CN109635833A - A kind of image-recognizing method and system based on cloud platform and model intelligent recommendation - Google Patents
A kind of image-recognizing method and system based on cloud platform and model intelligent recommendation Download PDFInfo
- Publication number
- CN109635833A CN109635833A CN201811278795.7A CN201811278795A CN109635833A CN 109635833 A CN109635833 A CN 109635833A CN 201811278795 A CN201811278795 A CN 201811278795A CN 109635833 A CN109635833 A CN 109635833A
- Authority
- CN
- China
- Prior art keywords
- images
- recognized
- markup information
- network model
- target nerve
- 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
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the invention provides a kind of image-recognizing method and system based on cloud platform and model intelligent recommendation, comprising: at least one images to be recognized for carrying markup information is obtained from images to be recognized set;The classification that markup information entrained by the images to be recognized of markup information is carried according to described at least one obtains target nerve network model from the preset model library in cloud platform;Wherein, the classification of a variety of markup informations and a variety of neural network models correspondingly are stored in the preset model library;The images to be recognized for not carrying markup information in the images to be recognized set is identified using the target nerve network model.User need to only upload the images to be recognized set that the images to be recognized of markup information is carried comprising part in use, cloud platform can the corresponding target nerve network model of intelligent recommendation, complete identification to images to be recognized, it is simple and easy, and accuracy rate is high.
Description
Technical field
The present embodiments relate to field of artificial intelligence, are based on cloud platform and model intelligence more particularly, to one kind
The image-recognizing method and system that can recommend.
Background technique
Machine learning is a branch of artificial intelligence.The research of artificial intelligence is to attach most importance to from " reasoning " to " to know
Know " attach most importance to, then attach most importance to " study ", a nature, clearly train of thought.Obviously, machine learning is to realize artificial intelligence
An approach, i.e., solve the problems in artificial intelligence by means of machine learning.Machine learning had developed at nearly more than 30 years
One multi-field cross discipline, is related to the multiple subjects such as probability theory, statistics, Approximation Theory, convextiry analysis, computational complexity theory.
Machine Learning Theory be mainly design and analyze it is some allow computer can automatic " study " algorithm.Machine learning algorithm is one
Class is automatically analyzed from data obtains rule, and the algorithm that assimilated equations predict unknown data.Because in learning algorithm
A large amount of statistical theory is related to, machine learning and inferencial statistics contact especially closely, also referred to as Statistical Learning Theory.
Algorithm design aspect, machine Learning Theory concern may be implemented, effective learning algorithm.
Deep learning is that a kind of method based on to data progress representative learning, the benefit of deep learning are in machine learning
Highly effective algorithm, which is extracted, with the feature learning and layered characteristic of non-supervisory formula or Semi-supervised obtains feature by hand to substitute.Depth
Habit is a new field in machine learning research, and motivation is to establish, simulate the nerve net that human brain carries out analytic learning
Network imitates the mechanism of human brain to explain data, wherein carrying out image recognition using neural network is popular domain in recent years.
But since many deep learning algorithm difficulty are larger, it are related to mathematical and computer sciences, answered by neural network
When for image recognition, the exploitation design for carrying out model with more high-quality professional is generally required, is unfavorable for promoting and answer
With.
Summary of the invention
The embodiment of the invention provides it is a kind of overcome the above problem or at least be partially solved the above problem based on cloud
The image-recognizing method and system of platform and model intelligent recommendation.
First aspect the embodiment of the invention provides a kind of image-recognizing method based on cloud platform and model intelligent recommendation,
Include:
At least one images to be recognized for carrying markup information is obtained from images to be recognized set;
The classification that markup information entrained by the images to be recognized of markup information is carried according to described at least one, from cloud
Target nerve network model is obtained in preset model library on platform;Wherein, one-to-one correspondence is stored in the preset model library
A variety of markup informations classification and a variety of neural network models;
Using the target nerve network model to not carrying the to be identified of markup information in the images to be recognized set
Image is identified.
On the other hand the embodiment of the invention provides a kind of image identification system based on cloud platform and model intelligent recommendation,
Include:
Markup information image collection module carries markup information for obtaining at least one from images to be recognized set
Images to be recognized;
Target nerve network obtains module, for carrying the images to be recognized institute of markup information according to described at least one
The classification of the markup information of carrying obtains target nerve network model from the preset model library in cloud platform;Wherein, described pre-
If being stored with the classification of a variety of markup informations and a variety of neural network models correspondingly in model library;
Picture recognition module, for using the target nerve network model to not marked in the images to be recognized set
Images to be recognized identified.
The embodiment of the invention provides include processor, communication interface, memory and bus for the third aspect, wherein processing
Device, communication interface, memory complete mutual communication by bus, and processor can call the logical order in memory,
To execute the image-recognizing method based on cloud platform and model intelligent recommendation of first aspect offer.
The embodiment of the invention provides a kind of non-transient computer readable storage medium, the non-transient calculating for fourth aspect
Machine readable storage medium storing program for executing stores computer instruction, the computer instruction make that the computer executes that first aspect provides based on
The image-recognizing method of cloud platform and model intelligent recommendation.
A kind of image-recognizing method and system based on cloud platform and model intelligent recommendation provided in an embodiment of the present invention, cloud
The type of platform markup information according to entrained by the images to be recognized for carrying markup information in images to be recognized set is from pre-
If choosing corresponding target nerve network model in model library, come to the images to be recognized not marked in image collection to be identified into
Row identification, user need to only upload the images to be recognized collection of the images to be recognized comprising carrying markup information in use
Close, cloud platform can the corresponding target nerve network model of intelligent recommendation, complete identification to images to be recognized, it is simple and easy,
And accuracy rate is high.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is this hair
Bright some embodiments for those of ordinary skill in the art without creative efforts, can be with root
Other attached drawings are obtained according to these attached drawings.
Fig. 1 is a kind of stream of the image-recognizing method based on cloud platform and model intelligent recommendation provided in an embodiment of the present invention
Cheng Tu;
Fig. 2 is a kind of knot of the image identification system based on cloud platform and model intelligent recommendation provided in an embodiment of the present invention
Structure block diagram;
Fig. 3 is the structural schematic diagram of a kind of electronic equipment provided in an embodiment of the present invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical solution in the embodiment of the present invention is explicitly described, it is clear that described embodiment is the present invention
A part of the embodiment, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art are not having
Every other embodiment obtained under the premise of creative work is made, shall fall within the protection scope of the present invention.
Fig. 1 is a kind of stream of the image-recognizing method based on cloud platform and model intelligent recommendation provided in an embodiment of the present invention
Cheng Tu, as shown in Figure 1, comprising:
S101 obtains at least one images to be recognized for carrying markup information from images to be recognized set;
S102 carries the class of markup information entrained by the images to be recognized of markup information according to described at least one
Not, target nerve network model is obtained from the preset model library in cloud platform;Wherein, one is stored in the preset model library
The classification of one corresponding a variety of markup informations and a variety of neural network models;
S103, using the target nerve network model to the images to be recognized not marked in the images to be recognized set
It is identified.
Wherein, in step s101, in the case where the identification target of the clear images to be recognized of user, user can pass through
The mode that artificial or preset algorithm calculates gets the recognition result of images to be recognized, using recognition result to images to be recognized into
The images to be recognized for carrying markup information can be obtained in rower note.For example, the identification target of user is to obtain images to be recognized
Gray value, user by preset algorithm calculate knows a certain images to be recognized recognition result be gray value Y, then use gray value
Y is labeled to get to the corresponding images to be recognized for carrying markup information (gray value Y) images to be recognized.Wherein,
The type of markup information correspond to recognition result and identify target type, can there are many, for example, pixel quantity, gray scale
Value etc..For the mark of part images to be recognized in images to be recognized set, generally had been manually done on interactive terminal by user,
Its quantity marked determines according to actual needs.
Cloud platform obtains at least one images to be recognized for carrying markup information from images to be recognized set, with determination
The type of markup information entrained by it.
In step s 102, cloud platform gets at least one images to be recognized for carrying markup information, determines its institute
After the type of the markup information of carrying, neural network model corresponding with the markup information type is chosen in preset model library
As target nerve network model.For example, choosing neural network corresponding with gray value when markup information type is gray value
Model is target nerve network model.
In step s 103, after obtaining target nerve network model, images to be recognized collection that cloud platform will acquire
The images to be recognized input target nerve network model not marked in conjunction, exports recognition result.For example, output images to be recognized
Gray value X.
A kind of image-recognizing method based on cloud platform and model intelligent recommendation provided in an embodiment of the present invention, cloud platform root
According to carrying the type of markup information entrained by the images to be recognized of markup information in images to be recognized set from preset model
Corresponding target nerve network model is chosen in library, to know to the images to be recognized not marked in image collection to be identified
Not, user need to only upload the images to be recognized set of the images to be recognized comprising carrying markup information, cloud in use
Platform can the corresponding target nerve network model of intelligent recommendation, complete identification to images to be recognized, it is simple and easy and accurate
Rate is high.
In the above-described embodiments, mark entrained by the images to be recognized of markup information is being carried according to described at least one
The classification for infusing information, before obtaining target nerve network model in the preset model library in cloud platform, further includes:
The preset model library is established in the cloud platform.
It specifically, is that other neural network model is stored in preset model correspondingly by the common various images that are used for
In library, for being selected when model intelligent recommendation.
In the above-described embodiments, it is described according at least one carry entrained by the images to be recognized of markup information
The classification of markup information obtains corresponding target nerve network model from the preset model library in cloud platform, specifically includes:
Mark entrained by the images to be recognized of markup information will be carried with described at least one in the preset model library
The corresponding neural network model of classification of information is infused as the target nerve network model.
In the above-described embodiments, using the target nerve network model to not carried in the images to be recognized set
Before the images to be recognized of markup information is identified, further includes:
Training dataset is obtained, the target nerve network model is trained using the training dataset and is instructed
The target nerve network model perfected.
Specifically, the accuracy rate that the subsequent identification that can make is trained to target nerve network model is higher.
In the above-described embodiments, the acquisition training dataset, using the training dataset to the target nerve net
Network model is trained to obtain trained target nerve network model, further comprises:
Using at least one images to be recognized for carrying markup information as the training dataset, and by each
Input of the images to be recognized of markup information as the neural network model is carried, carries markup information for each
The markup information of images to be recognized is trained the target nerve network model to obtain trained target mind as output
Through network model.
Specifically, when the quantity for the images to be recognized for carrying markup information is enough or the accuracy of image recognition
It is required that when not bery harsh, the images to be recognized for carrying markup information can be directly used as training dataset, then it is each to take
Input of the images to be recognized with markup information as the neural network model, by it is each carry markup information wait know
The corresponding markup information of other image is trained the neural network model to obtain trained neural network mould as output
Type.It may not need in this way and in addition obtain corresponding training dataset, save the time, enable image recognition faster.
In the above-described embodiments, the acquisition training dataset, using the training dataset to the target nerve net
Network model is trained to obtain trained target nerve network model, further comprises:
The images to be recognized for carrying markup information according to described at least one is from the default training dataset in cloud platform
The training dataset is chosen in conjunction, and the neural network model is trained using the training dataset and is trained
Neural network model.
Specifically, when the quantity for the images to be recognized for carrying markup information is inadequate or the accuracy of image recognition is wanted
When asking higher, it is necessary to which cloud platform reference carries default training dataset of the images to be recognized of markup information in cloud platform
The training data is chosen in conjunction.Each image that the same training data is concentrated needs markup information, in the training process, will
The training data concentrates each image as the input of the neural network model, concentrates each image corresponding the training data
Markup information as output, the neural network model is trained to obtain trained target nerve network model.
In the above-described embodiments, using the target nerve network model to not carrying mark in the images to be recognized set
Before the images to be recognized of note information is identified, further includes:
Image preprocessing is carried out to the images to be recognized for not carrying markup information in the images to be recognized set.Specifically
Ground, carrying out image preprocessing to image each in image collection to be identified can make image recognition accuracy rate higher.
Fig. 2 is a kind of knot of the image identification system based on cloud platform and model intelligent recommendation provided in an embodiment of the present invention
Structure block diagram, as shown in Figure 2, comprising: markup information image collection module 201, target nerve network obtain module 202 and image is known
Other module 203.Wherein:
Markup information image collection module 201 carries mark letter for obtaining at least one from images to be recognized set
The images to be recognized of breath.Target nerve network obtain module 202 be used for according to described at least one carry markup information to
The classification for identifying markup information entrained by image obtains target nerve network model from the preset model library in cloud platform;
Wherein, the classification of a variety of markup informations and a variety of neural network models correspondingly are stored in the preset model library.Figure
As identification module 203 is for be identified to not marking in the images to be recognized set using the target nerve network model
Image is identified.
Specifically, the system also includes preset model libraries to establish module, described pre- for establishing in the cloud platform
If model library.
Target nerve network obtains module 202, is specifically used for:
Mark entrained by the images to be recognized of markup information will be carried with described at least one in the preset model library
The corresponding neural network model of classification of information is infused as the target nerve network model.
The system also includes training modules, for obtaining training dataset, using the training dataset to the mind
It is trained to obtain trained neural network model through network model.
Training module is further used for:
Using the pre-set image set as training dataset, and using each pre-set image as the neural network model
Input, using the corresponding markup information of each pre-set image as output, the neural network model is trained and is instructed
The neural network model perfected.
Training module is further used for:
The training dataset is chosen from the default training data set in cloud platform according to the pre-set image set,
The neural network model is trained using the training dataset to obtain trained neural network model.
The system also includes image pre-processing module, for not carrying markup information in the images to be recognized set
Images to be recognized carry out image preprocessing.
A kind of image identification system based on cloud platform and model intelligent recommendation provided in an embodiment of the present invention, cloud platform root
According to carrying the type of markup information entrained by the images to be recognized of markup information in images to be recognized set from preset model
Corresponding target nerve network model is chosen in library, to know to the images to be recognized not marked in image collection to be identified
Not, user need to only upload the images to be recognized set of the images to be recognized comprising carrying markup information, cloud in use
Platform can the corresponding target nerve network model of intelligent recommendation, complete identification to images to be recognized, it is simple and easy and accurate
Rate is high.
Fig. 3 is the structural schematic diagram of a kind of electronic equipment provided in an embodiment of the present invention, as shown in figure 3, electronic equipment packet
It includes: processor (processor) 301, communication interface (Communications Interface) 302, memory (memory)
303 and bus 304, wherein processor 301, communication interface 302, memory 303 complete mutual communication by bus 304.
Processor 301 can call the logical order in memory 303, to execute following method, for example, from images to be recognized collection
At least one images to be recognized for carrying markup information is obtained in conjunction;According to described at least one carry markup information to
The classification for identifying markup information entrained by image obtains target nerve network model from the preset model library in cloud platform;
Wherein, the classification of a variety of markup informations and a variety of neural network models correspondingly are stored in the preset model library;Benefit
The images to be recognized for not carrying markup information in the images to be recognized set is known with the target nerve network model
Not.
Logical order in above-mentioned memory 302 can be realized and as independent by way of SFU software functional unit
Product when selling or using, can store in a computer readable storage medium.Based on this understanding, of the invention
Substantially the part of the part that contributes to existing technology or the technical solution can be produced technical solution in other words with software
The form of product embodies, which is stored in a storage medium, including some instructions are used so that one
Platform computer equipment (can be personal computer, server or the network equipment etc.) executes described in each embodiment of the present invention
The all or part of the steps of method.And storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory (ROM, Read-
Only Memory), random access memory (RAM, Random Access Memory), magnetic or disk etc. are various can be with
Store the medium of program code.
The embodiment of the present invention provides a kind of non-transient computer readable storage medium, the non-transient computer readable storage
Medium storing computer instruction, the computer instruction make the computer execute side provided by above-mentioned each method embodiment
Method, for example, at least one images to be recognized for carrying markup information is obtained from images to be recognized set;According to described
At least one carries the classification of markup information entrained by the images to be recognized of markup information, from the preset model in cloud platform
Target nerve network model is obtained in library;Wherein, one-to-one a variety of markup informations are stored in the preset model library
Classification and a variety of neural network models;Using the target nerve network model to not carrying mark in the images to be recognized set
The images to be recognized of note information is identified.
Those of ordinary skill in the art will appreciate that: realize that all or part of the steps of above method embodiment can pass through
The relevant hardware of program instruction is completed, and program above-mentioned can be stored in a computer readable storage medium, the program
When being executed, step including the steps of the foregoing method embodiments is executed;And storage medium above-mentioned includes: ROM, RAM, magnetic disk or light
The various media that can store program code such as disk.
The embodiments such as communication equipment described above are only schematical, wherein unit as illustrated by the separation member
It may or may not be physically separated, component shown as a unit may or may not be physics list
Member, it can it is in one place, or may be distributed over multiple network units.It can be selected according to the actual needs
In some or all of the modules achieve the purpose of the solution of this embodiment.Those of ordinary skill in the art are not paying creativeness
Labour in the case where, it can understand and implement.
Through the above description of the embodiments, those skilled in the art can be understood that each embodiment can
It realizes by means of software and necessary general hardware platform, naturally it is also possible to pass through hardware.Based on this understanding, on
Stating technical solution, substantially the part that contributes to existing technology can be embodied in the form of software products in other words, should
Computer software product may be stored in a computer readable storage medium, such as ROM/RAM, magnetic disk, CD, including several fingers
It enables and using so that a computer equipment (can be personal computer, server or the network equipment etc.) executes each implementation
The method of certain parts of example or embodiment.
Finally, it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations;Although
Present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: it still may be used
To modify the technical solutions described in the foregoing embodiments or equivalent replacement of some of the technical features;
And these are modified or replaceed, technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution spirit and
Range.
Claims (10)
1. a kind of image-recognizing method based on cloud platform and model intelligent recommendation characterized by comprising
At least one images to be recognized for carrying markup information is obtained from images to be recognized set;
The classification that markup information entrained by the images to be recognized of markup information is carried according to described at least one, from cloud platform
On preset model library in obtain target nerve network model;Wherein, it is stored in the preset model library one-to-one more
The classification of kind markup information and a variety of neural network models;
Using the target nerve network model to the images to be recognized for not carrying markup information in the images to be recognized set
It is identified.
2. method according to claim 1, which is characterized in that according to described at least one carry markup information wait know
The classification of markup information entrained by other image, from the preset model library in cloud platform obtain target nerve network model it
Before, further includes:
The preset model library is established in the cloud platform.
3. method according to claim 1, which is characterized in that it is described according at least one carry markup information to
The classification for identifying markup information entrained by image, obtains corresponding target nerve network from the preset model library in cloud platform
Model specifically includes:
The letter of mark entrained by the images to be recognized of markup information will be carried in the preset model library with described at least one
The corresponding neural network model of the classification of breath is as the target nerve network model.
4. method according to claim 1, which is characterized in that in the utilization target nerve network model to described to be identified
Do not carried in image collection markup information images to be recognized identified before, further includes:
Training dataset is obtained, the target nerve network model is trained using the training dataset and is trained
Target nerve network model.
5. method according to claim 4, which is characterized in that the acquisition training dataset utilizes the training dataset
The target nerve network model is trained to obtain trained target nerve network model, further comprises:
Using at least one images to be recognized for carrying markup information as the training dataset, and each is carried
Have input of the images to be recognized of markup information as the neural network model, by each carry markup information wait know
The markup information of other image is trained the target nerve network model to obtain trained target nerve net as output
Network model.
6. method according to claim 4, which is characterized in that the acquisition training dataset utilizes the training dataset
The target nerve network model is trained to obtain trained target nerve network model, further comprises:
The images to be recognized of markup information is carried from the default training data set in cloud platform according to described at least one
The training dataset is chosen, the neural network model is trained using the training dataset to obtain trained mind
Through network model.
7. any one of -6 the method according to claim 1, which is characterized in that in the utilization target nerve network model to institute
State do not carried in images to be recognized set markup information images to be recognized identified before, further includes:
Image preprocessing is carried out to the images to be recognized for not carrying markup information in the images to be recognized set.
8. a kind of image identification system based on cloud platform and model intelligent recommendation characterized by comprising
Markup information image collection module, for obtained from images to be recognized set at least one carry markup information to
Identify image;
Target nerve network obtains module, for being carried entrained by the images to be recognized of markup information according to described at least one
Markup information classification, from the preset model library in cloud platform obtain target nerve network model;Wherein, the default mould
The classification of a variety of markup informations and a variety of neural network models correspondingly are stored in type library;
Picture recognition module, for using the target nerve network model to do not mark in the images to be recognized set to
Identification image is identified.
9. a kind of electronic equipment, which is characterized in that including processor, communication interface, memory and bus, wherein processor leads to
Believe that interface, memory complete mutual communication by bus, processor can call the logical order in memory, to execute
Image-recognizing method as described in any one of claim 1 to 7 based on cloud platform and model intelligent recommendation.
10. a kind of non-transient computer readable storage medium, which is characterized in that the non-transient computer readable storage medium is deposited
Computer instruction is stored up, it is as described in any one of claim 1 to 7 flat based on cloud that the computer instruction executes the computer
The image-recognizing method of platform and model intelligent recommendation.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811278795.7A CN109635833A (en) | 2018-10-30 | 2018-10-30 | A kind of image-recognizing method and system based on cloud platform and model intelligent recommendation |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811278795.7A CN109635833A (en) | 2018-10-30 | 2018-10-30 | A kind of image-recognizing method and system based on cloud platform and model intelligent recommendation |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109635833A true CN109635833A (en) | 2019-04-16 |
Family
ID=66066897
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811278795.7A Pending CN109635833A (en) | 2018-10-30 | 2018-10-30 | A kind of image-recognizing method and system based on cloud platform and model intelligent recommendation |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109635833A (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110489240A (en) * | 2019-08-22 | 2019-11-22 | Oppo广东移动通信有限公司 | Image-recognizing method, device, cloud platform and storage medium |
CN111353477A (en) * | 2020-04-16 | 2020-06-30 | 银河水滴科技(北京)有限公司 | Gait recognition system and method |
CN111612034A (en) * | 2020-04-15 | 2020-09-01 | 中国科学院上海微系统与信息技术研究所 | Method and device for determining object recognition model, electronic equipment and storage medium |
CN111985565A (en) * | 2020-08-20 | 2020-11-24 | 上海风秩科技有限公司 | Picture analysis method and device, storage medium and electronic equipment |
CN112036465A (en) * | 2020-08-26 | 2020-12-04 | 中国建设银行股份有限公司 | Image recognition method, device, equipment and storage medium |
CN112598073A (en) * | 2020-12-28 | 2021-04-02 | 南方电网深圳数字电网研究院有限公司 | Power grid equipment image labeling method, electronic equipment and storage medium |
CN112699906A (en) * | 2019-10-22 | 2021-04-23 | 杭州海康威视数字技术股份有限公司 | Method, device and storage medium for acquiring training data |
CN113642416A (en) * | 2021-07-20 | 2021-11-12 | 武汉光庭信息技术股份有限公司 | Test cloud platform for AI (Artificial intelligence) annotation and AI annotation test method |
CN114694139A (en) * | 2022-06-01 | 2022-07-01 | 中科航迈数控软件(深圳)有限公司 | Machining feature identification method and system for complex structural part of numerical control machine tool |
CN117422952A (en) * | 2023-10-31 | 2024-01-19 | 北京东方国信科技股份有限公司 | Artificial intelligent image recognition model management method and device and cloud edge service platform |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101782976A (en) * | 2010-01-15 | 2010-07-21 | 南京邮电大学 | Automatic selection method for machine learning in cloud computing environment |
CN106067094A (en) * | 2016-06-14 | 2016-11-02 | 华北电力大学 | A kind of dynamic assessment method and system |
CN107766940A (en) * | 2017-11-20 | 2018-03-06 | 北京百度网讯科技有限公司 | Method and apparatus for generation model |
CN108197664A (en) * | 2018-01-24 | 2018-06-22 | 北京墨丘科技有限公司 | Model acquisition methods, device, electronic equipment and computer readable storage medium |
-
2018
- 2018-10-30 CN CN201811278795.7A patent/CN109635833A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101782976A (en) * | 2010-01-15 | 2010-07-21 | 南京邮电大学 | Automatic selection method for machine learning in cloud computing environment |
CN106067094A (en) * | 2016-06-14 | 2016-11-02 | 华北电力大学 | A kind of dynamic assessment method and system |
CN107766940A (en) * | 2017-11-20 | 2018-03-06 | 北京百度网讯科技有限公司 | Method and apparatus for generation model |
CN108197664A (en) * | 2018-01-24 | 2018-06-22 | 北京墨丘科技有限公司 | Model acquisition methods, device, electronic equipment and computer readable storage medium |
Non-Patent Citations (2)
Title |
---|
J. JEON, V. LAVRENKO 等,: "Automatic Image Annotation and Retrieval using Cross-Media Relevance Models", 《SIGIR "03: PROCEEDINGS OF THE 26TH ANNUAL INTERNATIONAL ACM SIGIR CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMAION RETRIEVAL》 * |
纪钢 等,: "图像信息处理及图像数据库模型分析", 《计算机工程与应用》 * |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110489240A (en) * | 2019-08-22 | 2019-11-22 | Oppo广东移动通信有限公司 | Image-recognizing method, device, cloud platform and storage medium |
CN112699906B (en) * | 2019-10-22 | 2023-09-22 | 杭州海康威视数字技术股份有限公司 | Method, device and storage medium for acquiring training data |
CN112699906A (en) * | 2019-10-22 | 2021-04-23 | 杭州海康威视数字技术股份有限公司 | Method, device and storage medium for acquiring training data |
CN111612034A (en) * | 2020-04-15 | 2020-09-01 | 中国科学院上海微系统与信息技术研究所 | Method and device for determining object recognition model, electronic equipment and storage medium |
CN111612034B (en) * | 2020-04-15 | 2024-04-12 | 中国科学院上海微系统与信息技术研究所 | Method and device for determining object recognition model, electronic equipment and storage medium |
CN111353477A (en) * | 2020-04-16 | 2020-06-30 | 银河水滴科技(北京)有限公司 | Gait recognition system and method |
CN111353477B (en) * | 2020-04-16 | 2024-04-19 | 公安部物证鉴定中心 | Gait recognition system and method |
CN111985565A (en) * | 2020-08-20 | 2020-11-24 | 上海风秩科技有限公司 | Picture analysis method and device, storage medium and electronic equipment |
CN112036465A (en) * | 2020-08-26 | 2020-12-04 | 中国建设银行股份有限公司 | Image recognition method, device, equipment and storage medium |
CN112598073A (en) * | 2020-12-28 | 2021-04-02 | 南方电网深圳数字电网研究院有限公司 | Power grid equipment image labeling method, electronic equipment and storage medium |
CN113642416A (en) * | 2021-07-20 | 2021-11-12 | 武汉光庭信息技术股份有限公司 | Test cloud platform for AI (Artificial intelligence) annotation and AI annotation test method |
CN114694139A (en) * | 2022-06-01 | 2022-07-01 | 中科航迈数控软件(深圳)有限公司 | Machining feature identification method and system for complex structural part of numerical control machine tool |
CN117422952A (en) * | 2023-10-31 | 2024-01-19 | 北京东方国信科技股份有限公司 | Artificial intelligent image recognition model management method and device and cloud edge service platform |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109635833A (en) | A kind of image-recognizing method and system based on cloud platform and model intelligent recommendation | |
CN109376844A (en) | The automatic training method of neural network and device recommended based on cloud platform and model | |
CN109816009A (en) | Multi-tag image classification method, device and equipment based on picture scroll product | |
CN109635918A (en) | The automatic training method of neural network and device based on cloud platform and preset model | |
CN108229478A (en) | Image, semantic segmentation and training method and device, electronic equipment, storage medium and program | |
CN110532996A (en) | The method of visual classification, the method for information processing and server | |
CN108780519A (en) | Structure learning in convolutional neural networks | |
CN108710847A (en) | Scene recognition method, device and electronic equipment | |
CN107679546A (en) | Face image data acquisition method, device, terminal device and storage medium | |
CN109242013A (en) | A kind of data mask method, device, electronic equipment and storage medium | |
CN106295591A (en) | Gender identification method based on facial image and device | |
CN110363084A (en) | A kind of class state detection method, device, storage medium and electronics | |
CN109902672A (en) | Image labeling method and device, storage medium, computer equipment | |
CN109145871A (en) | Psychology and behavior recognition methods, device and storage medium | |
CN111292262B (en) | Image processing method, device, electronic equipment and storage medium | |
CN109446783A (en) | A kind of efficient sample collection method and system of image recognition based on machine crowdsourcing | |
CN110232318A (en) | Acupuncture point recognition methods, device, electronic equipment and storage medium | |
CN111553419A (en) | Image identification method, device, equipment and readable storage medium | |
CN110610125A (en) | Ox face identification method, device, equipment and storage medium based on neural network | |
CN110222728A (en) | The training method of article discrimination model, system and article discrimination method, equipment | |
Gao et al. | A mobile application for plant recognition through deep learning | |
CN110826581A (en) | Animal number identification method, device, medium and electronic equipment | |
CN110516734A (en) | A kind of image matching method, device, equipment and storage medium | |
CN111126254A (en) | Image recognition method, device, equipment and storage medium | |
CN113505854A (en) | Method, device, equipment and medium for constructing facial image quality evaluation model |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190416 |