CN109558773A - Information identifying method, device and electronic equipment - Google Patents
Information identifying method, device and electronic equipment Download PDFInfo
- Publication number
- CN109558773A CN109558773A CN201710884606.XA CN201710884606A CN109558773A CN 109558773 A CN109558773 A CN 109558773A CN 201710884606 A CN201710884606 A CN 201710884606A CN 109558773 A CN109558773 A CN 109558773A
- Authority
- CN
- China
- Prior art keywords
- target object
- history
- current target
- testing result
- current
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/30—Scenes; Scene-specific elements in albums, collections or shared content, e.g. social network photos or video
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
Abstract
The embodiment of the present application provides a kind of information identifying method, device and electronic equipment, is related to computer application technology.Wherein, the image obtained to acquisition detects, to determine at least one current target object；Judge whether at least one described current target object is identical as the history target object in history testing result；Technical solution provided by the embodiments of the present application, which reduces the unnecessary time, to be identified to the current target object different from the history target object in history testing result, improves recognition efficiency.
Description
Technical field
The invention relates to computer application technology more particularly to a kind of information identifying methods, device and electricity
Sub- equipment.
Background technique
In the application fields such as attendance, gate inhibition, monitoring now, the demand for quickly confirming personnel identity is all referred to, and mesh
The preceding usual biological characteristic using human body carries out authentication, wherein face recognition application the most extensively.
Recognition of face is a kind of biological identification technology that the face feature based on people carries out identification, and recognition of face is first
It needs to carry out Face datection, to determine face, recognition of face is carried out to detected face again later, is with attendance application
Example, attendance checking system can determine in image whether include face by detecting to the image of acquisition；Based on the people detected
Face carries out recognition of face from registered employee database, to determine the corresponding employee information of the face, realizes identity validation
Purpose.
Since Image Acquisition usually carries out always, recognition of face will do it for each frame image, and adjacent several frames
Image may acquire to obtain for the same user, this will lead to repeated work, and influence the efficiency of identification.
Summary of the invention
The embodiment of the present application provides a kind of information identifying method, device and electronic equipment, knows in the prior art to solve
The lower technical problem of other efficiency.
In a first aspect, providing a kind of information identifying method in the embodiment of the present application, comprising:
The image obtained to acquisition detects, to obtain at least one current target object；
Determine whether at least one described current target object is identical as the history target object in history testing result；
The current target object different from the history target object in history testing result is identified.
Optionally, further includes:
To current target object identical with the history target object in history testing result without identification.
Optionally, at least one current target object described in the determination whether with the history target in history testing result
Object is identical to include:
Determine any history target object institute in any current target object position region and history testing result
It is whether consistent in the band of position, if so, determine that any current target object is identical as any history target object, it is no
Then, determine that any current target object is different from any history target object.
Optionally, it is described to current target object identical with the history target object in history testing result without know
Do not include:
Obtain in any current target object and history testing result with identical of any current target object
The characteristics of objects of one history target object；
Determine any current target object characteristics of objects whether with same any history target pair
The characteristics of objects of elephant is identical；
If so, to any current target object without identification；
If not, being identified to any current target object.
Optionally, at least one current target object described in the determination whether with the history target in history testing result
Object is identical to include:
The characteristics of objects of at least one current target object is obtained respectively；
It determines in history testing result, if it is special that there are the objects of characteristics of objects and at least one current target object
Levy identical history target object.
Optionally, it is described to current target object identical with the history target object in history testing result without know
Do not include:
It determines in history testing result, whether history target object identical with any current target object identifies success；
If so, to any current target object without identification；
If not, being identified to any current target object.
Optionally, any history in the determination any current target object position region and history testing result
Target object position region whether unanimously include:
Determine any history target object institute in any current target object position region and history testing result
The band of position positional shift whether in preset range.
Optionally, the target object is face.
Second aspect provides a kind of information recognition device in the embodiment of the present application, comprising:
Detection module, the image for obtaining to acquisition detects, to obtain at least one current target object；
Judgment module, for determine at least one described current target object whether with the history mesh in history testing result
It is identical to mark object；
First identification module, for the current target object different from the history target object in history testing result into
Row identification.
Optionally, further includes:
Second identification module, for current target object identical with the history target object in history testing result not
It is identified.
Optionally, the judgment module is specifically used for:
Determine any history target object institute in any current target object position region and history testing result
It is whether consistent in the band of position, if so, determine that any current target object is identical as any history target object, it is no
Then, determine that any current target object is different from any history target object.
Optionally, second identification module is specifically used for obtaining in any current target object and history testing result
The characteristics of objects of any history target object identical with any current target object；Determine any current goal pair
Whether the characteristics of objects of elephant is identical with the same characteristics of objects of any history target object；If so, to described
Any current target object is without identification；If not, being identified to any current target object.
Optionally, the judgment module is specifically used for: the object for obtaining at least one current target object respectively is special
Sign；It determines in history testing result, if there are the characteristics of objects phases of characteristics of objects and at least one current target object
Same history target object.
Optionally, second identification module is specifically used for determining in history testing result, with any current target object
Whether identical history target object identifies success；If so, to any current target object without identification；If
It is no, any current target object is identified.
Optionally, the judgment module is specifically used for: determining that any current target object position region and history are examined
The positional shift in any history target object position region in result is surveyed whether in preset range.
The third aspect provides a kind of electronic equipment, including processing component in the embodiment of the present application, and respectively with it is described
The memory of processing component connection；
The memory stores one or more computer program instructions, and one or more computer program instructions supply
The processing component is called and is executed；
The processing component is used for:
The image obtained to acquisition detects, to determine at least one current target object；
Determine whether at least one described current target object is identical as the history target object in history testing result；
The current target object different from the history target object in history testing result is identified.
It optionally, further include the acquisition component being connect with the processing component, for acquiring image；
The image that the processing component obtains acquisition detects, and is specifically at least one determining current target object
It acquires acquisition image to the acquisition component to detect, to determine at least one current target object.
In the embodiment of the present application, the image obtained to acquisition is detected, to determine at least one current target object；Really
Whether at least one fixed described current target object is identical as the target object in history testing result；Only knot is detected to history
The different current target object of target object in fruit is identified, therefore can reduce recognition time, improves recognition efficiency.
These aspects or other aspects of the application can more straightforward in the following description.
Detailed description of the invention
In order to illustrate the technical solutions in the embodiments of the present application or in the prior art more clearly, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is this Shen
Some embodiments please for those of ordinary skill in the art without creative efforts, can be with root
Other attached drawings are obtained according to these attached drawings.
Fig. 1 shows a kind of flow chart of information identifying method one embodiment provided by the present application；
Fig. 2 shows a kind of flow charts of another embodiment of information identifying method provided by the present application；
Fig. 3 shows a kind of flow chart of another embodiment of information identifying method provided by the present application；
Fig. 4 shows a kind of structural schematic diagram of information identification system one embodiment provided by the present application；
Fig. 5 shows a kind of structural schematic diagram of another embodiment of information identification system provided by the present application；
Fig. 6 shows a kind of structural schematic diagram of information recognition device one embodiment provided by the present application；
Fig. 7 shows a kind of structural schematic diagram of another embodiment of information recognition device provided by the present application；
Fig. 8 shows the structural schematic diagram of a kind of electronic equipment one embodiment provided by the present application；
Fig. 9 shows the structural schematic diagram of another embodiment of a kind of electronic equipment provided by the present application.
Specific embodiment
In order to make those skilled in the art more fully understand application scheme, below in conjunction in the embodiment of the present application
Attached drawing, the technical scheme in the embodiment of the application is clearly and completely described.
In some processes of the description in the description and claims of this application and above-mentioned attached drawing, contain according to
Multiple operations that particular order occurs, but it should be clearly understood that these operations can not be what appears in this article suitable according to its
Sequence is executed or is executed parallel, and serial number of operation such as 101,102 etc. is only used for distinguishing each different operation, serial number
It itself does not represent and any executes sequence.In addition, these processes may include more or fewer operations, and these operations can
To execute or execute parallel in order.It should be noted that the description such as " first " herein, " second ", is for distinguishing not
Same message, equipment, module etc., does not represent sequencing, does not also limit " first " and " second " and be different type.
The technical solution of the embodiment of the present application can be applied in the security fields such as attendance, gate inhibition, monitoring, security protection, be used for
Identification, the target object in the embodiment of the present application can be face, be also not excluded for certainly can be human body other biologies
Feature.It is similar with face recognition process, for target object identification equally firstly the need of being detected, to determine target pair
As, then detected target object is identified, to carry out identity validation to target object.
Recognition time can be reduced by the technical solution of the embodiment of the present application, recognition efficiency is improved, is particularly suitable for
In the scene identified simultaneously for multiple target objects.
By taking recognition of face as an example, as described in the background art, in face recognition process, Image Acquisition is carried out always,
Face datection can be carried out for each frame image, and in the short time, usual hundreds of milliseconds, and the position of acquisition target namely user
The usual little namely adjacent a few frame images of variation may be to acquire same or obtain with a collection of user.Existing skill
In art, Face datection and recognition of face will do it to each frame image, still, the face that may be detected has been identified as
Function, therefore will cause repetition identification, to increase recognition time, reduce recognition efficiency.
In order to improve recognition efficiency, inventor is by a series of the study found that since identification process is extremely complex, with face
For identification, such as need to extract face characteristic construction skin detection, then each face stored from database first
It is compared in feature templates, to determine the corresponding identity information of the skin detection, authentication is completed, if that can
To reduce the recognition of face time, then recognition efficiency can be greatly improved.
Accordingly, the technical solution of the application is proposed, in the embodiment of the present application, the image obtained to acquisition is examined
It surveys, to determine at least one current target object；Determine at least one described current target object whether with history testing result
In target object it is identical；Only the current target object different from the target object in history testing result is identified, because
This can reduce recognition time, improve recognition efficiency, will especially when being identified simultaneously there are multiple target objects
Significantly improve recognition efficiency.
Below in conjunction with the attached drawing in the embodiment of the present application, technical solutions in the embodiments of the present application carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of embodiments of the present application, instead of all the embodiments.It is based on
Embodiment in the application, those skilled in the art's every other implementation obtained without creative efforts
Example, shall fall in the protection scope of this application.
Fig. 1 is a kind of flow chart of information identifying method one embodiment provided by the embodiments of the present application, and this method can be with
Including the following steps:
101: the image obtained to acquisition detects, to obtain at least one current target object.
For the convenience of description, the target object that the image detection obtained from acquisition goes out is named as " current target object ".
It can be handled according to the technical solution of the application for the image for acquiring acquisition each time.
The image obtained to acquisition detects, and can obtain current detection as a result, including extremely in the current testing result
A few current target object.
Wherein, when target object is face, namely Face datection is carried out to the image that acquisition obtains, it can by Face datection
To identify the face obtained in image.
From the algorithm of extracting target from images object can there are many, such as may include based on histogram coarse segmentation and surprise
The detection algorithm of different value tag, the detection algorithm based on wavelet transformation, Adaboost algorithm etc., basic process can be utilization
Sample image trains classifier, and to realize the detection etc. of target object, same as the prior art, details are not described herein.
It may include multiple target objects in image in a practical application.
102: determine at least one described current target object whether with the history target object phase in history testing result
Together.
For the convenience of description, the target object in history testing result is named as " history target object ".
History testing result carries out detection acquisition by the image obtained to history acquisition.
Wherein, which can specifically refer to a preceding testing result, that is to say and obtain to preceding one acquisition
Image carry out detection acquisition.
In the present embodiment, current detection result and history testing result are compared, judge any current goal pair
As if it is no identical as any history target object in history testing result.
Wherein, judging whether target object is identical can carry out in embodiment below there are many implementation in detail
It introduces.
103: the current target object different from the history target object in history testing result is identified.
Current target object identical with the history target object in history testing result is i.e. without identification.Namely this reality
It applies in example and only the current target object different from the history target object in history testing result is identified.
Optionally, current target object identical with the history target object in history testing result is then continued
Identification.
Wherein, identified for example may include the characteristics of objects for extracting current target object to current target object, it will
It extracts the feature templates stored in the face characteristic and database obtained to scan for matching, calculation template similarity, if phase
It is greater than first predetermined value like degree, then can determines that the current recongnition of objects passes through, the corresponding identity information of this feature template
The as identity information of the current target object；If similarity is less than second predetermined value, the current goal pair can be determined
Do not pass through as identifying, if similarity is less than first predetermined value or is greater than second predetermined value, can determine the current goal
Object identifying failure, can not identify the identity information of the current target object, need to re-start identification etc..
Through this embodiment, only to any current goal different from any history target object in history testing result
Object identified, and if any current target object is identical as any history target object in history testing result, table
Identification has been carried out in the bright current target object, then may not need and identified again, to reduce recognition time, improves identification effect
Rate.
Wherein, as a kind of possible implementation, at least one current target object described in the determination whether with go through
History target object in history testing result is identical to may include:
The characteristics of objects of at least one current target object is obtained respectively；
It determines in history testing result, if it is special that there are the objects of characteristics of objects and at least one current target object
Levy identical history target object.
The characteristics of objects can be coarseness feature, extracted and obtained using feature extraction algorithm, and characteristics of objects generallys use
Multi-C vector data indicate that dimension can be lower than the dimension of the characteristics of objects of identification process extraction.
Feature extraction algorithm for example can with LBP (Local Binary Patterns, local binary patterns), be based on geometry
The method of feature, method based on statistical nature etc., same as the prior art, details are not described herein.
As alternatively possible implementation, since object detection can be carried out for each frame image, and to adjacent
The detection interval of two field pictures is very short, usual several ms, therefore, even if user is in moving condition, the change in location of user
Will not be little, therefore can judge whether target object of the front and back twice in testing result is same in such a way that position compares
One target object.As shown in Fig. 2, being a kind of process of another embodiment of information identifying method provided by the embodiments of the present application
Figure, this method may include following steps:
201: the image obtained to acquisition detects, to obtain at least one current target object.
202: determining any history target pair in any current target object position region and history testing result
As whether position region is consistent, if so, step 203 is executed, if not, executing step 204.
In the present embodiment, which specifically refers to a preceding testing result.
Since Image Acquisition carries out always, when user is located in the acquisition range of acquisition equipment, acquisition equipment can be certainly
It is dynamic to search for and shoot the image comprising user, it is needing to carry out recognition of face, that is, is shooting the facial image of user.
It is alternatively possible to be to judge that any current target object position region is gone through with any in history testing result
Whether the positional shift in history target object position region is in preset range.
Wherein, target object position region can be indicated with the position coordinates for presetting characteristic point in target object, with
Target object is for face, which for example can be left eye or right eye, nose, mouth in face etc..
In order to guarantee recognition accuracy, can also judge current sensing time and history detection time time difference whether
In allowed band, if so, judging any history in any current target object position region and history testing result again
Whether target object position region is consistent；Otherwise, then at least one current target object is directly identified.
203: determining any current target object and any history target object phase in history testing result
Together.
204: determining any current target object with any history target object in history testing result not
Together.
205: to current target object identical with the history target object in history testing result without identification.
206: the current target object different from the history target object in history testing result is identified.
Namely only the current target object different from each target object in history testing result is identified.
In the present embodiment, target object of the front and back twice in testing result can be determined in such a way that position compares whether
It is identical, it is identified to may not need for identical target object, then only different target objects is identified, passed through
Recognition time is reduced, to shorten recognition time, improves recognition efficiency.
Wherein, in order to guarantee recognition accuracy, in certain embodiments, it is described to the history mesh in history testing result
The identical current target object of object, which is marked, without identification may include:
Obtain in any current target object and history testing result with identical of any current target object
The characteristics of objects of one history target object；
Determine whether the characteristics of objects of any current target object is special with the object of any history target object
It levies identical；
If so, to any current target object without identification；
If not, being identified to any current target object.
Namely for identical as any current target object in any current target object and history testing result
Any history target object, further verified in conjunction with characteristics of objects.
The characteristics of objects can be coarse features, extracted and obtained using feature extraction algorithm, characteristics of objects generallys use more
Dimensional vector data indicate that dimension can be lower than the dimension of the characteristics of objects of identification process extraction.
Feature extraction algorithm for example can be LBP algorithm, the method based on geometrical characteristic, the method based on statistical nature
Deng same as the prior art, details are not described herein.
In addition, in conjunction with above description it is found that carrying out the recognition result of identification acquisition to target object may include being identified as
Perhaps recognition failures identify successfully include being identified by or identifying and do not pass through to function, be identified by namely database in there are mesh
The similarity of feature templates in the characteristics of objects and database of the mark corresponding identity information of object namely the target object is greater than
First predetermined value；By can consider, there is no the corresponding identity information of target object namely the targets in database for identification
The similarity of feature templates in the characteristics of objects and database of object is less than second predetermined value.Recognition failures show not confirming
The identity information of target object needs to re-start identification.
Therefore, if in history testing result, history recongnition of objects failure identical with current target object then should
Current target object is also required to re-start identification, to identify the identity information of the current target object, therefore in order to further
Guarantee recognition accuracy, it is in certain embodiments, described to identical with the history target object in history testing result current
Target object without identification may include:
It determines in history testing result, whether history target object identical with any current target object identifies success；
If so, to any current target object without identification；
If not, being identified to any current target object.
Wherein, optionally, it identifies for convenience, can identify pass flag to successful target object setting is identified, because
In this described judgement history testing result, whether history target object identical with any current target object identifies successfully can be with
It is:
It determines in history testing result, whether history target object identical with any current target object is provided with identification
Pass flag.
Therefore, after identifying to any current target object, it can be based on recognition result, identification is successful
Current target object setting identification pass flag.
In addition, in order to further increase identification convenience, in certain embodiments, it is described to in history testing result
The identical current target object of history target object without identification may include:
Different object numbers are set at least one described current target object, wherein current detection result and history are examined
The object number for surveying identical target object in result is identical；
Current target object identical with the object number of history target object in history testing result to object number
Without identification.
Wherein, if in history testing result, history target pair identical with the object number of any current target object
It, then can be to any current target object without identification as being provided with identification pass flag.
Technical solution in the embodiment of the present application can be applied in the application fields such as attendance, gate inhibition, be of course also apply to
The nets such as safety detection and monitoring in additional clause identification, important place, the identification in smart card, computer login
A variety of different security fields such as network security control.
Wherein, in practical applications, target object described in the embodiment of the present application specifically can refer to face, below
By taking target object is face as an example, the technical solution of the application is described.
As shown in figure 3, be a kind of flow chart of another embodiment of information identifying method provided by the embodiments of the present application, it should
Method may include following steps:
301: Face datection being carried out to the image that acquisition obtains, to obtain at least one current face.
302: determining any history face place in any current face position region and a preceding testing result
Whether the band of position is consistent, if it is step 303 is executed, if not, executing step 304.
It is alternatively possible to be any history judged in any current face position region and a preceding testing result
Whether the positional shift in face position region is in preset range.
Wherein, face position region can refer to the position coordinates of a certain default characteristic point in face, such as this is pre-
If characteristic point can be mouth, nose, left eye or right eye etc..
303: it is identical as any history face in a preceding testing result to determine any current face, and holds
Row step 305.
304: it is different from any history face in a preceding testing result to determine any current face, and holds
Row step 309.
305: obtaining the face feature of any current face and any history face respectively.
Wherein, face feature extracts can for example be realized using LBP algorithm.
306: determine any current face face feature whether the face feature phase with any history face
Together；If so, step 307 is executed, if not, executing step 309.
It is alternatively possible to different face numbers be arranged for each current face, in guarantee and a preceding testing result
The identical current face setting of any history face face number identical with any history face.
307: determining whether any history face is provided with identification pass flag, if so, executing step 308, such as
Fruit is no, executes step 309.
308: to any current face without identification.
309: recognition of face is carried out to any current face.
310: being based on recognition result, successfully identification pass flag is arranged in each current face by identification.
In the present embodiment, in face recognition process, it is based on a preceding testing result, if there is identical as current face
History face, then may indicate that the current face has already passed through identification, therefore may not need and identified again, so as to
Recognition time is reduced, the recognition of face time is reduced, improves recognition of face efficiency.
Wherein, the technical solution of the embodiment of the present application can be applied to as one embodiment in information identification system, such as
Shown in Fig. 4, which may include acquisition terminal 401 and certificate server 402；
Image is sent to certificate server 402 for acquiring image by acquisition terminal 401；It is right by certificate server 402
The image that acquisition obtains is detected, to obtain at least one current target object；Determine at least one described current goal pair
As if it is no identical as history target object in history testing result；To identical as the history target object in history testing result
Current target object without identification；And only to the current goal pair different from the history target object in history testing result
As being identified.
Namely Image Acquisition is realized by acquisition terminal 401, object detection and Object identifying mistake are realized by certificate server
Journey.
Acquisition terminal can carry out Image Acquisition for the multiple users being located in its acquisition range, so as to from image
Middle detection obtains multiple target objects, which can be the face of user.
As another embodiment, as shown in Figure 5, which may include detection terminal 501 and recognizes
Demonstrate,prove server 502；
Detection terminal 501 is for acquiring image, and the image obtained to acquisition detects, current to obtain at least one
Target object, and at least one described current target object is sent to certificate server；Determine at least one described current mesh
Whether identical as the history target object in history testing result mark object；Triggering authentication server 502 will be detected with history and be tied
The identical current target object of history target object in fruit is without identification；And triggering authentication server 502 will be with history
The different current target object of history target object in testing result is identified.
Namely Image Acquisition and object detection are realized by detection terminal, Object identifying is realized by certificate server, to protect
The process performance of card detection terminal and certificate server.
Certainly, the technical solution of the embodiment of the present application also can be applied in independent identification terminal, complete by identification terminal
It is operated at Image Acquisition, object detection and Object identifying etc..
In a practical application, above-mentioned acquisition terminal, detection terminal or identification terminal can be embodied as having respectively
There is the attendance recorder of different function, to realize attendance purpose.
In attendance application, after determining that target object corresponds to identity information, it can corresponding identity information record is examined
Diligent time etc..
Fig. 6 is a kind of structural schematic diagram of information recognition device one embodiment provided by the embodiments of the present application, wherein should
Device can be only fitted in certificate server as shown in Figure 4, also can be only fitted in detection terminal as shown in Figure 5, certainly
Also it can be only fitted in identification terminal.
The apparatus may include:
Detection module 601, the image for obtaining to acquisition detect, to determine at least one current target object.
Judgment module 602, for determine at least one described current target object whether with going through in history testing result
History target object is identical；
First identification module 603, for by the current goal pair different from the history target object in history testing result
As being identified.
Optionally, in addition, as shown in Figure 7, with Fig. 6 shown device the difference is that, which can also include:
Second identification module 604, for current goal pair identical with the history target object in history testing result
As being identified.
Through this embodiment, only to any current goal different from any history target object in history testing result
Object identified, and if any current target object is identical as any history target object in history testing result, table
Identification has been carried out in the bright current target object, then may not need and identified again, to reduce recognition time, improves identification effect
Rate.
As a kind of possible implementation, the judgment module can be specifically used for: obtain respectively it is described at least one
The characteristics of objects of current target object；It determines in history testing result, if there are characteristics of objects and described at least one is current
The identical history target object of the characteristics of objects of target object.
As alternatively possible implementation, the judgment module can be specifically used for:
Determine any history target object institute in any current target object position region and history testing result
It is whether consistent in the band of position, if so, determine that any current target object is identical as any history target object, it is no
Then, determine that any current target object is different from any history target object.It can be in such a way that position compares
Determine whether target object of the front and back twice in testing result be identical, is known to may not need for identical target object
Not, then only different target objects is identified, by reducing recognition time, to shorten recognition time, improves recognition efficiency.
Optionally, the judgment module can be specifically used for determining any current target object position region and history
Whether the positional shift in any history target object position region in testing result is in preset range.
Wherein, in order to guarantee recognition accuracy, in certain embodiments, second identification module can be specifically used for obtaining
Take any history target identical with any current target object in any current target object and history testing result
The characteristics of objects of object；Determine any current target object characteristics of objects whether with same any history
The characteristics of objects of target object is identical；If so, to any current target object without identification；If not, to described
Any current target object is identified.
Namely for identical as any current target object in any current target object and history testing result
Any history target object, further verified in conjunction with characteristics of objects.
In addition, in certain embodiments, second identification module can be specifically used for determining in history testing result, with
Whether the identical history target object of any current target object identifies success；If so, to any current target object
Without identification；If not, being identified to any current target object.
Wherein, optionally, it identifies for convenience, can identify pass flag to successful target object setting is identified, because
This described first identification module judges in history testing result that whether is history target object identical with any current target object
Identifying successfully can be specifically:
Judge in history testing result, whether history target object identical with any current target object is provided with identification
Pass flag.
Therefore, after second identification module identifies any current target object, it is also based on knowledge
Not as a result, successful current target object setting identification pass flag will be identified.
In addition, in certain embodiments, the first identification module can be specifically used in order to further increase identification convenience
Different object numbers are set at least one described current target object, wherein in current detection result and history testing result
The object number of identical target object is identical；
Current target object identical with the object number of history target object in history testing result to object number
Without identification.
Information recognition device described in Fig. 6 or 7 can execute information identifying method described in FIG. 1 to FIG. 3 any embodiment,
Its implementing principle and technical effect repeats no more.For the information recognition device in above-described embodiment wherein modules, unit
The concrete mode for executing operation is described in detail in the embodiment of the method, will be not set forth in detail herein
Explanation.
In a possible design, the information recognition device of Fig. 6 or embodiment illustrated in fig. 7 can be implemented as an electronics and set
It is standby, as shown in figure 8, the electronic equipment may include processing component 801, and deposited respectively with what the processing component 801 was connect
Reservoir 802；
The memory 802 stores one or more computer program instructions, and one or more computer program refers to
It enables and calls and execute for the processing component 801；
The processing component 801 is used for:
The image obtained to acquisition detects, to determine at least one current target object；
Determine whether at least one described current target object is identical as the history target object in history testing result；
The current target object different from the history target object in history testing result is identified.
Processing component 801 is also used to current target object identical with the history target object in history testing result not
It is identified.
Processing component pair current target object identical with the history target object in history testing result is then without knowing
Not.
In a practical application, which can be the certificate server connecting with acquisition terminal, and the acquisition is whole
End can be the picture pick-up devices such as camera.
In addition, as another embodiment, as shown in Figure 9, with embodiment illustrated in fig. 8 the difference is that, the electronics
Equipment can also include connecting with processing component 801, for acquiring the acquisition component 803 of image.
Processing component 801 is specifically that the image obtained to the acquisition component 803 acquisition detects, to determine at least one
A current target object.
In the embodiment, which can know for an independent realization Image Acquisition, object detection and object
Other identification terminal.
In addition, in certain embodiments, the current target object which determines can also be sent to certification clothes
Business device, processing component 801 is to current target object identical with the history target object in history testing result without identification
Can be triggering authentication server by current target object identical with the history target object in history testing result without
Identification.Processing component 801 carries out identification tool to the current target object different from the history target object in history testing result
Body can be triggering authentication server and carry out the current target object different from the history target object in history testing result
Identification.
Wherein, processing component 801 may include that one or more processors carry out computer instructions, above-mentioned to complete
All or part of the steps in method.Certain processing component may be one or more application specific integrated circuit (ASIC),
Digital signal processor (DSP), digital signal processing appts (DSPD), programmable logic device (PLD), field-programmable gate array
It arranges (FPGA), controller, microcontroller, microprocessor or other electronic components to realize, for executing the above method.
Memory 802 is configured as storing various types of data to support the operation in XX equipment.Memory can be by
Any kind of volatibility or non-volatile memory device or their combination realization, such as static random access memory
(SRAM), electrically erasable programmable read-only memory (EEPROM), Erasable Programmable Read Only Memory EPROM (EPROM) may be programmed
Read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, disk or CD.
Acquisition component 803 can be camera.
Certainly, electronic equipment necessarily can also include other component, such as input/output interface, communication component etc..
Input/output interface provides interface between processing component and peripheral interface module, and above-mentioned peripheral interface module can
To be output equipment, input equipment etc..
Communication component is configured to facilitate the communication of wired or wireless way between electronic equipment and other equipment, such as and
Certificate server communicates etc..
The embodiment of the present application also provides a kind of computer readable storage mediums, are stored with computer program, the calculating
The information identifying method of any one of above-mentioned FIG. 1 to FIG. 3 illustrated embodiment may be implemented in machine program when being computer-executed.
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description,
The specific work process of device and unit, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
The apparatus embodiments described above are merely exemplary, wherein described, unit can as illustrated by the separation member
It is physically separated with being or may not be, component shown as a unit may or may not be physics list
Member, it can it is in one place, or may be distributed over multiple network units.It can be selected according to the actual needs
In some or all of the modules achieve the purpose of the solution of this embodiment.Those of ordinary skill in the art are not paying creativeness
Labour in the case where, it can understand and implement.
Through the above description of the embodiments, those skilled in the art can be understood that each embodiment can
It realizes by means of software and necessary general hardware platform, naturally it is also possible to pass through hardware.Based on this understanding, on
Stating technical solution, substantially the part that contributes to existing technology can be embodied in the form of software products in other words, should
Computer software product may be stored in a computer readable storage medium, such as ROM/RAM, magnetic disk, CD, including several fingers
It enables and using so that a computer equipment (can be personal computer, server or the network equipment etc.) executes each implementation
Method described in certain parts of example or embodiment.
Finally, it should be noted that above embodiments are only to illustrate the technical solution of the application, rather than its limitations；Although
The application is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it still may be used
To modify the technical solutions described in the foregoing embodiments or equivalent replacement of some of the technical features；
And these are modified or replaceed, each embodiment technical solution of the application that it does not separate the essence of the corresponding technical solution spirit and
Range.
Claims (17)
1. a kind of information identifying method characterized by comprising
The image obtained to acquisition detects, to obtain at least one current target object；
Determine whether at least one described current target object is identical as the history target object in history testing result；
The current target object different from the history target object in history testing result is identified.
2. the method according to claim 1, wherein further include:
To current target object identical with the history target object in history testing result without identification.
3. method according to claim 1 or 2, which is characterized in that at least one current target object described in the determination
Whether identical as the history target object in history testing result include:
Determine that any history target object institute in any current target object position region and history testing result is in place
Whether consistent set region, if so, determine that any current target object is identical as any history target object, otherwise,
Determine that any current target object is different from any history target object.
4. according to the method described in claim 3, it is characterized in that, it is described to the history target object in history testing result
Identical current target object without identification include:
Obtain identical with any current target object in any current target object and history testing result any go through
The characteristics of objects of history target object；
Determine any current target object characteristics of objects whether with same any history target object
Characteristics of objects is identical；
If so, to any current target object without identification；
If not, being identified to any current target object.
5. method according to claim 1 or 2, which is characterized in that at least one current target object described in the determination
Whether identical as the history target object in history testing result include:
The characteristics of objects of at least one current target object is obtained respectively；
It determines in history testing result, if there are the characteristics of objects phases of characteristics of objects and at least one current target object
Same history target object.
6. according to the method described in claim 2, it is characterized in that, it is described to the history target object in history testing result
Identical current target object without identification include:
It determines in history testing result, whether history target object identical with any current target object identifies success；
If so, to any current target object without identification；
If not, being identified to any current target object.
7. according to the method described in claim 3, it is characterized in that, the determination any current target object position region
With any history target object position region in history testing result whether unanimously include:
Determine that any history target object institute in any current target object position region and history testing result is in place
The positional shift in region is set whether in preset range.
8. the method according to claim 1, wherein the target object is face.
9. a kind of information recognition device characterized by comprising
Detection module, the image for obtaining to acquisition detects, to obtain at least one current target object；
Judgment module, for determine at least one described current target object whether with the history target pair in history testing result
As identical；
First identification module, for knowing to the current target object different from the history target object in history testing result
Not.
10. device according to claim 9, which is characterized in that further include:
Second identification module, for current target object identical with the history target object in history testing result without
Identification.
11. device according to claim 9 or 10, which is characterized in that the judgment module is specifically used for:
Determine that any history target object institute in any current target object position region and history testing result is in place
Whether consistent set region, if so, determine that any current target object is identical as any history target object, otherwise,
Determine that any current target object is different from any history target object.
12. device according to claim 11, which is characterized in that second identification module is specifically used for obtaining any work as
Pair of any history target object identical with any current target object in preceding target object and history testing result
As feature；Determine any current target object characteristics of objects whether with same any history target object
Characteristics of objects it is identical；If so, to any current target object without identification；If not, to described any current
Target object is identified.
13. device according to claim 9 or 10, which is characterized in that the judgment module is specifically used for: obtaining institute respectively
State the characteristics of objects of at least one current target object；Determine in history testing result, if there are characteristics of objects and it is described extremely
The identical history target object of characteristics of objects of a few current target object.
14. device according to claim 10, which is characterized in that second identification module is specifically used for determining history inspection
It surveys in result, whether history target object identical with any current target object identifies success；If so, any working as to described
Preceding target object is without identification；If not, being identified to any current target object.
15. device according to claim 11, which is characterized in that the judgment module is specifically used for: determining any current
The positional shift in any history target object position region in target object position region and history testing result
Whether in preset range.
16. a kind of electronic equipment, which is characterized in that including processing component, and the storage being connect respectively with the processing component
Device；
The memory stores one or more computer program instructions, described in one or more computer program instructions supply
Processing component is called and is executed；
The processing component is used for:
The image obtained to acquisition detects, to determine at least one current target object；
Determine whether at least one described current target object is identical as the history target object in history testing result；
The current target object different from the history target object in history testing result is identified.
17. terminal according to claim 16, which is characterized in that further include the acquisition group being connect with the processing component
Part, for acquiring image；
The image that the processing component obtains acquisition detects, to determine that at least one current target object is specifically to institute
It states acquisition component acquisition acquisition image to be detected, to determine at least one current target object.
Priority Applications (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710884606.XA CN109558773B (en) | 2017-09-26 | 2017-09-26 | Information identification method and device and electronic equipment |
| TW107119428A TW201915830A (en) | 2017-09-26 | 2018-06-06 | Information recognition method and apparatus, and electronic device |
| PCT/CN2018/106102 WO2019062588A1 (en) | 2017-09-26 | 2018-09-18 | Information recognition method and apparatus, and electronic device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710884606.XA CN109558773B (en) | 2017-09-26 | 2017-09-26 | Information identification method and device and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109558773A true CN109558773A (en) | 2019-04-02 |
| CN109558773B CN109558773B (en) | 2023-04-07 |
Family
ID=65863117
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710884606.XA Active CN109558773B (en) | 2017-09-26 | 2017-09-26 | Information identification method and device and electronic equipment |
Country Status (3)
| Country | Link |
|---|---|
| CN (1) | CN109558773B (en) |
| TW (1) | TW201915830A (en) |
| WO (1) | WO2019062588A1 (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111275649A (en) * | 2020-02-03 | 2020-06-12 | 北京达佳互联信息技术有限公司 | Image processing method, image processing device, electronic equipment and storage medium |
| CN111401463A (en) * | 2020-03-25 | 2020-07-10 | 维沃移动通信有限公司 | Method for outputting detection result, electronic device, and medium |
| CN111522795A (en) * | 2020-04-23 | 2020-08-11 | 北京互金新融科技有限公司 | Method and device for processing data |
| CN111401463B (en) * | 2020-03-25 | 2024-04-30 | 维沃移动通信有限公司 | Method for outputting detection result, electronic equipment and medium |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111582047A (en) * | 2020-04-15 | 2020-08-25 | 浙江大华技术股份有限公司 | Face recognition verification passing method and related device thereof |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102017606A (en) * | 2008-04-23 | 2011-04-13 | 日本电气株式会社 | Image processing device, camera, image processing method, and program |
| CN102254148A (en) * | 2011-04-18 | 2011-11-23 | 周曦 | Method for identifying human faces in real time under multi-person dynamic environment |
| CN102880864A (en) * | 2012-04-28 | 2013-01-16 | 王浩 | Method for snap-shooting human face from streaming media file |
| US20150356345A1 (en) * | 2014-06-05 | 2015-12-10 | Promethean Limited | Systems and methods for detecting, identifying and tracking objects and events over time |
| CN105205482A (en) * | 2015-11-03 | 2015-12-30 | 北京英梅吉科技有限公司 | Quick facial feature recognition and posture estimation method |
| CN106446816A (en) * | 2016-09-14 | 2017-02-22 | 北京旷视科技有限公司 | Face recognition method and device |
| CN107105310A (en) * | 2017-05-05 | 2017-08-29 | 广州盈可视电子科技有限公司 | Figure image replacement method, device and a kind of recording and broadcasting system in a kind of net cast |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8121358B2 (en) * | 2009-03-06 | 2012-02-21 | Cyberlink Corp. | Method of grouping images by face |
| CN103491351A (en) * | 2013-09-29 | 2014-01-01 | 东南大学 | Intelligent video monitoring method for illegal buildings |
| CN104581003A (en) * | 2013-10-12 | 2015-04-29 | 北京航天长峰科技工业集团有限公司 | Video rechecking positioning method |
| CN104038742B (en) * | 2014-06-06 | 2017-12-01 | 上海卓悠网络科技有限公司 | A kind of door bell and button system based on face recognition technology |
-
2017
- 2017-09-26 CN CN201710884606.XA patent/CN109558773B/en active Active
-
2018
- 2018-06-06 TW TW107119428A patent/TW201915830A/en unknown
- 2018-09-18 WO PCT/CN2018/106102 patent/WO2019062588A1/en active Application Filing
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102017606A (en) * | 2008-04-23 | 2011-04-13 | 日本电气株式会社 | Image processing device, camera, image processing method, and program |
| CN102254148A (en) * | 2011-04-18 | 2011-11-23 | 周曦 | Method for identifying human faces in real time under multi-person dynamic environment |
| CN102880864A (en) * | 2012-04-28 | 2013-01-16 | 王浩 | Method for snap-shooting human face from streaming media file |
| US20150356345A1 (en) * | 2014-06-05 | 2015-12-10 | Promethean Limited | Systems and methods for detecting, identifying and tracking objects and events over time |
| CN105205482A (en) * | 2015-11-03 | 2015-12-30 | 北京英梅吉科技有限公司 | Quick facial feature recognition and posture estimation method |
| CN106446816A (en) * | 2016-09-14 | 2017-02-22 | 北京旷视科技有限公司 | Face recognition method and device |
| CN107105310A (en) * | 2017-05-05 | 2017-08-29 | 广州盈可视电子科技有限公司 | Figure image replacement method, device and a kind of recording and broadcasting system in a kind of net cast |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111275649A (en) * | 2020-02-03 | 2020-06-12 | 北京达佳互联信息技术有限公司 | Image processing method, image processing device, electronic equipment and storage medium |
| CN111401463A (en) * | 2020-03-25 | 2020-07-10 | 维沃移动通信有限公司 | Method for outputting detection result, electronic device, and medium |
| WO2021190387A1 (en) * | 2020-03-25 | 2021-09-30 | 维沃移动通信有限公司 | Detection result output method, electronic device, and medium |
| JP7467667B2 (en) | 2020-03-25 | 2024-04-15 | 維沃移動通信有限公司 | Detection result output method, electronic device and medium |
| CN111401463B (en) * | 2020-03-25 | 2024-04-30 | 维沃移动通信有限公司 | Method for outputting detection result, electronic equipment and medium |
| CN111522795A (en) * | 2020-04-23 | 2020-08-11 | 北京互金新融科技有限公司 | Method and device for processing data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109558773B (en) | 2023-04-07 |
| TW201915830A (en) | 2019-04-16 |
| WO2019062588A1 (en) | 2019-04-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109711243B (en) | Static three-dimensional face in-vivo detection method based on deep learning | |
| CN109325964B (en) | Face tracking method and device and terminal | |
| CN105518709B (en) | The method, system and computer program product of face for identification | |
| WO2021047232A1 (en) | Interaction behavior recognition method, apparatus, computer device, and storage medium | |
| CN106897658B (en) | Method and device for identifying human face living body | |
| WO2015165365A1 (en) | Facial recognition method and system | |
| WO2019127273A1 (en) | Multi-person face detection method, apparatus, server, system, and storage medium | |
| WO2019033572A1 (en) | Method for detecting whether face is blocked, device and storage medium | |
| CN109558773A (en) | Information identifying method, device and electronic equipment | |
| CN108197557A (en) | Testimony of a witness consistency check method, terminal device and computer readable storage medium | |
| CN109858371A (en) | The method and device of recognition of face | |
| CN108235770A (en) | image identification method and cloud system | |
| CN101556717A (en) | ATM intelligent security system and monitoring method | |
| CN106919921B (en) | Gait recognition method and system combining subspace learning and tensor neural network | |
| CN105488468A (en) | Method and device for positioning target area | |
| KR20130084437A (en) | Apparatus for real-time face recognition | |
| CN108090406A (en) | Face identification method and system | |
| CN109766755A (en) | Face identification method and Related product | |
| CN108108711A (en) | Face supervision method, electronic equipment and storage medium | |
| CN109492509A (en) | Personal identification method, device, computer-readable medium and system | |
| CN108875509A (en) | Biopsy method, device and system and storage medium | |
| CN111738199A (en) | Image information verification method, image information verification device, image information verification computing device and medium | |
| CN115862113A (en) | Stranger abnormity identification method, device, equipment and storage medium | |
| CN105427480B (en) | A kind of automatic teller machine based on graphical analysis | |
| CN113869110A (en) | Article detection method, device, terminal and computer readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |