CN112579802B - Agricultural product type model library establishment method - Google Patents
Agricultural product type model library establishment method Download PDFInfo
- Publication number
- CN112579802B CN112579802B CN202011174041.4A CN202011174041A CN112579802B CN 112579802 B CN112579802 B CN 112579802B CN 202011174041 A CN202011174041 A CN 202011174041A CN 112579802 B CN112579802 B CN 112579802B
- Authority
- CN
- China
- Prior art keywords
- agricultural product
- model library
- agricultural
- data
- library
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000013528 artificial neural network Methods 0.000 claims abstract description 25
- 238000013135 deep learning Methods 0.000 claims abstract description 24
- 230000008569 process Effects 0.000 claims abstract description 6
- 230000009471 action Effects 0.000 claims abstract description 4
- 238000003058 natural language processing Methods 0.000 claims abstract description 4
- 230000001502 supplementing effect Effects 0.000 claims abstract description 4
- 238000013500 data storage Methods 0.000 claims description 18
- 238000013523 data management Methods 0.000 claims description 16
- 238000013527 convolutional neural network Methods 0.000 claims description 10
- 238000013507 mapping Methods 0.000 claims description 9
- 230000006399 behavior Effects 0.000 claims description 7
- 230000006870 function Effects 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 3
- 230000007246 mechanism Effects 0.000 claims description 3
- 230000015654 memory Effects 0.000 claims description 3
- 238000004891 communication Methods 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 241000700605 Viruses Species 0.000 description 1
- 230000001580 bacterial effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 229920006395 saturated elastomer Polymers 0.000 description 1
- 238000012549 training Methods 0.000 description 1
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
- G06F16/51—Indexing; Data structures therefor; Storage structures
-
- 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
- G06N3/044—Recurrent networks, e.g. Hopfield 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
- G06N3/04—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)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of computer vision, in particular to a method for establishing an agricultural product type model library, which comprises the following steps of 3, establishing a graph library and an image library, manually calibrating characteristic values of graphs and images, and carrying out expression description to form a basic model library of agricultural product types; and 4, completing natural language processing expression generation through a manual calibration and automatic updating engine by using a basic model library of agricultural product types, and continuously perfecting and supplementing under the action of a deep learning artificial neural network. Compared with the prior art, the agricultural product type model library establishment method provided by the invention has the advantages that in the use process of a user, the artificial neural network continuously optimizes the model algorithm through the deep learning algorithm, so that higher recognition efficiency and accuracy are achieved, namely, the more the user uses, the higher the recognition accuracy is, and the recognition requirement of gradually improving people can be met.
Description
[ Field of technology ]
The invention relates to the technical field of computer vision, in particular to a method for establishing an agricultural product type model library.
[ Background Art ]
With the progress of society, particularly the high-speed development of modern logistics technology, more and more agricultural products enter the field of vision of people and are served on dining tables. The food safety problem becomes more and more a social problem while the material life of people is greatly enriched, and the bacterial virus becomes a great threat for people. How to quickly recognize the agricultural products and acquire the related information becomes a practical requirement for many consumers.
At present, some applications for object recognition are also presented, but most of the applications have the problems of low recognition rate, imperfect functions and incomplete information, and are difficult to truly meet the demands of people.
[ Invention ]
In order to overcome the problems, the invention provides an agricultural product type model library establishment method capable of effectively solving the problems.
The technical scheme provided by the invention for solving the technical problems is as follows: the utility model provides an agricultural product type model library establishment method, which comprises the following steps:
step 1, acquiring graphs and images of agricultural products, collecting basic data of the agricultural products through an existing agricultural product atlas of an agricultural science institute, and establishing initial data;
Step 2, shooting agricultural products in multiple directions and angles according to the requirements of a deep learning algorithm, establishing a rich graph library and an image library, storing graphs and images in an object-oriented mode, and establishing an efficient retrieval mechanism through indexes and weights;
Step 3, after the graph library and the image library are established, calibrating characteristic values of the graph and the image manually, and performing expression description to form a basic model library of agricultural product types;
Step 4, the basic model library of agricultural product types is generated by natural language processing and expression through manual calibration and an automatic updating engine, and is continuously perfected and supplemented under the action of a deep learning artificial neural network;
And 5, continuously perfecting a model base of the agricultural product types by adding samples, optimizing calibration data and adding expression data.
Preferably, the agricultural product type model library establishment method is realized by adopting an agricultural product identification system, wherein the agricultural product identification system comprises a data storage system, a data management system, a client and a server, and the data storage system, the data management system and the client are respectively connected with the server; the client is used for acquiring an image photo containing the agricultural product to be identified, which is shot by a user, obtaining an agricultural product picture to be identified in a slicing mode, and sending the agricultural product picture to be identified to the server; the server calls a basic model library of the agricultural product types to identify the agricultural product pictures to be identified, and sends an identification result to the client; and the client pushes the identification result and the associated agricultural product basic information data to a user.
Preferably, the deep learning artificial neural network is composed of 52 layers of negative feedback artificial neural networks, and each artificial neural network grid is composed of at least 64 nodes.
Preferably, the data management system manages graphic image data of agricultural products, basic information data of agricultural products.
Preferably, in the step 3, the farm product recognition system extracts the shape, color and texture characteristic values of the farm products to generate a farm product type basic model library.
Preferably, the data management system comprises a basic model library of agricultural product types and a basic information database of agricultural products, wherein the basic model library of agricultural product types is used for inputting multi-angle related image photos of the agricultural products, and the basic model library of the agricultural product types is continuously perfected and optimized through continuous practical combination of a target user and a deep learning algorithm; the basic information database of the agricultural products is used for inputting basic image-text information of the agricultural products.
Preferably, the agricultural product identification system configures a user behavior analysis system to record behavior data used by a user in the system.
Preferably, the data storage system comprises one or more processors and one or more memories configured to store a series of computer executable instructions and computer accessible data associated with the series of computer executable instructions; the series of computer-executable instructions, when executed by the one or more processors, cause the one or more processors to perform the agricultural product category model library building method according to the present invention.
Preferably, the data storage system further comprises an object oriented file system; the graphic image files are stored in a storage medium in an object-oriented storage manner; the storage medium is a non-transitory computer-readable storage medium having a series of computer-executable instructions stored thereon.
Preferably, the data storage system further comprises an object-oriented graphical image representation system for supplementing the representation data.
Compared with the prior art, the agricultural product type model library establishment method provided by the invention has the advantages that in the use process of a user, the artificial neural network continuously optimizes the model algorithm through the deep learning algorithm, so that higher recognition efficiency and accuracy are achieved, namely, the more the user uses, the higher the recognition accuracy is, and the recognition requirement of gradually improving people can be met.
[ Description of the drawings ]
FIG. 1 is a flow chart of a method for building a agricultural product type model library according to the present invention;
FIG. 2 is a diagram of a model base data structure of the agricultural product type model base creation method of the present invention;
FIG. 3 is a block diagram of an agricultural product identification system of the method for creating a model library of agricultural product types of the present invention.
[ Detailed description ] of the invention
The present invention will be described in further detail with reference to the accompanying drawings and examples of implementation in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
It should be noted that in embodiments of the present invention, all directional indications (such as up, down, left, right, front, back … …) are limited to relative positions on a given view, not absolute positions.
Furthermore, descriptions such as those referred to as "first," "second," and the like, are provided for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implying an order of magnitude of the indicated technical features in the present disclosure. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present invention, the meaning of "plurality" means at least two, for example, two, three, etc., unless specifically defined otherwise.
Referring to fig. 1 to 3, the method for establishing an agricultural product type model library of the present invention includes the following steps:
step 1, acquiring graphs and images of agricultural products, collecting basic data of the agricultural products through an existing agricultural product atlas of an agricultural science institute, and establishing initial data;
Step 2, shooting agricultural products in multiple directions and angles according to the requirements of a deep learning algorithm, establishing a rich graph library and an image library, storing graphs and images in an object-oriented mode, and establishing an efficient retrieval mechanism through indexes and weights;
step 3, after the graph library and the image library are established, calibrating characteristic values of the graph and the image by means of manpower, and performing expression description to form a basic model library of agricultural product types, wherein the expression description provides enough auxiliary judgment for the identification of the agricultural products;
step 4, the basic model library of agricultural product types is generated by natural language processing and expression through manual calibration and an automatic updating engine, is continuously perfected and supplemented under the action of a deep learning artificial neural network, and is automatically updated and perfected by the deep learning artificial neural network;
In the step 4, the deep learning artificial neural network may include, for example, a deep Convolutional Neural Network (CNN) or a deep residual network (Resnet). The depth convolution neural network is a depth feedforward neural network, and the depth feedforward neural network scans the agricultural product picture by utilizing a convolution kernel to extract the features to be identified in the agricultural product picture, so as to identify the features to be identified of the agricultural product. In addition, in the process of identifying the agricultural product picture, the original agricultural product picture can be directly input into the deep convolutional neural network model without preprocessing the agricultural product picture. Compared with other recognition models, the deep convolutional neural network model has higher recognition accuracy and recognition efficiency. Compared with a deep convolutional neural network model, the depth residual network model is added with an identity mapping layer, and the phenomenon that the accuracy is saturated and even reduced due to the convolutional neural network along with the increase of the network depth (the number of layers in the network) can be avoided. The identity mapping function of the identity mapping layer in the residual network model needs to satisfy: the sum of the identity mapping function and the input of the residual network model is equal to the output of the residual network model. After the identity mapping is introduced, the change of the residual network model to the output is more obvious, so that the recognition accuracy and recognition efficiency of agricultural product recognition can be greatly improved, and the recognition accuracy and recognition efficiency of agricultural products are further improved. In the invention, the deep learning artificial neural network is composed of 52 layers of negative feedback artificial neural networks, and each artificial neural network grid is composed of at least 64 nodes:
def szFnet_body(x):
the # # # szFnet model has 52 2D network layers
x＝szFnet2D_BN(32,(3,3))(x)
x＝resblock_body(x,64,1,False)
x＝resblock_body(x,128,2)
x＝resblock_body(x,256,8)
x＝resblock_body(x,512,8)
x＝resblock_body(x,1024,4)
return x。
The deep learning artificial neural network is used in the process of using the user, the model algorithm is continuously optimized through the deep learning algorithm, and higher recognition efficiency and accuracy are achieved, namely, the more the user uses, the higher the recognition accuracy is.
And 5, continuously perfecting a model base of the agricultural product types by adding samples, optimizing calibration data and adding expression data.
In the method for establishing the agricultural product type model library, the agricultural product type model library is formed by deep learning training of a system after basic data are input through a management end, and is continuously optimized and perfected along with the use of a user. The agricultural product type model library is used for identifying the agricultural product type by identifying the agricultural product picture, and is a neural network model for deep learning.
The agricultural product type model library establishment method is realized by adopting an agricultural product identification system, wherein the agricultural product identification system comprises a data storage system, a data management system, a client and a server, and the data storage system, the data management system and the client are respectively connected with the server. The agricultural product type model library is established by a data storage system, a data management system and graphic image expression data, a user shoots and submits a target agricultural product picture to a server through a client, the server analyzes and compares the agricultural product picture submitted by the user through the data management system, and finally, a type identification result is returned and pushed to the user through the client. The client is used for acquiring an image photo containing the agricultural product to be identified, which is shot by a user, obtaining the agricultural product picture to be identified in a slicing mode, and sending the agricultural product picture to be identified to the server. And the server calls a basic model library of the agricultural product type of the data management system to identify the agricultural product picture to be identified, and sends an identification result to the client. And the client pushes the identification result and the associated agricultural product basic information data to a user.
The data management system manages graphic image data of agricultural products and basic information data of the agricultural products. The basic information data of agricultural products comprise basic graphic information such as agricultural product producing areas, classification, introduction, planting methods, eating methods and the like. In the step 2, an administrator inputs multi-angle related graphic images containing agricultural products, and a rich graphic library and an image library are established. In the step 3, the farm product recognition system extracts characteristic values such as shapes, colors, textures and the like of the farm products to generate an agricultural product type basic model library. The data storage system adopts an object-oriented storage mode to store graphic image data, calibration data and expression data.
The data management system comprises a basic model library of agricultural products and a basic information database of agricultural products, wherein the basic model library of agricultural products is used for inputting multi-angle related image photos containing the agricultural products, the basic model library of the agricultural products is continuously perfected and optimized through continuous practical combination of a target user and a deep learning algorithm, and the basic information database of the agricultural products is used for inputting basic image-text information such as agricultural product producing places, classification, introduction, planting methods, eating methods and the like.
Preferably, the agricultural product identification system is configured with a high-performance message service system, target user input information, server communication scheduling information, server return result information and complete image-text information of agricultural products can be rapidly and accurately transmitted through the Internet, hysteresis condition is avoided, and a user can obtain better use experience.
Preferably, the agricultural product recognition system is configured with a user behavior analysis system, can completely record behavior data used by a user in the system, can provide the user with a function of checking and searching histories on one hand, and can serve as basic data of large user behavior data on the other hand, so as to establish a large regional data model.
Preferably, the agricultural product identification system supports infinite expansion, and can continuously add and perfect an agricultural product type basic model base through a data storage system and a data management system, so as to support the object identification field expanded outside agricultural products.
The data storage system includes one or more processors and one or more memories configured to store a series of computer-executable instructions and computer-accessible data associated with the series of computer-executable instructions, wherein the series of computer-executable instructions, when executed by the one or more processors, cause the one or more processors to perform the agricultural product category model library establishment method in accordance with the present invention.
The data storage system further includes an object-oriented file system; the graphic image files are stored in a storage medium in an object-oriented storage mode, and the storage medium can be physical or virtual. The storage medium is a non-transitory computer-readable storage medium having stored thereon a series of computer-executable instructions that, when executed by one or more computing devices, cause the one or more computing devices to perform the agricultural product category model library building method according to the present invention.
The data storage system also comprises an object-oriented graphic image expression system which can be used for supplementing expression data, and is beneficial to improving the recognition precision and learning capacity of the agricultural product recognition system.
Compared with the prior art, the agricultural product type model library establishment method provided by the invention has the advantages that in the use process of a user, the artificial neural network continuously optimizes the model algorithm through the deep learning algorithm, so that higher recognition efficiency and accuracy are achieved, namely, the more the user uses, the higher the recognition accuracy is, and the recognition requirement of gradually improving people can be met.
The foregoing description of the preferred embodiments of the invention is not intended to limit the scope of the invention, but is intended to cover any modifications, equivalents, and improvements within the spirit of the invention.
Claims (6)
1. The agricultural product type model library establishing method is characterized by comprising the following steps:
step 1, acquiring graphs and images of agricultural products, collecting basic data of the agricultural products through an existing agricultural product atlas of an agricultural science institute, and establishing initial data;
Step 2, shooting agricultural products in multiple directions and angles according to the requirements of a deep learning algorithm, establishing a rich graph library and an image library, storing graphs and images in an object-oriented mode, and establishing an efficient retrieval mechanism through indexes and weights;
Step 3, after the graph library and the image library are established, calibrating characteristic values of the graph and the image manually, and performing expression description to form a basic model library of agricultural product types;
Step 4, the basic model library of agricultural product types is generated by natural language processing and expression through manual calibration and an automatic updating engine, and is continuously perfected and supplemented under the action of a deep learning artificial neural network;
Step 5, continuously perfecting a model library of agricultural product types by adding samples, optimizing calibration data and adding expression data;
In the step 4, the deep learning artificial neural network comprises a deep convolutional neural network, wherein the deep convolutional neural network is a deep feed-forward neural network, and the deep convolutional neural network scans the agricultural product picture by using a convolutional kernel to extract the features to be identified in the agricultural product picture, so as to identify the features to be identified of the agricultural product; in addition, in the process of identifying the agricultural product picture, the original agricultural product picture can be directly input into a deep convolutional neural network model;
the deep learning artificial neural network comprises a deep residual network, an identity mapping layer is added to the deep residual network model, and the identity mapping function of the identity mapping layer needs to meet the following requirements: the sum of the identity mapping function and the input of the depth residual network model is equal to the output of the depth residual network model;
The deep learning artificial neural network is composed of 52 layers of negative feedback artificial neural networks, and each artificial neural network grid is composed of at least 64 nodes;
The agricultural product type model library establishment method is realized by adopting an agricultural product identification system, wherein the agricultural product identification system comprises a data storage system, a data management system, a client and a server, and the data storage system, the data management system and the client are respectively connected with the server; the client is used for acquiring an image photo containing the agricultural product to be identified, which is shot by a user, obtaining an agricultural product picture to be identified in a slicing mode, and sending the agricultural product picture to be identified to the server; the server calls a basic model library of the agricultural product types to identify the agricultural product pictures to be identified, and sends an identification result to the client; the client pushes the identification result and associated agricultural product basic information data;
The agricultural product identification system is configured with a user behavior analysis system and records behavior data used by a user in the system;
The agricultural product identification system is provided with a high-performance message service system, and target user input information, server communication scheduling information, server return result information and complete image-text information of agricultural products can be rapidly and accurately transmitted through the Internet;
the data storage system further includes an object-oriented graphical image representation system for supplementing the representation data.
2. The agricultural product category model library creation method of claim 1, wherein the data management system manages graphic image data of agricultural products, basic information data of agricultural products.
3. The agricultural product type model library creating method as claimed in claim 1, wherein in said step 3, the farm product recognition system extracts the shape, color and texture feature values of the agricultural products to create the agricultural product type basic model library.
4. The agricultural product type model library building method of claim 1, wherein the data management system comprises a basic model library of agricultural product types and a basic information database of agricultural products, wherein the basic model library of agricultural product types is used for inputting multi-angle related image photos of the agricultural products, and the basic model library of agricultural product types is continuously perfected and optimized through continuous practical combination of a target user and a deep learning algorithm; the basic information database of the agricultural products is used for inputting basic image-text information of the agricultural products.
5. The agricultural product category model library creation method of claim 1, wherein the data storage system comprises one or more processors and one or more memories configured to store a series of computer-executable instructions and computer-accessible data associated with the series of computer-executable instructions; the series of computer-executable instructions, when executed by the one or more processors, cause the one or more processors to perform the agricultural product category model library building method according to the present invention.
6. The agricultural product category model library creation method of claim 5, wherein said data storage system further comprises an object-oriented file system; the graphic image files are stored in a storage medium in an object-oriented storage manner; the storage medium is a non-transitory computer-readable storage medium having a series of computer-executable instructions stored thereon.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011174041.4A CN112579802B (en) | 2020-10-28 | 2020-10-28 | Agricultural product type model library establishment method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011174041.4A CN112579802B (en) | 2020-10-28 | 2020-10-28 | Agricultural product type model library establishment method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112579802A CN112579802A (en) | 2021-03-30 |
| CN112579802B true CN112579802B (en) | 2024-10-15 |
Family
ID=75120021
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011174041.4A Active CN112579802B (en) | 2020-10-28 | 2020-10-28 | Agricultural product type model library establishment method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112579802B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109472280A (en) * | 2018-09-10 | 2019-03-15 | 广东数相智能科技有限公司 | A kind of method, storage medium and electronic equipment updating species identification model library |
| CN109962975A (en) * | 2019-02-15 | 2019-07-02 | 深圳绿米联创科技有限公司 | Information-pushing method, device, electronic equipment and system based on object identification |
| CN110674805A (en) * | 2019-10-11 | 2020-01-10 | 杭州睿琪软件有限公司 | Insect identification method and system |
| CN110851638A (en) * | 2019-11-06 | 2020-02-28 | 杭州睿琪软件有限公司 | Method and device for acquiring species identification name |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107798277A (en) * | 2016-09-05 | 2018-03-13 | 合肥美的智能科技有限公司 | Food materials identifying system and method, food materials model training method, refrigerator and server |
| CN107247957A (en) * | 2016-12-16 | 2017-10-13 | 广州中国科学院先进技术研究所 | A kind of intelligent agricultural product sorting technique and system based on deep learning and cloud computing |
| CN108921058A (en) * | 2018-06-19 | 2018-11-30 | 厦门大学 | Fish identification method, medium, terminal device and device based on deep learning |
| CN109447140B (en) * | 2018-10-19 | 2021-10-12 | 广州四十五度科技有限公司 | Image identification and cognition recommendation method based on neural network deep learning |
| CN109829888A (en) * | 2018-12-27 | 2019-05-31 | 北京林业大学 | Wild animal monitoring analysis system and method based on depth convolutional neural networks |
-
2020
- 2020-10-28 CN CN202011174041.4A patent/CN112579802B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109472280A (en) * | 2018-09-10 | 2019-03-15 | 广东数相智能科技有限公司 | A kind of method, storage medium and electronic equipment updating species identification model library |
| CN109962975A (en) * | 2019-02-15 | 2019-07-02 | 深圳绿米联创科技有限公司 | Information-pushing method, device, electronic equipment and system based on object identification |
| CN110674805A (en) * | 2019-10-11 | 2020-01-10 | 杭州睿琪软件有限公司 | Insect identification method and system |
| CN110851638A (en) * | 2019-11-06 | 2020-02-28 | 杭州睿琪软件有限公司 | Method and device for acquiring species identification name |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112579802A (en) | 2021-03-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104991959A (en) | Method and system for retrieving same or similar image based on content | |
| CN104572965A (en) | Search-by-image system based on convolutional neural network | |
| CN111415379A (en) | A 3D point cloud data registration method based on cuckoo optimization | |
| US20160098437A1 (en) | Information retrieval method and apparatus | |
| CN109919084B (en) | Pedestrian re-identification method based on depth multi-index hash | |
| CN105868706A (en) | Method for identifying 3D model based on sparse coding | |
| CN110321421A (en) | Expert recommendation method and computer storage medium for website Knowledge Community system | |
| CN107220325A (en) | A kind of similar icon search methods of APP based on convolutional neural networks and system | |
| US20240061980A1 (en) | Machine-learning for topologically-aware cad retrieval | |
| CN105183795A (en) | Content based remote sensing image change detection information retrieval method | |
| CN109522288A (en) | A kind of method and system for being stored to oceanographic data | |
| CN107506362A (en) | Image classification based on customer group optimization imitates brain storage method | |
| CN110674333B (en) | Large-scale image high-speed retrieval method based on multi-view enhanced depth hashing | |
| CN116089502A (en) | Order retrieval analysis system and method based on self-adaptive model | |
| CN112579802B (en) | Agricultural product type model library establishment method | |
| CN102024029A (en) | Local visual attention-based color image retrieving method | |
| CN108304588B (en) | Image retrieval method and system based on k neighbor and fuzzy pattern recognition | |
| CN106780062A (en) | Based on groups of users update method and system that social networks and big data are analyzed | |
| CN114168770A (en) | Deep learning-based method and device for searching images by images | |
| CN106599926A (en) | Expression picture pushing method and system | |
| Weng et al. | Image inpainting technique based on smart terminal: A case study in CPS ancient image data | |
| JP5818023B2 (en) | Data index dimension reduction method and data search method and apparatus using the same | |
| CN113836330A (en) | Image retrieval method and device based on generation antagonism automatic enhanced network | |
| CN110705572B (en) | Image recognition method | |
| CN118113899A (en) | 3D model quick retrieval method based on 2D image |
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 |