:
step (1): three sets (V) of line segment distance sets for two comparison models (i.e., model 1 and model 2) 1 ，V 2 ，V 3 ) Histograms h1, h2 formed by the kth set of (b), similarity metrics:
the line segment is measured from the total similarity of the three histograms as the first similarity: v=α 1 d 1 +α 2 d 2 +α 3 d 3 Wherein alpha is 1 ，α 2 ，α 3 Weights of the corresponding sets of the two models respectively, wherein alpha 1 ＝(n 11 +n 21 )/2n，α 2 ＝(n 12 +n 22 )/2n，α 3 ＝(n 13 +n 23 )/2n。n ik Representing the number in the kth set of classes in the ith model. n is the total number of segments taken in each model.
Step (2): as above, the total similarity measure Q of the three histograms of ratios can be calculated as the second similarity.
Step (3): the similarity measure of the two models is obtained by weighted summation of the first similarity and the second similarity: d=0.7v+0.3q;
step (4): mapping the similarity measure to interval (0, 1), yielding: per=1/(1+d).
Step (5): traversing all characteristic values of a characteristic index library, and sorting from big to small based on per.
Step (6): the first n similar three-dimensional model IDs are selected.
Step (7): and finally, finding out a corresponding model in the model library according to the ID, and returning.
Embodiment two:
it is an object of the present embodiment to provide a similarity matching search system based on geometric features of a three-dimensional model.
A similarity matching search system based on geometric features of a three-dimensional model, comprising:
the feature extraction unit is used for extracting features of the three-dimensional model to be searched by using a preset geometric feature extraction model to obtain geometric features of the model to be searched;
the model searching unit is used for calculating the similarity between the geometric shape characteristics and the three-dimensional model in the characteristic index library constructed in advance and obtaining a model corresponding to the model to be searched based on the similarity calculation result;
wherein, the feature index library stores a plurality of three-dimensional models and geometric feature extracted by a preset geometric feature extraction model corresponding to the three-dimensional models; the geometric feature extraction model specifically performs the following processing procedures: acquiring point and surface data of a three-dimensional model; selecting a preset number of faces, and constructing a feature point set by taking the gravity center of each face as a feature point of the face; constructing a distance set based on the distances between every two feature points in the feature point set; calculating the distance ratio corresponding to every two feature points based on the distance from each feature point to the origin of the model, and constructing a distance ratio set; dividing the distance set and the distance ratio set into a plurality of subsets according to a preset rule, and forming a corresponding histogram for each subset; the obtained histogram and the number of elements in the subset are taken as the characteristics of the three-dimensional model.
Further, the system in this embodiment corresponds to the method in the first embodiment, and the specific details thereof have been described in the first embodiment, so that they will not be described herein.
In further embodiments, there is also provided:
an electronic device comprising a memory and a processor and computer instructions stored on the memory and running on the processor, which when executed by the processor, perform the method described in embodiment two. For brevity, the description is omitted here.
It should be understood that in this embodiment, the processor may be a central processing unit CPU, and the processor may also be other general purpose processors, digital signal processors DSP, application specific integrated circuits ASIC, off-the-shelf programmable gate array FPGA or other programmable logic device, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory may include read only memory and random access memory and provide instructions and data to the processor, and a portion of the memory may also include non-volatile random access memory. For example, the memory may also store information of the device type.
A computer readable storage medium storing computer instructions which, when executed by a processor, perform the method described in embodiment two.
The method in the second embodiment may be directly implemented as a hardware processor executing or implemented by a combination of hardware and software modules in the processor. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in a memory, and the processor reads the information in the memory and, in combination with its hardware, performs the steps of the above method. To avoid repetition, a detailed description is not provided herein.
Those of ordinary skill in the art will appreciate that the elements of the various examples described in connection with the present embodiments, i.e., the algorithm steps, can be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
The similarity matching search method and the system based on the geometric shape characteristics of the three-dimensional model can be realized, and have wide application prospects.
The foregoing description of the preferred embodiments of the present disclosure is provided only and not intended to limit the disclosure so that various modifications and changes may be made to the present disclosure by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present disclosure should be included in the protection scope of the present disclosure.
Claims (10)
1. The similarity matching search method based on the geometric shape characteristics of the three-dimensional model is characterized by comprising the following steps of:
extracting features of the three-dimensional model to be searched by using a preset geometric feature extraction model to obtain geometric features of the model to be searched;
calculating the similarity between the geometric shape features and a three-dimensional model in a pre-constructed feature index library based on the geometric shape features, and obtaining a model corresponding to the model to be searched based on a similarity calculation result;
wherein, the feature index library stores a plurality of three-dimensional models and geometric feature extracted by a preset geometric feature extraction model corresponding to the three-dimensional models; the geometric feature extraction model specifically performs the following processing procedures: acquiring point and surface data of a three-dimensional model; selecting a preset number of faces, and constructing a feature point set by taking the gravity center of each face as a feature point of the face; constructing a distance set based on the distances between every two feature points in the feature point set; calculating the distance ratio corresponding to every two feature points based on the distance from each feature point to the origin of the model, and constructing a distance ratio set; dividing the distance set and the distance ratio set into a plurality of subsets according to a preset rule, and forming a corresponding histogram for each subset; the obtained histogram and the number of elements in the subset are taken as the characteristics of the three-dimensional model.
2. The method for searching for similarity matching based on geometric shape features of three-dimensional model according to claim 1, wherein the distance set and the distance ratio set are divided into a plurality of subsets according to a preset rule, specifically: and calculating an included angle between a line segment formed by every two feature points in the feature point set and normal vectors of the two feature points, dividing the distance set and the distance ratio set into a plurality of subsets based on the included angle, and counting the number of elements in each subset.
3. The method for searching similarity matching based on geometric shape features of three-dimensional model according to claim 1, wherein the calculating the included angle between the line segment formed by every two feature points in the feature point set and the normal vector of two feature points is specifically as follows: for the characteristic points P1 and P2, calculating a first included angle between the line segment P1P2 and the normal vector of the characteristic point P1, and calculating a second included angle between the line segment P2P1 and the normal vector of the characteristic point P2; and dividing the distance set and the distance ratio set into subsets according to the first included angle and the second included angle and a preset angle threshold.
4. The similarity matching search method based on the geometric shape characteristics of the three-dimensional model according to claim 1, wherein the obtaining of the normal vector of the characteristic points is specifically as follows: the surface of the three-dimensional model adopts a triangular surface, the normal vector of the triangular surface is calculated based on three vertex data of the triangular surface, and the normal vector of the triangular surface is used as the normal vector of the corresponding characteristic point of the current triangular surface.
5. The method for searching for similarity matching based on geometric features of a three-dimensional model according to claim 1, wherein for the distance ratio corresponding to each of the feature points, when the distance ratio between the two feature points is greater than 1, the reciprocal thereof is taken as the final distance ratio.
6. The method for searching similarity matching based on geometric features of three-dimensional model according to claim 1, wherein the calculating the similarity between the geometric features and the three-dimensional model in the pre-constructed feature index library specifically comprises the following steps: calculating a similarity value of a histogram corresponding to a distance set in the model geometric shape features of the model to be searched and the model geometric shape features in the feature index library, and taking the similarity value as a first similarity; calculating a similarity value of a histogram corresponding to a distance ratio set in the geometric shape features of the model to be searched and the model in the feature index library, and taking the similarity value as a second similarity; and obtaining the final similarity through weighted summation of the first similarity and the second similarity.
7. The similarity matching search method based on the geometric shape features of the three-dimensional model according to claim 1, wherein all models in the feature index library are traversed, the similarity between each model and the model to be searched is calculated, the models are ranked from large to small based on the similarity, and a preset number of models with the front ranking are selected for display.
8. A similarity matching search system based on geometric features of a three-dimensional model, comprising:
the feature extraction unit is used for extracting features of the three-dimensional model to be searched by using a preset geometric feature extraction model to obtain geometric features of the model to be searched;
the model searching unit is used for calculating the similarity between the geometric shape characteristics and the three-dimensional model in the characteristic index library constructed in advance and obtaining a model corresponding to the model to be searched based on the similarity calculation result;
wherein, the feature index library stores a plurality of three-dimensional models and geometric feature extracted by a preset geometric feature extraction model corresponding to the three-dimensional models; the geometric feature extraction model specifically performs the following processing procedures: acquiring point and surface data of a three-dimensional model; selecting a preset number of faces, and constructing a feature point set by taking the gravity center of each face as a feature point of the face; constructing a distance set based on the distances between every two feature points in the feature point set; calculating the distance ratio corresponding to every two feature points based on the distance from each feature point to the origin of the model, and constructing a distance ratio set; dividing the distance set and the distance ratio set into a plurality of subsets according to a preset rule, and forming a corresponding histogram for each subset; the obtained histogram and the number of elements in the subset are taken as the characteristics of the three-dimensional model.
9. An electronic device comprising a memory, a processor and a computer program stored for execution on the memory, wherein the processor implements a similarity matching search method based on geometric features of a three-dimensional model as claimed in any one of claims 1-7 when executing the program.
10. A non-transitory computer readable storage medium having stored thereon a computer program, which when executed by a processor implements a similarity matching search method based on geometric features of a three-dimensional model as claimed in any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310330609.4A CN116342908A (en) | 2023-03-28 | 2023-03-28 | Similarity matching search method and system based on geometric shape features of three-dimensional model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310330609.4A CN116342908A (en) | 2023-03-28 | 2023-03-28 | Similarity matching search method and system based on geometric shape features of three-dimensional model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116342908A true CN116342908A (en) | 2023-06-27 |
Family
ID=86883786
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310330609.4A Pending CN116342908A (en) | 2023-03-28 | 2023-03-28 | Similarity matching search method and system based on geometric shape features of three-dimensional model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116342908A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116701698A (en) * | 2023-08-09 | 2023-09-05 | 北京凯锐远景科技有限公司 | Model retrieval method, device, medium and equipment based on vector retrieval technology |
-
2023
- 2023-03-28 CN CN202310330609.4A patent/CN116342908A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116701698A (en) * | 2023-08-09 | 2023-09-05 | 北京凯锐远景科技有限公司 | Model retrieval method, device, medium and equipment based on vector retrieval technology |
| CN116701698B (en) * | 2023-08-09 | 2023-10-17 | 北京凯锐远景科技有限公司 | Model retrieval method, device, medium and equipment based on vector retrieval technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Liu et al. | Efficient global 2d-3d matching for camera localization in a large-scale 3d map | |
| Yang et al. | Toward the repeatability and robustness of the local reference frame for 3D shape matching: An evaluation | |
| JP5705147B2 (en) | Representing 3D objects or objects using descriptors | |
| Wang et al. | MARCH: Multiscale-arch-height description for mobile retrieval of leaf images | |
| Houle et al. | Dimensional testing for multi-step similarity search | |
| CN111079785A (en) | Image identification method and device and terminal equipment | |
| CN109271441B (en) | High-dimensional data visual clustering analysis method and system | |
| Ion et al. | Matching 2D and 3D articulated shapes using the eccentricity transform | |
| CN114359042A (en) | Point cloud splicing method and device, three-dimensional scanner and electronic equipment | |
| CN109447100A (en) | A kind of three-dimensional point cloud recognition methods based on the detection of B-spline surface similitude | |
| CN116342908A (en) | Similarity matching search method and system based on geometric shape features of three-dimensional model | |
| US11321953B2 (en) | Method and apparatus for posture, dimension and shape measurements of objects in 3D scenes | |
| Pickup et al. | Euclidean-distance-based canonical forms for non-rigid 3D shape retrieval | |
| Wu et al. | A vision-based indoor positioning method with high accuracy and efficiency based on self-optimized-ordered visual vocabulary | |
| CN104850820A (en) | Face identification method and device | |
| Li et al. | Investigating the bag-of-words method for 3D shape retrieval | |
| CN116205889A (en) | Offset detection method, offset detection device, electronic equipment and storage medium | |
| CN107389071B (en) | Improved indoor KNN positioning method | |
| Hao et al. | Rotational Voxels Statistics Histogram for both real-valued and binary feature representations of 3D local shape | |
| Stamatopoulos et al. | Fully automated image orientation in the absence of targets | |
| Tang et al. | A GMS-guided approach for 2D feature correspondence selection | |
| Sintunata et al. | Skewness map: estimating object orientation for high speed 3D object retrieval system | |
| Mehrdad et al. | 3D object retrieval based on histogram of local orientation using one-shot score support vector machine | |
| Frosini et al. | Persistent Betti numbers for a noise tolerant shape-based approach to image retrieval | |
| CN111723847A (en) | Method, system, terminal device and storage medium for calculating similarity between graphs |
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 |