CN106682187A - Method and device for establishing image bottom libraries - Google Patents
Method and device for establishing image bottom libraries Download PDFInfo
- Publication number
- CN106682187A CN106682187A CN201611247448.9A CN201611247448A CN106682187A CN 106682187 A CN106682187 A CN 106682187A CN 201611247448 A CN201611247448 A CN 201611247448A CN 106682187 A CN106682187 A CN 106682187A
- Authority
- CN
- China
- Prior art keywords
- image
- bottom storehouse
- storehouse
- different types
- type
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/5866—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, manually generated location and time information
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
- G06F16/5854—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using shape and object relationship
Abstract
The invention provides a method and device for establishing image bottom libraries. The method comprises the steps that at least two different types of images acquired for the same object are received; based on the first type of images in the different types of images, the object is identified by utilizing the first image bottom library; the second type of images in the different types of images are marked based on identification results to establish the second image bottom library based on the marked second type of images. According to the method and device for establishing the image bottom libraries, objects in corresponding types of images are identified based on existing image bottom libraries, the identified objects are relevant with another type of images acquired for the object based on the identification results to establish another type of image bottom libraries, new image bottom libraries can be rapidly and efficiently established, and the labor and time costs are greatly reduced.
Description
Technical field
The present invention relates to image identification technical field, relates more specifically to a kind of method and dress for setting up image bottom storehouse
Put.
Background technology
The identification of current image recognition, such as facial image, majority is based on color image recognition.The knowledge of coloured image
Do not depend on coloured image bottom storehouse.In the application (such as security protection, financial field etc.) of some high safety ranks, to prevent from adopting
Assumed another's name to recognize with the image usurped, in addition it is also necessary to carry out In vivo detection to face to be identified.Based on such demand, can adopt red
Outer photographic head shoots infrared image and is assisted in identifying, it is therefore desirable to set up infrared image bottom storehouse to support the knowledge of infrared image
Not.
At present, the bottom storehouse photo for producing during the commonplace presence of the image in coloured image bottom storehouse, such as identity card typing, because
This coloured image bottom storehouse is relatively easily set up.But infrared image bottom storehouse is relatively free of relatively broad application, needs to re-establish.
However, the existing method for setting up image bottom storehouse is very loaded down with trivial details.For example, when setting up infrared image bottom storehouse, need to be taken the photograph based on infrared
As head resurveys image and then marks the infrared bottom storehouse of typing after various relevant informations manually, flow process is troublesome, it is difficult to fast run-up
Stand a huge data base.
The content of the invention
The present invention is proposed in order to solve the above problems.According to an aspect of the present invention, there is provided one kind is used to set up image
The method in bottom storehouse, methods described includes：Receive at least two different types of images for same target collection；Based on described
First kind image in different types of image, is identified using the first image bottom storehouse to the object；And based on institute
The result for stating identification is labeled to the Second Type image in the different types of image, for based on Jing after mark
The Second Type image sets up the second image bottom storehouse.
In one embodiment of the invention, methods described also includes：Set up right between the different types of image
Should be related to.
In one embodiment of the invention, the different types of image is gathered simultaneously for same target.
In one embodiment of the invention, the different types of image is by different types of image capture device
For same target collection.
In one embodiment of the invention, the first kind image is coloured image, and the Second Type image is
Infrared image, described first image bottom storehouse is coloured image bottom storehouse, and the second image bottom storehouse is infrared image bottom storehouse.
In one embodiment of the invention, the step of identification is included in search and institute in the storehouse of described first image bottom
State the destination object of match objects.
In one embodiment of the invention, if searched in the storehouse of described first image bottom and the match objects
Destination object, then pair Second Type image that there is corresponding relation with the first kind image be labeled, it is described
Mark includes setting up the Second Type image with the corresponding relation of the destination object.
In one embodiment of the invention, it is described to set up Second Type image pass corresponding with the destination object
The step of being includes：The relevant information of the destination object in the storehouse of described first image bottom is added to into the Second Type figure
Picture.
In one embodiment of the invention, the title of the relevant information of the destination object including the object or
Name, or also including the adeditive attribute information of the destination object.
In one embodiment of the invention, the step of identification is included in search and institute in the storehouse of described first image bottom
The destination object of match objects is stated, if not searching the target with the match objects in the storehouse of described first image bottom
Object, then it is described mark include set up the Second Type image with the corresponding relation of the first kind image.
In one embodiment of the invention, the object is face.
According to a further aspect of the invention, there is provided a kind of device for setting up image bottom storehouse, described device includes：Receive
Module, for receiving at least two different types of images for same target collection；Identification module, for based on it is described not
First kind image in the image of same type, is identified using the first image bottom storehouse to the object；And labeling module,
The Second Type image in the different types of image is labeled for the result based on the identification, for being based on
The Second Type image Jing after mark sets up the second image bottom storehouse.
In one embodiment of the invention, the labeling module is additionally operable to：Set up between the different types of image
Corresponding relation.
In one embodiment of the invention, the different types of image is gathered simultaneously for same target.
In one embodiment of the invention, the different types of image is by different types of image capture device
For same target collection.
In one embodiment of the invention, the first kind image is coloured image, and the Second Type image is
Infrared image, described first image bottom storehouse is coloured image bottom storehouse, and the second image bottom storehouse is infrared image bottom storehouse.
In one embodiment of the invention, the identification step of the identification module is included in the storehouse of described first image bottom
Search for the destination object with the match objects.
In one embodiment of the invention, if the identification module is searched and institute in the storehouse of described first image bottom
The destination object of match objects is stated, then the labeling module pair has described the of corresponding relation with the first kind image
Two types of image are labeled, and the annotation step of the labeling module includes setting up the Second Type image and the target pair
The corresponding relation of elephant.
In one embodiment of the invention, the labeling module sets up the Second Type image and the destination object
Corresponding relation the step of include：The relevant information of the destination object in the storehouse of described first image bottom is added to into described
Two types of image.
In one embodiment of the invention, the title of the relevant information of the destination object including the object or
Name, or also including the adeditive attribute information of the destination object.
In one embodiment of the invention, the identification step of the identification module is included in the storehouse of described first image bottom
Search for and the destination object of the match objects, if the identification module do not search in the storehouse of described first image bottom with
The destination object of the match objects, then the annotation step of the labeling module include set up the Second Type image and institute
State the corresponding relation of first kind image.
In one embodiment of the invention, the object is face.
According to another aspect of the invention, a kind of device for setting up image bottom storehouse is additionally provided, described device includes place
Reason device, memorizer and the computer program being stored in the memorizer, wherein, the computer program is by the process
Device performs following steps when running：Receive at least two different types of images for same target collection；Based on it is described not
First kind image in the image of same type, is identified using the first image bottom storehouse to the object；And based on described
The result of identification is labeled to the Second Type image in the different types of image, for based on the institute Jing after mark
State Second Type image and set up the second image bottom storehouse.
Method and device for setting up image bottom storehouse according to embodiments of the present invention is known based on existing image bottom storehouse
Object in other respective type image, and it is based on recognition result that the object for being recognized is another kind of with what is gathered for the object
Type image is associated for setting up another type of image bottom storehouse, can realize quickly and efficiently setting up new image bottom
Storehouse, substantially reduces artificial and time cost.
Description of the drawings
The embodiment of the present invention is described in more detail by combining accompanying drawing, above-mentioned and other purposes of the present invention,
Feature and advantage will be apparent from.Accompanying drawing is used for providing further understanding the embodiment of the present invention, and constitutes explanation
A part for book, is used to explain the present invention together with the embodiment of the present invention, is not construed as limiting the invention.In the accompanying drawings,
Identical reference number typically represents same parts or step.
Fig. 1 illustrates the example electricity for setting up the method and apparatus in image bottom storehouse for realizing according to embodiments of the present invention
The schematic block diagram of sub- equipment；
Fig. 2 illustrates the indicative flowchart for setting up the method in image bottom storehouse according to embodiments of the present invention；
Fig. 3 illustrates the schematic block diagram for setting up the device in image bottom storehouse according to embodiments of the present invention；And
Fig. 4 illustrates the schematic block diagram for setting up the system in image bottom storehouse according to embodiments of the present invention.
Specific embodiment
In order that the object, technical solutions and advantages of the present invention become apparent from, root is described in detail below with reference to accompanying drawings
According to the example embodiment of the present invention.Obviously, described embodiment is only a part of embodiment of the present invention, rather than this
Bright whole embodiments, it should be appreciated that the present invention is not limited by example embodiment described herein.Described in the present invention
The embodiment of the present invention, those skilled in the art's all other embodiment resulting in the case where creative work is not paid
All should fall under the scope of the present invention.
First, with reference to Fig. 1 describing the method and apparatus for setting up image bottom storehouse for realizing the embodiment of the present invention
Exemplary electronic device 100.
As shown in figure 1, electronic equipment 100 includes one or more processors 102, one or more storage devices 104, defeated
Enter device 106, output device 108 and imageing sensor 110, these components are by bus system 112 and/or other forms
Bindiny mechanism's (not shown) interconnection.It should be noted that the component and structure of the electronic equipment 100 shown in Fig. 1 are exemplary, and
Nonrestrictive, as needed, the electronic equipment can also have other assemblies and structure.
The processor 102 can be CPU (CPU) or perform with data-handling capacity and/or instruction
The processing unit of the other forms of ability, and it is desired to perform to control other components in the electronic equipment 100
Function.
The storage device 104 can include one or more computer programs, and the computer program can
With including various forms of computer-readable recording mediums, such as volatile memory and/or nonvolatile memory.It is described easy
The property lost memorizer can for example include random access memory (RAM) and/or cache memory (cache) etc..It is described non-
Volatile memory can for example include read only memory (ROM), hard disk, flash memory etc..In the computer-readable recording medium
On can store one or more computer program instructions, processor 102 can run described program instruction, to realize hereafter institute
The client functionality (realized by processor) in the embodiment of the present invention stated and/or other desired functions.In the meter
Various application programs and various data can also be stored in calculation machine readable storage medium storing program for executing, such as application program use and/or
Various data for producing etc..
The input equipment 106 can be device of the user for input instruction, and can include keyboard, mouse, wheat
One or more in gram wind and touch screen etc..
The output device 108 can export various information (such as image or sound) to outside (such as user), and
One or more in display, speaker etc. can be included.
Described image sensor 110 can shoot the desired image of user (such as photo, video etc.), and will be captured
Image be stored in the storage device 104 so that other components are used.
Exemplarily, for realizing the example for setting up the method and apparatus in image bottom storehouse according to embodiments of the present invention
Electronic equipment may be implemented as smart mobile phone, panel computer etc..
Below, the method 200 for setting up image bottom storehouse according to embodiments of the present invention will be described with reference to Fig. 2.
In step S210, at least two different types of images for same target collection are received.
In one embodiment, the image type for being received can depend on existing image bottom storehouse type and will build
The type in vertical image bottom storehouse.For example, in one example, it is assumed that existing image bottom storehouse is coloured image (RGB image) bottom
Storehouse, the image bottom storehouse that will be set up is infrared image bottom storehouse, then in this example, the image for being received can be included for same
Coloured image and infrared image that object is gathered.In another example, it is assumed that existing image bottom storehouse is gray level image bottom
Storehouse, the image bottom storehouse that will be set up is coloured image bottom storehouse and infrared image bottom storehouse, then in this example, the image for being received can
With the gray level image, coloured image and the infrared image that include being gathered for same target.In other examples, received
Image type can be any desired image type for same target collection.
In one example, respective type can be gathered for same target by different types of image capture device
Image.For example, in first above-mentioned example, can be respectively by RGB photographic head and infrared camera come for a pair
As gathering coloured image and infrared image.In another example, it is also possible to by same or mutually the same image acquisition
Equipment gathering a type of image, the another type of image required for then being generated by certain image procossing,
By the example, another type required for obtaining by algorithm by need not setting up new image capture device can be realized
Image so that required another type of image be easy to obtain.For example, in second above-mentioned example, Ke Yifen
Coloured image and infrared image are not gathered for same target by RGB photographic head and infrared camera, as gray level image,
Can be generated by the way that the coloured image of collection is carried out into certain process.In a word, image acquisition can be arranged according to practical situation
Equipment needs the image of reception to gather in step S210.It is of course also possible to from the image needed for any source direct access, and nothing
Need to be acquired.That is, " collection " in step S210 can be interpreted as into Real-time Collection, it is understood that for non real-time
Obtain.
Further, the different types of image of same target collection can be carried out simultaneously.For example, above-mentioned
In one example, coloured image and infrared can simultaneously be gathered for same target by RGB photographic head and infrared camera
Image.The different types of image for being gathered so not only be may insure for same target, and save collection image
Time, can be with without the need for the cooperation of the object of collected image, as long as needing the place for gathering image to arrange respective type
Image capture device.
In step S220, based on the first kind image in the different types of image, using the first image bottom storehouse pair
The object is identified.
In one embodiment, first kind image can be the image of the type corresponding with existing image bottom storehouse.Phase
Ying Di, the first image bottom storehouse can be the image bottom storehouse corresponding with first kind image.Exemplarily, " corresponding " (or " phase
Should ") the meaning can be image that the first image bottom storehouse includes first kind image this type, or the first image bottom storehouse is wrapped
Include feature templates of image of first kind image this type etc..
In at least two different types of images that step S210 is received, will can have corresponding image bottom storehouse
The image of type be referred to as first kind image, (that is, its phase will be set up without respective image bottom storehouse by other one or more
Answer image bottom storehouse) the image of type be referred to as Second Type image.Herein, " first " and " second " is merely to distinguish each other
And define, not play any limited effect.
Then above example, it is assumed that existing image bottom storehouse is coloured image bottom storehouse, and the image bottom storehouse that will be set up is
Infrared image bottom storehouse, then in this example, the image received in step S210 can include what is gathered for same target
Coloured image and infrared image.Wherein, coloured image is first kind image, and existing coloured image bottom storehouse is the first figure
As bottom storehouse.Infrared image is Second Type image, and the infrared image bottom storehouse that will be set up is the second image bottom storehouse.
In one embodiment, the step of being identified to the object using the first image bottom storehouse can be included in described
The destination object with the match objects is searched in first image bottom storehouse.For example, the first kind is gathered or obtained for object A
Type image, then the step of identification can include following process：In the first kind image detection object A, it is carried out it is pre-
Process and then carry out feature extraction, match cognization is carried out based on the first image bottom storehouse.In other examples, it is also possible to by appointing
What his suitable process or step are identified using the first image bottom storehouse to the object, are not limited thereof herein.
It is in order in known different types of image, using corresponding with the image of one of which type in the step
Image bottom storehouse set up the image bottom storehouse corresponding with another kind of or polytype image as bridge, therefore the step
In " identification " process or method it is unrestricted, whether existing method or the method for following exploitation, all should fall at this
Within the scope of bright.
In step S230, the result based on the identification is carried out to the Second Type image in the different types of image
Mark, for setting up the second image bottom storehouse based on the Second Type image Jing after mark.
Based on " identification " of step S220, recognition result is obtained, the recognition result can include " in described first image
The destination object with the match objects is searched in the storehouse of bottom " and " do not search in the storehouse of described first image bottom and institute
State the destination object of match objects ".
In one embodiment, if searching the target pair with the match objects in the storehouse of described first image bottom
As then " mark " in step S230 can include setting up the Second Type image with the corresponding relation of the destination object.
For example, when searching in the storehouse of described first image bottom and the object (such as the object A in above example) phase
During destination object (such as be referred to as destination object A1) of matching, then can be in the storehouse of direct access described first image bottom with regard to the target
The relevant information of object A1.By the Second Type image of the relevant information and the object (such as the object A in above example)
Association is mapped, you can set up the second image bottom storehouse corresponding with Second Type image, so as to without the need for additionally individually to institute
Stating the Second Type image of object carries out relevant information addition, only by matching existing first image bottom storehouse and obtaining the first figure
Existing relevant information in as bottom storehouse can complete the foundation in the second image bottom storehouse so that the foundation in the second image bottom storehouse is convenient fast
It is prompt.
In one embodiment, it is described set up the Second Type image and the destination object corresponding relation the step of
Can include：The relevant information of the destination object in the storehouse of described first image bottom is added to into the Second Type image.
Exemplarily, the relevant information of the destination object can include the various information related to the destination object, for example, related
Information can include the title or name of the object, or also including the adeditive attribute information of the destination object.
Then above example, can be based on and the destination object matched with object A is searched in the first image bottom storehouse
The recognition result of A1, by the relevant information of destination object A1, the title or name of such as object A (i.e. destination object A1) are added to
Second Type image as mark, so as to the title or name can be set up with the Second Type image gathered for object A
Corresponding relation.Additionally, except title or name, it is also possible to the other additional category with regard to object A (i.e. destination object A1) of addition
Property information, for example when object A (i.e. destination object A1) be people when, its adeditive attribute information can include its age, sex, height
Etc..It is possible to further only the identifier of the details comprising object A (i.e. destination object A1) or link are added to into the
Two types of image not only can so reduce the data volume of mark as mark, be also based on less data amount and obtain big
The details of amount, simultaneously as being added to the relevant information in the second image bottom storehouse to derive from the first image bottom storehouse, this is just
Ensure that reliability and accuracy that relevant information originates, it is to avoid the information addition that independent addition relevant information may result in
Mistake.
In another embodiment, if not searching the mesh with the match objects in the storehouse of described first image bottom
Mark object, then " mark " in step S230 can be right with the first kind image including the Second Type image is set up
Should be related to.In this embodiment, because recognition result is not search out the destination object for matching, therefore the first image cannot be based on
Object (such as object A in above example) of the bottom storehouse directly in " learning " first kind image and Second Type image " be
Whose ".At this point it is possible to first set up the corresponding relation of Second Type image and first kind image, the corresponding relation for example can be：
Determine that the object in Second Type image and first kind image is same target.So, based on such corresponding relation, if
Once learning the relevant information of the object in any one in Second Type image and first kind image, then can directly learn
The relevant information of object in another in Second Type image and first kind image.Based on the phase with regard to object learnt
Close message, you can rapidly set up the image bottom storehouse corresponding with them.
In yet another embodiment, after first kind image and Second Type image is received, the first kind can first be set up
Corresponding relation between type image and Second Type image, is then searched for based on first kind image again in the first image bottom storehouse
The destination object (being for example referred to as destination object A1) matched with the object (such as the object A in above example).When
When searching the destination object with the match objects in one image bottom storehouse, can according to the first kind image set up and
Corresponding relation between Second Type image, sets up corresponding between the destination object and Second Type image of the matching for searching
Relation, so as to quickly set up the second image bottom storehouse.In this embodiment it is possible to be directed to multiple objects, that each object is gathered respectively is each
From different types of image, based on the foundation of the corresponding relation between different types of image respective to each object,
Any time after image is gathered for multiple objects, can like clockwork for the different types of image reality of each object
Follow-up " identification " step and " mark " step are applied, without the need for for implementing follow-up " identification " at once after each object collection image
Step and " mark " step, so as to new image bottom storehouse that is more convenient and efficiently setting up the image for including multiple objects.
Based on above description, the method for setting up image bottom storehouse according to embodiments of the present invention is based on existing image
Bottom storehouse to recognize respective type image in object, and based on recognition result by the object for being recognized with gathered for the object
Another type image associate for setting up another type of image bottom storehouse, can realize quickly and efficiently setting up new
Image bottom storehouse, substantially reduces artificial and time cost.
Exemplarily, the method for setting up image bottom storehouse according to embodiments of the present invention can be with memorizer and place
Realize in the unit or system of reason device.
Method for setting up image bottom storehouse according to embodiments of the present invention can apply to security protection application or finance
Application, for example, can arrange different types of image capture device (such as color at the man face image acquiring end of gate control system
Color image photographic head and infrared image photographic head), existed by the method for setting up image bottom storehouse according to embodiments of the present invention
Infrared image bottom storehouse is quickly set up again on the basis of existing coloured image bottom storehouse, can be in the application of gate control system plus infrared
Image assists in identifying, it is possible to achieve In vivo detection, it is to avoid the recognition of face pretended to be using photo.Similarly, in financial application
Field, it is also possible to assisting in identifying plus infrared image, realizes In vivo detection, so as to be further ensured that transaction security.
Method for setting up image bottom storehouse according to embodiments of the present invention can be deployed at personal terminal, such as intelligently
Phone, panel computer, personal computer etc..Alternatively, the method for setting up image bottom storehouse according to embodiments of the present invention is also
Server end (or high in the clouds) can be deployed in.Alternatively, the method for setting up image bottom storehouse according to embodiments of the present invention is also
It is deployed in being distributed at server end (or high in the clouds) and personal terminal.
Showing included by the method for setting up image bottom storehouse according to embodiments of the present invention is described above exemplarily
Example property steps flow chart.
The device for setting up image bottom storehouse of another aspect of the present invention offer is described with reference to Fig. 3.Fig. 3 shows root
According to the schematic block diagram for setting up the device 300 in image bottom storehouse of the embodiment of the present invention.
As shown in figure 3, the device 300 for setting up image bottom storehouse according to embodiments of the present invention include receiver module 310,
Identification module 320 and labeling module 330.The modules can be performed respectively above in conjunction with Fig. 2 descriptions for setting up
Each step/function of the method in image bottom storehouse.Below only to for set up image bottom storehouse device 300 each unit it is main
Function is described, and omits the detail content having been described above.
Receiver module 310 is used to receive at least two different types of images for same target collection.Identification module
320 are used to, based on the first kind image in the different types of image, carry out the object using the first image bottom storehouse
Identification.Labeling module 330 is used to enter the Second Type image in the different types of image based on the result of the identification
Rower is noted, for setting up the second image bottom storehouse based on the Second Type image Jing after mark.Receiver module 310, identification module
320 and labeling module 330 can be as shown in Figure 1 electronic equipment in the Running storage device 104 of processor 102 in store
Programmed instruction realizing.
In one embodiment, the image type that receiver module 310 is received can depend on existing image bottom storehouse class
Type and the type in the image bottom storehouse that will be set up.For example, in one example, it is assumed that existing image bottom storehouse is coloured image
(RGB image) bottom storehouse, the image bottom storehouse that will be set up is infrared image bottom storehouse, then in this example, receiver module 310 is received
Image can include coloured image and the infrared image gathered for same target.In another example, it is assumed that existing
Image bottom storehouse be gray level image bottom storehouse, the image bottom storehouse that will be set up is coloured image bottom storehouse and infrared image bottom storehouse, then exist
In the example, the image that receiver module 310 is received can include gray level image, the coloured image gathered for same target
And infrared image.In other examples, the image type that receiver module 310 is received can be for same target collection
Any desired image type.
In one example, the different types of image that receiver module 310 is received can pass through different types of image
Collecting device is acquired for same target.For example, in first above-mentioned example, can respectively by RGB photographic head and
Infrared camera is being directed to same target collection coloured image and infrared image.In another example, it is also possible to by same
Individual or mutually the same image capture device gathering a type of image, needed for then being generated by certain image procossing
The another type of image wanted, by the example, can realize passing through algorithm by need not setting up new image capture device
Another type of image required for obtaining so that required another type of image is easy to obtain.In a word, can basis
Practical situation arranges image capture device to gather the image that reception is needed in receiver module 310.Certainly, receiver module 310
From the image needed for any source direct access, and need not can be acquired by image capture device.
Further, the different types of image that receiver module 310 is received can be image capture device for same
What object was gathered simultaneously.For example, in above-mentioned first example, can be by RGB photographic head and infrared camera come for same
One object gathers coloured image and infrared image simultaneously.So not only may insure that the different types of image for being gathered is to be directed to
Same target, and the time for gathering image is saved, can be with without the need for the cooperation of the object of collected image, as long as needing
The place of collection image arranges the image capture device of respective type.
In one embodiment, first kind image can be the image of the type corresponding with existing image bottom storehouse.Phase
Ying Di, the first image bottom storehouse can be the image bottom storehouse corresponding with first kind image.Exemplarily, " corresponding " (or " phase
Should ") the meaning can be image that the first image bottom storehouse includes first kind image this type, or the first image bottom storehouse is wrapped
Include feature templates of image of first kind image this type etc..
In at least two different types of images that receiver module 310 is received, will can have corresponding image
The image of the type in bottom storehouse is referred to as first kind image, and other one or more (that is, will be set up without respective image bottom storehouse
Its respective image bottom storehouse) the image of type be referred to as Second Type image.Herein, " first " and " second " is merely to difference
Define each other, not play any limited effect.
Then above example, it is assumed that existing image bottom storehouse is coloured image bottom storehouse, and the image bottom storehouse that will be set up is
Infrared image bottom storehouse, then in this example, the image that receiver module 310 is received can include what is gathered for same target
Coloured image and infrared image.Wherein, coloured image is first kind image, and existing coloured image bottom storehouse is the first figure
As bottom storehouse.Infrared image is Second Type image, and the infrared image bottom storehouse that will be set up is the second image bottom storehouse.
In one embodiment, the step of identification module 320 is identified using the first image bottom storehouse to the object can
The destination object with the match objects is searched in be included in described first image bottom storehouse.For example, for object A collection or
First kind image is obtained, then can include following process the step of identification module 320 is identified：In first kind figure
As in detection object A, pretreatment is carried out to it and then feature extraction is carried out, match cognization is carried out based on the first image bottom storehouse.
In other examples, identification module 320 can also utilize the first image bottom storehouse to institute by any other suitable process or step
State object to be identified, be not limited thereof herein.
Based on " identification " of identification module 320, recognition result is obtained, the recognition result can include " described first
The destination object with the match objects is searched in the storehouse of image bottom " and " do not search in the storehouse of described first image bottom
With the destination object of the match objects ".
In one embodiment, if identification module 320 is searched and the object phase in the storehouse of described first image bottom
The destination object of matching, then " mark " of labeling module 330 can include set up the Second Type image and the target pair
The corresponding relation of elephant.
In one embodiment, it is described set up the Second Type image and the destination object corresponding relation the step of
Can include：The relevant information of the destination object in the storehouse of described first image bottom is added to into the Second Type image.
Exemplarily, the relevant information of the destination object can include the various information related to the destination object, for example, related
Information can include the title or name of the object, or also including the adeditive attribute information of the destination object, wherein attached
Additive attribute information can be other attribute informations outside object oriented or name, such as age, sex, height, native place, crime
The information such as record, figure and features feature.
Then above example, the mesh matched with object A is searched based on identification module 320 in the first image bottom storehouse
The recognition result of mark object A1, labeling module 330 can be by the relevant information of destination object A1, such as object A (i.e. destination objects
A1 title or name) is added to Second Type image as mark, so as to setting up the title or name and being directed to object A institutes
The corresponding relation of the Second Type image of collection.Additionally, except title or name, labeling module 330 can also add others
With regard to the adeditive attribute information of object A (i.e. destination object A1), such as when object A (i.e. destination object A1) is people, it is added
Attribute information can include its age, sex, height etc..Further, labeling module 330 only can will include object A (i.e.
Destination object A1) details identifier or link be added to Second Type image as mark, so not only can subtract
The data volume of few mark, is also based on less data amount and obtains substantial amounts of details, simultaneously as being added to the second figure
The first image bottom storehouse is derived from as the relevant information in the storehouse of bottom, this guarantees relevant information source reliability with it is accurate
Property, it is to avoid the information addition mistake that independent addition relevant information may result in.
In another embodiment, if identification module 320 do not search in the storehouse of described first image bottom it is right with described
As the destination object for matching, then " mark " of labeling module 330 can include setting up the Second Type image with described the
The corresponding relation of one types of image.In this embodiment, because recognition result is not search out the destination object for matching, therefore nothing
Method is based on the object in the first image bottom storehouse directly " learning " first kind image and Second Type image (such as in above example
Object A) " whom is ".Now, labeling module 330 can first set up Second Type image pass corresponding with first kind image
It is that the corresponding relation for example can be：Determine that the object in Second Type image and first kind image is same target.That
, based on such corresponding relation, if once learnt in any one in Second Type image and first kind image
The relevant information of object, then can directly learn the related letter of Second Type image and object in another in first kind image
Breath.Based on the related news with regard to object learnt, you can rapidly set up the image bottom storehouse corresponding with them.
In yet another embodiment, after receiver module 310 receives first kind image and Second Type image, Ke Yixian
The corresponding relation set up between first kind image and Second Type image by labeling module 330, then again by identification module 320
Searched in the first image bottom storehouse based on first kind image and matched with the object (such as the object A in above example)
Destination object (is for example referred to as destination object A1).When identification module 320 is searched and the object phase in the first image bottom storehouse
During the destination object of matching, labeling module 330 can be according between the first kind image and Second Type image set up
Corresponding relation, the corresponding relation set up between the destination object and Second Type image of the matching for searching, so as to quickly set up
Second image bottom storehouse.
Based on above description, the device for setting up image bottom storehouse according to embodiments of the present invention is based on existing image
Bottom storehouse to recognize respective type image in object, and based on recognition result by the object for being recognized with gathered for the object
Another type image associate for setting up another type of image bottom storehouse, can realize quickly and efficiently setting up new
Image bottom storehouse, substantially reduces artificial and time cost.
Fig. 4 shows the schematic block diagram for setting up the system 400 in image bottom storehouse according to embodiments of the present invention.For
Setting up the system 400 in image bottom storehouse includes storage device 410 and processor 420.
Wherein, storage device 410 stores the method for setting up image bottom storehouse for realizing according to embodiments of the present invention
In corresponding steps program code.Processor 420 is used for the program code stored in Running storage device 410, to perform root
According to the corresponding steps for setting up the method in image bottom storehouse of the embodiment of the present invention, and for realizing according to embodiments of the present invention
The device for setting up image bottom storehouse in corresponding module.Additionally, the system 400 for setting up image bottom storehouse can also include
Image collecting device (not shown in FIG. 4), it can be used for gathering at least two different types of figures for same target
Picture.Certainly, image collecting device is not required, can directly receive from other sources for same target at least two not
The input of the image of same type.
In one embodiment, when described program code is run by processor 420 so that for setting up image bottom storehouse
System 400 performs following steps：Receive at least two different types of images for same target collection；Based on the difference
First kind image in the image of type, is identified using the first image bottom storehouse to the object；And based on the knowledge
Other result is labeled to the Second Type image in the different types of image, described in being based on Jing after mark
Second Type image sets up the second image bottom storehouse.
In one embodiment, when described program code is run by processor 420 also so that for setting up image bottom storehouse
System 400 perform following steps：The corresponding relation set up between the different types of image.
In one embodiment, the different types of image is gathered simultaneously for same target.
In one embodiment, the different types of image is for same by different types of image capture device
Object collection.
In one embodiment, the first kind image is coloured image, and the Second Type image is infrared image,
Described first image bottom storehouse is coloured image bottom storehouse, and the second image bottom storehouse is infrared image bottom storehouse.
In one embodiment, when described program code is run by processor 420 so that for setting up image bottom storehouse
System 400 perform based on first kind imagery exploitation the first image bottom storehouse in the different types of image to the object
The step of being identified includes：The destination object with the match objects is searched in the storehouse of described first image bottom.
In one embodiment, if when described program code is run by processor 420 so that for setting up image bottom
The identification step that the system 400 in storehouse is performed searches the target pair with the match objects in the storehouse of described first image bottom
As then when described program code is run by processor 420 so that the system 400 for setting up image bottom storehouse performs following step
Suddenly：Pair Second Type image for having corresponding relation with the first kind image is labeled, and the mark includes building
Found the corresponding relation of the Second Type image and the destination object.
In one embodiment, when described program code is run by processor 420 so that for setting up image bottom storehouse
System 400 perform it is described set up the Second Type image and the destination object corresponding relation the step of include：By institute
The relevant information for stating the destination object in the first image bottom storehouse is added to the Second Type image.
In one embodiment, the relevant information of the destination object includes the title or name of the object, or
Person is also including the adeditive attribute information of the destination object.
In one embodiment, when described program code is run by processor 420 so that for setting up image bottom storehouse
System 400 perform based on first kind imagery exploitation the first image bottom storehouse in the different types of image to the object
The step of being identified includes：The destination object with the match objects is searched in the storehouse of described first image bottom, if
So that the identification step that performs of the system 400 for setting up image bottom storehouse is in institute when described program code is run by processor 420
The destination object not searched in the first image bottom storehouse with the match objects is stated, then in described program code by processor
The mark that the system 400 for setting up image bottom storehouse is performed is caused to include setting up the Second Type image during 420 operation
With the corresponding relation of the first kind image.
In one embodiment, the object is face.
Additionally, according to embodiments of the present invention, additionally providing a kind of storage medium, program is stored on said storage
Instruction, when described program is instructed and run by computer or processor for perform the embodiment of the present invention for setting up image bottom
The corresponding steps of the method in storehouse, and for realizing the device for setting up image bottom storehouse according to embodiments of the present invention in phase
Answer module.The storage medium can for example include storage card, the memory unit of panel computer, the personal computer of smart phone
Hard disk, read only memory (ROM), Erasable Programmable Read Only Memory EPROM (EPROM), portable compact disc read only memory
(CD-ROM), the combination in any of USB storage or above-mentioned storage medium.The computer-readable recording medium can be one
The combination in any of individual or multiple computer-readable recording mediums, such as one computer-readable recording medium is comprising receiving image
Computer-readable program code, computer-readable program generation of another computer-readable recording medium comprising identification object
Code, computer-readable program code of another computer-readable recording medium comprising mark image.
In one embodiment, the computer program instructions can be realized according to of the invention real when being run by computer
Apply example for setting up each functional module of the device in image bottom storehouse, and/or can perform according to embodiments of the present invention
The method for setting up image bottom storehouse.
In one embodiment, the computer program instructions make computer or place by computer or processor when running
Reason device performs following steps：Receive at least two different types of images for same target collection；Based on the inhomogeneity
First kind image in the image of type, is identified using the first image bottom storehouse to the object；And based on the identification
Result the Second Type image in the different types of image is labeled, for based on described the Jing after mark
Two types of image set up the second image bottom storehouse.
In one embodiment, the computer program instructions also make when being run by computer or processor computer or
Computing device following steps：The corresponding relation set up between the different types of image.
In one embodiment, the different types of image is gathered simultaneously for same target.
In one embodiment, the different types of image is for same by different types of image capture device
Object collection.
In one embodiment, the first kind image is coloured image, and the Second Type image is infrared image,
Described first image bottom storehouse is coloured image bottom storehouse, and the second image bottom storehouse is infrared image bottom storehouse.
In one embodiment, the computer program instructions make when being run by computer or processor computer or
Computing device based on first kind imagery exploitation the first image bottom storehouse in the different types of image to the object
The step of being identified includes：The destination object with the match objects is searched in the storehouse of described first image bottom.
In one embodiment, if the computer program instructions make computer by computer or processor when running
Or the identification step of computing device searches the destination object with the match objects in the storehouse of described first image bottom, then
Computer or computing device following steps are made when running by computer or processor in the computer program instructions：Pair with
The Second Type image that the first kind image has corresponding relation is labeled, and the mark includes setting up described the
The corresponding relation of two types of image and the destination object.
In one embodiment, the computer program instructions make computer or place by computer or processor when running
Reason device perform it is described set up the Second Type image and the destination object corresponding relation the step of include：By described
The relevant information of the destination object in one image bottom storehouse is added to the Second Type image.
In one embodiment, the relevant information of the destination object includes the title or name of the object, or
Person is also including the adeditive attribute information of the destination object.
In one embodiment, the computer program instructions make when being run by computer or processor computer or
Computing device based on first kind imagery exploitation the first image bottom storehouse in the different types of image to the object
The step of being identified includes：The destination object with the match objects is searched in the storehouse of described first image bottom, if institute
State computer program instructions makes the identification step of computer or computing device described by computer or processor when running
The destination object with the match objects is not searched in first image bottom storehouse, then the computer program instructions are being calculated
Machine or processor make when running the mark of computer or computing device include setting up the Second Type image with it is described
The corresponding relation of first kind image.
In one embodiment, the object is face.
The method for setting up image bottom storehouse according to embodiments of the present invention, device, system and storage medium are based on
Some image bottoms storehouse to recognize respective type image in object, and based on recognition result by the object for being recognized be directed to this pair
As the another type image for being gathered is associated for setting up another type of image bottom storehouse, can realize quickly and efficiently
New image bottom storehouse is set up, artificial and time cost is substantially reduced.
Although the example embodiment by reference to Description of Drawings here, it should be understood that above-mentioned example embodiment is merely exemplary
, and be not intended to limit the scope of the invention to this.Those of ordinary skill in the art can wherein carry out various changes
And modification, it is made without departing from the scope of the present invention and spirit.All such changes and modifications are intended to be included in claims
Within required the scope of the present invention.
Those of ordinary skill in the art are it is to be appreciated that the list of each example with reference to the embodiments described herein description
Unit and algorithm steps, being capable of being implemented in combination in electronic hardware or computer software and electronic hardware.These functions are actually
Performed with hardware or software mode, depending on the application-specific and design constraint of technical scheme.Professional and technical personnel
Each specific application can be used different methods to realize described function, but this realization it is not considered that exceeding
The scope of the present invention.
In several embodiments provided herein, it should be understood that disclosed apparatus and method, it can be passed through
Its mode is realized.For example, apparatus embodiments described above are only schematic, for example, the division of the unit, and only
Only a kind of division of logic function, can there is other dividing mode when actually realizing, such as multiple units or component can be tied
Close or be desirably integrated into another equipment, or some features can be ignored, or do not perform.
In description mentioned herein, a large amount of details are illustrated.It is to be appreciated, however, that the enforcement of the present invention
Example can be put into practice in the case of without these details.In some instances, known method, structure is not been shown in detail
And technology, so as not to obscure the understanding of this description.
Similarly, it will be appreciated that in order to simplify the present invention and help understand one or more in each inventive aspect, exist
To the present invention exemplary embodiment description in, the present invention each feature be grouped together into sometimes single embodiment, figure,
Or in descriptions thereof.However, the method for the present invention should be construed to reflect following intention：It is i.e. required for protection
The more features of feature that application claims ratio is expressly recited in each claim.More precisely, such as corresponding power
As sharp claim reflects, its inventive point is can be with the spy of all features less than certain disclosed single embodiment
Levy to solve corresponding technical problem.Therefore, it then follows it is concrete that thus claims of specific embodiment are expressly incorporated in this
Separate embodiments of the embodiment, wherein each claim as the present invention itself.
It will be understood to those skilled in the art that in addition to mutually exclusive between feature, any combinations pair can be adopted
All features and so disclosed any method disclosed in this specification (including adjoint claim, summary and accompanying drawing)
Or all processes or unit of equipment are combined.Unless expressly stated otherwise, this specification (will including adjoint right
Ask, make a summary and accompanying drawing) disclosed in each feature can, equivalent identical by offer or similar purpose alternative features replacing.
Although additionally, it will be appreciated by those of skill in the art that some embodiments described herein include other embodiments
In included some features rather than further feature, but the combination of the feature of different embodiments means in of the invention
Within the scope of and form different embodiments.For example, in detail in the claims, embodiment required for protection one of arbitrarily
Can in any combination mode using.
The present invention all parts embodiment can be realized with hardware, or with one or more processor operation
Software module realize, or with combinations thereof realization.It will be understood by those of skill in the art that can use in practice
Microprocessor or digital signal processor (DSP) to realize article analytical equipment according to embodiments of the present invention in some moulds
The some or all functions of block.The present invention is also implemented as the part for performing method as described herein or complete
The program of device (for example, computer program and computer program) in portion.Such program for realizing the present invention can be stored
On a computer-readable medium, or can have one or more signal form.Such signal can be from the Internet
Download on website and obtain, or provide on carrier signal, or provide in any other form.
It should be noted that above-described embodiment the present invention will be described rather than limits the invention, and ability
Field technique personnel can design without departing from the scope of the appended claims alternative embodiment.In the claims,
Any reference markss between bracket should not be configured to limitations on claims.Word "comprising" is not excluded the presence of not
Element listed in the claims or step.Word "a" or "an" before element does not exclude the presence of multiple such
Element.The present invention can come real by means of the hardware for including some different elements and by means of properly programmed computer
It is existing.If in the unit claim for listing equipment for drying, several in these devices can be by same hardware branch
To embody.The use of word first, second, and third does not indicate that any order.These words can be explained and be run after fame
Claim.
The above, the only specific embodiment of the present invention or the explanation to specific embodiment, the protection of the present invention
Scope is not limited thereto, any those familiar with the art the invention discloses technical scope in, can be easily
Expect change or replacement, all should be included within the scope of the present invention.Protection scope of the present invention should be with claim
Protection domain is defined.
Claims (21)
1. a kind of method for setting up image bottom storehouse, it is characterised in that methods described includes：
Receive at least two different types of images for same target collection；
Based on the first kind image in the different types of image, the object is known using the first image bottom storehouse
Not；And
Result based on the identification is labeled to the Second Type image in the different types of image, for being based on
The Second Type image Jing after mark sets up the second image bottom storehouse.
2. method according to claim 1, it is characterised in that methods described also includes：Set up the different types of figure
Corresponding relation as between.
3. method according to claim 1 and 2, it is characterised in that the different types of image is for same target
Collection simultaneously, or, the different types of image is adopted for same target by different types of image capture device
Collection.
4. method according to claim 1 and 2, it is characterised in that the first kind image is coloured image, described the
Two types of image are infrared image, and described first image bottom storehouse is coloured image bottom storehouse, and the second image bottom storehouse is infrared figure
As bottom storehouse.
5. method according to claim 2, it is characterised in that be included in described first image bottom storehouse the step of the identification
The middle destination object searched for the match objects.
6. method according to claim 5, it is characterised in that if search in the storehouse of described first image bottom with it is described
The destination object of match objects, then pair Second Type image that there is corresponding relation with the first kind image carry out
Mark, the mark includes setting up the Second Type image with the corresponding relation of the destination object.
7. method according to claim 6, it is characterised in that described to set up the Second Type image and the target pair
The step of corresponding relation of elephant, includes：The relevant information of the destination object in the storehouse of described first image bottom is added to described
Second Type image.
8. method according to claim 7, it is characterised in that it is described right that the relevant information of the destination object includes
The title or name of elephant, or also including the adeditive attribute information of the destination object.
9. method according to claim 1, it is characterised in that be included in described first image bottom storehouse the step of the identification
The middle destination object searched for the match objects, if do not searched in the storehouse of described first image bottom and the object phase
The destination object of matching, then including setting up, the Second Type image is corresponding with the first kind image to close the mark
System.
10. method according to claim 1, it is characterised in that the object is face.
11. a kind of devices for setting up image bottom storehouse, it is characterised in that described device includes：
Receiver module, for receiving at least two different types of images for same target collection；
Identification module, for based on the first kind image in the different types of image, using the first image bottom storehouse to institute
State object to be identified；And
Labeling module, rower is entered for the result based on the identification to the Second Type image in the different types of image
Note, for setting up the second image bottom storehouse based on the Second Type image Jing after mark.
12. devices according to claim 11, it is characterised in that the labeling module is additionally operable to：Set up the inhomogeneity
Corresponding relation between the image of type.
13. devices according to claim 11 or 12, it is characterised in that the different types of image is for a pair
As gathering simultaneously, or, the different types of image is to be directed to same target by different types of image capture device
Collection.
14. devices according to claim 11 or 12, it is characterised in that the first kind image be coloured image, institute
It is infrared image to state Second Type image, and described first image bottom storehouse is coloured image bottom storehouse, and the second image bottom storehouse is red
Outer image bottom storehouse.
15. devices according to claim 12, it is characterised in that the identification step of the identification module is included in described
The destination object with the match objects is searched in one image bottom storehouse.
16. devices according to claim 15, it is characterised in that if the identification module is in described first image bottom storehouse
In search destination object with the match objects, then the labeling module pair has corresponding with the first kind image
The Second Type image of relation is labeled, and the annotation step of the labeling module includes setting up the Second Type image
With the corresponding relation of the destination object.
17. devices according to claim 16, it is characterised in that the labeling module set up the Second Type image with
The step of corresponding relation of the destination object, includes：By the relevant information of the destination object in the storehouse of described first image bottom
It is added to the Second Type image.
18. devices according to claim 17, it is characterised in that the relevant information of the destination object includes described
The title or name of object, or also including the adeditive attribute information of the destination object.
19. devices according to claim 11, it is characterised in that the identification step of the identification module is included in described
The destination object with the match objects is searched in one image bottom storehouse, if the identification module is in described first image bottom storehouse
In do not search destination object with the match objects, then the annotation step of the labeling module includes setting up described second
The corresponding relation of types of image and the first kind image.
20. devices according to claim 11, it is characterised in that the object is face.
21. a kind of devices for setting up image bottom storehouse, it is characterised in that described device includes processor, memorizer and deposits
The computer program being stored in the memorizer, wherein, the computer program performs as follows when being run by the processor
Step：
Receive at least two different types of images for same target collection；
Based on the first kind image in the different types of image, the object is known using the first image bottom storehouse
Not；And
Result based on the identification is labeled to the Second Type image in the different types of image, for being based on
The Second Type image Jing after mark sets up the second image bottom storehouse.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611247448.9A CN106682187B (en) | 2016-12-29 | 2016-12-29 | Method and device for establishing image base |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611247448.9A CN106682187B (en) | 2016-12-29 | 2016-12-29 | Method and device for establishing image base |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106682187A true CN106682187A (en) | 2017-05-17 |
| CN106682187B CN106682187B (en) | 2020-04-17 |
Family
ID=58873073
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611247448.9A Active CN106682187B (en) | 2016-12-29 | 2016-12-29 | Method and device for establishing image base |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106682187B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107545241A (en) * | 2017-07-19 | 2018-01-05 | 百度在线网络技术（北京）有限公司 | Neural network model is trained and biopsy method, device and storage medium |
| CN108875485A (en) * | 2017-09-22 | 2018-11-23 | 北京旷视科技有限公司 | A kind of base map input method, apparatus and system |
| CN111866376A (en) * | 2020-06-22 | 2020-10-30 | 上海摩象网络科技有限公司 | Feature recognition method and device, pan-tilt camera and storage medium |
| CN112395436A (en) * | 2019-08-14 | 2021-02-23 | 北京迈格威科技有限公司 | Bottom library input method and device |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101202845A (en) * | 2007-11-14 | 2008-06-18 | 北京大学 | Method for changing infrared image into visible light image |
| CN101526991A (en) * | 2008-03-03 | 2009-09-09 | 联想(北京)有限公司 | Notebook computer and face recognition method thereof |
| CN103413270A (en) * | 2013-08-15 | 2013-11-27 | 北京小米科技有限责任公司 | Method and device for image processing and terminal device |
| CN104217503A (en) * | 2014-08-26 | 2014-12-17 | 杭州摩科商用设备有限公司 | Self-service terminal identity identification method and corresponding house property certificate printing method |
| CN104700087A (en) * | 2015-03-23 | 2015-06-10 | 上海交通大学 | Mutual conversion method of visible light and near-infrared human face images |
| CN106101545A (en) * | 2016-06-30 | 2016-11-09 | 维沃移动通信有限公司 | A kind of image processing method and mobile terminal |
-
2016
- 2016-12-29 CN CN201611247448.9A patent/CN106682187B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101202845A (en) * | 2007-11-14 | 2008-06-18 | 北京大学 | Method for changing infrared image into visible light image |
| CN101526991A (en) * | 2008-03-03 | 2009-09-09 | 联想(北京)有限公司 | Notebook computer and face recognition method thereof |
| CN103413270A (en) * | 2013-08-15 | 2013-11-27 | 北京小米科技有限责任公司 | Method and device for image processing and terminal device |
| CN104217503A (en) * | 2014-08-26 | 2014-12-17 | 杭州摩科商用设备有限公司 | Self-service terminal identity identification method and corresponding house property certificate printing method |
| CN104700087A (en) * | 2015-03-23 | 2015-06-10 | 上海交通大学 | Mutual conversion method of visible light and near-infrared human face images |
| CN106101545A (en) * | 2016-06-30 | 2016-11-09 | 维沃移动通信有限公司 | A kind of image processing method and mobile terminal |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107545241A (en) * | 2017-07-19 | 2018-01-05 | 百度在线网络技术（北京）有限公司 | Neural network model is trained and biopsy method, device and storage medium |
| CN107545241B (en) * | 2017-07-19 | 2022-05-27 | 百度在线网络技术（北京）有限公司 | Neural network model training and living body detection method, device and storage medium |
| US11610394B2 (en) | 2017-07-19 | 2023-03-21 | Baidu Online Network Technology (Beijing) Co., Ltd. | Neural network model training method and apparatus, living body detecting method and apparatus, device and storage medium |
| CN108875485A (en) * | 2017-09-22 | 2018-11-23 | 北京旷视科技有限公司 | A kind of base map input method, apparatus and system |
| CN112395436A (en) * | 2019-08-14 | 2021-02-23 | 北京迈格威科技有限公司 | Bottom library input method and device |
| CN111866376A (en) * | 2020-06-22 | 2020-10-30 | 上海摩象网络科技有限公司 | Feature recognition method and device, pan-tilt camera and storage medium |
| CN111866376B (en) * | 2020-06-22 | 2022-03-22 | 上海摩象网络科技有限公司 | Feature recognition method and device, pan-tilt camera and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106682187B (en) | 2020-04-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107545241B (en) | Neural network model training and living body detection method, device and storage medium | |
| US20210216830A1 (en) | Content tagging | |
| CN106203305B (en) | Face living body detection method and device | |
| CN105938552B (en) | Face recognition method and device for automatically updating base map | |
| CN106650662B (en) | Target object shielding detection method and device | |
| CN109284729B (en) | Method, device and medium for acquiring face recognition model training data based on video | |
| CN106845352B (en) | Pedestrian detection method and device | |
| US20130258198A1 (en) | Video search system and method | |
| CN106682187A (en) | Method and device for establishing image bottom libraries | |
| CN110008903A (en) | Face identification method, device, system, storage medium and face method of payment | |
| CN108573268A (en) | Image-recognizing method and device, image processing method and device and storage medium | |
| US20170337222A1 (en) | Image searching method and apparatus, an apparatus and non-volatile computer storage medium | |
| CN110675433A (en) | Video processing method and device, electronic equipment and storage medium | |
| JP6969663B2 (en) | Devices and methods for identifying the user's imaging device | |
| WO2019184140A1 (en) | Vr-based application program opening method, electronic apparatus, device and storage medium | |
| CN106096028A (en) | Historical relic indexing means based on image recognition and device | |
| CN108875476B (en) | Automatic near-infrared face registration and recognition method, device and system and storage medium | |
| CN108875515A (en) | Face identification method, device, system, storage medium and capture machine | |
| CN106203425B (en) | Character recognition method and device | |
| CN110031697B (en) | Method, device, system and computer readable medium for testing target identification equipment | |
| CN108875484A (en) | Face unlocking method, device and system and storage medium for mobile terminal | |
| CN106462349A (en) | Method and apparatus for displaying electronic picture, and mobile device | |
| CN106156794B (en) | Character recognition method and device based on character style recognition | |
| KR20180121273A (en) | Method for outputting content corresponding to object and electronic device thereof | |
| KR102316846B1 (en) | Method for sorting a media content and electronic device implementing the same |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 100190 Beijing, Haidian District Academy of Sciences, South Road, No. 2, block A, No. 313 Applicant after: MEGVII INC. Applicant after: Beijing maigewei Technology Co., Ltd. Address before: 100190 Beijing, Haidian District Academy of Sciences, South Road, No. 2, block A, No. 313 Applicant before: MEGVII INC. Applicant before: Beijing aperture Science and Technology Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |