CN108229578A - Image data target identification method based on three layers of data, information and knowledge collection of illustrative plates framework - Google Patents
Image data target identification method based on three layers of data, information and knowledge collection of illustrative plates framework Download PDFInfo
- Publication number
- CN108229578A CN108229578A CN201810074539.XA CN201810074539A CN108229578A CN 108229578 A CN108229578 A CN 108229578A CN 201810074539 A CN201810074539 A CN 201810074539A CN 108229578 A CN108229578 A CN 108229578A
- Authority
- CN
- China
- Prior art keywords
- image
- illustrative plates
- data
- entity
- unidentified
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Databases & Information Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Animal Behavior & Ethology (AREA)
- Computational Linguistics (AREA)
- Image Analysis (AREA)
Abstract
The present invention is a kind of image data target identification method based on three layers of data, information and knowledge collection of illustrative plates framework, belongs to Distributed Calculation and Software Engineering technology crossing domain.The present invention is primarily introduced into data collection of illustrative plates, Information Atlas, knowledge mapping framework and carries out knowledge reasoning to non-identification image, so as to fulfill automated intelligent identify in picture or shot by camera to image in physical object.Specific implementation step is to have identified target by analysis, past path can be connected with unidentified target by being found in data collection of illustrative plates, Information Atlas or knowledge mapping, entity in traverse path is carried out at the same time characteristic matching, is eventually found and the unidentified highest recognition result of object matching degree.
Description
Technical field
The present invention is a kind of image data target identification method based on three layers of data, information and knowledge collection of illustrative plates framework.It is main
Be used for machine automated intelligent identify in picture or shot by camera to image in physical object.Belong to distribution
Formula calculates and Software Engineering technology crossing domain.
Background technology
Most traditional image recognition technology is manual identified, and having passed through can be identified by the method for deep learning and marked
The image of knowledge, machine gradually simulate an equation in same class object is identified repeatedly, this equation, which approaches, to be identified pair
The common trait of elephant finally reaches the purpose of identification, but the method for deep learning can not solve the identification of non-identification image
Problem.Knowledge mapping has become represents the strong tools of knowledge, and provide the language of text message with the digraph form of label
Justice.Knowledge mapping is by the way that each project, entity or user done node expression, and by edge by interaction between each other
Those nodes are chained up the figure of construction.Side between node can represent arbitrary relationship.Compared with uml class, knowledge mapping
With more rich natural semantic, expression mechanism is closer and natural language, contains more more complete semantic informations.Now very
Carry out auto-modeling application program using UML less, one reason for this is that UML lacks the formal key needed to application program
The semanteme that part is modeled, by the three-decker proposed by the present invention based on data collection of illustrative plates, Information Atlas and knowledge mapping
Relationship frame carries out image information identification.The present invention mainly by by data collection of illustrative plates, Information Atlas, knowledge mapping frame
Structure goes correctly to identify the object as much as possible not being identified.
Invention content
Technical problem：The present invention be primarily introduced into data collection of illustrative plates, Information Atlas, knowledge mapping framework to non-identification image into
Row knowledge reasoning, so as to automated intelligent identify in picture or shot by camera to image in physical object.This
Invention is analyzed identified target first, and being found in data collection of illustrative plates, Information Atlas or knowledge mapping can connect with unidentified target
Lead to past path, the entity in traverse path is carried out at the same time characteristic matching, is eventually found and unidentified object matching degree highest
Recognition result.
Technical solution：The present invention is a kind of tactic method, and the image object that can be applied to picture or video camera is known
Not, contribute to the identification for solving the problems, such as not identifying physical object in current machine study.The present invention be primarily introduced into data collection of illustrative plates,
Information Atlas, knowledge mapping framework carry out knowledge reasoning to non-identification image, so as to fulfill identifying in picture for automated intelligent
Or shot by camera to image in physical object.Embodiment be by analysis identified target, data collection of illustrative plates,
Past path can be connected with unidentified target by being found in Information Atlas or knowledge mapping, the entity in traverse path simultaneously into
Row characteristic matching is eventually found and the unidentified highest recognition result of object matching degree.We define in knowledge mapping
Semantic relation between where, when and entity node is as shown in Figure 1：
1. fully necessity relationship：Node A is certainly existed under conditions of when and where are determined, if while node A exist, can
To obtain determining where or when；
2. abundant unnecessary relationship：Node A is certainly existed under conditions of when and where are determined, if but node A presence,
Where and when can not be determined；
3. necessary insufficient condition：Node A is not necessarily present under conditions of when and where are determined, if but node A presence,
Where or when can be uniquely determined；
4. both insufficient or unnecessary condition：Node A is not necessarily present under conditions of when and where are determined, if while tying
Point A exists, and where or when can not also be determined.
Architecture：The present invention be primarily introduced into data collection of illustrative plates, Information Atlas, knowledge mapping framework to non-identification image into
Row knowledge reasoning, so as to fulfill automated intelligent identify in picture or shot by camera to image in entity mesh
Mark.The present invention sets three kinds of situations first：Identify that image and unidentified image are in same data structure, identification figure
As with unidentified image have directly or indirectly interactive relation, identified that image and unidentified image are in same environment, needle
These three situations are traversed, and on data collection of illustrative plates, Information Atlas and knowledge mapping at three layers respectively to having identified image
Past path can be connected with unidentified target by being found in collection of illustrative plates, found the entity occurred on path and carried out characteristic matching, most
After find with the unidentified highest entity of object matching degree as recognition result.At present, we can use deep learning
Identify identified image, the present invention on this basis, introduces data collection of illustrative plates, Information Atlas, knowledge mapping framework to not marking
Know image and carry out knowledge reasoning, so as to fulfill the image entities that in picture or shot by camera arrives of identifying of automated intelligent
Target.Structure data collection of illustrative plates, Information Atlas, knowledge mapping is given below to illustrate:
Data collection of illustrative plates：Data collection of illustrative plates can record the frequency of entity appearance, the frequency including three structure, time and space levels.
Our definition structure frequency appear in the number in different data structure for entity, and time frequency is the time locus of entity, empty
Between frequency be defined as the space tracking of entity.Data collection of illustrative plates can describe the entity attribute that can be observed directly in the picture,
Including color, shape etc., the static relation between entity can also be described, including direction relations and topological relation and each knot
Associated tightness degree between point, we term it density, can reflect which entity relationship is close, which entity relationship is dilute
It dredges.But the accuracy of entity is not analyzed on data collection of illustrative plates, in fact it could happen that the entity but expression same thing of different names,
This generates data redundancies.To sum up, data collection of illustrative plates can only handle the image identification of static relation（Identified image with it is unidentified
Image is in same data structure, such as apple is grown on apple tree）, it is unpredictable and analyze with interactive relation
Image；
Information Atlas：Information is conveyed by the context after data and data combination, by concept mapping and correlation
The information of suitable analysis and explanation after composition of relations.Information Atlas can be expressed according to relational database.Information Atlas
The interactive relation between entity can be expressed（Such as the shock on apple and ground）, the frequency on Information Atlas refer to entity with
The frequency of interaction between entity can carry out data cleansing on Information Atlas, eliminate redundant data.It can be with according to algorithm 1
Obtain all interaction paths between two entities：
Advantageous effect：The present invention is a kind of image data target identification side based on three layers of data, information and knowledge collection of illustrative plates framework
Method has the following remarkable advantage：
（1）The present invention constructs data collection of illustrative plates, Information Atlas and knowledge mapping three-tier architecture, progressive, realizes efficient identification；
（2）It can correctly identify image unidentified in deep learning method；
（3）The present invention is directed to the relationship for having identified image and unidentified image respectively in data collection of illustrative plates, Information Atlas and knowledge graph
It is traversed in spectrum, makes recognition result more accurate.
Description of the drawings
Fig. 1 is the formal definitions to data collection of illustrative plates, Information Atlas and knowledge mapping；
Wherein (1) data collection of illustrative plates
Circle represents entity, and box represents entity attributes, wherein A1, A2, B1, C1, C2, C3, in same data structure.
A3, B2, C4 are in same data structure.
(2) Information Atlas
B1 and D1 interaction frequency is that 2 and D2 interaction frequency is 3；B1 and E2, E1 indirect interaction；B2 and D4, D5 direct interaction
(3) knowledge mapping
1. fully the necessary insufficient relationship 4. of necessity relationship 2. fully unnecessary relationship 3. is both insufficient or unnecessary relationship
Fig. 2 is the idiographic flow of the image entities target identification process based on data collection of illustrative plates, Information Atlas and knowledge mapping framework
Figure.
Specific embodiment
It is a kind of based on data, the image data target identification method of three layers of collection of illustrative plates framework of information and knowledge idiographic flow such as
Under：
Step 1）According to existing image resource, establish based on data collection of illustrative plates, Information Atlas, knowledge mapping frame；
Step 2）Obtain images to be recognized；
Step 3）Images to be recognized is divided into and has identified two modules of image { Bi } and unidentified image X；
Step 6）If A and B has direct interaction relationship：In Information Atlas according to interaction frequency order traversal from big to small
Identify the neighbouring node { Di } of image { Bi }, note { Di } is { Xi }, performs step 5；If A and B has indirect interaction relationship：Believing
The neighbouring node { Ei } of image { Di } is identified in breath collection of illustrative plates according to the order traversal of interaction frequency from big to small, note { Ei } is
{ Xi } performs step 5, if not finding recognition result, continually looks for the neighbouring node of { Ei }, repeat the above process, until
Until finding；
Step 7）If having identified, image is in same environment with unidentified image：The identification image obtained based on step 3
{ Bi } traverses knowledge mapping, finds " Where " corresponding in image and " When ", and find at corresponding " Where " and
The entity type being likely to occur in " When " is denoted as { Xi }, performs step 5；
Step 8）Export recognition result.
Claims (1)
1. the present invention is primarily introduced into data collection of illustrative plates, Information Atlas and knowledge mapping framework and non-identification image progress knowledge is pushed away
Reason, so as to fulfill automated intelligent identify in picture or shot by camera to image in physical object, it is specific to flow
Journey is as follows：
Step 1）According to existing image resource, the frame based on data collection of illustrative plates, Information Atlas and knowledge mapping is established；
Step 2）Obtain images to be recognized；
Step 3）Images to be recognized is divided into and has identified two modules of image { Bi } and unidentified image X；
Step 4）If A and B are present among a data structure：The image B ergodic data figures of identification obtained based on step 3
Spectrum, thus it is speculated that go out it and be likely to be present among the data structure of which entity, these entities are denoted as { Ai }；{ Ai } is divided
Analysis, all entities being likely to occur in acquisition { Ai }, is denoted as { Ci }；It is { Xi } to remember { Ai } ∪ { Ci }；
Step 5）The unidentified image X obtained based on step 3 and entity { Xi } are subjected to characteristic matching, matched by formula 1
R is spent, when R is more than some threshold value, using R as recognition result, it is assumed that entity attribute feature and Ai matching values in data collection of illustrative plates
For μ（α）, α expressions Xi can be with an attribute of unidentified images match, and x expressions are all can be with matched attribute, including shape
Shape, color, topological relation, direction relations etc.；
（2）
Step 6）If A and B has direct interaction relationship：In Information Atlas according to interaction frequency order traversal from big to small
Identify the neighbouring node { Di } of image { Bi }, note { Di } is { Xi }, performs step 5；If A and B has indirect interaction relationship：Believing
The neighbouring node { Ei } of image { Di } is identified in breath collection of illustrative plates according to the order traversal of interaction frequency from big to small, note { Ei } is
{ Xi } performs step 5, if not finding recognition result, continually looks for the neighbouring node of { Ei }, repeat the above process, until
Until finding；
Step 7）If having identified, image is in same environment with unidentified image：The identification image obtained based on step 3
{ Bi } traverses knowledge mapping, finds " Where " corresponding in image and " When ", and find at corresponding " Where " and
The entity type being likely to occur in " When " is denoted as { Xi }, performs step 5；
Step 8）Export recognition result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810074539.XA CN108229578B (en) | 2018-01-25 | 2018-01-25 | Image data target identification method based on three layers of data, information and knowledge map framework |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810074539.XA CN108229578B (en) | 2018-01-25 | 2018-01-25 | Image data target identification method based on three layers of data, information and knowledge map framework |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108229578A true CN108229578A (en) | 2018-06-29 |
| CN108229578B CN108229578B (en) | 2019-10-11 |
Family
ID=62667370
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810074539.XA Active CN108229578B (en) | 2018-01-25 | 2018-01-25 | Image data target identification method based on three layers of data, information and knowledge map framework |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108229578B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110210387A (en) * | 2019-05-31 | 2019-09-06 | 华北电力大学（保定） | Insulator object detection method, system, the device of knowledge based map |
| CN111143626A (en) * | 2019-12-25 | 2020-05-12 | 深圳云天励飞技术有限公司 | Group partner identification method, device, equipment and computer readable storage medium |
| CN111309827A (en) * | 2020-03-23 | 2020-06-19 | 平安医疗健康管理股份有限公司 | Knowledge graph construction method and device, computer system and readable storage medium |
| CN111460206A (en) * | 2020-04-03 | 2020-07-28 | 百度在线网络技术（北京）有限公司 | Image processing method, image processing device, electronic equipment and computer readable storage medium |
| CN112528993A (en) * | 2020-12-17 | 2021-03-19 | 济南浪潮高新科技投资发展有限公司 | Method for improving image recognition accuracy rate based on knowledge graph |
| CN115050085A (en) * | 2022-08-15 | 2022-09-13 | 珠海翔翼航空技术有限公司 | Method, system and equipment for recognizing objects of analog machine management system based on map |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150331866A1 (en) * | 2012-12-12 | 2015-11-19 | Google Inc. | Ranking search results based on entity metrics |
| CN106776564A (en) * | 2016-12-21 | 2017-05-31 | 张永成 | The method for recognizing semantics and system of a kind of knowledge based collection of illustrative plates |
| CN107038508A (en) * | 2017-06-06 | 2017-08-11 | 海南大学 | The study point tissue and execution route of the learning ability modeling of knowledge based collection of illustrative plates and the target drives of dynamic self-adapting recommend method |
| CN107085618A (en) * | 2017-06-01 | 2017-08-22 | 海南大学 | Study point and learning path towards the 5W target drives based on data collection of illustrative plates, Information Atlas and knowledge mapping are recommended |
-
2018
- 2018-01-25 CN CN201810074539.XA patent/CN108229578B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150331866A1 (en) * | 2012-12-12 | 2015-11-19 | Google Inc. | Ranking search results based on entity metrics |
| CN106776564A (en) * | 2016-12-21 | 2017-05-31 | 张永成 | The method for recognizing semantics and system of a kind of knowledge based collection of illustrative plates |
| CN107085618A (en) * | 2017-06-01 | 2017-08-22 | 海南大学 | Study point and learning path towards the 5W target drives based on data collection of illustrative plates, Information Atlas and knowledge mapping are recommended |
| CN107038508A (en) * | 2017-06-06 | 2017-08-11 | 海南大学 | The study point tissue and execution route of the learning ability modeling of knowledge based collection of illustrative plates and the target drives of dynamic self-adapting recommend method |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110210387A (en) * | 2019-05-31 | 2019-09-06 | 华北电力大学（保定） | Insulator object detection method, system, the device of knowledge based map |
| CN111143626A (en) * | 2019-12-25 | 2020-05-12 | 深圳云天励飞技术有限公司 | Group partner identification method, device, equipment and computer readable storage medium |
| CN111309827A (en) * | 2020-03-23 | 2020-06-19 | 平安医疗健康管理股份有限公司 | Knowledge graph construction method and device, computer system and readable storage medium |
| CN111460206A (en) * | 2020-04-03 | 2020-07-28 | 百度在线网络技术（北京）有限公司 | Image processing method, image processing device, electronic equipment and computer readable storage medium |
| US12056184B2 (en) | 2020-04-03 | 2024-08-06 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method and apparatus for generating description information of an image, electronic device, and computer readable storage medium |
| CN112528993A (en) * | 2020-12-17 | 2021-03-19 | 济南浪潮高新科技投资发展有限公司 | Method for improving image recognition accuracy rate based on knowledge graph |
| CN115050085A (en) * | 2022-08-15 | 2022-09-13 | 珠海翔翼航空技术有限公司 | Method, system and equipment for recognizing objects of analog machine management system based on map |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108229578B (en) | 2019-10-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108229578A (en) | Image data target identification method based on three layers of data, information and knowledge collection of illustrative plates framework | |
| Fey et al. | Hierarchical inter-message passing for learning on molecular graphs | |
| Wang et al. | Zero-shot recognition via semantic embeddings and knowledge graphs | |
| CN107480191A (en) | A kind of entity alignment model of iteration | |
| CN106228398A (en) | Specific user's digging system based on C4.5 decision Tree algorithms and method thereof | |
| Jiang et al. | An incremental decision tree algorithm based on rough sets and its application in intrusion detection | |
| Sun et al. | Maximizing modularity intensity for community partition and evolution | |
| CN108052680B (en) | Image data target identification Enhancement Method based on data map, Information Atlas and knowledge mapping | |
| CN116431914A (en) | Cross-domain recommendation method and system based on personalized preference transfer model | |
| CN112949929B (en) | Knowledge tracking method and system based on collaborative embedded enhanced topic representation | |
| Gogoi et al. | A rough set–based effective rule generation method for classification with an application in intrusion detection | |
| CN110263236A (en) | Social network user multi-tag classification method based on dynamic multi-view learning model | |
| WO2023029111A1 (en) | Bidirectional unsupervised domain adaptation and merger-based cross-satellite remotely sensed image semantic segmentation method | |
| WO2022262320A1 (en) | Information completion method for knowledge graph-based power distribution network cim model, and system | |
| Yang et al. | Out-of-distribution detection with semantic mismatch under masking | |
| CN113283243B (en) | Entity and relationship combined extraction method | |
| CN104933442A (en) | Method for propagating image label based on minimal cost path | |
| Jabbour et al. | Triangle-driven community detection in large graphs using propositional satisfiability | |
| CN107798146A (en) | A kind of education resource Ontology Matching method based on subgraph approximation isomorphism | |
| Yang et al. | A few-shot inductive link prediction model in knowledge graphs | |
| CN112836511B (en) | Knowledge graph context embedding method based on cooperative relationship | |
| CN105205161A (en) | Simultaneous target searching and dividing method based on Internet images | |
| CN116089812A (en) | Fault diagnosis method based on semi-supervised contrast domain generalization intelligent model | |
| Liu et al. | GANN: A Graph alignment neural network for video partial copy detection | |
| Berry et al. | Triangulation and clique separator decomposition of claw-free 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |