CN107491459A - The search method and device of three-dimensional image - Google Patents
The search method and device of three-dimensional image Download PDFInfo
- Publication number
- CN107491459A CN107491459A CN201610414781.8A CN201610414781A CN107491459A CN 107491459 A CN107491459 A CN 107491459A CN 201610414781 A CN201610414781 A CN 201610414781A CN 107491459 A CN107491459 A CN 107491459A
- Authority
- CN
- China
- Prior art keywords
- dimensional image
- image
- information
- convolutional neural
- colouring information
- 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
Classifications
-
- 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
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
- G06F16/5838—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Library & Information Science (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Databases & Information Systems (AREA)
- Image Analysis (AREA)
Abstract
This application discloses a kind of search method of three-dimensional image and device, wherein, the search method of three-dimensional image includes:Determine the colouring information and depth information of three-dimensional image to be retrieved;The colouring information of three-dimensional image and depth information are inputted to the convolutional neural networks model of training in advance, wherein, convolutional neural networks model is established according to the colouring information and depth information of three-dimensional image sample;The characteristics of image of three-dimensional image is exported by convolutional neural networks model;Retrieval result is obtained according to characteristics of image.The search method and device of the three-dimensional image of the embodiment of the present application, the degree of accuracy for obtaining retrieval result corresponding to three-dimensional image can be effectively improved.
Description
Technical field
The application is related to field of computer technology, more particularly to the search method and device of a kind of three-dimensional image.
Background technology
With the high speed development of internet, increasing user begins to use in a manner of scheming to search figure to obtain oneself institute
The information needed.At present, image indexing system primarily directed to two dimensional image extract Expressive Features (such as CNN features, SIFT feature,
Color histogram feature, two dimensional image Expressive Features etc.), the higher figure of similarity is obtained to match by foregoing description feature
Picture.But for the retrieval of 3-D view, the difference of same object iamge description feature corresponding under different angle is very
Greatly, if continuing to continue to use traditional method, the retrieval result that may result in acquisition is not accurate enough.
Apply for content
The application is intended to one of technical problem at least solving in correlation technique to a certain extent.Therefore, the application
One purpose is to propose a kind of search method of three-dimensional image, can effectively improve acquisition three-dimensional image and correspond to
Retrieval result the degree of accuracy, so as to lift user experience.
Second purpose of the application is the retrieval device for proposing a kind of three-dimensional image.
To achieve these goals, the application first aspect embodiment proposes a kind of retrieval side of three-dimensional image
Method, including:Determine the colouring information and depth information of three-dimensional image to be retrieved;By the color of the three-dimensional image
Information and depth information are inputted to the convolutional neural networks model of training in advance, wherein, the convolutional neural networks model is root
Established according to the colouring information and depth information of three-dimensional image sample;By described in convolutional neural networks model output
The characteristics of image of three-dimensional image;Retrieval result is obtained according to described image feature.
The search method of the three-dimensional image of the embodiment of the present application, by the face for determining three-dimensional image to be retrieved
Color information and depth information, the colouring information of the three-dimensional image and depth information are inputted to the convolution god of training in advance
Through network model, and pass through the characteristics of image of the convolutional neural networks model output three-dimensional image, final basis
Characteristics of image obtains retrieval result, can effectively improve the degree of accuracy for obtaining retrieval result corresponding to three-dimensional image, from
And lift user experience.
The application second aspect embodiment proposes a kind of retrieval device of three-dimensional image, including:Determining module, use
In it is determined that the colouring information and depth information of three-dimensional image to be retrieved;Input module, for by the 3 dimensional drawing
The colouring information and depth information of picture are inputted to the convolutional neural networks model of training in advance, wherein, the convolutional neural networks
Model is established according to the colouring information and depth information of three-dimensional image sample;Output module, for passing through the volume
Product neural network model exports the characteristics of image of the three-dimensional image;Acquisition module, for being obtained according to described image feature
Take retrieval result.
The retrieval device of the three-dimensional image of the embodiment of the present application, by the face for determining three-dimensional image to be retrieved
Color information and depth information, the colouring information of the three-dimensional image and depth information are inputted to the convolution god of training in advance
Through network model, and pass through the characteristics of image of the convolutional neural networks model output three-dimensional image, final basis
Characteristics of image obtains retrieval result, can effectively improve the degree of accuracy for obtaining retrieval result corresponding to three-dimensional image, from
And lift user experience.
Brief description of the drawings
Fig. 1 is the first pass figure according to the search method of the three-dimensional image of the application one embodiment;
Fig. 2 is the second flow chart according to the search method of the three-dimensional image of the application one embodiment;
Fig. 3 is the flow chart for establishing convolutional neural networks model according to the application one embodiment;
Fig. 4 is the first structure schematic diagram according to the retrieval device of the three-dimensional image of the application one embodiment;
Fig. 5 is the second structural representation according to the retrieval device of the three-dimensional image of the application one embodiment;
Fig. 6 is the 3rd structural representation according to the retrieval device of the three-dimensional image of the application one embodiment.
Embodiment
Embodiments herein is described below in detail, the example of the embodiment is shown in the drawings, wherein from beginning to end
Same or similar label represents same or similar element or the element with same or like function.Below with reference to attached
The embodiment of figure description is exemplary, it is intended to for explaining the application, and it is not intended that limitation to the application.
Below with reference to the accompanying drawings the search method and device of the three-dimensional image of the embodiment of the present application are described.
Fig. 1 is the first pass figure according to the search method of the three-dimensional image of the application one embodiment.
As shown in figure 1, the search method of three-dimensional image may include:
S1, the colouring information and depth information for determining three-dimensional image to be retrieved.
Specifically, the three-dimensional image of user's input can first be received.Wherein, three-dimensional image can be by such as
3D camera grabs as Kinect obtain.Then, the colouring information and depth information of three-dimensional image can be obtained.
Three-dimensional image is specifically to be described by colouring information and depth information.Wherein, colouring information can be RGB
Color mode or YUV color modes.In the present embodiment, rgb color pattern is mainly taken to illustrate.In rgb color
In pattern, it may include describe the channel B of the R passages of red, the G passages of description green and description blueness.The value of each passage
Scope is between 0 to 255, that is to say, that and 256 grades of rgb color can be combined into about 16,780,000 kinds of colors altogether, i.e., 256 ×
256 × 256=16777216.Therefore, the color of certain point in image can be described by the numerical value of three above passage.
Depth information is the information of the distance of each point and lens plane described in three-dimensional image.
S2, the colouring information of three-dimensional image and depth information inputted to the convolutional neural networks mould of training in advance
Type.
Wherein, convolutional neural networks model is established according to the colouring information and depth information of three-dimensional image sample
's.
S3, the characteristics of image by convolutional neural networks model output three-dimensional image.
S4, according to characteristics of image obtain retrieval result.
Specifically, the distance between data characteristics of candidate image in characteristics of image and database can be calculated.Then may be used
Candidate image is ranked up according to distance order from small to large, finally can using the candidate image sorted positioned at preceding N names as
Retrieval result.Wherein, database is the database for preserving three-dimensional image pre-established.Wherein, distance can be
Euclidean distance or COS distance.
It should be appreciated that the similarity between the nearlyer expression image of distance is higher, thus, candidate image can be arranged
Sequence, so as to obtain more accurately retrieval result.
In addition, as shown in Fig. 2 embodiments herein may also include step S5.
S5, before colouring information and depth information to be inputted to the convolutional neural networks model to training in advance, to three-dimensional
The colouring information and depth information of stereo-picture are normalized.
First, first the colouring information of three-dimensional image can be normalized.
Specifically, can obtain in three-dimensional image R passage numerical value j, G passage numerical value k and channel B numerical value l a little,
Then respectively by R passage numerical value j, G passage numerical value k, channel B numerical value l divided by 255, so as to obtain the R passage numerical value after normalization
J ', G passage numerical value k ' and channel B numerical value l '.Because j, k, l span are between 0 to 255, therefore, corresponding j ', k '
And l ' span is between 0 to 1.
Then, then to the depth information of three-dimensional image it is normalized.
Specifically, can obtain in three-dimensional image depth value h, minimum-depth numerical value a a little (put down apart from camera lens
The nearest value in face) and depth capacity numerical value b (value farthest apart from lens plane).Wherein, a≤h≤b.Then, depth can be obtained
The first difference between numerical value h and minimum-depth numerical value a, then obtain it is second poor between depth capacity numerical value b and depth value h
Value, finally by the first difference divided by the second difference, the final depth value obtained after normalization.Depth value after normalization
Between span is 0 to 1.
Colouring information and depth information after normalized be typically represented by the image such as 256 of a fixed dimension ×
The two dimensional image of 256 pixels.
The process for establishing convolutional neural networks model is described in detail below.
Specifically, as shown in Figure 3, it may include following steps:
S31, the colouring information and depth information for extracting three-dimensional image sample.
S32, colouring information and depth information to three-dimensional image sample are normalized, with corresponding to generation
Normalized image sample.
First, first the colouring information of three-dimensional image sample can be normalized.
Specifically, can obtain in three-dimensional image sample R passages numerical value, G passages numerical value and channel B number a little
Value, then respectively by R passages numerical value, G passages numerical value, channel B numerical value divided by 255, so as to obtain the R port numbers after normalization
Value, G passages numerical value and channel B numerical value.Between the span of each passage numerical value after normalization is 0 to 1.
Then, the depth information of three-dimensional image sample can be normalized.
Specifically, can obtain in three-dimensional image sample depth value a little, minimum-depth numerical value (apart from camera lens
The nearest value of plane) and depth capacity numerical value (value farthest apart from lens plane).Then, depth value can be obtained and minimum is deep
The first difference between number of degrees value, then the second difference between depth capacity numerical value and depth value is obtained, it is finally poor by first
Value divided by the second difference, the final depth value obtained after normalization.The span of depth value after normalization is 0 to 1
Between.
After this, normalized image sample can be generated according to the colouring information and depth information after normalization.For convenience
Calculate, normalized image sample can typically may be scaled to a fixed dimension such as 256 × 256 pixels.
S33, normalized image sample is trained, to establish convolutional neural networks model.
Specifically, the parameter of convolutional neural networks model can be trained based on multi-task learning method, to improve volume
The identification precision of product neural network model.Wherein, task can be to the classification task of image pattern, can also be to image
Sorting task of sample etc..
The search method of the three-dimensional image of the embodiment of the present application, by the face for determining three-dimensional image to be retrieved
Color information and depth information, the colouring information of three-dimensional image and depth information are inputted to the convolutional Neural net of training in advance
Network model, and by the characteristics of image of convolutional neural networks model output three-dimensional image, finally obtained according to characteristics of image
Retrieval result, the degree of accuracy for obtaining retrieval result corresponding to three-dimensional image can be effectively improved, is made so as to lift user
With experience.
To achieve the above object, the application also proposes a kind of retrieval device of three-dimensional image.
Fig. 4 is the first structure schematic diagram according to the retrieval device of the three-dimensional image of the application one embodiment.
As shown in figure 4, the retrieval device of three-dimensional image may include:Determining module 110, input module 120, output mould
Block 130 and acquisition module 140.
Determining module 110 is used for the colouring information and depth information for determining three-dimensional image to be retrieved.Specifically, may be used
First receive the three-dimensional image of user's input.Wherein, three-dimensional image can pass through the 3D video cameras as Kinect
Catch and obtain.Then, the colouring information and depth information of three-dimensional image can be obtained.
Three-dimensional image is specifically to be described by colouring information and depth information.Wherein, colouring information can be RGB
Color mode or YUV color modes.In the present embodiment, rgb color pattern is mainly taken to illustrate.In rgb color
In pattern, it may include describe the channel B of the R passages of red, the G passages of description green and description blueness.The value of each passage
Scope is between 0 to 255, that is to say, that and 256 grades of rgb color can be combined into about 16,780,000 kinds of colors altogether, i.e., 256 ×
256 × 256=16777216.Therefore, the color of certain point in image can be described by the numerical value of three above passage.
Depth information is the information of the distance of each point and lens plane described in three-dimensional image.
Input module 120 is used to input the colouring information of three-dimensional image and depth information to the convolution of training in advance
Neural network model.Wherein, convolutional neural networks model is the colouring information and depth information according to three-dimensional image sample
Establish.
Output module 130 is used for the characteristics of image that three-dimensional image is exported by convolutional neural networks model.
Acquisition module 140 is used to obtain retrieval result according to characteristics of image.Specifically, characteristics of image and database can be calculated
In the distance between the data characteristics of candidate image.Then candidate image can be arranged according to the order of distance from small to large
Sequence, the candidate image that finally can be located at preceding N names using sorting is as retrieval result.Wherein, database is to pre-establish for protecting
Deposit the database of three-dimensional image.Wherein, distance can be Euclidean distance or COS distance.
It should be appreciated that the similarity between the nearlyer expression image of distance is higher, thus, candidate image can be arranged
Sequence, so as to obtain more accurately retrieval result.
In addition, as shown in figure 5, the retrieval device of three-dimensional image may also include normalization module 150.
Normalization module 150 is used to input to the convolutional neural networks mould of training in advance by colouring information and depth information
Before type, the colouring information and depth information of three-dimensional image are normalized.
First, first the colouring information of three-dimensional image can be normalized.
Specifically, can obtain in three-dimensional image R passage numerical value j, G passage numerical value k and channel B numerical value l a little,
Then respectively by R passage numerical value j, G passage numerical value k, channel B numerical value l divided by 255, so as to obtain the R passage numerical value after normalization
J ', G passage numerical value k ' and channel B numerical value l '.Because j, k, l span are between 0 to 255, therefore, corresponding j ', k '
And l ' span is between 0 to 1.
Then, then to the depth information of three-dimensional image it is normalized.
Specifically, can obtain in three-dimensional image depth value h, minimum-depth numerical value a a little (put down apart from camera lens
The nearest value in face) and depth capacity numerical value b (value farthest apart from lens plane).Wherein, a≤h≤b.Then, depth can be obtained
The first difference between numerical value h and minimum-depth numerical value a, then obtain it is second poor between depth capacity numerical value b and depth value h
Value, finally by the first difference divided by the second difference, the final depth value obtained after normalization.Depth value after normalization
Between span is 0 to 1.
Colouring information and depth information after normalized be typically represented by the image such as 256 of a fixed dimension ×
The two dimensional image of 256 pixels.
In addition, as shown in fig. 6, the retrieval device of three-dimensional image may also include extraction module 160, generation module 170
With establish module 180.
Extraction module 160 is used for the colouring information and depth information for extracting three-dimensional image sample.
Generation module 170 is used to the colouring information and depth information of three-dimensional image sample be normalized,
With normalized image sample corresponding to generation.
First, first the colouring information of three-dimensional image sample can be normalized.
Specifically, can obtain in three-dimensional image sample R passages numerical value, G passages numerical value and channel B number a little
Value, then respectively by R passages numerical value, G passages numerical value, channel B numerical value divided by 255, so as to obtain the R port numbers after normalization
Value, G passages numerical value and channel B numerical value.Between the span of each passage numerical value after normalization is 0 to 1.
Then, the depth information of three-dimensional image sample can be normalized.
Specifically, can obtain in three-dimensional image sample depth value a little, minimum-depth numerical value (apart from camera lens
The nearest value of plane) and depth capacity numerical value (value farthest apart from lens plane).Then, depth value can be obtained and minimum is deep
The first difference between number of degrees value, then the second difference between depth capacity numerical value and depth value is obtained, it is finally poor by first
Value divided by the second difference, the final depth value obtained after normalization.The span of depth value after normalization is 0 to 1
Between.
After this, normalized image sample can be generated according to the colouring information and depth information after normalization.For convenience
Calculate, normalized image sample can typically may be scaled to a fixed dimension such as 256 × 256 pixels.
Establish module 180 to be used to be trained normalized image sample, to establish convolutional neural networks model.Specifically
Ground, the parameter of convolutional neural networks model can be trained based on multi-task learning method, to improve convolutional neural networks mould
The identification precision of type.Wherein, task can be to the classification task of image pattern, can also be that sequence to image pattern is appointed
Business etc..
The retrieval device of the three-dimensional image of the embodiment of the present application, by the face for determining three-dimensional image to be retrieved
Color information and depth information, the colouring information of three-dimensional image and depth information are inputted to the convolutional Neural net of training in advance
Network model, and by the characteristics of image of convolutional neural networks model output three-dimensional image, finally obtained according to characteristics of image
Retrieval result, the degree of accuracy for obtaining retrieval result corresponding to three-dimensional image can be effectively improved, is made so as to lift user
With experience.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or the spy for combining the embodiment or example description
Point is contained at least one embodiment or example of the application.In this manual, to the schematic representation of above-mentioned term not
Identical embodiment or example must be directed to.Moreover, specific features, structure, material or the feature of description can be with office
Combined in an appropriate manner in one or more embodiments or example.In addition, in the case of not conflicting, the skill of this area
Art personnel can be tied the different embodiments or example and the feature of different embodiments or example described in this specification
Close and combine.
Although embodiments herein has been shown and described above, it is to be understood that above-described embodiment is example
Property, it is impossible to the limitation to the application is interpreted as, one of ordinary skill in the art within the scope of application can be to above-mentioned
Embodiment is changed, changed, replacing and modification.
Claims (10)
1. a kind of search method of three-dimensional image, it is characterised in that comprise the following steps:
Determine the colouring information and depth information of three-dimensional image to be retrieved;
The colouring information of the three-dimensional image and depth information are inputted to the convolutional neural networks model of training in advance, its
In, the convolutional neural networks model is established according to the colouring information and depth information of three-dimensional image sample;
The characteristics of image of the three-dimensional image is exported by the convolutional neural networks model;
Retrieval result is obtained according to described image feature.
2. the method as described in claim 1, it is characterised in that retrieval result is obtained according to described image feature, including:
Calculate the distance between data characteristics of candidate image in described image feature and database;
The candidate image is ranked up according to the order of distance from small to large;
The candidate image for being located at preceding N names using sorting is as the retrieval result.
3. method as claimed in claim 2, it is characterised in that the distance includes Euclidean distance, COS distance.
4. the method as described in claim 1, it is characterised in that believed according to the colouring information of three-dimensional image sample and depth
Breath establishes the convolutional neural networks model, including:
Extract the colouring information and depth information of the three-dimensional image sample;
The colouring information and depth information of the three-dimensional image sample are normalized, to generate corresponding normalizing
Change image pattern;
The normalized image sample is trained, to establish the convolutional neural networks model.
5. the method as described in claim 1, it is characterised in that inputted by the colouring information and the depth information to pre-
Before the convolutional neural networks model first trained, in addition to:
The colouring information and depth information of the three-dimensional image are normalized.
A kind of 6. retrieval device of three-dimensional image, it is characterised in that including:
Determining module, for determining the colouring information and depth information of three-dimensional image to be retrieved;
Input module, for the colouring information of the three-dimensional image and depth information to be inputted to the convolution god of training in advance
Through network model, wherein, the convolutional neural networks model is believed according to the colouring information and depth of three-dimensional image sample
What breath was established;
Output module, for exporting the characteristics of image of the three-dimensional image by the convolutional neural networks model;
Acquisition module, for obtaining retrieval result according to described image feature.
7. device as claimed in claim 6, it is characterised in that the acquisition module, be used for:
Calculate the distance between data characteristics of candidate image in described image feature and database;
The candidate image is ranked up according to the order of distance from small to large;
The candidate image for being located at preceding N names using sorting is as the retrieval result.
8. device as claimed in claim 7, it is characterised in that the distance includes Euclidean distance, COS distance.
9. device as claimed in claim 6, it is characterised in that described device also includes:
Extraction module, for extracting the colouring information and depth information of the three-dimensional image sample;
Generation module, it is normalized for the colouring information to the three-dimensional image sample and depth information, with
Normalized image sample corresponding to generation;
Module is established, for being trained to the normalized image sample, to establish the convolutional neural networks model.
10. device as claimed in claim 6, it is characterised in that described device also includes:
Module is normalized, for being inputted by the colouring information and the depth information to the convolutional neural networks of training in advance
Before model, the colouring information and depth information of the three-dimensional image are normalized.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610414781.8A CN107491459A (en) | 2016-06-13 | 2016-06-13 | The search method and device of three-dimensional image |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610414781.8A CN107491459A (en) | 2016-06-13 | 2016-06-13 | The search method and device of three-dimensional image |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107491459A true CN107491459A (en) | 2017-12-19 |
Family
ID=60642288
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610414781.8A Pending CN107491459A (en) | 2016-06-13 | 2016-06-13 | The search method and device of three-dimensional image |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107491459A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109410318A (en) * | 2018-09-30 | 2019-03-01 | 先临三维科技股份有限公司 | Threedimensional model generation method, device, equipment and storage medium |
CN109857895A (en) * | 2019-01-25 | 2019-06-07 | 清华大学 | Stereoscopic vision search method and system based on polycyclic road view convolutional neural networks |
CN111105343A (en) * | 2018-10-26 | 2020-05-05 | Oppo广东移动通信有限公司 | Method and device for generating three-dimensional model of object |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050240885A1 (en) * | 2004-04-21 | 2005-10-27 | Nec Laboratories America, Inc. | Efficient SAT-based unbounded symbolic model checking |
CN104572965A (en) * | 2014-12-31 | 2015-04-29 | 南京理工大学 | Search-by-image system based on convolutional neural network |
CN104778441A (en) * | 2015-01-07 | 2015-07-15 | 深圳市唯特视科技有限公司 | Multi-mode face identification device and method fusing grey information and depth information |
CN105224942A (en) * | 2015-07-09 | 2016-01-06 | 华南农业大学 | A kind of RGB-D image classification method and system |
CN105354228A (en) * | 2015-09-30 | 2016-02-24 | 小米科技有限责任公司 | Similar image searching method and apparatus |
CN105512674A (en) * | 2015-11-25 | 2016-04-20 | 中国科学院自动化研究所 | RGB-D object identification method and apparatus based on dense matching sub adaptive similarity measure |
CN105654103A (en) * | 2014-11-12 | 2016-06-08 | 联想(北京)有限公司 | Image identification method and electronic equipment |
-
2016
- 2016-06-13 CN CN201610414781.8A patent/CN107491459A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050240885A1 (en) * | 2004-04-21 | 2005-10-27 | Nec Laboratories America, Inc. | Efficient SAT-based unbounded symbolic model checking |
CN105654103A (en) * | 2014-11-12 | 2016-06-08 | 联想(北京)有限公司 | Image identification method and electronic equipment |
CN104572965A (en) * | 2014-12-31 | 2015-04-29 | 南京理工大学 | Search-by-image system based on convolutional neural network |
CN104778441A (en) * | 2015-01-07 | 2015-07-15 | 深圳市唯特视科技有限公司 | Multi-mode face identification device and method fusing grey information and depth information |
CN105224942A (en) * | 2015-07-09 | 2016-01-06 | 华南农业大学 | A kind of RGB-D image classification method and system |
CN105354228A (en) * | 2015-09-30 | 2016-02-24 | 小米科技有限责任公司 | Similar image searching method and apparatus |
CN105512674A (en) * | 2015-11-25 | 2016-04-20 | 中国科学院自动化研究所 | RGB-D object identification method and apparatus based on dense matching sub adaptive similarity measure |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109410318A (en) * | 2018-09-30 | 2019-03-01 | 先临三维科技股份有限公司 | Threedimensional model generation method, device, equipment and storage medium |
US11978157B2 (en) | 2018-09-30 | 2024-05-07 | Shining 3D Tech Co., Ltd. | Method and apparatus for generating three-dimensional model, device, and storage medium |
CN111105343A (en) * | 2018-10-26 | 2020-05-05 | Oppo广东移动通信有限公司 | Method and device for generating three-dimensional model of object |
CN111105343B (en) * | 2018-10-26 | 2023-06-09 | Oppo广东移动通信有限公司 | Method and device for generating three-dimensional model of object |
CN109857895A (en) * | 2019-01-25 | 2019-06-07 | 清华大学 | Stereoscopic vision search method and system based on polycyclic road view convolutional neural networks |
CN109857895B (en) * | 2019-01-25 | 2020-10-13 | 清华大学 | Stereo vision retrieval method and system based on multi-loop view convolutional neural network |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108197587B (en) | Method for performing multi-mode face recognition through face depth prediction | |
CN109711281A (en) | A kind of pedestrian based on deep learning identifies again identifies fusion method with feature | |
CN102012939B (en) | Method for automatically tagging animation scenes for matching through comprehensively utilizing overall color feature and local invariant features | |
CN106650806A (en) | Cooperative type deep network model method for pedestrian detection | |
CN110298404A (en) | A kind of method for tracking target based on triple twin Hash e-learnings | |
CN108629319B (en) | Image detection method and system | |
CN103714181B (en) | A kind of hierarchical particular persons search method | |
CN102542275B (en) | Automatic identification method for identification photo background and system thereof | |
CN108388905B (en) | A kind of Illuminant estimation method based on convolutional neural networks and neighbourhood context | |
CN103065153A (en) | Video key frame extraction method based on color quantization and clusters | |
CN104484658A (en) | Face gender recognition method and device based on multi-channel convolution neural network | |
CN107330750A (en) | A kind of recommended products figure method and device, electronic equipment | |
CN103186538A (en) | Image classification method, image classification device, image retrieval method and image retrieval device | |
CN107330360A (en) | A kind of pedestrian's clothing colour recognition, pedestrian retrieval method and device | |
CN107633038A (en) | Tealeaves recognition methods and its system based on image recognition technology | |
CN106845513A (en) | Staff detector and method based on condition random forest | |
CN107194348A (en) | The domain color recognition methods of target object in a kind of image | |
CN107491459A (en) | The search method and device of three-dimensional image | |
CN107948586A (en) | Trans-regional moving target detecting method and device based on video-splicing | |
CN109213886A (en) | Image search method and system based on image segmentation and Fuzzy Pattern Recognition | |
Wong et al. | Computer vision algorithm development for classification of palm fruit ripeness | |
CN105374010A (en) | A panoramic image generation method | |
CN105404682B (en) | A kind of book retrieval method based on digital image content | |
CN111738310B (en) | Material classification method, device, electronic equipment and storage medium | |
CN111160262A (en) | Portrait segmentation method fusing human body key point detection |
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 | ||
REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 1248335 Country of ref document: HK |
|
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171219 |
|
RJ01 | Rejection of invention patent application after publication |