CN109919109A - Image-recognizing method, device and equipment - Google Patents
Image-recognizing method, device and equipment Download PDFInfo
- Publication number
- CN109919109A CN109919109A CN201910182393.5A CN201910182393A CN109919109A CN 109919109 A CN109919109 A CN 109919109A CN 201910182393 A CN201910182393 A CN 201910182393A CN 109919109 A CN109919109 A CN 109919109A
- Authority
- CN
- China
- Prior art keywords
- equipment
- data
- recognized
- images
- data set
- 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
Landscapes
- Image Analysis (AREA)
Abstract
This application discloses object type recognition methods, device and the equipment in image, this method comprises: if first equipment utilization the first clear data collection fails to identify images to be recognized, the corresponding data of the images to be recognized are then sent to the second equipment, so that first data set of the second equipment utilization identifies the images to be recognized, wherein, first data set is the union of the first clear data collection and the second plaintext data set；And after second equipment identifies the images to be recognized, the recognition result for the images to be recognized that second equipment is sent is received.The scheme of the embodiment of the present invention encrypts the partial data in the database of the user of offer, and complete data can be prevented to be stolen or reveal, and ensure that the safety of data.
Description
Technical field
This application involves intelligent identification technology fields, in particular to image-recognizing method, device and equipment.
Background technique
In recent years, image recognition technology is rapidly developed and is widely applied.This is a kind of based on known identification object
Image is analyzed using computer or embedded device, and then detects the one of identification object using identification object features in body library
Gate technique.Specifically, using the feature formation algorithm of various identification objects, computer is allowed to learn identification object, and benefit
With sorting algorithm, by object identification or the technology that detected.Identification object library is storable in computer or embedded device sheet
Ground also can store beyond the clouds.Storage can save the local storage space of computer or embedded device beyond the clouds, but due to by
Network technology limitation, totally cannot rapidly obtain recognition result, therefore object library can only will be identified in many application scenarios
It is supplied to user and is stored in local, this entirely to identify that the data in object library have the risk for being stolen or revealing.
Summary of the invention
In view of problem above, the embodiment of the present invention provides image-recognizing method, device and equipment, can solve above-mentioned back
The technical issues of scape technology segment is mentioned.
The image-recognizing method of embodiment according to the invention is applied to the first equipment, wherein first equipment includes
First clear data collection and the first encrypted data set encrypted by second plaintext data set, which comprises if first
Equipment utilization the first clear data collection fails to identify images to be recognized, then the corresponding data of the images to be recognized is sent to the
Two equipment, so that first data set of the second equipment utilization identifies the images to be recognized, wherein first number
It is the union of the first clear data collection and the second plaintext data set according to collection；And second equipment to it is described to
After identification image is identified, the recognition result for the images to be recognized that second equipment is sent is received.
The image-recognizing method of embodiment according to the invention is applied to the second equipment, comprising: receives the first equipment and sends
The corresponding data of images to be recognized, first equipment includes the first clear data collection and being encrypted by second plaintext data set
The first encrypted data set arrived；The images to be recognized is identified using the first data set according to the data, wherein institute
State the union that the first data set is the first clear data collection and the second plaintext data set；By the images to be recognized
Recognition result is sent to first equipment.
The pattern recognition device of embodiment according to the invention is applied to the first equipment, wherein first equipment includes
First clear data collection and the first encrypted data set encrypted by second plaintext data set, described device include: the first hair
Module is sent, if failing to identify images to be recognized for first equipment utilization the first clear data collection, by the images to be recognized
Corresponding data are sent to the second equipment, so that first data set of the second equipment utilization knows the images to be recognized
Not, wherein first data set is the union of the first clear data collection and the second plaintext data set；First receives
Module, for after second equipment identifies the images to be recognized, receiving the described of the second equipment transmission
The recognition result of images to be recognized.
The pattern recognition device of embodiment according to the invention is applied to the second equipment, comprising: the second receiving module is used
In the corresponding data of images to be recognized for receiving the first equipment and sending, first equipment includes the first clear data collection and by the
The first encrypted data set that two clear data collection encrypt；Identification module, for utilizing the first data set according to the data
The images to be recognized is identified, wherein first data set is the first clear data collection and described second bright
The union of literary data set；Second sending module, for the recognition result of the images to be recognized to be sent to first equipment.
The electronic equipment of embodiment according to the invention, comprising: processor；And memory, it is stored thereon with executable
Instruction；Wherein, the processor is configured to execute the executable instruction to implement image-recognizing method above-mentioned.
The computer readable storage medium of embodiment according to the invention is stored thereon with computer program, the calculating
Machine program includes executable instruction, when the executable instruction is executed by processor, implements image-recognizing method above-mentioned.
In the scheme of the embodiment of the present invention, before the first data set is supplied to user, first partial data is encrypted,
So that user is only capable of identifying images to be recognized using the clear data of unencryption, when clear data part fails identification figure
When picture, then it can request to identify images to be recognized using the first data set to the first data set provider, so may be used
To prevent complete data to be stolen or reveal, the safety of data ensure that.
Detailed description of the invention
Fig. 1 is that present invention could apply to exemplary system architecture figures therein；
Fig. 2 is the interaction embodiment schematic diagram of the image-recognizing method of one embodiment of the invention；
Fig. 3 is the interaction embodiment schematic diagram of the image-recognizing method of another embodiment of the present invention；
Fig. 4 is the interaction embodiment schematic diagram of the image-recognizing method of further embodiment of this invention；
Fig. 5 is the flow chart of the image-recognizing method of one embodiment of the invention；
Fig. 6 is the flow chart of the image-recognizing method of another embodiment of the present invention；
Fig. 7 is the schematic diagram of the pattern recognition device of one embodiment of the invention；
Fig. 8 is the schematic diagram of the pattern recognition device of another embodiment of the present invention；
Fig. 9 is the schematic diagram of the electronic equipment of one embodiment of the invention.
Specific embodiment
Theme described herein is discussed referring now to example embodiment.It should be understood that discussing these embodiments only
It is in order to enable those skilled in the art can better understand that being not to claim to realize theme described herein
Protection scope, applicability or the exemplary limitation illustrated in book.It can be in the protection scope for not departing from present disclosure
In the case of, the function and arrangement of the element discussed are changed.Each example can according to need, omit, substitute or
Add various processes or component.For example, described method can be executed according to described order in a different order, with
And each step can be added, omits or combine.In addition, feature described in relatively some examples is in other examples
It can be combined.
As used in this article, term " includes " and its modification indicate open term, are meant that " including but not limited to ".
Term "based" indicates " being based at least partially on ".Term " one embodiment " and " embodiment " expression " at least one implementation
Example ".Term " another embodiment " expression " at least one other embodiment ".Term " first ", " second " etc. may refer to not
Same or identical object.Here may include other definition, either specific or implicit.Unless bright in context
It really indicates, otherwise the definition of a term is consistent throughout the specification.
In being described below, for illustration and not for limitation, propose such as specific system structure, interface, technology it
The detail of class, to understand thoroughly the present invention.However, it will be clear to one skilled in the art that there is no these specific
The present invention also may be implemented in the other embodiment of details.In other situations, omit to well-known device, circuit with
And the detailed description of method, in case unnecessary details interferes description of the invention.
It should be noted that in the absence of conflict, the feature in embodiment and embodiment in the present invention can phase
Mutually combine.The present invention will be described in detail below with reference to the accompanying drawings and embodiments.The image-recognizing method or device of the application
It can be the identification to the object type in image type or image.
Fig. 1 is shown can be using the exemplary system frame of one embodiment of image-recognizing method or device of the invention
Structure 100.
As shown in Figure 1, system architecture 100 may include the first equipment 101,102,103, network 104 and the second equipment
105.Wherein, the first equipment 101,102,103 can be stored with the first clear data collection and encrypt to obtain by second plaintext data set
The first encrypted data set, the second equipment 105 can be stored with the first data set, and the first data set is the first clear data collection and the
The union of two clear data collection encrypts the second plaintext data set in the first data set to form the first encrypted data set, and
Unencryption part is then the first clear data collection.In the embodiment of the present application, carrying out encryption to second plaintext data set is to second
Each of clear data collection or every a kind of data element are encrypted respectively, each or every a kind of data element correspond to
One decruption key in the embodiment of the present application can be using symmetric encipherment algorithm to the second plaintext data in the first data set
Collection is encrypted to obtain the first encrypted data set.In the embodiment of the present application, data set can be stored in database.
In the embodiment of the present application, data set is the set of data element.Data element includes label data and and number of tags
According to associated image data, a data element of each image data and label data associated with it composition data set,
In, label data includes the type information of image, and image data includes the characteristic of image, and label data and image data can
To be binary data.It specifically, can be above-mentioned by executing image labeling (Image Annotation) processing acquisition to image
Data set.Image labeling processing is known technology, omits descriptions thereof herein.Same type information may include multiple
Label data, then same type information may include multiple data elements, then corresponds to multiple data elements of same type information
Element can be used as a kind of data element.
In the embodiment of the present application, the first clear data collection of the first equipment 101,102,103 storage or the first encryption number
Can be identical according to the data element for collecting included, can not also be identical, i.e., for the first different equipment, can use different
Strategy selected part data element from the first data set is encrypted to obtain the first encrypted data set, and unencryption part forms the
One clear data collection.
Network 104 between the first equipment 101,102,103 and the second equipment 105 to provide the medium of communication link.
Network 104 may include various connection types, such as wired, wireless communication link or fiber optic cables etc..
First equipment 101,102,103 can be various electronic equipments, such as, but not limited to smart phone, tablet computer,
Pocket computer on knee and desktop computer etc., can be with operation image recognizer in the first equipment 101,102,103, benefit
Images to be recognized is identified with image recognition algorithm.In the embodiment of the present application, the first equipment 101,102 sets for terminal
Standby, the first equipment 103 is server, and the user terminal 106 that the first equipment 103 can be connect with it carries out data interaction, is received
User terminal 106 send identification request to images to be recognized carry out identification and by recognition result return user terminal 106, first
Equipment 103 for example can be Edge Server.
Second equipment 105 can be central server, for receiving the image data of the first equipment 101,102,103 transmission
And image is identified, and recognition result is fed back into the first equipment 101,102,103.It can be transported in second equipment 105
Row image recognition algorithm identifies image using image recognition algorithm.
It should be understood that, the number of the first equipment, network and the second equipment in Fig. 1 is only schematical.According to reality
Border needs, and can have any number of first equipment, network and the second equipment.
Fig. 2 shows the interaction embodiment schematic diagram for the image-recognizing method that one embodiment of the application provides, this method 200
It may comprise steps of:
S202: the first equipment obtains the corresponding data of images to be recognized T.
In the embodiment of the present application, the first equipment can be from the locally or remotely corresponding number of acquisition images to be recognized T
According to.The data for the images to be recognized T that first equipment obtains can be characteristic, such as can be by other equipment to figure to be identified
As T carries out feature extraction and the characteristic extracted being issued the first equipment, alternatively, by the first equipment interconnection receive wait know
Other image T carries out feature extraction to obtain characteristic.
In the embodiment of the present application, if to identify to the target object in images to be recognized T, the first equipment can
To carry out positioning and dividing processing to the target object in images to be recognized T, and pass through the spy of feature extraction acquisition target object
Data are levied, are set it is of course also possible to which the characteristic of the target object in images to be recognized T is sent to first by other equipment
It is standby.In the embodiment of the present application, the target object in images to be recognized T is such as, but not limited to the production in product defects identification field
Face in product defect, field of face identification, the article in article identification field, word in handwritten word identification field etc..
S204: the first equipment utilization the first clear data collection identifies images to be recognized T.
In the embodiment of the present application, the first equipment includes the first clear data collection and encrypts to obtain by second plaintext data set
The first encrypted data set, the first equipment is only capable of identifying images to be recognized T using the first clear data collection.
First equipment such as, but not limited to can be by image recognition algorithms such as neural network model, classifiers to be identified
Image T is identified, specifically, the first equipment can be by the feature of the target object in images to be recognized T or images to be recognized T
Input of the data as neural network model or classifier, exported in a manner of probability distribution (confidence level) images to be recognized T or
Target object in the images to be recognized T size the data element labeling that the first clear data is concentrated a possibility that.
S206: if the first equipment fails to identify images to be recognized T, the corresponding data of images to be recognized T are sent to the
Two equipment.
In the embodiment of the present application, confidence threshold value can be set in the first equipment, if images to be recognized T or images to be recognized
Target object in T concentrates the data element having greater than confidence threshold value in the first clear data, then it represents that the first equipment energy
Identify images to be recognized T, then the first equipment can will be greater than the label data of the data element of confidence threshold value as recognition result
It exports or is sent to the user terminal.If the target object in images to be recognized T or images to be recognized T is in the first clear data collection
In be not greater than the data element of confidence threshold value, it is determined that the first equipment fails to identify images to be recognized T.
In the embodiment of the present application, the corresponding data of images to be recognized T can be sent to second by network by the first equipment
Equipment.
S208: the second equipment carries out images to be recognized T using the first data set according to the corresponding data of images to be recognized T
Identification.
In the embodiment of the present application, the first data set is the first clear data collection and second plaintext number of the first equipment storage
According to the union of collection, the second equipment can such as, but not limited to be treated by image recognition algorithms such as neural network model, classifiers
Identification image T is identified, specifically, the first equipment can be by the target object in images to be recognized T or images to be recognized T
Input of the characteristic as neural network model or classifier exports images to be recognized in a manner of probability distribution (confidence level)
A possibility that data element labeling in the first data set of target object in T or images to be recognized T size.First sets
Standby and the second equipment image recognition algorithm can be identical, can not also be identical.
The recognition result of images to be recognized T is sent to the first equipment by the S210: the second equipment.
In the embodiment of the present application, the second equipment can confidence level be maximum in the first data set by images to be recognized T
The label data of data element is sent to the first equipment as recognition result, and confidence threshold value also can be set, by figure to be identified
As the label data of the T data element that confidence level is greater than confidence threshold value in the first data set is sent to the as recognition result
One equipment.
Illustrate the image-recognizing method of the embodiment of the present application below in conjunction with a kind of application scenarios.
In a kind of application scenarios using image recognition testing product defect, the second equipment can be to provide product defects
The central server of the manufacturer of intelligent terminal is detected, the first equipment can sell for the manufacturer detects intelligence to the product defects of user
Can the corresponding Edge Server of terminal, manufacturer is according to the actual needs of user (such as consumer products common several defect types)
The first plaintext number is chosen from the first data set comprising defect image and defective labels of the database purchase of central server
According to collection, it then will choose remaining second plaintext data set and encrypted to obtain the first encrypted data set using Encryption Algorithm, it will
In the database for the Edge Server that first clear data collection and the first encrypted data set are stored in user, use the product by the user scarce
Detection smart terminal product image is fallen into, and product image is sent to Edge Server, utilizes the first plaintext number of Edge Server
The defects of product image is identified according to collection, when Edge Server can identify the defect type of product, then edge
Server returns to recognition result to product defects detection intelligent terminal, when Edge Server not can recognize that the defect type of product
When, product image is sent to central server by Edge Server, and central server is utilized comprising the first clear data collection and the
After first data set of two clear data collection identifies product image, recognition result is returned into Edge Server, and by
Edge Server is sent on product defects detection intelligent terminal and is shown.
It can be seen from the above that the scheme of the embodiment of the present application has the advantages that (1) first equipment can
To be identified using the first clear data collection to images to be recognized, since the first clear data collection is normally stored in local data
Library or the Edge Server being closer, therefore the image that can be identified for the first equipment can rapidly feedback identifying result；
(2) image unrecognized for the first equipment can be identified by central server using the first data set, in this way may be used
The partial data element being supplied in the first data set of user is encrypted, complete first data set can be prevented stolen
It takes or reveals, ensure that the safety of data.
Fig. 3 shows the interaction embodiment schematic diagram for the image-recognizing method that another embodiment of the application provides, this method
300 may comprise steps of:
S302: the first equipment obtains the corresponding data of images to be recognized T.
S304: the first equipment utilization the first clear data collection identifies images to be recognized T.
S306: if the first equipment fails to identify images to be recognized T, the corresponding data of images to be recognized T are sent to the
Two equipment.
S308: the second equipment carries out images to be recognized T using the first data set according to the corresponding data of images to be recognized T
Identification.
S310: the second equipment obtains the decruption key of data element corresponding with the recognition result of images to be recognized T.
In the embodiment of the present application, the second equipment is obtained according to the label data in recognition result and is associated with the label data
Image data, to obtain the corresponding data element of recognition result.Specifically, identification of second equipment to images to be recognized T
As a result be label " PD (1) ", then by the tab indexes to image data associated with it, thus acquisition by label " PD (1) " and
The data element of image data composition associated with it.Since image type each in data set may include multiple data elements
Element, therefore, the second equipment can obtain the multiple data elements for corresponding to same image type, example simultaneously according to label data
Such as, the data element that label data " PD (1) ", " PD (2) ", " PD (3) " and difference image data associated with it form.
In the embodiment of the present application, according to encryption method and decryption rule, in a first aspect, the second equipment is available and knows
The decruption key of the corresponding data element of other result label data；Second aspect, the second equipment are available with recognition result
Multiple decruption keys of the corresponding multiple data elements of image type；The third aspect, the second equipment is available and recognition result
The corresponding multiple data elements of image type a decruption key.Wherein, first aspect and second aspect are to data
Each data element is encrypted respectively when element is encrypted, the third aspect is when encrypting to data element to same
Multiple data element packaging cipherings of one image type.The decruption key that first aspect obtains is only used for decryption and recognition result mark
The corresponding data element of data is signed, the decruption key that second aspect and the third aspect obtain is used to decrypt and recognition result
The corresponding a kind of data element of image type.
Recognition result and decruption key are sent to the first equipment by the S312: the second equipment.
S314: the first equipment utilization decruption key to the first encryption data concentrate corresponding with recognition result data element into
Row decryption.
In the embodiment of the present application, the first equipment to the first encryption data concentrate corresponding with recognition result data element into
The clear data of the data element is obtained after row decryption, the first encrypted data set forms new encryption number after decrypted partial data
According to collection, the clear data obtained after the first clear data collection and decryption forms new clear data collection.
In the embodiment of the present application, the first equipment receives part of the decruption key to the first encrypted data set of the second equipment
Data are decrypted, and can so be set when again identifying that images to be recognized T corresponding image type next time using being stored in first
Standby clear data collection can recognize, improve the feedback speed of recognition result, while also mitigating the load of the second equipment.
Fig. 4 shows the interaction embodiment schematic diagram for the image-recognizing method that the another embodiment of the application provides, this method
400 may comprise steps of:
S402: the first equipment obtains the corresponding data of images to be recognized T.
S404: the first equipment utilization the first clear data collection identifies images to be recognized T.
S406: if the first equipment fails to identify images to be recognized T, the corresponding data of images to be recognized T are sent to the
Two equipment.
S408: the second equipment carries out images to be recognized T using the first data set according to the corresponding data of images to be recognized T
Identification.
S410: the second equipment judges whether the first equipment meets preset condition.If it is not, thening follow the steps S412；If so,
Execute step S414-S418.
In the embodiment of the present application, preset condition for example may include at least one below: (a) first equipment
First request number of times reaches preset threshold, and first request number of times is first equipment of second device statistics pre-
If the period obtains the number of the recognition result；(b) the second request number of times of first equipment is lower than preset threshold,
In, second request number of times is the number of second equipment of the first device request identification of second device statistics；(c)
First equipment has the permission that the identification decruption key is obtained from second equipment.
In preset condition (a), the second equipment can recorde the historical requests information of the first equipment, historical requests packet
Recognition result acquired in historical requests is included, after the recognition result for obtaining images to be recognized T, counts the first equipment when default
Between section obtain images to be recognized T recognition result number, thus obtain the first equipment the first request number of times.Pass through setting the
One request number of times can be reduced decruption key corresponding to the recognition result for sending to the first equipment and occurring once in a while, to guarantee data
Safety.
In preset condition (b), the second equipment can recorde the historical requests information of the first device request identification image,
After the recognition result for obtaining images to be recognized T, the number of statistics the first device request identification image, to obtain the second request time
Number.By the way that the second request number of times is arranged, it can prevent that identification request is a large amount of or whole decruption keys by largely sending.
In preset condition (c), the second equipment can recorde the authority information of the first equipment, obtain images to be recognized T
Recognition result after, judge whether the first equipment has the power for the decruption key for obtaining data corresponding with the recognition result
Limit.By the way that permission is arranged, it can be further ensured that the safety of data, and safeguard the value of data.
The recognition result of images to be recognized T is sent to the first equipment by the S412: the second equipment.
S414: the second equipment obtains the decruption key of data element corresponding with the recognition result of images to be recognized T.
Recognition result and decruption key are sent to the first equipment by the S416: the second equipment.
S418: the first equipment utilization decruption key to the first encryption data concentrate corresponding with recognition result data element into
Row decryption.
Fig. 5 shows the flow chart of the image-recognizing method according to one embodiment of the application.Method 500 shown in fig. 5 is answered
For the first equipment, wherein the first equipment include the first clear data collection and by second plaintext data set encrypt first plus
Ciphertext data collection.
As shown in figure 5, method 500 may comprise steps of: S502, if first the first clear data of equipment utilization collection is not
It can identify images to be recognized, then the corresponding data of the images to be recognized are sent to the second equipment, so that second equipment
The images to be recognized is identified using the first data set, wherein first data set is first clear data
The union of collection and the second plaintext data set.
Method 500 can be the following steps are included: S504, identifies the images to be recognized in second equipment
Afterwards, the recognition result for the images to be recognized that second equipment is sent is received.
In one aspect, the method also includes: after second equipment identifies the images to be recognized, connect
Receive the decruption key of data element corresponding with the recognition result in the first data set that second equipment is sent；Using institute
It states decruption key and concentrates data element corresponding with the recognition result to be decrypted first encryption data.
Fig. 6 shows the flow chart of the image-recognizing method according to another embodiment of the application.Method 600 shown in fig. 6
Applied to the second equipment.
As shown in fig. 6, method 600 may comprise steps of: S602 receives the images to be recognized pair that the first equipment is sent
The data answered, first equipment include the first clear data collection and by second plaintext data set encrypt first encryption number
According to collection.
Method 600 can be the following steps are included: S604, utilizes the first data set to described to be identified according to the data
Image is identified, wherein first data set be the first clear data collection and the second plaintext data set and
Collection.
Method 600 can be the following steps are included: S606, be sent to described for the recognition result of the images to be recognized
One equipment.
In one aspect, the method also includes: obtain the decruption key of corresponding with recognition result data element；
The decruption key is sent to first equipment, so that decruption key described in first equipment utilization adds to described first
Ciphertext data concentrates data element corresponding with the recognition result to be decrypted.
On the other hand, before the step of obtaining the decruption key of data element corresponding with the recognition result,
The method also includes: judge whether first equipment meets preset condition；It is obtained and the recognition result if so, executing
The step of decruption key of corresponding data element.
In yet another aspect, the preset condition includes at least one below: (a) the first request of first equipment
Number reaches preset threshold, and first request number of times is first equipment of second device statistics in preset time period
Obtain the number of the recognition result；(b) the second request number of times of first equipment is lower than preset threshold, wherein described the
Two request number of times are the numbers of second equipment of the first device request identification of second device statistics；(c) described first
Equipment has the permission that the identification decruption key is obtained from second equipment.
Fig. 7 shows the schematic diagram of the pattern recognition device of one embodiment according to the application, device shown in Fig. 7
700 can use the mode of software, hardware or software and hardware combining to realize.Device 700 may be mounted in the first equipment,
In, the first equipment includes the first clear data collection and the first encrypted data set for being encrypted by second plaintext data set.Device
700 embodiment is substantially similar to the embodiment of method, so describing fairly simple, related place is referring to embodiment of the method
Part illustrates.
As shown in fig. 7, device 700 may include the first sending module 702 and the first receiving module 704.First sends mould
If block 702 fails to identify images to be recognized for first equipment utilization the first clear data collection, by the images to be recognized pair
The data answered are sent to the second equipment, so that first data set of the second equipment utilization knows the images to be recognized
Not, wherein first data set is the union of the first clear data collection and the second plaintext data set.First receives
Module 704 is used for after second equipment identifies the images to be recognized, receives the institute that second equipment is sent
State the recognition result of images to be recognized.
In one aspect, the first receiving module 704 is also used to know the images to be recognized in second equipment
After not, the decryption for receiving data element corresponding with the recognition result in the first data set that second equipment is sent is close
Key.Correspondingly, device 700 further includes deciphering module, the deciphering module is used to add using the decruption key to described first
Ciphertext data concentrates data element corresponding with the recognition result to be decrypted.
Fig. 8 shows the schematic diagram of the pattern recognition device of another embodiment according to the application, device shown in Fig. 8
800 can use the mode of software, hardware or software and hardware combining to realize.Device 800 may be mounted in the second equipment.Device
800 embodiment is substantially similar to the embodiment of method, so describing fairly simple, related place is referring to embodiment of the method
Part illustrates.
As shown in figure 8, device 800 may include the second receiving module 802, identification module 804 and the second sending module
806.Second receiving module 802 is used to receive the corresponding data of images to be recognized of the first equipment transmission, the first equipment packet
The first encrypted data set for including the first clear data collection and being encrypted by second plaintext data set.Identification module 804 is used for root
The images to be recognized is identified using the first data set according to the data, wherein first data set is described the
The union of one clear data collection and the second plaintext data set.Second sending module 806 is used for the images to be recognized
Recognition result is sent to first equipment.
In one aspect, device 800 further includes the first acquisition module.First, which obtains module, ties for obtaining with the identification
The decruption key of the corresponding data element of fruit.Correspondingly, the second sending module 806 is also used to the decruption key being sent to institute
The first equipment is stated, is tied so that decruption key described in first equipment utilization concentrates first encryption data with the identification
The corresponding data element of fruit is decrypted.
On the other hand, device 800 further includes judgment module.Judgment module is for judging whether first equipment is full
Sufficient preset condition；If so, calling first to obtain module.
In yet another aspect, the preset condition includes at least one below: (a) the first request of first equipment
Number reaches preset threshold, and first request number of times is first equipment of second device statistics in preset time period
Obtain the number of the recognition result；(b) the second request number of times of first equipment is lower than preset threshold, wherein described the
Two request number of times are the numbers of second equipment of the first device request identification of second device statistics；(c) described first
Equipment has the permission that the identification decruption key is obtained from second equipment.
The embodiment of the present application also provides a kind of electronic equipment, refers to Fig. 9, and Fig. 9 is the embodiment of the present application electronic equipment one
A embodiment schematic diagram.As shown in figure 9, for ease of description, illustrating only part relevant to the embodiment of the present application, specific skill
Art details does not disclose, please refers to the embodiment of the present application method part.
As shown in figure 9, electronic equipment 900 may include processor 902 and memory 904, wherein deposited on memory 904
Contain executable instruction, wherein the executable instruction makes processor 902 execute any implementation of Fig. 5 or Fig. 6 upon being performed
Method shown in mode.
As shown in figure 9, electronic equipment 900 can also include connecting different system components (including processor 902 and memory
904) bus 906.Bus 906 indicates one of a few class bus structures or a variety of, including memory bus or memory
Controller, peripheral bus, graphics acceleration port, processor or the local using any bus structures in a variety of bus structures
Bus.For example, these architectures include but is not limited to industry standard architecture (ISA) bus, microchannel system knot
Structure (MAC) bus, enhanced isa bus, Video Electronics Standards Association (VESA) local bus and peripheral component interconnection (PCI)
Bus.
Electronic equipment 900 typically comprises a variety of computer system readable media.These media can be it is any can be by
The usable medium that electronic equipment 900 accesses, including volatile and non-volatile media, moveable and immovable medium.
Memory 904 may include the computer system readable media of form of volatile memory, such as arbitrary access is deposited
Reservoir (RAM) 908 and and/or cache memory 910.Electronic equipment 900 may further include it is other it is removable/can not
Mobile, volatile/non-volatile computer system storage medium.Only as an example, storage system 912 can be used for reading and writing not
Movably, non-volatile magnetic media (Fig. 9 do not show, commonly referred to as " hard disk drive ").It, can be with although being not shown in Fig. 9
The disc driver for reading and writing to removable non-volatile magnetic disk (such as " floppy disk ") is provided, and non-volatile to moving
The CD drive of CD (such as CD-ROM, DVD-ROM or other optical mediums) read-write.In these cases, each driving
Device can be connected by one or more data media interfaces with bus 906.Memory 904 may include at least one program
Product, the program product have one group of (for example, at least one) program module, these program modules are configured to perform the present invention
The function of above-mentioned Fig. 5 or Fig. 6 embodiment.
Program/utility 914 with one group of (at least one) program module 916, can store in such as memory
In 904, such program module 916 includes but is not limited to operating system, one or more application program, other program modules
And program data, it may include the realization of network environment in each of these examples or certain combination.Program module 916
Usually execute the function and/or method in above-mentioned Fig. 5 or Fig. 6 embodiment described in the invention.
Electronic equipment 900 can also be with one or more external equipments 922 (such as keyboard, sensing equipment, display 924
Deng) communication, can also be enabled a user to one or more equipment interact with the electronic equipment 900 communicate, and/or with make
Any equipment (such as network interface card, the modem that the electronic equipment 900 can be communicated with one or more of the other calculating equipment
Etc.) communication.This communication can be carried out by input/output (I/O) interface 918.Also, electronic equipment 900 can also lead to
Cross network adapter 920 and one or more network (such as local area network (LAN), wide area network (WAN) and/or public network, example
Such as internet) communication.As shown in figure 9, network adapter 920 is communicated by bus 906 with other modules of electronic equipment 900.
It should be understood that although not shown in the drawings, other hardware and/or software module can not used in conjunction with electronic equipment 900, including but not
It is limited to: microcode, device driver, redundant processor, external disk drive array, RAID system, tape drive and number
According to backup storage system etc..
The program that processor 902 is stored in memory 904 by operation, thereby executing various function application and data
Processing, such as realize method shown in above-described embodiment.
Embodiments herein also provides a kind of computer storage medium, is stored thereon with computer program, the calculating
Machine program includes executable instruction, when the executable instruction is executed by processor, implements the image of foregoing individual embodiments
Any one embodiment in recognition methods.
The computer storage medium of the present embodiment may include in the memory 904 in above-mentioned embodiment illustrated in fig. 9 with
Machine accesses memory (RAM) 908, and/or cache memory 910, and/or storage system 912.
With the development of science and technology, the route of transmission of computer program is no longer limited by tangible medium, it can also be directly from net
Network downloading, or obtained using other modes.Therefore, the computer storage medium in the present embodiment not only may include tangible
Medium can also include invisible medium.
It will be understood by those skilled in the art that the embodiment of the present invention can provide as method, apparatus or computer program production
Product.Therefore, in terms of the embodiment of the present invention can be used complete hardware embodiment, complete software embodiment or combine software and hardware
Embodiment form.Moreover, it wherein includes computer available programs generation that the embodiment of the present invention, which can be used in one or more,
The meter implemented in the computer-usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) of code
The form of calculation machine program product.
The embodiment of the present invention be referring to according to the method for the embodiment of the present invention, the process of device and computer program product
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing terminal devices
To generate a machine, so that being produced by the instruction that computer or the processor of other programmable data processing terminal devices execute
Life is for realizing the function of specifying in one or more flows of the flowchart and/or one or more blocks of the block diagram
Device.
The specific embodiment illustrated above in conjunction with attached drawing describes exemplary embodiment, it is not intended that may be implemented
Or fall into all embodiments of the protection scope of claims." exemplary " meaning of the term used in entire this specification
Taste " be used as example, example or illustration ", be not meant to than other embodiments " preferably " or " there is advantage ".For offer pair
The purpose of the understanding of described technology, specific embodiment include detail.However, it is possible in these no details
In the case of implement these technologies.In some instances, public in order to avoid the concept to described embodiment causes indigestion
The construction and device known is shown in block diagram form.
The foregoing description of present disclosure is provided so that any those of ordinary skill in this field can be realized or make
Use present disclosure.To those skilled in the art, the various modifications carried out to present disclosure are apparent
, also, can also answer generic principles defined herein in the case where not departing from the protection scope of present disclosure
For other modifications.Therefore, present disclosure is not limited to examples described herein, but with meet principle disclosed herein
It is consistent with the widest scope of novel features.
Claims (10)
1. image-recognizing method is applied to the first equipment, wherein first equipment is including the first clear data collection and by second
The first encrypted data set that clear data collection encrypts, which comprises
If first equipment utilization the first clear data collection fails to identify images to be recognized, by the corresponding number of the images to be recognized
According to the second equipment is sent to, so that first data set of the second equipment utilization identifies the images to be recognized, wherein
First data set is the union of the first clear data collection and the second plaintext data set；And
After second equipment identifies the images to be recognized, the described to be identified of the second equipment transmission is received
The recognition result of image.
2. according to the method described in claim 1, wherein, the method also includes:
After second equipment identifies the images to be recognized, the first data set that second equipment is sent is received
In data element corresponding with the recognition result decruption key；
Data element corresponding with the recognition result is concentrated to solve first encryption data using the decruption key
It is close.
3. image-recognizing method is applied to the second equipment, which comprises
Receive the first equipment transmission the corresponding data of images to be recognized, first equipment include the first clear data collection and by
The first encrypted data set that second plaintext data set encrypts；
The images to be recognized is identified using the first data set according to the data, wherein first data set is
The union of the first clear data collection and the second plaintext data set；
The recognition result of the images to be recognized is sent to first equipment.
4. according to the method described in claim 3, wherein, the method also includes:
Obtain the decruption key of data element corresponding with the recognition result；
The decruption key is sent to first equipment, so that decruption key described in first equipment utilization is to described
One encryption data concentrates data element corresponding with the recognition result to be decrypted.
5. according to the method described in claim 4, wherein, obtaining the decruption key of data element corresponding with the recognition result
The step of before, the method also includes:
Judge whether first equipment meets preset condition；Data corresponding with the recognition result are obtained if so, executing
The step of decruption key of element.
6. according to the method described in claim 5, wherein, the preset condition includes at least one below:
(a) the first request number of times of first equipment reaches preset threshold, and first request number of times is second equipment
First equipment of statistics obtains the number of the recognition result in preset time period；
(b) the second request number of times of first equipment is lower than preset threshold, wherein second request number of times is described second
The number of second equipment of the first device request identification of device statistics；
(c) first equipment has the permission that the identification decruption key is obtained from second equipment.
7. pattern recognition device is applied to the first equipment, wherein first equipment is including the first clear data collection and by second
The first encrypted data set that clear data collection encrypts, described device include:
First sending module will be described if failing to identify images to be recognized for first equipment utilization the first clear data collection
The corresponding data of images to be recognized are sent to the second equipment, so that first data set of the second equipment utilization is to described to be identified
Image is identified, wherein first data set be the first clear data collection and the second plaintext data set and
Collection；
First receiving module is set for after second equipment identifies the images to be recognized, receiving described second
The recognition result for the images to be recognized that preparation is sent.
8. pattern recognition device is applied to the second equipment, comprising:
Second receiving module, for receiving the corresponding data of images to be recognized of the first equipment transmission, first equipment includes
First clear data collection and the first encrypted data set encrypted by second plaintext data set；
Identification module, for being identified using the first data set to the images to be recognized according to the data, wherein described
First data set is the union of the first clear data collection and the second plaintext data set；
Second sending module, for the recognition result of the images to be recognized to be sent to first equipment.
9. electronic equipment, comprising:
Processor；And
Memory is stored thereon with executable instruction；
Wherein, the processor is configured to execute the executable instruction to implement side as claimed in any one of claims 1 to 6
Method.
10. computer readable storage medium is stored thereon with computer program, the computer program includes executable instruction,
When the executable instruction is executed by processor, implement as the method according to claim 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910182393.5A CN109919109A (en) | 2019-03-12 | 2019-03-12 | Image-recognizing method, device and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910182393.5A CN109919109A (en) | 2019-03-12 | 2019-03-12 | Image-recognizing method, device and equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109919109A true CN109919109A (en) | 2019-06-21 |
Family
ID=66964382
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910182393.5A Pending CN109919109A (en) | 2019-03-12 | 2019-03-12 | Image-recognizing method, device and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109919109A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114202781A (en) * | 2020-08-27 | 2022-03-18 | 腾讯科技（深圳）有限公司 | Face recognition method and device, electronic equipment and readable storage medium |
| CN114691898A (en) * | 2022-03-10 | 2022-07-01 | 北京旷视科技有限公司 | Image query method, terminal device, system and computer-readable storage medium |
| CN115019291A (en) * | 2021-11-22 | 2022-09-06 | 荣耀终端有限公司 | Character recognition method for image, electronic device and storage medium |
-
2019
- 2019-03-12 CN CN201910182393.5A patent/CN109919109A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114202781A (en) * | 2020-08-27 | 2022-03-18 | 腾讯科技（深圳）有限公司 | Face recognition method and device, electronic equipment and readable storage medium |
| CN115019291A (en) * | 2021-11-22 | 2022-09-06 | 荣耀终端有限公司 | Character recognition method for image, electronic device and storage medium |
| CN114691898A (en) * | 2022-03-10 | 2022-07-01 | 北京旷视科技有限公司 | Image query method, terminal device, system and computer-readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109886417A (en) | Model parameter training method, device, equipment and medium based on federation's study | |
| CN108197891A (en) | A kind of electronic signature device and method based on block chain | |
| CN104495545B (en) | Electronic elevator maintenance supervision and management system and method for elevator maintenance based on dynamic two-dimensional codes | |
| CN109919109A (en) | Image-recognizing method, device and equipment | |
| CN112100679B (en) | Data processing method and device based on privacy protection and server | |
| CN105611488A (en) | Automatic Bluetooth connection method and master device, slave device and system | |
| CN110197541A (en) | A kind of shared automobile management method based on block chain | |
| CN112365001B (en) | Model generation method, device and server | |
| CN107181714A (en) | Verification method and device, the generation method of service code and device based on service code | |
| CN106603496A (en) | Data transmission protection method, intelligent card, server, and communication system | |
| CN111985921B (en) | Verification processing method based on block chain offline payment and digital financial service platform | |
| CN103532960B (en) | Decrypt device | |
| CN110401542A (en) | Electronic identity voucher generation method, terminal and server | |
| CN109150513A (en) | Private key storage method, computer equipment and storage medium based on block chain | |
| CN105656669A (en) | Remote reparation method of electronic device, device, repaired device and system | |
| CN107742141B (en) | Intelligent identity information acquisition method and system based on RFID technology | |
| CN202870898U (en) | Radio frequency-based commodity information identification system | |
| CN112417485A (en) | Model training method, system and device based on trusted execution environment | |
| CN110069907A (en) | Big data source tracing method and system based on digital watermarking | |
| CN105847883A (en) | Program stream push method and apparatus based on user trust grades | |
| CN106991332A (en) | The method and device that a kind of mass data is stored safely | |
| CN110968885A (en) | Model training data storage method and device, electronic equipment and storage medium | |
| CN112597525A (en) | Data processing method and device based on privacy protection and server | |
| CN109933679A (en) | Object type recognition methods, device and equipment in image | |
| CN116611107A (en) | Data processing method, device and equipment, chip, board card and medium |
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 |