CN109977974A - The online experience platform of image detection and the image detecting method for using it - Google Patents
The online experience platform of image detection and the image detecting method for using it Download PDFInfo
- Publication number
- CN109977974A CN109977974A CN201711456181.9A CN201711456181A CN109977974A CN 109977974 A CN109977974 A CN 109977974A CN 201711456181 A CN201711456181 A CN 201711456181A CN 109977974 A CN109977974 A CN 109977974A
- Authority
- CN
- China
- Prior art keywords
- image
- platform
- detection
- online experience
- cargo
- 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
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
Abstract
This disclosure relates to field of artificial intelligence, a kind of online experience platform of image detection and the image detecting method using it are provided, the online experience platform of image detection includes: platform user end, for uploading the detection demand of image to be detected and user and showing image testing result；Platform Server, for calling corresponding algorithm interface to detect image to be detected according to detection demand；And arithmetic server, for running algorithm corresponding with the algorithm interface of Platform Server request call.Based on online experience platform, it solves the problems, such as trained deep learning model insertion must just be can be used into corresponding hardware device in the past, open deep learning algorithm interface, by platform to the calling of associated depth learning algorithm interface, user can experience online using different function deep learning algorithm as a result, the configuration of product function can be realized in conjunction with itself different demand simultaneously.
Description
Technical field
This disclosure relates to field of artificial intelligence, and in particular to a kind of online experience platform of image detection and use it
Image detecting method.
Background technique
After internet+epoch, artificial intelligence opens the new page of human history again.Artificial intelligence
(Artificial Intelligence), english abbreviation AI, it is research, develops intelligence for simulating, extending and extending people
Can theory, method, a new technological sciences of technology and application system.
Artificial intelligence is a branch of computer science, it attempts to understand essence of intelligence, and is produced a kind of new
The intelligence machine that can be made a response in such a way that human intelligence is similar, the research in the field include robot, language identification, image
Identification, natural language processing and expert system etc..Artificial intelligence is since the birth, and theory and technology is increasingly mature, application field
Also constantly expand, it is contemplated that the following artificial intelligence bring sci-tech product, it will be the wisdom of humanity " container ".Artificial intelligence
Can consciousness to people, thinking information process simulation.Artificial intelligence is not the intelligence of people, but can think deeply as people,
It may also be more than the intelligence of people.
Artificial intelligence be include very extensive science, it is made of different fields, such as machine learning, computer vision
Etc., generally speaking, the main target of artificial intelligence study is to enable the machine to be competent at some to usually require human intelligence
The complex work that could be completed.Image recognition is the key areas of artificial intelligence.
Present field of safety check carries out the identification and detection of target object, the retrieval of picture material using deep learning algorithm
It is even more the pioneer that deep learning algorithm uses with identification.Deep learning need to expend a large amount of GPU (graphics processor, English:
Graphics Processing Unit, abbreviation: GPU also known as shows core, vision processor, display chip etc.) carry out model
Training, instantly in more popular method, a kind of dispositions method is to obtain image or video in use site, carries out a period of time
Training after obtain model, and the identification and detection of target object are carried out to the image and video newly obtained using the model, should
Method is generally required using matched hardware device acquisition video or image, is placed on local GPU and is carried out in offline form
Training；Another deployment way, and generally use instantly, it is to use the picture laboratory to be understood at a large amount of safety check scenes
GPU is trained after obtaining model, which is carried out into hardware using.
There are two kinds of defects for both application methods, first, requiring to get spy using fixed hardware device collection
The image file for the formula that fixes is trained；Second, no matter field deployment GPU, or model insertion is mounted in hardware device.
Both methods, user do not have real experiences cross algorithm function and carefully evaluate whether the algorithm meet self-demand feelings
Under condition, user requires the buying for spending a large amount of money to carry out relevant device in advance, can just see the using effect of product, if
It is expected that differing too big with the function of description or effect, will cause largely to lose.Therefore, it is a kind of based on deep learning algorithm
The exploitation that wire body tests platform service seems extremely urgent.
Therefore, it is necessary to a kind of online experience platforms of new image detection.
Above- mentioned information are only used for reinforcing the understanding to the background of the disclosure, therefore it disclosed in the background technology part
It may include the information not constituted to the prior art known to persons of ordinary skill in the art.
Summary of the invention
A kind of online experience platform for being designed to provide image detection of the disclosure and image detecting method using it,
And then one or more is overcome the problems, such as caused by the limitation and defect due to the relevant technologies at least to a certain extent.
Other characteristics and advantages of the disclosure will be apparent from by the following detailed description, or partially by the disclosure
Practice and acquistion.
According to the disclosure in a first aspect, disclosing a kind of online experience platform of image detection, comprising:
Platform user end, for uploading the detection demand of image to be detected and user and showing image testing result；
Platform Server, for calling corresponding algorithm interface to detect image to be detected according to detection demand；With
And
Arithmetic server, for running algorithm corresponding with the algorithm interface of Platform Server request call.
According to an example embodiment of the disclosure, wherein online experience platform is based on Django framework establishment.
According to an example embodiment of the disclosure, wherein algorithm is deep learning algorithm.
According to an example embodiment of the disclosure, wherein deep learning algorithm is Fast-RCNN algorithm.
According to an example embodiment of the disclosure, wherein platform user end is also used to upload relevant to image to be detected
Supplementary text file.
According to an example embodiment of the disclosure, wherein whether detection demand includes: in detection image containing any contraband；
Whether detection image, which declares content with customs declaration, is consistent；It is carried secretly in detection image with the presence or absence of cargo；Or in detection image whether
Which kind of there are three wastes cargo and judge to be three wastes cargo.
According to an example embodiment of the disclosure, wherein contraband includes knife, rifle or explosive.
According to an example embodiment of the disclosure, wherein showing that image testing result includes: to outline according to coordinate data
The position of contraband or entrainment cargo in testing image, and the probability there are contraband or entrainment is marked in corresponding position；Root
According to the percentage of testing image and customs declaration content matching, it is for reference to provide following examination result: single goods is consistent, suggests looking into
It tests or single goods is not inconsistent；Or the testing result according to image, the cargo in image is judged for the probability of three wastes cargo, when probability is greater than
Show that cargo maximum probability is three wastes cargo to user when one predetermined threshold, and according to probability value show cargo it is most possible belonging to
The kind of three wastes cargo.
According to an example embodiment of the disclosure, wherein platform user end is PC or mobile phone mobile terminal.
According to the second aspect of the disclosure, a kind of online experience platform progress using any image detection above-mentioned is disclosed
The method of image detection, comprising:
The detection demand of image to be detected and user is uploaded to Platform Server by platform user end；
Platform Server called according to detection demand run on respective algorithms on arithmetic server to image to be detected into
Row detection；And
Image detection result is showed in platform user end.
According to an example embodiment of the disclosure, wherein image detection result be showed in platform user end including:
Arithmetic result is returned to Platform Server by arithmetic server；
Platform Server parses arithmetic result to obtain image detection result；And
Image detection result return platform user end is shown.
According to some example embodiments of the disclosure, it is based on online experience platform, solving must will train in the past
Deep learning model insertion the problem of just can be used into corresponding hardware device, open deep learning algorithm interface passes through
Platform can experience the deep learning algorithm using different function to the calling of associated depth learning algorithm interface, user online
As a result, the configuration of product function can be realized in conjunction with itself different demand simultaneously.
According to other example embodiments of the disclosure, it is equal the work such as to be trained to great amount of images for buying to GPU
It concentrates and carries out in the lab, to the open test interface of online experience platform after the completion of training, avoid user before usage experience
The waste for just needing that mint of money is spent to buy a large amount of hardware devices, while it is big to save equipment purchase, software deployment installation etc.
It the time of amount, improves work efficiency.
It should be understood that the above general description and the following detailed description are merely exemplary, this can not be limited
It is open.
Detailed description of the invention
Its example embodiment is described in detail by referring to accompanying drawing, above and other target, feature and the advantage of the disclosure will
It becomes more fully apparent.
Fig. 1 shows the block diagram of the online experience platform of the image detection according to one example embodiment of the disclosure.
Fig. 2 shows the sterograms according to the online experience platform of the image detection of one example embodiment of the disclosure.
Fig. 3 shows the flow chart that the method for image detection is carried out using the online experience platform of image detection shown in FIG. 1.
Specific example embodiment
Example embodiment is described more fully with reference to the drawings.However, example embodiment can be real in a variety of forms
It applies, and is not understood as limited to embodiment set forth herein；On the contrary, thesing embodiments are provided so that the disclosure will be comprehensively and complete
It is whole, and the design of example embodiment is comprehensively communicated to those skilled in the art.Identical appended drawing reference indicates in figure
Same or similar part, thus repetition thereof will be omitted.
In addition, described feature, structure or characteristic can be incorporated in one or more implementations in any suitable manner
In example.In the following description, many details are provided to provide and fully understand to embodiment of the disclosure.However,
It will be appreciated by persons skilled in the art that can with technical solution of the disclosure without one or more in specific detail,
Or it can be using other methods, constituent element, device, step etc..In other cases, it is not shown in detail or describes known side
Method, device, realization or operation are to avoid fuzzy all aspects of this disclosure.
Block diagram shown in the drawings is only functional entity, not necessarily must be corresponding with physically separate entity.
I.e., it is possible to realize these functional entitys using software form, or realized in one or more hardware modules or integrated circuit
These functional entitys, or these functional entitys are realized in heterogeneous networks and/or processor device and/or microcontroller device.
Flow chart shown in the drawings is merely illustrative, it is not necessary to including all content and operation/step,
It is not required to execute by described sequence.For example, some operation/steps can also decompose, and some operation/steps can close
And or part merge, therefore the sequence actually executed is possible to change according to the actual situation.
It should be understood that although herein various assemblies may be described using term first, second, third, etc., these groups
Part should not be limited by these terms.These terms are to distinguish a component and another component.Therefore, first group be discussed herein below
Part can be described as the second component without departing from the teaching of disclosure concept.As used herein, term " and/or " include associated
All combinations for listing any of project and one or more.
It will be understood by those skilled in the art that attached drawing is the schematic diagram of example embodiment, module or process in attached drawing
Necessary to not necessarily implementing the disclosure, therefore it cannot be used for the protection scope of the limitation disclosure.
A kind of online experience platform for being designed to provide image detection of the disclosure and image detecting method using it,
The online experience platform of image detection includes: platform user end, for uploading the detection demand of image to be detected and user and opening up
Diagram is as testing result；Platform Server, for calling corresponding algorithm interface to carry out image to be detected according to detection demand
Detection；And arithmetic server, for running algorithm corresponding with the algorithm interface of Platform Server request call.Based on online
Experience platform, solving in the past trained deep learning model insertion just must can be used into corresponding hardware device
Problem, open deep learning algorithm interface, by platform to the calling of associated depth learning algorithm interface, user can be in wire body
Test the deep learning algorithm for using different function as a result, can realize product function in conjunction with itself different demand simultaneously
Configuration.Meanwhile the buying to GPU, it work is trained etc. to great amount of images concentrates in the lab and carry out, after the completion of training
To the open test interface of online experience platform, user is avoided just to need that mint of money is spent to buy a large amount of hardware before usage experience
The waste of equipment, while a large amount of times such as equipment purchase, software deployment installation are saved, it improves work efficiency.
Below with reference to the image detection of Fig. 1-3 pairs of disclosure online experience platform and using its image detecting method into
Row is described in detail, wherein Fig. 1 shows the box of the online experience platform of the image detection according to one example embodiment of the disclosure
Figure；Fig. 2 shows the sterograms according to the online experience platform of the image detection of one example embodiment of the disclosure；Fig. 3 shows benefit
The flow chart of the method for image detection is carried out with the online experience platform of image detection shown in FIG. 1.
Fig. 1-2 is combined to carry out specifically the online experience platform of the image detection of one example embodiment of the disclosure first
It is bright, wherein Fig. 1 shows the block diagram of the online experience platform of the image detection according to one example embodiment of the disclosure；Fig. 2 shows
Out according to the sterogram of the online experience platform of the image detection of one example embodiment of the disclosure.
As shown in Figure 1, the online experience platform of image detection includes: platform user end 1, for upload image to be detected and
The detection demand of user simultaneously shows image testing result；Platform Server 2, for calling corresponding algorithm to connect according to detection demand
Mouth detects image to be detected；And arithmetic server 3, for running and the algorithm interface of Platform Server request call
Corresponding algorithm.
Wherein this platform be based on Django frame (Django is the Web application framework an of open source code, by
Python is write as.Using the framework mode of MT'V, i.e. model M, template T and view V.It is had been developed to for managing
Some websites based on news content under Lao Lunsi Publishing Group, as CMS (Content Management System) software) building
Network service platform, there is provided after the image detection based on deep learning for meeting different function demand for the characteristic of the platform
Platform algorithm, user upload the image and relevant complementary character property file for needing to detect, and are called from the background by interface remote
The corresponding deep learning algorithm at arithmetic server end is detected and analyzed upload image and file, and quickly ties correlation
Fruit is back to the online experience platform, makes user that can experience the application of related software before installing equipment.
Herein it should be strongly noted that the online experience platform of the image detection of the disclosure is not limited to based on depth
The image detection backstage algorithm of habit is also possible to based on other image detection algorithms.
The online experience platform of the image detection mainly includes the following aspects:
(1) platform user end uploads the inspection of readable image to be detected and its relevant auxiliary agents file and user
Request demand is surveyed to Platform Server；
(2) after Platform Server receives associated materials, according to the detection of user request demand (in such as detection image whether
Contain the special articles/contraband such as knife, rifle or explosive；Check whether scan image declares content with customs declaration and be consistent；It checks
It is carried secretly in image cargo with the presence or absence of cargo；Which kind of or with the presence or absence of three wastes cargo and judge to be three wastes cargo etc. in detection image
Deng), different algorithm interfaces is called, algorithm is run on independent deep learning arithmetic server, utilizes Fast-RCNN algorithm
(Fast-RCNN algorithm is a kind of image processing algorithm that target detection is carried out using deep learning, and Fast-RCNN is built upon
Effectively classified on depth convolutional neural networks before and target detection, but it has used several innovative points to improve
Trained and test speed, and also improve detection accuracy) each layer feature for extracting associated picture detected, and to input
Complementary character property file carries out data analysis, and both comprehensive analysis (exists as a result, providing final algorithm conclusion in such as image
The probability of the contrabands such as weapons is the possible coordinate of how many and contraband；Scan image and customs declaration declare content matching percentage
Than etc.)；
(3) result is returned to Platform Server by arithmetic server, and platform arithmetic result is parsed and be presented to user, such as
The position of the contrabands such as knife in image, rifle or explosive is outlined according to coordinate data or carries the position of cargo secretly, and in corresponding positions
Set the probability marked there are contraband or entrainment；According to the percentage of obtained scan image and customs declaration content matching, give
It is for reference intuitively to check result for the examinations such as " single goods is consistent " " it is recommended that examination " and " single goods is not inconsistent " out；Or according to image
Testing result, judge that the cargo in image for the probability of three wastes cargo, is shown when probability is greater than a predetermined threshold to user
Cargo maximum probability is three wastes cargo, and the kind of the most possible affiliated three wastes cargo of cargo is shown according to probability value.
Herein it should be strongly noted that the online experience platform of the image detection of one example embodiment of the disclosure uses
Django Web frame is disposed, but the online experience platform of the image detection of the disclosure is not limited to this, and also can be used
Other Web frames are disposed, and identical effect can also be obtained.
According to an example embodiment of the disclosure, wherein platform user end is PC or mobile phone mobile terminal.
The sterogram and workflow of the online experience platform of the image detection of the disclosure are as shown in Figure 2.
The process that concrete operations are carried out using the online experience platform of image detection is illustrated how below by two examples:
Whether example 1: user needs to experience gun detection function, that is, check and upload in image containing violated objects such as gun
Product, user upload container cargo X-ray scan image in the online experience platform of image detection, and platform calls corresponding function
Algorithm api interface image is tested, algorithm returns to test result to platform, if containing the contrabands such as gun, can
The detection block coordinate of target object is returned, and determines that it is the size of the probability of rifle, platform is red drawn in the figure according to coordinate
Color rectangle frame simultaneously marks probability for gun；
Example 2: user, which needs to experience, schemes single comparing function, that is, checks that the cargo scan image of upload and customs declaration declare letter
It whether consistent ceases.User needs to upload the X-ray (X-ray) of container cargo first in the online experience platform of image detection
Scan image, then customs declaration comparison is uploaded, backstage algorithm utilizes deep learning algorithm discharging of goods image feature information, and passes through
Data analysis obtains and corresponds to the HS-CODE of cargo on customs declaration (HS-CODE is the letter of "HS"("Harmonized Commodity Description and Coding System")
Claim.Coding coordination system is formulated by international council, customs, and English name is The Harmonization System Code
It (HS-Code), is the system for be recruited/answering the entry and exit of various different products the drawback tax rate to carry out quantitative management.Customs, various countries,
Commodity entry-exit management mechanism confirms merchandise classification, carries out category management, audit tariff standard, examines marketing quality index
Fundamental be exactly the general proof of identification of import-export commodity --- HS-CODE/HS coding), will be corresponding in background data base
The image feature information of HS-CODE is matched with the characteristics of image acquired, and provides a matching confidence level；The confidence
After degree returns to platform, platform parses the confidence level, is translated into the number of hundred-mark system, and score is higher, then matches
Degree is higher, and according to the score value size, provides intuitive judgment information, such as " being consistent substantially ", " it is recommended that examination ", and " single goods is not inconsistent "
Deng the suggestion that user is returned by platform can decide the processing to the cargo in its sole discretion.
Image detection is carried out below with reference to online experience platform using any above-mentioned image detection of the Fig. 3 to the disclosure
Method be illustrated.
Fig. 3 shows the flow chart that the method for image detection is carried out using the online experience platform of image detection shown in FIG. 1.
In S301, the detection demand of image to be detected and user is uploaded to Platform Server by platform user end.
In S302, Platform Server calls the respective algorithms run on arithmetic server to be detected according to detection demand
Image is detected.
In S303, image detection result is showed in platform user end.
According to an example embodiment of the disclosure, wherein image detection result be showed in platform user end including:
Arithmetic result is returned to Platform Server by arithmetic server；
Platform Server parses arithmetic result to obtain image detection result；And
Image detection result return platform user end is shown.
By above detailed description, those skilled in the art is it can be readily appreciated that according to the embodiment of the present disclosure in wire body
One or more of test platform and had the following advantages that using its image detecting method.
According to some example embodiments of the disclosure, it is based on online experience platform, solving must will train in the past
Deep learning model insertion the problem of just can be used into corresponding hardware device, open deep learning algorithm interface passes through
Platform can experience the deep learning algorithm using different function to the calling of associated depth learning algorithm interface, user online
As a result, the configuration of product function can be realized in conjunction with itself different demand simultaneously.
According to other example embodiments of the disclosure, it is equal the work such as to be trained to great amount of images for buying to GPU
It concentrates and carries out in the lab, to the open test interface of online experience platform after the completion of training, avoid user before usage experience
The waste for just needing that mint of money is spent to buy a large amount of hardware devices, while it is big to save equipment purchase, software deployment installation etc.
It the time of amount, improves work efficiency.
Those skilled in the art after considering the specification and implementing the invention disclosed here, will readily occur to its of the disclosure
Its embodiment.The disclosure is intended to cover any variations, uses, or adaptations of the disclosure, these modifications, purposes or
Person's adaptive change follows the general principles of this disclosure and including the undocumented common knowledge in the art of the disclosure
Or conventional techniques.The description and examples are only to be considered as illustrative, and the true scope and spirit of the disclosure are by following
Claim is pointed out.
It should be understood that the present disclosure is not limited to the precise structures that have been described above and shown in the drawings, and
And various modifications and changes may be made without departing from the scope thereof.The scope of the present disclosure is only limited by the accompanying claims.
Claims (11)
1. a kind of online experience platform of image detection, comprising:
Platform user end, for uploading the detection demand of image to be detected and user and showing image testing result；
Platform Server, for calling corresponding algorithm interface to detect image to be detected according to detection demand；And
Arithmetic server, for running algorithm corresponding with the algorithm interface of Platform Server request call.
2. online experience platform according to claim 1, which is characterized in that wherein online experience platform is based on Django frame
Framework is built.
3. online experience platform according to claim 1, which is characterized in that wherein algorithm is deep learning algorithm.
4. online experience platform according to claim 3, which is characterized in that wherein deep learning algorithm is Fast-RCNN
Algorithm.
5. online experience platform according to claim 1, which is characterized in that wherein platform user end be also used to upload with to
The relevant supplementary text file of detection image.
6. online experience platform according to claim 1, which is characterized in that wherein detecting demand includes: in detection image
Whether any contraband is contained；Whether detection image, which declares content with customs declaration, is consistent；It is carried secretly in detection image with the presence or absence of cargo；Or
It whether there is three wastes cargo in detection image and judge to be which kind of three wastes cargo.
7. online experience platform according to claim 6, which is characterized in that wherein contraband includes knife, rifle or explosive.
8. online experience platform according to claim 1, which is characterized in that wherein show that image testing result includes: root
Contraband in testing image is outlined according to coordinate data or carries the position of cargo secretly, and marks in corresponding position that there are contraband or folders
Probability with object；According to the percentage of testing image and customs declaration content matching, it is for reference to provide following examination result: single
Goods is consistent, suggestion is checked or single goods is not inconsistent；Or the testing result according to image, judge the cargo in image for the general of three wastes cargo
Rate shows that cargo maximum probability is three wastes cargo to user when probability is greater than a predetermined threshold, and shows cargo according to probability value
The kind of three wastes cargo belonging to most possible.
9. online experience platform according to claim 1, which is characterized in that wherein platform user end is PC or hand
Machine mobile terminal.
10. the side that a kind of online experience platform using the image detection as described in claim 1-9 is any carries out image detection
Method, comprising:
The detection demand of image to be detected and user is uploaded to Platform Server by platform user end；
Platform Server calls the respective algorithms run on arithmetic server to examine image to be detected according to detection demand
It surveys；And
Image detection result is showed in platform user end.
11. online experience platform according to claim 1, which is characterized in that be wherein showed in image detection result flat
Platform user terminal includes:
Arithmetic result is returned to Platform Server by arithmetic server；
Platform Server parses arithmetic result to obtain image detection result；And
Image detection result return platform user end is shown.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711456181.9A CN109977974A (en) | 2017-12-28 | 2017-12-28 | The online experience platform of image detection and the image detecting method for using it |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711456181.9A CN109977974A (en) | 2017-12-28 | 2017-12-28 | The online experience platform of image detection and the image detecting method for using it |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109977974A true CN109977974A (en) | 2019-07-05 |
Family
ID=67074256
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711456181.9A Pending CN109977974A (en) | 2017-12-28 | 2017-12-28 | The online experience platform of image detection and the image detecting method for using it |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109977974A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103917862A (en) * | 2011-09-07 | 2014-07-09 | 拉皮斯坎系统股份有限公司 | X-ray inspection system that integrates manifest data with imaging/detection processing |
| CN104751308A (en) * | 2013-12-30 | 2015-07-01 | 同方威视技术股份有限公司 | Whole process visualization system and whole process visualization method for logistics articles |
| CN105372715A (en) * | 2015-12-14 | 2016-03-02 | 同方威视技术股份有限公司 | Cargo transportation security check method, system and security check apparatus |
| CN106708823A (en) * | 2015-07-20 | 2017-05-24 | 阿里巴巴集团控股有限公司 | Search processing method, apparatus and system |
| CN106803301A (en) * | 2017-03-28 | 2017-06-06 | 广东工业大学 | A kind of recognition of face guard method and system based on deep learning |
| US20170177972A1 (en) * | 2015-12-21 | 2017-06-22 | Nokia Technologies Oy | Method for analysing media content |
| CN107169598A (en) * | 2017-05-05 | 2017-09-15 | 上海斐讯数据通信技术有限公司 | A kind of weather prediction method and system based on deep learning |
-
2017
- 2017-12-28 CN CN201711456181.9A patent/CN109977974A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103917862A (en) * | 2011-09-07 | 2014-07-09 | 拉皮斯坎系统股份有限公司 | X-ray inspection system that integrates manifest data with imaging/detection processing |
| CN104751308A (en) * | 2013-12-30 | 2015-07-01 | 同方威视技术股份有限公司 | Whole process visualization system and whole process visualization method for logistics articles |
| CN106708823A (en) * | 2015-07-20 | 2017-05-24 | 阿里巴巴集团控股有限公司 | Search processing method, apparatus and system |
| CN105372715A (en) * | 2015-12-14 | 2016-03-02 | 同方威视技术股份有限公司 | Cargo transportation security check method, system and security check apparatus |
| US20170177972A1 (en) * | 2015-12-21 | 2017-06-22 | Nokia Technologies Oy | Method for analysing media content |
| CN106803301A (en) * | 2017-03-28 | 2017-06-06 | 广东工业大学 | A kind of recognition of face guard method and system based on deep learning |
| CN107169598A (en) * | 2017-05-05 | 2017-09-15 | 上海斐讯数据通信技术有限公司 | A kind of weather prediction method and system based on deep learning |
Non-Patent Citations (1)
| Title |
|---|
| 陈敏: "《认知计算导论》", 30 April 2017, 华中科技大学出版社 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Cabrio et al. | Five years of argument mining: A data-driven analysis. | |
| Gosiewska et al. | Do not trust additive explanations | |
| CN108734184B (en) | Method and device for analyzing sensitive image | |
| EP3699579B1 (en) | Inspection method and inspection device and computer-readable medium | |
| US20190130233A1 (en) | Method and apparatus for improved segmentation and recognition of images | |
| CN112966823B (en) | Site identification method based on knowledge graph reasoning | |
| CN108550054B (en) | Content quality evaluation method, device, equipment and medium | |
| US9514496B2 (en) | System for management of sentiments and methods thereof | |
| CN107077640A (en) | Analyzed via experience ownership, it is qualification and intake unstructured data sources system and processing | |
| Suglia et al. | CompGuessWhat?!: A multi-task evaluation framework for grounded language learning | |
| CN110309402A (en) | Detect the method and system of website | |
| Jia et al. | A two-dimensional complexity evaluation model of megaprojects based on structure and attributes | |
| CN114118398A (en) | Method and system for detecting target type website, electronic equipment and storage medium | |
| Subhashini et al. | Assessing the effectiveness of a three-way decision-making framework with multiple features in simulating human judgement of opinion classification | |
| CN109977974A (en) | The online experience platform of image detection and the image detecting method for using it | |
| CN116415581A (en) | Teaching data analysis system based on intelligent education | |
| CN108694404B (en) | Method and device for cargo inspection based on radiation image | |
| CN109993165A (en) | The identification of tablet plate medicine name and tablet plate information acquisition method, device and system | |
| CN115525750A (en) | Robot phonetics detection visualization method and device, electronic equipment and storage medium | |
| Busch et al. | Automated verification of a topographic reference dataset: System design and practical results | |
| CN115841316A (en) | Method and system for matching human posts, electronic equipment and storage medium | |
| Zabrodin et al. | Development of an automated system for recognizing the parameters of a railway carriage (railway tanks) | |
| Damian et al. | Checklist‐based techniques with gamification and traditional approaches for inspection of interaction models | |
| Muñoz et al. | Diseño y desarrollo de aplicación móvil para la clasificación de flora nativa chilena utilizando redes neuronales convolucionales | |
| CHIOU et al. | Machine learning tool development in fire safety design review |
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 |