CN107480587A - A kind of method and device of model configuration and image recognition - Google Patents
A kind of method and device of model configuration and image recognition Download PDFInfo
- Publication number
- CN107480587A CN107480587A CN201710544836.1A CN201710544836A CN107480587A CN 107480587 A CN107480587 A CN 107480587A CN 201710544836 A CN201710544836 A CN 201710544836A CN 107480587 A CN107480587 A CN 107480587A
- Authority
- CN
- China
- Prior art keywords
- identification
- video
- identification model
- parameter
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/94—Hardware or software architectures specially adapted for image or video understanding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
Abstract
A kind of model configuration of disclosure and the method and device of image recognition, client obtains at least one identification parameter from server in this method, and according at least one identification parameter got and local preset parameter is stored in advance in, configure at least one identification model.Because client dynamically can obtain the identification parameter for configuring identification model from server, the identification parameter got is different, and the identification model configured is also different, and the object that the identification model configured can be identified is also different.In image recognition processes, each identification model only needs the partial video frame of video, image recognition can be quickly carried out, and when object is not present in the partial video frame for determining identification, changes other identification models to carry out image recognition by the another partial video frame of the video.
Description
Technical field
The application is related to field of computer technology, more particularly to the method and dress of a kind of configuration of model and image recognition
Put.
Background technology
With the continuous development of computer technology, more and more emerging services based on new science and technology are presented in face of people,
These business also bring brand-new experience while business efficiency is improved for users.
Currently, image recognition technology has been used in multiple business scene, and image recognition technology and other emerging technologies
Combined use, also provide new approaches for the further development of multiple business.For example, the implementation procedure of some current business
In, it is necessary to which object is identified by client by user.User can be scanned by terminal-pair object, be got
The video of the object, and client will carry out image recognition by the identification model trained to the video, when it is determined that passing through
When the identification model identifies the object, then the execution of business is triggered.
Based on prior art, it is necessary to make client possess the dynamic expansion ability of image recognition, and lift client
Image recognition efficiency.
The content of the invention
The method that the embodiment of the present application provides a kind of configuration of model, to solve in the prior art, during process of service execution
Client does not possess the problem of image recognition dynamic expansion ability.
The embodiment of the present application provides a kind of method of model configuration, including：
Client obtains at least one identification parameter that server is sent；
According at least one identification parameter and local preset parameter is stored in advance in, configures at least one identification
Model, the identification model configured using different identification parameters are used to identify different objects.
The embodiment of the present application provides a kind of device of model configuration, to solve in the prior art, during process of service execution
Client does not possess the problem of image recognition dynamic expansion ability.
The embodiment of the present application provides a kind of device of model configuration, including：
Acquisition module, obtain at least one identification parameter that server is sent；
Configuration module, according at least one identification parameter and local preset parameter is stored in advance in, configuration is extremely
A few identification model, the identification model configured using different identification parameters are used to identify different objects.
The equipment that the embodiment of the present application provides a kind of configuration of model, to solve in the prior art, during process of service execution
Client does not possess the problem of image recognition dynamic expansion ability.
The embodiment of the present application provides a kind of equipment of model configuration, including：One or more memories and processor,
The memory storage program, and be configured to by one or more of computing device following steps：
Obtain at least one identification parameter that server is sent；
According at least one identification parameter and local preset parameter is stored in advance in, configures at least one identification
Model, the identification model configured using different identification parameters are used to identify different objects.
The embodiment of the present application provides a kind of method of image recognition, to solve in the prior art, during process of service execution
The problem of client image recognition is less efficient.
The embodiment of the present application provides a kind of method of image recognition, including：
Obtain video；
From at least one identification model enabled, identification model is selected；
By the identification model of selection, identify and whether there is object in m frame of video in the video；
If being not present, identification model, and the identification by reselecting are selected from other identification models enabled again
N frame of video in video described in Model Identification, untill the object is identified, wherein, m and n are positive integer, described
M frame of video and the n frame of video are incomplete same.
The embodiment of the present application provides a kind of device of image recognition, to solve in the prior art, during process of service execution
The problem of client image recognition is less efficient.
The embodiment of the present application provides a kind of device of image recognition, including：
Acquisition module, obtain video；
Selecting module, from least one identification model enabled, select identification model；
Identification module, by the identification model of selection, identify and whether there is target in m frame of video in the video
Thing；If being not present, identification model is selected from other identification models enabled again, and the identification model by reselecting is known
N frame of video in not described video, untill the object is identified, wherein, m and n are positive integer, and the m regard
Frequency frame and the n frame of video are incomplete same.
The embodiment of the present application provides a kind of equipment of image recognition, to solve in the prior art, during process of service execution
The problem of client image recognition is less efficient.
The embodiment of the present application provides a kind of equipment of image recognition, including：One or more memories and processor,
The memory storage program, and be configured to by one or more of computing device following steps：
Obtain video；
From at least one identification model enabled, identification model is selected；
By the identification model of selection, identify and whether there is object in m frame of video in the video；If do not deposit
Again identification model is being selected from other identification models enabled, and regarded described in the identification of the identification model by reselecting
N frame of video in frequency, untill the object is identified, wherein, m and n are positive integer, the m frame of video and institute
It is incomplete same to state n frame of video.
Above-mentioned at least one technical scheme that the embodiment of the present application uses can reach following beneficial effect：
In the embodiment of the present application, because client dynamically can obtain the knowledge for configuring identification model from server
Other parameter, the identification parameter got is different, and the identification model configured is also different, and the identification model configured can be identified
Object it is also different.In other words, the identification model set in client is not changeless, its mesh that can be identified
Mark thing changes with the identification parameter that server is sent, so that client possesses the dynamic expansion energy of image recognition
Power.Moreover, in image recognition processes, each identification model only needs based on the partial video in complete video client
Frame, image recognition can be quickly carried out, and when object is not present in the partial video frame for determining identification, change other knowledges
Other model to carry out image recognition to another part frame of video.So for compared to prior art, client can not only be made
Possess the ability of Dynamic Recognition object, also can effectively improve the efficiency of client image recognition.
Brief description of the drawings
Accompanying drawing described herein is used for providing further understanding of the present application, forms the part of the application, this Shen
Schematic description and description please is used to explain the application, does not form the improper restriction to the application.In the accompanying drawings：
Fig. 1 is the schematic diagram for the model configuration process that the embodiment of the present application provides；
Fig. 2 is the process schematic for the image recognition that the embodiment of the present application provides；
Fig. 3 is the detailed process schematic diagram for the image recognition processes that the embodiment of the present application provides；
Fig. 4 is the detailed process for the client executing business that the embodiment of the present application provides；
Fig. 5 is the schematic device for the model configuration that the embodiment of the present application provides；
Fig. 6 is the schematic device for the image recognition that the embodiment of the present application provides；
Fig. 7 is the equipment schematic diagram for the model configuration that the embodiment of the present application provides；
Fig. 8 is the equipment schematic diagram for the image recognition that the embodiment of the present application provides.
Embodiment
In order that those skilled in the art more fully understand the technical scheme in the application, it is real below in conjunction with the application
The accompanying drawing in example is applied, the technical scheme in the embodiment of the present application is clearly and completely described, it is clear that described implementation
Example only some embodiments of the present application, rather than whole embodiments.It is common based on the embodiment in the application, this area
The every other embodiment that technical staff is obtained under the premise of creative work is not made, it should all belong to the application protection
Scope.
In the prior art, the identification model configured in client is generally all changeless, and these identification models are led to
Fixed object can only be often identified, and the dynamic expansion of image recognition can not be realized.Therefore, in this application, client can
To obtain the identification parameter for configuring different identification models from server, identification parameter can control what identification model can identify
Object, therefore, the identification parameter got is different, and the object that identification model can be identified is also different, thus effectively
The object identification ability to client carried out dynamic expansion, so as to improve image of the client in process of service execution
Recognition capability.Wherein, the application to object carry out image recognition executive agent can with client or terminal, under
The model collocation method and image-recognizing method that face is provided the application only by taking client as an example illustrate.
Fig. 1 is the schematic diagram for the model configuration process that the embodiment of the present application provides, and specifically includes following steps：
S102：Client obtains at least one identification parameter that server is sent.
In the embodiment of the present application, client can be obtained first during image recognition is carried out to object from server
At least one identification parameter is got, wherein, the identification parameter that server provides to client is different, what client can be identified
Object is also just different.
The execution action that client obtains at least one identification parameter from server can meet necessarily monitoring itself
Triggered during condition, e.g., when client monitors start to itself, then actively can obtain at least one knowledge from server
Other parameter, at least one identification parameter can also be obtained from server when monitoring to trigger the specified function of itself setting.And
Multiple identification parameters that client obtains from server can be different identification parameters corresponding to different business or same
Multiple identification parameters corresponding to one business.
S104：According at least one identification parameter and local preset parameter is stored in advance in, configuration at least one
Individual identification model, the identification model configured using different identification parameters are used to identify different objects.
Client can be joined after server gets at least one identification parameter according to local fixing is stored in advance in
Number, configures different identification models.Wherein, referred to herein as preset parameter refer to what is be pre-configured with client, not with mesh
Mark the parameter of thing change.Such as, it is necessary to be carried by certain feature during client is by identification model progress image recognition
Mode is taken, characteristic, and then the characteristic by extracting are extracted from the video got, carries out image recognition.With
It will not generally be changed in the feature extraction mode of extraction characteristic, so, the parameter related to feature extraction mode is then
It can be preset parameter.
Certainly, preset parameter and the parameter or other specification related to feature extraction mode are not merely referred to, in a word
Referred to herein as preset parameter do not change with the object that client can identify.
And the identification parameter got from server is then to determine identification model can recognize that the pass of which object
Key, identification model can specifically identify which object is determined by identification parameter by obtained characteristic, therefore, lead to
Identification to different target thing can be realized by crossing the identification model that different identification parameters are configured, so, join relative to fixed
For number, identification parameter is then variable element.
Client can get at least one identification model mark during identification model is configured from server.
After client gets identification model mark, each identification model can be directed to and identified, joined from local fixing is stored in advance in
The preset parameter corresponding to the identification model is determined in number, and is determined and the identification mould from the identification parameter got
Identification parameter corresponding to type mark.
After client determines each identification model mark corresponding identification parameter and preset parameter, it can be respectively configured
Each identification model, and enable each identification model configured, with subsequent process, by these identification models for enabling and
The video got, carry out image recognition.Wherein, one or more identification may be needed by configuring same identification model
Parameter.
It should be noted that being previously stored with client, each identification model mark is corresponding between each preset parameter to close
System, and client is in addition to needing to get identification model mark and identification parameter, it is also desirable to get identification model mark
With the corresponding relation of identification parameter.Client obtains identification parameter and each identification model mark and can synchronously carried out, i.e., obtains simultaneously
Identification model mark corresponding to taking each identification parameter and each identification parameter difference, successively can also sequentially carry out obtaining each knowledge
Other parameter and each identification model mark.
In from the above as can be seen that because client can be obtained dynamically for configuring identification model from server
Identification parameter, the identification parameter that gets is different, and the identification model configured is also different, and the identification model configured can be known
The object not gone out is also different.So no matter how the object for needing in process of service execution client to identify changes, client
End only need to get corresponding identification parameter from server, you can the identification model that can recognize that object is configured, this
Sample allows for the dynamic expansion ability that client possesses image recognition.
Client by these identification models and can be got after at least one identification model of configuration is enabled
Video, carries out image recognition, and detailed process is as shown in Figure 2.
Fig. 2 is the process schematic for the image recognition that the embodiment of the present application provides, and specifically includes following steps：
S202：Obtain video.
Client can get the video needed for image recognition during image recognition is carried out.Wherein, client
Actual object can be scanned, by such as imaging first-class image collecting device to get on object to be identified
Video.One section of video for carrying out image recognition can certainly be obtained from other-end or server.
S204：From at least one identification model enabled, identification model is selected.
After client gets above-mentioned video, an identification mould can be selected from least one identification model enabled
Type, and then during follow-up, some frame of video in the video are identified by the identification model selected.Wherein, enable
At least one identification model be client previously according at least one identification parameter for being got from server, and deposit in advance
Store up what the preset parameter in local configured.
S206：By the identification model of selection, identify and whether there is object in m frame of video in the video；If
In the presence of then performing step S208；If being not present, step S210 is performed；
S208：Perform business corresponding to the object；
S210：Again identification model, and the identification model by reselecting are selected from other identification models enabled
N frame of video in the video is identified, untill the object is identified, wherein, m and n are positive integer, and the m is individual
Frame of video and the n frame of video are incomplete same.
During image recognition, client can choose m frame of video from the video got, and by selecting
Identification model, this m frame of video is identified, to determine to whether there is object in this m frame of video.Wherein, here
Object can refer to trigger client executing business object.Client identifies an industry from the video got
The corresponding object of business, can trigger and perform the business.In the embodiment of the present application, different business can correspond to different
Object, a business can also correspond to multiple objects.
When client, which identifies, object not be present in m frame of video, n can be chosen again from the video got
Frame of video, and select an identification model again from other identification models enabled, to pass through the knowledge selected again
Other model carries out image recognition to this n frame of video selected again.
Wherein, m and n is positive integer, and m and n be able to can not also be waited with equal, also, m frame of video and n frame of video
The simply partial video frame in above-mentioned video, and m frame of video and n frame of video are also incomplete same, i.e. client continuous two
It is partly identical that the frame of video of secondary identification, which at most only has,.
It should be noted that m frame of video and n frame of video are incomplete same, refer at least there is one in m frame of video
Individual frame of video is not present in n described frame of video, meanwhile, there is also at least one frame of video it is institute in n frame of video
It is not present in the m frame of video stated.
When client is determined still identify the target in n frame of video by the identification model selected again
During thing, then it can continue to choose some frame of video from the video got by the way of same as described above, and enable
An identification model different from last time, and then the identification model by selecting are selected in identification model, if to selecting
Dry frame of video carries out image recognition, untill object is identified.
In other words, client is identified and whether there is in the video got by way of constantly switching identification model
Object.When client does not identify object by the identification model selected from a part of frame of video in video, you can
Another identification model is switched to, so that another part frame of video in the video to be identified, wherein, this two-part video
Frame is incomplete same, as long as and client could not identify object from video, you can in this way always identify under
Go, untill object is identified from video.
In the embodiment of the present application, client during selecting video frame, can only choose a frame of video (i.e. m from video
Take 1), and next frame of video (i.e. n takes 1) of the frame of video can be only chosen during image recognition next time, by that analogy.Client
An identification model list can be safeguarded, and repeating query selects the knowledge in the identification model list according to each identification model enabled
Other model, to carry out image recognition to different video frame.
Whole image identification process is more apparent from for convenience, below will by way of illustration, will be whole
Individual process is completely described, as shown in Figure 3.
Fig. 3 is the detailed process schematic diagram for the image recognition processes that the embodiment of the present application provides.
It is assumed that client selects first identification model from the identification model list of maintenance, for being regarded to what is got
The frame of video of t is identified in frequency, when not identifying object from the frame of video of t by first identification model
When, then second identification model is can switch to, and the frame of video at t+1 moment in the video is identified, by that analogy.And work as
When not identifying object from the frame of video of the video by last identification model in identification model list, then again
First identification model is selected, the frame of video in video is identified.
It should be noted that in actual applications, object and may be not present in the video that client is got, for
For such case, when the frame of video in video is identified by the identification model selected for client, two are likely to be obtained
Kind result, a kind of result are that client successfully have identified the object included in video, but are not object；Another result
It is then that client does not identify any object by the identification model of selection from video, the knowledge that client obtains in this case
Other result is recognition failures.It is also a kind of it may be the case that be to include object in the video that client is got, it is but objective
Which identification model no matter family end select, and it can not be identified.
So in the embodiment of the present application, when client is determined after setting time, still not over the knowledge enabled
Other model during success object, then can send the video got to server from the video got, to pass through service
Device to carry out image recognition to the frame of video in the video, is identified result.
Wherein, recognition result here can be divided into two kinds of situations, and one, identify successfully, i.e., it is successful to be identified from the video
Go out object；2nd, recognition failures, i.e. do not identify object from the video.Recognition failures are there is also two kinds of possibility, and one
Kind is that server does not identify any object from the video, although another kind is server have identified thing from video
Body, but the object is not object.
Server can will be identified result and return to client, by client according to the recognition result, it is determined whether hold
The corresponding business of row.
Client also can be by monitoring the number of the image recognition consumed in whole image identification process, to determine whether
The video for needing to get is sent to server, replaces client that the frame of video in video is identified by server generation,
It is identified result.
Specifically, after client is determined by setting identification number, it is still not successful to be identified from the video
During object, then the video can be sent to server.Wherein, client often selects an identification model identification frame of video one
Secondary, that is, can be regarded as is an image recognition.
Setting identification number mentioned above can determine according to the quantity of the identification model enabled, e.g., if enabling 3
Identification model, the then setting identify that number could be arranged to 9 times.Setting identification number can be not less than the number of the identification model enabled
Amount.
Client can then trigger when object be present in identifying the video and perform business corresponding to the object.
And during execution business is triggered, image corresponding to the business can be first shown, then carries out other business steps again.Its
In, different business can correspond to different images.Image corresponding to business can be prestored in the client, and client also may be used
By image information address, to obtain image information and rendering parameter corresponding to image, and then render and show the image.This
In the image information mentioned refer to the particular content of image, and rendering parameter is then the parameter on controlling image display pattern.
And the image in the embodiment of the present application can be augmented reality (Augmented Reality, AR) image, certainly, client wash with watercolours
What is contaminated and show can also be other images.
In order to which further clearly explanation client carries out the process of model configuration, image recognition in business scenario, under
Face will be described by taking the business scenario of a reality as an example, as shown in Figure 4.
Fig. 4 is the detailed process for the client executing business that the embodiment of the present application provides.
For example, it is assumed that an operation regulation user identifies that lantern, firecracker, good fortune word can be got respectively using client
The coupon of different amounts.When user successfully identifies any one in these three objects using client, this can be triggered
Business, but image corresponding to shown business when triggering the business by different objects is different.During client terminal start-up,
The identification parameter on these three objects can be got from server, and is directed to these three objects, according to what is got
Three identification parameters and the preset parameter prestored, it is respectively configured and enables the identification mould for identifying these three objects
Type, and the identification model list for including these three identification models is safeguarded, wherein, the row of identification model in the identification model list
Row order be：Firecracker identification model, good fortune word identification model, lantern identification model.
When user performs the business, if being first scanned using client to lantern, client can get on
The video of lantern.Client can select to come the firecracker identification model of first in identification model list, for identifying that this is regarded
Frame of video a in frequency, (because firecracker identification model can only identify when it is determined that not identifying any object from frame of video a
Firecracker, for good fortune word, lantern, the equal None- identified of firecracker identification model comes out, so, lantern is entered using firecracker identification model
Row identification will not identify any object), then second good fortune word identification model is selected, for identifying next frame of video b,
And when it is determined that not identifying any object from frame of video b, then the 3rd lantern identification model is selected, for identifying frame of video
c.When it is determined that identifying lantern from frame of video c by lantern identification model, then corresponding image information and wash with watercolours are obtained
Parameter is contaminated, renders image as shown in Figure 4, and get the coupon that lantern corresponds to amount.
In from the above as can be seen that when client identifies object by the identification model of selection, it is only necessary to identify
Partial video frame in whole video, and when it is determined that object is not present, select other identification models to identify another in the video
A part of frame of video, to determine to whether there is object in the video, wherein, the incomplete phase of two parts frame of video continuously identified
Together.That is, identification model object can essentially be identified by a frame of video in the video, and
It is determined that when not identifying object by the identification model of selection, switch to next identification model and identify the next of the video
Frame of video.So each identification model during object is identified, is not known to all videos frame of the video
Not, relative to the method for needing all videos frame of the video to be identified using each identification model in the prior art,
The above method that the application provides can effectively improve the image recognition efficiency of client.
Client can also identify object, the object can by the identification model selected from the video got
Can be the object that triggering business performs, it is also possible to other objects.The object that client can will identify that is corresponding with business
Object is matched, and when it is determined that both are identical, then triggers execution business, when it is determined that both are different, then can be reselected
Identification model, some frame of video chosen from the video are identified.
It should be noted that in addition to the object in upper example, client can also identify bar code, Quick Response Code, bank
Card etc. is used for the object for paying, transferring accounts, and client identifies that the identification model of these objects is different.So, use
Family such as will not can not be paid, be transferred accounts at the business because of the limitation of object, so as to further improve client
Business execution efficiency.
The model collocation method and the method for image recognition provided above for the embodiment of the present application, based on same think of
Road, the embodiment of the present application also provide the device of model configuration and the device of image recognition respectively, as shown in Figure 5,6.
Fig. 5 is the schematic device for the model configuration that the embodiment of the present application provides, and is specifically included：
Acquisition module 501, obtain at least one identification parameter that server is sent；
Configuration module 502, according at least one identification parameter and local preset parameter is stored in advance in, configured
At least one identification model, the identification model configured using different identification parameters are used to identify different objects.
The acquisition module 501, when the client terminal start-up, obtain at least one identification parameter that server is sent；
Or when monitoring to trigger the specified function of the client, obtain at least one identification parameter that server is sent.
The acquisition module 501, at least one identification parameter and each identification parameter for obtaining server transmission are right respectively
The identification model mark answered；
The configuration module 501, identify for each identification model, determined from being stored in advance in local preset parameter
Preset parameter corresponding to identification model mark；According to preset parameter and the identification model mark corresponding to identification model mark
Identification parameter corresponding to knowledge, configure identification model corresponding to identification model mark.
Described device also includes：
Starting module 503, start at least one identification model of configuration.
Fig. 6 is the schematic device for the image recognition that the embodiment of the present application provides, and is specifically included：
Acquisition module 601, obtain video；
Selecting module 602, from least one identification model enabled, select identification model；
Identification model 603, by the identification model of selection, identify and whether there is mesh in m frame of video in the video
Mark thing；If being not present, identification model, and the identification model by reselecting are selected from other identification models enabled again
N frame of video in the video is identified, untill the object is identified, wherein, m and n are positive integer, and the m is individual
Frame of video and the n frame of video are incomplete same.
The identification module 603, when not identifying object yet after setting time, the video is sent to service
Device, so that the video to be identified by the server.
The identification module 603, if object be present, perform business corresponding to the object.
The identification module 603, obtain image information and rendering parameter corresponding to the business；According to the institute got
Rendering parameter and described image information are stated, renders image.
The image rendered is augmented reality AR images.
The method of model configuration based on Fig. 1, the also corresponding equipment for providing model configuration of the embodiment of the present application, such as Fig. 7
It is shown.The equipment of model configuration includes one or more processors and memory, and the memory storage has a program, and by
It is configured to by one or more of computing device following steps：
Obtain at least one identification parameter that server is sent；
According at least one identification parameter and local preset parameter is stored in advance in, configures at least one identification
Model, the identification model configured using different identification parameters are used to identify different objects.
The method of image recognition based on Fig. 2, the also corresponding equipment for providing image recognition of the embodiment of the present application, such as Fig. 8
It is shown.The equipment of the image recognition includes one or more processors and memory, and the memory storage has a program, and by
It is configured to by one or more of computing device following steps：
Obtain video；
From at least one identification model enabled, identification model is selected；
By the identification model of selection, identify and whether there is object in m frame of video in the video；
If being not present, identification model, and the identification by reselecting are selected from other identification models enabled again
N frame of video in video described in Model Identification, untill the object is identified, wherein, m and n are positive integer, described
M frame of video and the n frame of video are incomplete same.
In the embodiment of the present application, client obtains at least one identification parameter from server, and according to get to
Lack an identification parameter and be stored in advance in local preset parameter, configure at least one identification model.Because client can
Dynamically to obtain the identification parameter for configuring identification model from server, the identification parameter got is different, configures
Identification model is also different, and the object that the identification model configured can be identified is also different.In other words, set in client
Identification model be not changeless, its object that can be identified changes with the identification parameter that server is sent,
The ability for so causing client to possess Dynamic Recognition object.Moreover, in image recognition processes, each identification model
The partial video frame based on complete video is only needed, can quickly carry out image recognition, and in the partial video for determining identification
When object is not present in frame, other identification models are changed to carry out image recognition by another part frame of video of the video.
So for compared to prior art, client can not only be made to possess the dynamic expansion ability of image recognition, additionally it is possible to realize
Quick identification to object.
In the 1990s, the improvement for a technology can clearly distinguish be on hardware improvement (for example,
Improvement to circuit structures such as diode, transistor, switches) or software on improvement (improvement for method flow).So
And as the development of technology, the improvement of current many method flows can be considered as directly improving for hardware circuit.
Designer nearly all obtains corresponding hardware circuit by the way that improved method flow is programmed into hardware circuit.Cause
This, it cannot be said that the improvement of a method flow cannot be realized with hardware entities module.For example, PLD
(Programmable Logic Device, PLD) (such as field programmable gate array (Field Programmable Gate
Array, FPGA)) it is exactly such a integrated circuit, its logic function is determined by user to device programming.By designer
Voluntarily programming comes a digital display circuit " integrated " on a piece of PLD, without asking chip maker to design and make
Special IC chip.Moreover, nowadays, substitution manually makes IC chip, this programming is also used instead mostly " patrols
Volume compiler (logic compiler) " software realizes that software compiler used is similar when it writes with program development,
And the source code before compiling also write by handy specific programming language, this is referred to as hardware description language
(Hardware Description Language, HDL), and HDL is also not only a kind of, but have many kinds, such as ABEL
(Advanced Boolean Expression Language)、AHDL(Altera Hardware Description
Language)、Confluence、CUPL(Cornell University Programming Language)、HDCal、JHDL
(Java Hardware Description Language)、Lava、Lola、MyHDL、PALASM、RHDL(Ruby
Hardware Description Language) etc., VHDL (Very-High-Speed are most generally used at present
Integrated Circuit Hardware Description Language) and Verilog.Those skilled in the art also should
This understands, it is only necessary to method flow slightly programming in logic and is programmed into integrated circuit with above-mentioned several hardware description languages,
Can is readily available the hardware circuit for realizing the logical method flow.
Controller can be implemented in any suitable manner, for example, controller can take such as microprocessor or processing
Device and storage can by the computer of the computer readable program code (such as software or firmware) of (micro-) computing device
Read medium, gate, switch, application specific integrated circuit (Application Specific Integrated Circuit,
ASIC), the form of programmable logic controller (PLC) and embedded microcontroller, the example of controller include but is not limited to following microcontroller
Device：ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20 and Silicone Labs C8051F320, are deposited
Memory controller is also implemented as a part for the control logic of memory.It is also known in the art that except with
Pure computer readable program code mode realized beyond controller, completely can be by the way that method and step is carried out into programming in logic to make
Controller is obtained in the form of gate, switch, application specific integrated circuit, programmable logic controller (PLC) and embedded microcontroller etc. to come in fact
Existing identical function.Therefore this controller is considered a kind of hardware component, and various for realizing to including in it
The device of function can also be considered as the structure in hardware component.Or even, can be by for realizing that the device of various functions regards
For that not only can be the software module of implementation method but also can be the structure in hardware component.
System, device, module or the unit that above-described embodiment illustrates, it can specifically be realized by computer chip or entity,
Or realized by the product with certain function.One kind typically realizes that equipment is computer.Specifically, computer for example may be used
Think personal computer, laptop computer, cell phone, camera phone, smart phone, personal digital assistant, media play
It is any in device, navigation equipment, electronic mail equipment, game console, tablet PC, wearable device or these equipment
The combination of equipment.
For convenience of description, it is divided into various units during description apparatus above with function to describe respectively.Certainly, this is being implemented
The function of each unit can be realized in same or multiple softwares and/or hardware during application.
It should be understood by those skilled in the art that, embodiments of the invention can be provided as method, system or computer program
Product.Therefore, the present invention can use the reality in terms of complete hardware embodiment, complete software embodiment or combination software and hardware
Apply the form of example.Moreover, the present invention can use the computer for wherein including computer usable program code in one or more
The computer program production that usable storage medium is implemented on (including but is not limited to magnetic disk storage, CD-ROM, optical memory etc.)
The form of product.
The present invention is the flow with reference to method according to embodiments of the present invention, equipment (system) and computer program product
Figure and/or block diagram describe.It should be understood that can be by every first-class in computer program instructions implementation process figure and/or block diagram
Journey and/or the flow in square frame and flow chart and/or block diagram and/or the combination of square frame.These computer programs can be provided
The processors of all-purpose computer, special-purpose computer, Embedded Processor or other programmable data processing devices is instructed to produce
A raw machine so that produced by the instruction of computer or the computing device of other programmable data processing devices for real
The device for the function of being specified in present one flow of flow chart or one square frame of multiple flows and/or block diagram or multiple square frames.
These computer program instructions, which may be alternatively stored in, can guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works so that the instruction being stored in the computer-readable memory, which produces, to be included referring to
Make the manufacture of device, the command device realize in one flow of flow chart or multiple flows and/or one square frame of block diagram or
The function of being specified in multiple square frames.
These computer program instructions can be also loaded into computer or other programmable data processing devices so that counted
Series of operation steps is performed on calculation machine or other programmable devices to produce computer implemented processing, so as in computer or
The instruction performed on other programmable devices is provided for realizing in one flow of flow chart or multiple flows and/or block diagram one
The step of function of being specified in individual square frame or multiple square frames.
In a typical configuration, computing device includes one or more processors (CPU), input/output interface, net
Network interface and internal memory.
Internal memory may include computer-readable medium in volatile memory, random access memory (RAM) and/or
The forms such as Nonvolatile memory, such as read-only storage (ROM) or flash memory (flash RAM).Internal memory is computer-readable medium
Example.
Computer-readable medium includes permanent and non-permanent, removable and non-removable media can be by any method
Or technology come realize information store.Information can be computer-readable instruction, data structure, the module of program or other data.
The example of the storage medium of computer includes, but are not limited to phase transition internal memory (PRAM), static RAM (SRAM), moved
State random access memory (DRAM), other kinds of random access memory (RAM), read-only storage (ROM), electric erasable
Programmable read only memory (EEPROM), fast flash memory bank or other memory techniques, read-only optical disc read-only storage (CD-ROM),
Digital versatile disc (DVD) or other optical storages, magnetic cassette tape, the storage of tape magnetic rigid disk or other magnetic storage apparatus
Or any other non-transmission medium, the information that can be accessed by a computing device available for storage.Define, calculate according to herein
Machine computer-readable recording medium does not include temporary computer readable media (transitory media), such as data-signal and carrier wave of modulation.
It should also be noted that, term " comprising ", "comprising" or its any other variant are intended to nonexcludability
Comprising so that process, method, commodity or equipment including a series of elements not only include those key elements, but also wrapping
Include the other element being not expressly set out, or also include for this process, method, commodity or equipment intrinsic want
Element.In the absence of more restrictions, the key element limited by sentence "including a ...", it is not excluded that wanted including described
Other identical element also be present in the process of element, method, commodity or equipment.
It will be understood by those skilled in the art that embodiments herein can be provided as method, system or computer program product.
Therefore, the application can be using the embodiment in terms of complete hardware embodiment, complete software embodiment or combination software and hardware
Form.Deposited moreover, the application can use to can use in one or more computers for wherein including computer usable program code
The shape for the computer program product that storage media is implemented on (including but is not limited to magnetic disk storage, CD-ROM, optical memory etc.)
Formula.
The application can be described in the general context of computer executable instructions, such as program
Module.Usually, program module includes performing particular task or realizes routine, program, object, the group of particular abstract data type
Part, data structure etc..The application can also be put into practice in a distributed computing environment, in these DCEs, by
Task is performed and connected remote processing devices by communication network.In a distributed computing environment, program module can be with
In the local and remote computer-readable storage medium including storage device.
Each embodiment in this specification is described by the way of progressive, identical similar portion between each embodiment
Divide mutually referring to what each embodiment stressed is the difference with other embodiment.It is real especially for system
For applying example, because it is substantially similar to embodiment of the method, so description is fairly simple, related part is referring to embodiment of the method
Part explanation.
It is above-mentioned that this specification specific embodiment is described.Other embodiments are in the scope of the appended claims
It is interior.In some cases, the action recorded in detail in the claims or step can be come according to different from the order in embodiment
Perform and still can realize desired result.In addition, the process described in the accompanying drawings not necessarily require show it is specific suitable
Sequence or consecutive order could realize desired result.In some embodiments, multitasking and parallel processing be also can
With or be probably favourable.
Embodiments herein is the foregoing is only, is not limited to the application.For those skilled in the art
For, the application can have various modifications and variations.All any modifications made within spirit herein and principle, it is equal
Replace, improve etc., it should be included within the scope of claims hereof.
Claims (20)
1. a kind of method of model configuration, including：
Client obtains at least one identification parameter that server is sent；
According at least one identification parameter and local preset parameter is stored in advance in, configures at least one identification mould
Type, the identification model configured using different identification parameters are used to identify different objects.
2. the method as described in claim 1, at least one identification parameter that server is sent is obtained, is specifically included：
When the client terminal start-up, at least one identification parameter that server is sent is obtained；Or
When monitoring to trigger the specified function of the client, at least one identification parameter that server is sent is obtained.
3. the method as described in claim 1, client obtains at least one identification parameter that server is sent, and specifically includes：
Identification model mark corresponding at least one identification parameter and each identification parameter difference that acquisition server is sent；
According at least one identification parameter and local preset parameter is stored in advance in, configures at least one identification mould
Type, specifically include：
Identify for each identification model, determined from being stored in advance in local preset parameter corresponding to identification model mark
Preset parameter；
According to identification parameter corresponding to preset parameter corresponding to identification model mark and identification model mark, the knowledge is configured
Identification model corresponding to other model identification.
4. method as claimed in claim 3, methods described also include：
Enable at least one identification model of configuration.
5. a kind of method of image recognition, including：
Obtain video；
From at least one identification model enabled, identification model is selected；
By the identification model of selection, identify and whether there is object in m frame of video in the video；
If being not present, identification model, and the identification model by reselecting are selected from other identification models enabled again
N frame of video in the video is identified, untill the object is identified, wherein, m and n are positive integer, and the m is individual
Frame of video and the n frame of video are incomplete same.
6. method as claimed in claim 5, methods described also include：
When not identifying object yet after setting time, the video is sent to server, to pass through the service
The video is identified device.
7. method as claimed in claim 5, methods described also include：
If object be present, business corresponding to the object is performed.
8. method as claimed in claim 7, perform the object corresponding to business, specifically include：
Obtain image information and rendering parameter corresponding to the business；
According to the rendering parameter and described image information got, image is rendered.
9. method as claimed in claim 8, the image rendered is augmented reality AR images.
10. a kind of device of model configuration, including：
Acquisition module, obtain at least one identification parameter that server is sent；
Configuration module, according at least one identification parameter and local preset parameter is stored in advance in, configuration at least one
Individual identification model, the identification model configured using different identification parameters are used to identify different objects.
11. device as claimed in claim 10, the acquisition module, when the client terminal start-up, obtain server and send
At least one identification parameter；Or when monitoring to trigger the specified function of the client, obtain server and send at least
One identification parameter.
12. device as claimed in claim 10, the acquisition module, obtain at least one identification parameter that server sends with
And identification model mark corresponding to each identification parameter difference；
The configuration module, identified for each identification model, the identification is determined from being stored in advance in local preset parameter
Preset parameter corresponding to model identification；It is corresponding according to preset parameter corresponding to identification model mark and identification model mark
Identification parameter, configure the identification model mark corresponding to identification model.
13. device as claimed in claim 12, described device also include：
Starting module, start at least one identification model of configuration.
14. a kind of device of image recognition, including：
Acquisition module, obtain video；
Selecting module, from least one identification model enabled, select identification model；
Identification model, by the identification model of selection, identify and whether there is object in m frame of video in the video；If
It is not present, selects identification model, and the identification of the identification model by reselecting institute from other identification models enabled again
N frame of video in video is stated, untill the object is identified, wherein, m and n are positive integer, the m frame of video
It is incomplete same with the n frame of video.
15. device as claimed in claim 14, the identification module, when not identifying object yet after setting time
When, the video is sent to server, so that the video to be identified by the server.
16. device as claimed in claim 14, the identification module, if object be present, perform corresponding to the object
Business.
17. device as claimed in claim 16, the identification module, obtain image information corresponding to the business and render
Parameter；According to the rendering parameter and described image information got, image is rendered.
18. device as claimed in claim 17, the image rendered is augmented reality AR images.
19. a kind of equipment of model configuration, including：One or more processors and memory, the memory storage have program,
And it is configured to by one or more of computing device following steps：
Obtain at least one identification parameter that server is sent；
According at least one identification parameter and local preset parameter is stored in advance in, configures at least one identification mould
Type, the identification model configured using different identification parameters are used to identify different objects.
20. a kind of equipment of image recognition, including：One or more processors and memory, the memory storage have program,
And it is configured to by one or more of computing device following steps：
Obtain video；
From at least one identification model enabled, identification model is selected；
By the identification model of selection, identify and whether there is object in m frame of video in the video；
If being not present, identification model, and the identification model by reselecting are selected from other identification models enabled again
N frame of video in the video is identified, untill the object is identified, wherein, m and n are positive integer, and the m is individual
Frame of video and the n frame of video are incomplete same.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110020715.3A CN112800858B (en) | 2017-07-06 | 2017-07-06 | Model configuration and image recognition method and device |
| CN201710544836.1A CN107480587B (en) | 2017-07-06 | 2017-07-06 | Model configuration and image recognition method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710544836.1A CN107480587B (en) | 2017-07-06 | 2017-07-06 | Model configuration and image recognition method and device |
Related Child Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110020715.3A Division CN112800858B (en) | 2017-07-06 | 2017-07-06 | Model configuration and image recognition method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107480587A true CN107480587A (en) | 2017-12-15 |
| CN107480587B CN107480587B (en) | 2020-12-08 |
Family
ID=60596391
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710544836.1A Active CN107480587B (en) | 2017-07-06 | 2017-07-06 | Model configuration and image recognition method and device |
| CN202110020715.3A Active CN112800858B (en) | 2017-07-06 | 2017-07-06 | Model configuration and image recognition method and device |
Family Applications After (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110020715.3A Active CN112800858B (en) | 2017-07-06 | 2017-07-06 | Model configuration and image recognition method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN107480587B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108492352A (en) * | 2018-03-22 | 2018-09-04 | 腾讯科技（深圳）有限公司 | Implementation method, device, system, computer equipment and the storage medium of augmented reality |
| CN108875519A (en) * | 2017-12-19 | 2018-11-23 | 北京旷视科技有限公司 | Method for checking object, device and system and storage medium |
| CN109963163A (en) * | 2017-12-26 | 2019-07-02 | 阿里巴巴集团控股有限公司 | Internet video live broadcasting method, device and electronic equipment |
| CN110781834A (en) * | 2019-10-28 | 2020-02-11 | 上海眼控科技股份有限公司 | Traffic abnormality image detection method, device, computer device and storage medium |
| CN111832366A (en) * | 2019-04-22 | 2020-10-27 | 鸿富锦精密电子(天津)有限公司 | Image recognition device and method |
| CN112199987A (en) * | 2020-08-26 | 2021-01-08 | 北京贝思科技术有限公司 | Multi-algorithm combined configuration strategy method in single area, image processing device and electronic equipment |
| WO2021114837A1 (en) * | 2019-12-10 | 2021-06-17 | 支付宝(杭州)信息技术有限公司 | Graphic code recognizing method and device |
| CN113365101A (en) * | 2020-03-05 | 2021-09-07 | 腾讯科技（深圳）有限公司 | Method for multitasking video and related equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103116754A (en) * | 2013-01-24 | 2013-05-22 | 浙江大学 | Batch image segmentation method and batch image segmentation system based on recognition models |
| CN105934760A (en) * | 2014-01-24 | 2016-09-07 | 微软技术许可有限责任公司 | Adaptable image search with computer vision assistance |
| CN106709506A (en) * | 2016-11-28 | 2017-05-24 | 广东工业大学 | Method for identifying and classifying species and different origins of Chinese herbal medicine |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7519690B1 (en) * | 2002-02-28 | 2009-04-14 | Sprint Communications Company L.P. | Dynamically updateable parameters in integrated services hub |
| JP5018404B2 (en) * | 2007-11-01 | 2012-09-05 | ソニー株式会社 | Image identification apparatus, image identification method, and program |
| CN101520849B (en) * | 2009-03-24 | 2011-12-28 | 上海水晶石信息技术有限公司 | Reality augmenting method and reality augmenting system based on image characteristic point extraction and random tree classification |
| US9218530B2 (en) * | 2010-11-04 | 2015-12-22 | Digimarc Corporation | Smartphone-based methods and systems |
| CN103310099A (en) * | 2013-05-30 | 2013-09-18 | 佛山电视台南海分台 | Method and system for realizing augmented reality by adopting image capture and recognition technology |
| US9122931B2 (en) * | 2013-10-25 | 2015-09-01 | TCL Research America Inc. | Object identification system and method |
| JP6490430B2 (en) * | 2014-03-03 | 2019-03-27 | 株式会社東芝 | Image processing apparatus, image processing system, image processing method, and program |
| CN105094305B (en) * | 2014-05-22 | 2018-05-18 | 华为技术有限公司 | Identify method, user equipment and the Activity recognition server of user behavior |
-
2017
- 2017-07-06 CN CN201710544836.1A patent/CN107480587B/en active Active
- 2017-07-06 CN CN202110020715.3A patent/CN112800858B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103116754A (en) * | 2013-01-24 | 2013-05-22 | 浙江大学 | Batch image segmentation method and batch image segmentation system based on recognition models |
| CN105934760A (en) * | 2014-01-24 | 2016-09-07 | 微软技术许可有限责任公司 | Adaptable image search with computer vision assistance |
| CN106709506A (en) * | 2016-11-28 | 2017-05-24 | 广东工业大学 | Method for identifying and classifying species and different origins of Chinese herbal medicine |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108875519A (en) * | 2017-12-19 | 2018-11-23 | 北京旷视科技有限公司 | Method for checking object, device and system and storage medium |
| CN109963163A (en) * | 2017-12-26 | 2019-07-02 | 阿里巴巴集团控股有限公司 | Internet video live broadcasting method, device and electronic equipment |
| CN108492352A (en) * | 2018-03-22 | 2018-09-04 | 腾讯科技（深圳）有限公司 | Implementation method, device, system, computer equipment and the storage medium of augmented reality |
| CN108492352B (en) * | 2018-03-22 | 2021-10-22 | 腾讯科技（深圳）有限公司 | Augmented reality implementation method, device, system, computer equipment and storage medium |
| CN111832366A (en) * | 2019-04-22 | 2020-10-27 | 鸿富锦精密电子(天津)有限公司 | Image recognition device and method |
| CN111832366B (en) * | 2019-04-22 | 2024-04-02 | 富联精密电子(天津)有限公司 | Image recognition apparatus and method |
| CN110781834A (en) * | 2019-10-28 | 2020-02-11 | 上海眼控科技股份有限公司 | Traffic abnormality image detection method, device, computer device and storage medium |
| WO2021114837A1 (en) * | 2019-12-10 | 2021-06-17 | 支付宝(杭州)信息技术有限公司 | Graphic code recognizing method and device |
| CN113365101A (en) * | 2020-03-05 | 2021-09-07 | 腾讯科技（深圳）有限公司 | Method for multitasking video and related equipment |
| CN112199987A (en) * | 2020-08-26 | 2021-01-08 | 北京贝思科技术有限公司 | Multi-algorithm combined configuration strategy method in single area, image processing device and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112800858B (en) | 2024-04-26 |
| CN107480587B (en) | 2020-12-08 |
| CN112800858A (en) | 2021-05-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107480587A (en) | A kind of method and device of model configuration and image recognition | |
| CN107562775A (en) | A kind of data processing method and equipment based on block chain | |
| CN107957831A (en) | A kind of data processing method, device and processing equipment for showing interface content | |
| CN107391526A (en) | A kind of data processing method and equipment based on block chain | |
| CN110688974B (en) | Identity recognition method and device | |
| CN107679700A (en) | Business flow processing method, apparatus and server | |
| CN110019903A (en) | Generation method, searching method and terminal, the system of image processing engine component | |
| CN108388833A (en) | A kind of image-recognizing method, device and equipment | |
| CN108491897A (en) | A kind of information identifying method, server, client and system | |
| CN108537085A (en) | A kind of barcode scanning image-recognizing method, device and equipment | |
| CN108647076A (en) | A kind of page processing method, device and equipment | |
| CN108647065A (en) | A kind of information displaying method, device and equipment | |
| CN115981870B (en) | Data processing method and device, storage medium and electronic equipment | |
| CN108268289A (en) | Method for parameter configuration, the apparatus and system of web applications | |
| CN109271587A (en) | A kind of page generation method and device | |
| CN109325508A (en) | The representation of knowledge, machine learning model training, prediction technique, device and electronic equipment | |
| CN108021610A (en) | Random walk, random walk method, apparatus and equipment based on distributed system | |
| CN110244985A (en) | A kind of view rendering method, computer storage medium and terminal device | |
| CN112347512A (en) | Image processing method, device, equipment and storage medium | |
| CN110032582A (en) | A kind of data processing method, device, equipment and system | |
| CN108614693A (en) | It is a kind of for the processing method of page assembly, device and equipment | |
| CN110069523A (en) | A kind of data query method, apparatus and inquiry system | |
| CN108345536A (en) | A kind of dispositions method, device and the equipment of continuous integrating environment | |
| CN107609051A (en) | A kind of image rendering method, device and electronic equipment | |
| CN111381745B (en) | Page switching method, device and equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 1248014 Country of ref document: HK |
|
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20201019 Address after: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman Islands Applicant after: Innovative advanced technology Co.,Ltd. Address before: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman Islands Applicant before: Advanced innovation technology Co.,Ltd. Effective date of registration: 20201019 Address after: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman Islands Applicant after: Advanced innovation technology Co.,Ltd. Address before: A four-storey 847 mailbox in Grand Cayman Capital Building, British Cayman Islands Applicant before: Alibaba Group Holding Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |