CN109933679A - Object type recognition methods, device and equipment in image - Google Patents
Object type recognition methods, device and equipment in image Download PDFInfo
- Publication number
- CN109933679A CN109933679A CN201910182408.8A CN201910182408A CN109933679A CN 109933679 A CN109933679 A CN 109933679A CN 201910182408 A CN201910182408 A CN 201910182408A CN 109933679 A CN109933679 A CN 109933679A
- Authority
- CN
- China
- Prior art keywords
- equipment
- data
- data set
- object type
- image
- 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 the first data set of equipment utilization fails to identify the object type in images to be recognized, the corresponding data of described image are then sent to the second equipment, and second data set of the second equipment utilization is requested to identify the object type in described image, wherein, first data set is the subset of second data set;And after second equipment identifies the object type in described image, the recognition result of the object type in the described image that second equipment is sent is received.It is not necessary that complete second data set is supplied to user in the scheme of the embodiment of the present invention, it is only necessary to common partial data are supplied to user, complete data can be prevented to be stolen or reveal, ensure that the safety of data.
Description
Technical field
This application involves digital image recognition technical fields, in particular to object type recognition methods, device in image
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 picture number
According to library, image is analyzed using computer or embedded device, and then detect using sample image feature in image data base
A special kind of skill of images to be recognized.Specifically, using the feature formation algorithm of various sample images, allow computer to figure to be identified
As being learnt, and sorting algorithm is utilized, the technology that images to be recognized is identified or be detected.Image data base is storable in
Computer or embedded device are local, also can store beyond the clouds.Storage can save computer or embedded device beyond the clouds
Local storage space, but due to being limited by network technology, recognition result totally cannot be rapidly obtained, therefore in many applied fields
Image data base can only be supplied to user in scape and be stored in local, this makes the total data presence of image data base be stolen
Or the risk of leakage.
Summary of the invention
In view of problem above, the embodiment of the present invention provides object type recognition methods, device and the equipment in image,
It can solve the technical issues of above-mentioned background technology part is mentioned.
Object type recognition methods in the image of embodiment according to the invention is applied to the first equipment, comprising: if the
One the first data set of equipment utilization not can recognize that the object type in images to be recognized, then sends out the corresponding data of described image
It send to the second equipment, and second data set of the second equipment utilization is requested to identify the object type in described image,
Wherein, first data set is the subset of second data set;And in second equipment to pair in described image
After type identification, the identification information of the object type in the described image that second equipment is sent is received.
Object type recognition methods in the image of embodiment according to the invention is applied to the second equipment, comprising: receives
The corresponding data of images to be recognized that first equipment is sent, first equipment include the first data set;According to the data benefit
Identification is carried out to obtain identification information to the object type in described image with the second data set, wherein first data
Collection is the subset of second data set;The identification information is sent to first equipment.
Object type identification device in the image of embodiment according to the invention is applied to the first equipment, comprising: first
Sending module, if not can recognize that the object type in images to be recognized for first the first data set of equipment utilization, by institute
It states the corresponding data of image and is sent to the second equipment, and request second data set of the second equipment utilization in described image
Object type is identified, wherein first data set is the subset of second data set;First receiving module, is used for
After second equipment is to the object type identification in described image, receive in the described image that second equipment is sent
The identification information of object type.
Object type identification device in the image of embodiment according to the invention 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 the first data
Collection;Identification module, for according to the data using the second data set to the object type in described image carry out identification to
Obtain identification information, wherein first data set is the subset of second data set;Second sending module is used for institute
It states identification information and is 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 the identification of the object type in image above-mentioned
Method.
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 the object class in image above-mentioned
Type recognition methods.
It can be seen from the above that in the scheme of the embodiment of the present invention image data base total data owning side without
Total data (the second data set) need to be supplied to user, it is only necessary to which common partial data (the first data set) is supplied to use
Family, such user both can use common partial data and quickly identified to the object type in images to be recognized, can also
Sending identification request to the owning side of total data and receiving knowledge when not can recognize that the object type in images to be recognized
Other information, so prevents the total data of image data base to be stolen or reveal, and ensure that the safety of data;Simultaneously as
User locally only stores partial data, has saved the memory space of local device.
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 object type recognition methods in the image of one embodiment of the invention;
Fig. 3 is the interaction embodiment schematic diagram of the object type recognition methods in the image of another embodiment of the present invention;
Fig. 4 is the interaction embodiment schematic diagram of the object type recognition methods in the image of further embodiment of this invention;
Fig. 5 is the flow chart of the object type recognition methods in the image of one embodiment of the invention;
Fig. 6 is the flow chart of the object type recognition methods in the image of another embodiment of the present invention;
Fig. 7 is the schematic diagram of the object type identification device in the image of one embodiment of the invention;
Fig. 8 is the schematic diagram of the object type identification device in the image 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.
Fig. 1 is shown can be using one embodiment of object type recognition methods or device in image of the invention
Exemplary system architecture 100.
As shown in Figure 1, system 100 may include the first equipment 101,102,103, network 104 and the second equipment 105.Its
In, the first equipment 101,102,103 can be stored with the first data set, and the second equipment 105 can be stored with the second data set.Network
104 between the first equipment 101,102,103 and the second equipment 105 to provide the medium of communication link.Network 104 can wrap
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 and be such as, but not limited to STB (Set Top Box, machine top
Box), router, UE (User Equipment, user terminal) or node server etc., in embodiments of the present invention, first sets
Standby 101,102,103 can implement in a variety of manners.For example, may include such as mobile phone, smart phone, notebook electricity
Brain, digit broadcasting receiver, PDA (personal digital assistant), PAD (tablet computer), PMP (portable media player) etc.
Mobile terminal, the fixed terminal and Edge Server of such as desktop computer etc..In first equipment 101,102,103
The object type in images to be recognized can be identified using image recognition algorithm with operation image recognizer.First sets
First data set of standby 101,102,103 storage can be identical, can not also be identical.
Second equipment 105 can be data center server, for receive the first equipment 101,102,103 transmission wait know
The corresponding data of other image simultaneously identify the object type in images to be recognized, and identification information that identification obtains is returned
Back to the first equipment 101,102,103.In second equipment 105 image recognition algorithm pair can be utilized with operation image recognizer
Object type in images to be recognized is identified.
In the embodiment of the present invention, the second data set is the set of the total data in image data base, and the first data set is
The set of partial data in image data base, therefore the first data set is the subset of the second data set.In image data base
Data include label data corresponding with identification information and with the associated sample image data of label data.Identification information can be
Object-type information in image, the object in image are such as, but not limited to product defects in product defects identification field, people
People in face identification field, the article in article identification field, the word in handwritten word identification field etc..Object-type information can
To be the specific classification information of above-mentioned various objects.Same identification information can correspond to multiple label datas, each label data
A sample image data is respectively associated.For example, same target type can be acquired to obtain by different angle to object
Multiple sample image datas are taken, the number of tags that image labeling obtains each sample image data is carried out to each sample image data
According to.The recognition methods of the embodiment of the present invention can use the sample image data in image data base and know to data to be identified
Not, and obtain with the associated label data of sample image data, corresponding identification information is obtained according to label data.Specifically,
The similarity that images to be recognized data and sample image data can be calculated (such as can be by calculating Euclidean distance or Hamming distance
To calculate similarity), it obtains similarity and meets the sample image data of preset requirement, to obtain identification information;Alternatively, can benefit
Use sample image data as input, label data obtains neural network model or classifier as output, training, will be to be identified
The corresponding data of image input trained neural network model or classifier, export the confidence level of all kinds of labels, obtain confidence
Degree meets the label data of preset requirement, to obtain identification information.
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.
The interaction embodiment signal of the object type recognition methods in image provided Fig. 2 shows one embodiment of the application
Figure, this method 200 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, such as the corresponding data of images to be recognized T that the receivable user terminal of the first equipment is sent.First equipment can be to be identified
Object in image T carries out positioning and dividing processing, to obtain the characteristic of the object in images to be recognized T, wherein positioning
Object is split from image with dividing processing, is conducive to the subsequent quick and accurate identification to object type.Positioning with
Dividing processing is known technology, omits descriptions thereof herein.In other embodiments, what the first equipment obtained is to be identified
The characteristic of image T is also possible to the characteristic of the object in images to be recognized T, such as knowledge can be treated by other equipment
Object in other image T carries out positioning and dividing processing, and extracts the characteristic of object, and the characteristic of object is sent out
Give the first equipment.Characteristic for example can be feature vector.
In the embodiment of the present application, the object in images to be recognized T for example can be the target object to be identified, such as but
It is not limited to the product defects in product defects identification field, the people in field of face identification, the article in article identification field, hand
The word etc. to write in identification field.
S204: the first equipment is according to the corresponding data of images to be recognized T using the first data set in images to be recognized T
Object type is identified.
In the embodiment of the present application, the first data set can be stored in the collection of the data of the image data base of the first equipment
Close, the data in image data base include label data corresponding with identification information and with the associated sample image number of label data
According to.First equipment can be by calculating the similarity of the corresponding data of images to be recognized T and sample image data come to be identified
Object type in image T is identified, with the nerve net that can also pass through utilization sample image data and label data training
Network model or classifier identify the object type in images to be recognized T.
S206:, will be to if first the first data set of equipment utilization not can recognize that the object type in images to be recognized T
The corresponding data of identification image T are sent to the second equipment.
In the embodiment of the present application, similarity threshold for example can be set in the first equipment, and the first equipment calculates figure to be identified
As the similarity of T corresponding data and sample image data, similarity is greater than or equal to the sample graph of similarity threshold if it exists
As data, it is determined that first the first data set of equipment utilization can identify the object type in images to be recognized T, then first set
It is standby will to meet the output of identification information corresponding to the sample image data of similarity threshold or return;Similarity is big if it does not exist
In or equal to similarity threshold sample image data, it is determined that first the first data set of equipment utilization cannot be identified wait know
Object type in other image T.First equipment can also first pass through classifier and obtain the first sample that confidence level meets preset requirement
Then this image data calculates the similarity of first sample image data and the corresponding data of images to be recognized T, judges similarity
Whether meet the requirements, so that it is determined that whether the first equipment can recognize that the object type in images to be recognized T, judgment method can adopt
With above-mentioned similarity threshold.
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 is according to the corresponding data of images to be recognized T using the second data set in images to be recognized T
Object type is identified, to obtain the identification information of the object type in images to be recognized T.
In the embodiment of the present application, the second data set can be stored in the collection of the data of the image data base of the second equipment
It closes, wherein the second data set includes the first data set, i.e. the first data set is the subset of the second data set.Second equipment can also
By calculating similarity, alternatively, being known by neural network model or classifier to the object type in images to be recognized T
Not.
Identification information is sent to the first equipment by the S210: the second equipment.
In the embodiment of the present application, the sample image data pair that the second equipment can meet the requirements similarity or confidence level
The identification information answered is sent to the first equipment, such as can be by similarity or the corresponding knowledge of the maximum sample image data of confidence level
Other information is sent to the first equipment, and preset threshold also can be set, and similarity or confidence level are greater than or equal to preset threshold
The corresponding identification information of sample image data is sent to the first equipment.
It can be seen from the above that the scheme of the embodiment of the present invention has the advantages that (1) first equipment can
To be identified first with the first data set to the object type in images to be recognized, since the first data set is stored in local,
It therefore being capable of rapidly feedback identifying information;(2) it is not necessary that all images data of image data base are supplied to user, it is only necessary to
Common part image data is supplied to user, complete image data can be prevented to be stolen or reveal, guarantees picture number
According to safety;(3) first equipment only storage section image data, has saved the memory space of the first equipment.
The interaction that Fig. 3 shows the object type recognition methods in the image that another embodiment of the application provides is implemented to illustrate
It is intended to, 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 is according to the corresponding data of images to be recognized T using the first data set in images to be recognized T
Object type is identified.
S306:, will be to if first the first data set of equipment utilization not can recognize that the object type in images to be recognized T
The corresponding data of identification image T are sent to the second equipment.
S308: the second equipment is according to the corresponding data of images to be recognized T using the second data set in images to be recognized T
Object type is identified, to obtain the identification information of the object type in images to be recognized T.
S310: the second equipment obtains the first number corresponding with the identification information according to identification information from the second data set
According to.
In the embodiment of the present application, the second equipment can obtain in the second data set corresponding with identification information according to identification information
At least one label data, and obtain with the associated sample image data of label data.Same identification information can correspond to more
A label data, then the second equipment can obtain multiple label datas according to identification information, and obtain with multiple label datas one by one
Associated sample image data.The label data and sample image data of acquisition constitute the first data corresponding with identification information.
Corresponding first data of identification information and identification information are sent to the first equipment by the S312: the second equipment.
First data are stored in the first data set by the S314: the first equipment.
In the embodiment of the present application, the first equipment receives the first data that the second equipment is sent, and then deposits the first data
It is stored in the first data set, so can recognize, improve using the first data set when again identifying that the object type next time
The feedback speed of identification information, while also mitigating the load of the second equipment.
The interaction that Fig. 4 shows the object type recognition methods in the image that the another embodiment of the application provides is implemented to illustrate
It is intended to, 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 is according to the corresponding data of images to be recognized T using the first data set in images to be recognized T
Object type is identified.
S406:, will be to if first the first data set of equipment utilization not can recognize that the object type in images to be recognized T
The corresponding data of identification image T are sent to the second equipment.
S408: the second equipment is according to the corresponding data of images to be recognized T using the second data set in images to be recognized T
Object type is identified, to obtain the identification information of the object type in images to be recognized T.
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 period obtain the number of the identification information;(b) the second request number of times of first equipment is lower than preset threshold, institute
State the number that the second request number of times is second equipment of the first device request identification of second device statistics;(c) described
First equipment has the permission that first data are obtained from second equipment.
In preset condition (a), the second equipment can recorde the historical requests information of the first device request identification data, go through
History solicited message includes identification information acquired in historical requests, after the identification information for obtaining images to be recognized T, statistics first
Equipment obtains the number of the identification information of the object type in images to be recognized T in preset time period, to obtain the first equipment
The first request number of times.By the way that the first request number of times is arranged, it is a large amount of to can be reduced data corresponding to the identification information occurred once in a while
The case where occupying the first device memory appearance.
In preset condition (b), the second equipment can recorde the historical requests information of the first device request identification image,
After the identification information for obtaining the object type in images to be recognized T, the number of statistics the first device request identification image, to obtain
Obtain the second request number of times.By the way that the second request number of times is arranged, can prevent by largely sending identification request image data base
Partial data.
In preset condition (c), the second equipment can recorde the authority information of the first equipment, obtain images to be recognized T
In object type identification information after, judge whether the first equipment has the power for obtaining data corresponding with the identification information
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 identification information of object type in images to be recognized T is sent to the first equipment by the S412: the second equipment.
S414: the second equipment obtains the first number corresponding with the identification information according to identification information from the second data set
According to.
Corresponding first data of identification information and identification information are sent to the first equipment by the S416: the second equipment.
First data are stored in the first data set by the S418: the first equipment.
Fig. 5 shows the flow chart of the object type recognition methods in the image according to one embodiment of the application.Shown in Fig. 5
Method 500 be applied to the first equipment.
As shown in figure 5, method 500 may comprise steps of: S502, if first the first data set of equipment utilization fails to know
Not Chu object type in images to be recognized, then the corresponding data of described image are sent to the second equipment, and request described
Two the second data sets of equipment utilization identify the object type in described image, wherein first data set is described
The subset of second data set.
Method 500 can be the following steps are included: S504, knows the object type in described image in second equipment
After not, the identification information of the object type in the described image that second equipment is sent is received.
In one aspect, after second equipment identifies the object type in described image, the method is also
It may include the following contents: receiving corresponding with the identification information the in second data set that second equipment is sent
One data;First data are stored in first data set.
Fig. 6 shows the flow chart of the object type recognition methods in the image according to another embodiment of the application.Fig. 6 institute
The method 600 shown is 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 data set.
Method 600 can be the following steps are included: S604, utilizes the second data set in described image according to the data
Object type carry out identification to obtaining identification information, wherein first data set is the subset of second data set.
Method 600 can be the following steps are included: S606, be sent to first equipment for the identification information.
In one aspect, after identifying to the object type in described image, the method also includes the following contents:
Obtain the first data corresponding with the identification information in second data set;First data are sent to described first
Equipment, so that first data are stored in first data set by first equipment.
On the other hand, the first data corresponding with the object type in described image in second data set are obtained
The step of before, the method also includes: judge whether first equipment meets preset condition;Institute is obtained if so, executing
The step of stating the first data corresponding with the object type in described image in the second data set.
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 the preset time
Section obtains the number of the identification information;(b) the second request number of times of first equipment is lower than preset threshold, and described second asks
Seeking number is the number of second equipment of the first device request identification of second device statistics;(c) first equipment
With the permission for obtaining first data from second equipment.
Fig. 7 shows the schematic diagram of the object type identification device in the image according to one embodiment of the application, Fig. 7
Shown in device 700 can use the mode of software, hardware or software and hardware combining to realize.Device 700 may be mounted at first
In equipment.The embodiment of device 700 is substantially similar to the embodiment of method, so describe fairly simple, related place referring to
The part of embodiment of the method 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 not can recognize that the object type in images to be recognized for first the first data set of equipment utilization, by the figure
As corresponding data are sent to the second equipment, and request second data set of the second equipment utilization to the object in described image
Type is identified, wherein first data set is the subset of second data set.First receiving module 704 is used for
After second equipment is to the object type identification in described image, pair in the described image that second equipment is sent is received
As the identification information of type.
In one aspect, the first receiving module 704 is also used in second equipment to the object type in described image
After identification, the first data corresponding with the identification information in second data set that second equipment is sent are received.Phase
It answers, device 700 further includes memory module, and the memory module is used to first data being stored in first data set
In.
Fig. 8 shows the schematic diagram of the object type identification device in the image according to another embodiment of the application,
Device 800 shown in Fig. 8 can use the mode of software, hardware or software and hardware combining to realize.Device 800 may be mounted at
In two equipment.The embodiment of device 800 is substantially similar to the embodiment of method, so describe fairly simple, related place ginseng
See the part explanation of embodiment of the method.
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
Include the first data set.Identification module 804 is used for according to the data using the second data set to the object type in described image
Identification is carried out to obtain identification information, wherein first data set is the subset of second data set.Second sends mould
Block 806 is used to the identification information being sent to first equipment.
In one aspect, device 800 further includes the first acquisition module.First acquisition module is for obtaining second data
Concentrate the first data corresponding with the identification information.Correspondingly, the second sending module 806 is also used to send out first data
It send to first equipment, so that first data are stored in first data set by first equipment.
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 described 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 the preset time
Section obtains the number of the identification information;(b) the second request number of times of first equipment is lower than preset threshold, and described second asks
Seeking number is the number of second equipment of the first device request identification of second device statistics;(c) first equipment
With the permission for obtaining first data 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
In object type recognition methods in any one embodiment.
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. the object type recognition methods in image is applied to the first equipment, comprising:
It is if first the first data set of equipment utilization not can recognize that the object type in images to be recognized, described image is corresponding
Data be sent to the second equipment, and request second data set of the second equipment utilization to the object type in described image into
Row identification, wherein first data set is the subset of second data set;And
After second equipment is to the object type identification in described image, the described image that second equipment is sent is received
In object type identification information.
2. according to the method described in claim 1, wherein, the method also includes:
After second equipment is to the object type identification in described image, second equipment is sent described second is received
The first data corresponding with the identification information in data set;
First data are stored in first data set.
3. the object type recognition methods in image is applied to the second equipment, comprising:
The corresponding data of images to be recognized of the first equipment transmission are received, first equipment includes the first data set;
The object type in described image is carried out identifying to obtain identification information using the second data set according to the data,
Wherein, first data set is the subset of second data set;
The identification information is sent to first equipment.
4. according to the method described in claim 3, wherein, the method also includes:
Obtain the first data corresponding with the identification information in second data set;
First data are sent to first equipment so that first equipment first data are stored in it is described
In first data set.
5. according to the method described in claim 4, wherein, obtain in second data set with the object type in described image
Before the step of corresponding first data, the method also includes:
Judge whether first equipment meets preset condition;If so, execute obtain in second data set with the figure
The step of object type corresponding first data as in.
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 identification information in the preset period;
(b) the second request number of times of first equipment is lower than preset threshold, and second request number of times is second equipment
The number of second equipment of the first device request identification of statistics;
(c) first equipment has the permission that first data are obtained from second equipment.
7. the object type identification device in image is applied to the first equipment, comprising:
First sending module, if not can recognize that the object class in images to be recognized for first the first data set of equipment utilization
The corresponding data of described image are then sent to the second equipment by type, and request second data set of the second equipment utilization to institute
The object type stated in image is identified, wherein first data set is the subset of second data set;
First receiving module, for receiving described second after second equipment is to the object type identification in described image
The identification information for the object type in described image that equipment is sent.
8. the object type identification device in image 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 data set;
Identification module, for according to the data using the second data set to the object type in described image carry out identification to
Obtain identification information, wherein first data set is the subset of second data set;
Second sending module, for the identification information 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 |
---|---|---|---|
CN201910182408.8A CN109933679A (en) | 2019-03-12 | 2019-03-12 | Object type recognition methods, device and equipment in image |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910182408.8A CN109933679A (en) | 2019-03-12 | 2019-03-12 | Object type recognition methods, device and equipment in image |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109933679A true CN109933679A (en) | 2019-06-25 |
Family
ID=66986940
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910182408.8A Pending CN109933679A (en) | 2019-03-12 | 2019-03-12 | Object type recognition methods, device and equipment in image |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109933679A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
GB2585938A (en) * | 2019-07-26 | 2021-01-27 | Arm Ip Ltd | Recognition apparatus and method |
WO2021047664A1 (en) * | 2019-09-12 | 2021-03-18 | 华为技术有限公司 | Biometric feature recognition method and related device |
-
2019
- 2019-03-12 CN CN201910182408.8A patent/CN109933679A/en active Pending
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
GB2585938A (en) * | 2019-07-26 | 2021-01-27 | Arm Ip Ltd | Recognition apparatus and method |
GB2588496A (en) * | 2019-07-26 | 2021-04-28 | Arm Ip Ltd | Recognition apparatus and method |
US11367270B2 (en) | 2019-07-26 | 2022-06-21 | Arm Ip Limited | Recognition apparatus and method |
GB2585938B (en) * | 2019-07-26 | 2023-09-13 | Arm Ip Ltd | Recognition apparatus and method |
GB2588496B (en) * | 2019-07-26 | 2023-09-20 | Arm Ip Ltd | Recognition apparatus and method |
WO2021047664A1 (en) * | 2019-09-12 | 2021-03-18 | 华为技术有限公司 | Biometric feature recognition method and related device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Shen et al. | BBAS: Towards large scale effective ensemble adversarial attacks against deep neural network learning | |
US20210049505A1 (en) | Adversarial example detection method and apparatus, computing device, and non-volatile computer-readable storage medium | |
CN111476309A (en) | Image processing method, model training method, device, equipment and readable medium | |
CN108076154A (en) | Application message recommends method, apparatus and storage medium and server | |
CN104094194A (en) | Method and apparatus for identifying a gesture based upon fusion of multiple sensor signals | |
CN109074497B (en) | Identifying activity in a sequence of video images using depth information | |
CN110008984B (en) | Target fraud transaction model training method and device based on multitasking samples | |
CN103473492A (en) | Method and user terminal for recognizing permission | |
CN109409241A (en) | Video checking method, device, equipment and readable storage medium storing program for executing | |
CN109918949A (en) | Recognition methods, device, electronic equipment and storage medium | |
CN102375987A (en) | Image processing device and image feature vector extracting and image matching method | |
CN107729768A (en) | A kind of page display method, device, Intelligent flat and storage medium | |
CN109933679A (en) | Object type recognition methods, device and equipment in image | |
US11348254B2 (en) | Visual search method, computer device, and storage medium | |
US9424484B2 (en) | Feature interpolation | |
CN110895602B (en) | Identity authentication method and device, electronic equipment and storage medium | |
CN112843681B (en) | Virtual scene control method and device, electronic equipment and storage medium | |
CN109919109A (en) | Image-recognizing method, device and equipment | |
CN109947850A (en) | Data distributing method, device and equipment | |
CN115700845A (en) | Face recognition model training method, face recognition device and related equipment | |
CN109981755A (en) | Image-recognizing method, device and electronic equipment | |
CN112435035A (en) | Data auditing method, device and equipment | |
Wang et al. | SSFS: A space-saliency fingerprint selection framework for crowdsourcing based mobile location recognition | |
CN109933999A (en) | Recognition methods, device, electronic equipment and storage medium | |
US20190378230A1 (en) | Information processing apparatus and information processing method |
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 |