CN109829381A - A kind of dog only identifies management method, device, system and storage medium - Google Patents
A kind of dog only identifies management method, device, system and storage medium Download PDFInfo
- Publication number
- CN109829381A CN109829381A CN201811628347.5A CN201811628347A CN109829381A CN 109829381 A CN109829381 A CN 109829381A CN 201811628347 A CN201811628347 A CN 201811628347A CN 109829381 A CN109829381 A CN 109829381A
- Authority
- CN
- China
- Prior art keywords
- dog
- identified
- face image
- feature
- dog face
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Collating Specific Patterns (AREA)
Abstract
The present invention provides a kind of dogs only to identify management method, device, system and computer storage medium.The dog only identifies that management method includes: to obtain dog face image to be identified, and determine recognition mode, and recognition mode includes: Validation Mode and search pattern；Under Validation Mode, dog face image to be identified is compared with reference picture is compared, determines that dog face image to be identified compares whether reference picture belongs to same dog with described；Under search pattern, dog face image to be identified is scanned in dog number of elements according to bottom library, the identity information of dog face image to be identified is obtained.According to the method for the present invention, device, system and computer storage medium, dog authentication both may be implemented based on different recognition modes, determine that dog face image to be identified compares whether reference picture belongs to same dog with described, it can be realized identity search again, dog management method providing system, meeting more demands, easy to operate, recognition result is accurate.
Description
Technical field
The present invention relates to technical field of image processing, relate more specifically to the processing of dog face image.
Background technique
Currently, the product solution based on face recognition technology more and more appears in daily life and city
In city's security protection, for example, the online identity service for checking credentials is being that the key businesses such as more than 200 internet Finance and Banking mechanisms are protected
Convoy is driven, it is anti-that intelligent security guard system then combines typical scene and actual combat demand in public business to advance man-computer cooperation, intelligence
The police service mode of control.The implementation of the prior art has ensured the property safety of citizen, and public security department is helped to lock suspicion personnel rapidly,
However it can not but solve dog and only hurt sb.'s feelings bring personal safety hidden danger.It is reported that dog wounding event is more frequent, dog owner
But it is difficult to trace, its civil liability can not be investigated.Therefore, to solve the problems, such as that dog suffers from extremely urgent.
Therefore, dog in the prior art only manages in the presence of that can not identify that dog identity or recognizer are complicated, and real-time is not
High and low accuracy rate problem.
Summary of the invention
The present invention is proposed in view of the above problem.The present invention provides a kind of dogs only to identify management method, device, is
System and computer storage medium, both may be implemented dog authentication based on different recognition modes, and had determined dog face image to be identified
Compare whether reference picture belongs to same dog with described, but can be realized identity search, provide system, meet more demands
Dog management method, easy to operate, recognition result is accurate.
According to an aspect of the present invention, it provides a kind of dog and only identifies management method, comprising:
Dog face image to be identified is obtained, and determines recognition mode, recognition mode includes: Validation Mode and search pattern；
Under Validation Mode, dog face image to be identified is compared with reference picture is compared, determines dog face figure to be identified
As comparing whether reference picture belongs to same dog with described；
Under search pattern, dog face image to be identified is scanned in dog number of elements according to bottom library, dog face figure to be identified is obtained
The identity information of picture.
Illustratively, the method also includes: determine recognition property, wherein recognition property includes dog face attribute or dog nose
Line attribute；Then, the dog face image to be identified is compared with reference picture is compared according to the recognition property；According to described
Recognition property is by dog face image to be identified in dog number of elements according to scanning in the library of bottom.
Illustratively, dog face image to be identified is compared according to the recognition property with reference picture is compared, is determined
Dog face image to be identified and compare whether reference picture belongs to same dog, comprising:
Feature extraction is carried out respectively to the dog face image to be identified and comparison reference picture according to determining recognition property,
Obtain the feature to be compared of the dog face image to be identified and the fixed reference feature of the comparison reference picture；
It compares the feature to be compared and the fixed reference feature determines dog face image to be identified and whether compares reference picture
Belong to same dog.
Illustratively, dog face image to be identified and reference is compared than described determine to feature to be compared and the fixed reference feature
Whether image belongs to same dog, comprising:
The feature to be compared is calculated at a distance from the fixed reference feature；
If the distance, which is less than, compares distance threshold, confirm that the dog face image to be identified is with reference picture is compared
Belong to same dog.
Illustratively, dog face image to be identified is scanned in dog number of elements according to bottom library according to the recognition property, is obtained
The identity identification information of dog face image to be identified, comprising:
Feature extraction is carried out to the dog face image to be identified according to determining recognition property and obtains dog face image to be identified
Feature to be identified；
Search is compared according to the multiple template feature in the library of bottom with the dog number of elements based on the feature to be identified, will search
Identity identification information of the identity information corresponding to the template characteristic that rope obtains as dog face image to be identified.
Illustratively, it is compared with the dog number of elements according to the multiple template feature in the library of bottom based on the feature to be identified
Search, obtains the identity identification information of dog face image to be identified, comprising:
The feature to be identified is calculated at a distance from the template characteristic；
Using the identity information corresponding to the smallest template characteristic as the identification of dog face image to be identified
Information.
Illustratively, the method also includes:
It, will be described when the feature to be identified is all larger than identification distance threshold at a distance from template characteristic described in each
Dog face image to be identified and corresponding identity information typing are to data bottom library.
According to a further aspect of the invention, it provides a kind of dog and only identifies managing device, comprising:
Image collection module, for obtaining dog face image to be identified；
Pattern recognition module, for determining that recognition mode, the recognition mode include: Validation Mode and search pattern；
Authentication module determines dog face figure to be identified for dog face image to be identified to be compared with reference picture is compared
As comparing whether reference picture belongs to same dog with described；
Search module obtains dog face figure to be identified for scanning for dog face image to be identified according to bottom library in dog number of elements
The identity information of picture.
Illustratively, image collection module includes:
Real-time acquisition module, for implementing acquisition image data；
Local uploading module uploads image data for local；
Framing module, for being regarded to the video data in the image data implementing acquisition and/or locally uploading
Frequency image framing；
Dog face detection module generates dog face image to be identified for carrying out the detection of dog face to every frame image.
Illustratively, dog face obtains module further include:
Image receiver module, for receiving the image data of other data sources.
Illustratively, the real-time acquisition module is also used to: the environment attribute of acquisition dog only in real time；When the environment attribute
Meet scheduled acquisition when requiring, dog face image described in automatic collection.
Illustratively, the dog only identifies managing device further include:
Recognition property module, for determining recognition property, wherein recognition property includes dog face attribute or dog noseprint attribute；
Then, the dog face image to be identified and comparison reference picture are compared according to the recognition property；Belonged to according to the identification
Property is by dog face image to be identified in dog number of elements according to scanning in the library of bottom.
Illustratively, the dog only identifies managing device further include:
Characteristic extracting module, for the dog face image to be identified and/or comparing reference according to determining recognition property
Image carries out feature extraction respectively, obtain the dog face image to be identified feature to be compared and/or the comparison reference picture
Fixed reference feature.
Illustratively, the characteristic extracting module is also used to:
It is according to the recognition property that the dog face image to be identified and/or comparison reference picture input is trained
Feature extraction network model obtains the feature to be compared of the dog face image to be identified and/or compares the reference spy of reference picture
Sign.
Illustratively, according to the recognition property of the determination, the feature to be compared of the dog face image to be identified and described
The fixed reference feature for comparing reference picture can be dog face feature and/or dog noseprint feature.
Illustratively, authentication module is also used to:
It compares the feature to be compared and the fixed reference feature determines dog face image to be identified and whether compares reference picture
Belong to same dog.
Illustratively, described image obtains module and is also used to: acquiring the comparison reference picture and/or local upload in real time
The comparison reference picture.
Illustratively, the authentication module includes:
Computing module is verified, for calculating the feature to be compared at a distance from the fixed reference feature；
Judgment module is verified, distance threshold is compared if be less than for the distance, confirms the dog face figure to be identified
As with to compare reference picture be to belong to same dog.
Illustratively, verifying judgment module is also used to: if the feature to be compared surpasses at a distance from the fixed reference feature
Comparison distance threshold is crossed, then confirm the dog face image to be identified and compares reference picture and is not belonging to same dog.
Illustratively, described search module is also used to:
Search is compared according to the multiple template feature in the library of bottom with the dog number of elements based on the feature to be identified, will search
Identity identification information of the identity information corresponding to the template characteristic that rope obtains as dog face image to be identified.
Illustratively, the dog only identifies managing device further include:
Dog Registration Module, for being all larger than identification at a distance from template characteristic described in each when the feature to be identified
When distance threshold, by the dog face image to be identified and corresponding identity information typing to data bottom library.
Illustratively, the dog Registration Module is also used to: the dog face image to be identified is stored into the dog bottom
When library, I D number is distributed for the dog face picture to be identified and is put on record in dog database.Not only expand dog in this way
The coverage area of database, and be conducive to search/comparison operation of other users, enrich the number in dog database
According to.
According to a further aspect of the invention, a kind of dog identification and management system, including memory, processor and storage are provided
The computer program run on the memory and on the processor, which is characterized in that described in the processor executes
The step of above method is realized when computer program.
According to a further aspect of the invention, a kind of computer readable storage medium is provided, computer program is stored thereon with,
It is characterized in that, the step of realizing the above method when computer program is computer-executed.
Dog according to an embodiment of the present invention only identifies management method, device, system and computer storage medium, based on difference
Dog authentication had both may be implemented in recognition mode, determined that dog face image to be identified compares whether reference picture belongs to together with described
One dog, and can be realized identity search, dog management method providing system, meeting more demands is easy to operate, identification
As a result accurate.
Detailed description of the invention
The embodiment of the present invention is described in more detail in conjunction with the accompanying drawings, the above and other purposes of the present invention,
Feature and advantage will be apparent.Attached drawing is used to provide to further understand the embodiment of the present invention, and constitutes explanation
A part of 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 label typically represents same parts or step.
Fig. 1 is the exemplary electronic device that management method and device are only identified for realizing dog according to an embodiment of the present invention
Schematic block diagram；
Fig. 2 is the schematic flow chart that dog according to an embodiment of the present invention only identifies management method；
Fig. 3 is that dog according to an embodiment of the present invention only identifies the exemplary schematic diagram of the Validation Mode of management method；
Fig. 4 is that dog according to an embodiment of the present invention only identifies the exemplary schematic diagram of the search pattern of management method；
Fig. 5 is that dog according to an embodiment of the present invention only identifies the exemplary schematic diagram of the search pattern of management method；
Fig. 6 is that dog according to an embodiment of the present invention only identifies the exemplary schematic diagram of the search pattern of management method；
Fig. 7 is the exemplary schematic diagram that dog according to an embodiment of the present invention only identifies management method；
Fig. 8 is the schematic block diagram that dog according to an embodiment of the present invention only identifies managing device；
Fig. 9 is the schematic block diagram of dog identification and management system according to an embodiment of the present invention.
Specific embodiment
In order to enable the object, technical solutions and advantages of the present invention become apparent, root is described in detail below with reference to accompanying drawings
According to example embodiments of the present invention.Obviously, described embodiment is only a part of the embodiments of the present invention, rather than this hair
Bright whole embodiments, it should be appreciated that the present invention is not limited by example embodiment described herein.Based on described in the present invention
The embodiment of the present invention, those skilled in the art's obtained all other embodiment in the case where not making the creative labor
It should all fall under the scope of the present invention.
Firstly, being described with reference to Figure 1 the example for only identifying management method and device for realizing the dog of the embodiment of the present invention
Electronic equipment 100.
As shown in Figure 1, electronic equipment 100 include one or more processors 101, it is one or more storage device 102, defeated
Enter device 103, output device 104, imaging sensor 105, the company that these components pass through bus system 106 and/or other forms
The interconnection of connection mechanism (not shown).It should be noted that the component and structure of electronic equipment 100 shown in FIG. 1 are only exemplary, rather than
Restrictive, as needed, the electronic equipment also can have other assemblies and structure.
The processor 101 can be central processing unit (CPU) or have data-handling capacity and/or instruction execution
The processing unit of the other forms of ability, and the other components that can control in the electronic equipment 100 are desired to execute
Function.
The storage device 102 may include one or more computer program products, and the computer program product can
To include various forms of computer readable storage mediums, such as volatile memory and/or nonvolatile memory.It is described easy
The property lost memory for example may include random access memory (RAM) and/or cache memory (cache) etc..It is described non-
Volatile memory for example may include read-only memory (ROM), hard disk, flash memory etc..In the computer readable storage 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
Can also store various application programs and various data in calculation machine readable storage medium storing program for executing, for example, the application program use and/or
The various data etc. generated.
The input unit 103 can be the device that user is used to input instruction, and may include keyboard, mouse, wheat
One or more of gram wind and touch screen etc..
The output device 104 can export various information (such as image or sound) to external (such as user), and
It may include one or more of display, loudspeaker etc..
Described image sensor 105 can be shot the desired image of user (such as photo, video etc.), and will be captured
Image be stored in the storage device 102 for other components use.
Illustratively, only identify that the exemplary electron of management method and device is set for realizing dog according to an embodiment of the present invention
It is standby to may be implemented as smart phone, tablet computer, video acquisition end of access control system etc..
Dog according to an embodiment of the present invention, which is described, next, with reference to Fig. 2 only identifies management method 200.
Firstly, obtaining dog face image to be identified, and determine recognition mode, recognition mode includes: verifying mould in step S210
Formula and search pattern；
In step S220, under Validation Mode, dog face image to be identified is compared with reference picture is compared, is determined
Dog face image to be identified compares whether reference picture belongs to same dog with described；
Under search pattern, dog face image to be identified is scanned in dog number of elements according to bottom library, dog face figure to be identified is obtained
The identity information of picture.
Illustratively, dog according to an embodiment of the present invention only identifies that management method can be with memory and processor
It is realized in unit or system.
Dog according to an embodiment of the present invention only identifies that management method can be deployed at Image Acquisition end, for example, can portion
Administration is at personal terminal, smart phone, tablet computer, personal computer etc..Alternatively, dog according to an embodiment of the present invention
Only identification management method can also be deployed at server end (or cloud) and personal terminal with being distributed.For example, can service
Device end (or cloud) generates dog face image, and dog face image generated is passed to personal terminal by server end (or cloud), a
People's terminal is compared and/or is identified according to the received dog face image of institute.For another example can be generated in server end (or cloud)
Dog face image, the video information transmitting for video information and the non-image sensor acquisition that personal terminal acquires imaging sensor
Server end (or cloud) is given, then server end (or cloud) into comparison and/or identifies.
Dog according to an embodiment of the present invention only identifies management method, and dog identity both may be implemented based on different recognition modes
Verifying determines that dog face image to be identified compares whether reference picture belongs to same dog with described, and can be realized identity search,
Dog management method providing system, meeting more demands, easy to operate, recognition result is accurate.
According to embodiments of the present invention, can further include in step 210: described to obtain dog face image packet to be identified
It includes: receiving the image data of dog face to be identified；Video image framing is carried out to the video data in described image data, and to every
Frame image carries out the detection of dog face and generates dog face image to be identified.
Illustratively, described to obtain dog face image to be identified including acquiring the dog face image and/or this ground in real time
Pass the dog face image.In one embodiment, the dog face image that obtains can also receive the dog that other data sources are sent
Face image.
Illustratively, described to acquire the environment attribute that the dog face image includes: real-time acquisition dog in real time；When the ring
Border attribute meets scheduled acquisition when requiring, dog face image described in automatic collection.Wherein, environment attribute includes the bat of the dog only
Angle is taken the photograph, light, at least one of camera site are shot.In this way, can fill up to a certain extent human eye, people it is anti-
It answers the loophole time of speed, preferably help user grabs the image for collecting high quality as identification basis.Because based on high-quality
The image of amount reduces the noise in image processing process, be conducive to further increase the dog only compare or identify it is accurate
Degree.
Wherein, image data includes video data and non-video data, and non-video data may include single-frame images, at this time
Single-frame images does not need to carry out sub-frame processing, can be directly as dog face image.
Efficient quick file access may be implemented in the access that video data carries out file in a streaming manner；The video flowing
Storage mode may include one of following storage mode: local (local) storage, database purchase, distributed file system
(hdfs) storage and long-range storage, storing service address may include server ip and Service-Port.Wherein, it is locally stored
Refer to video flowing in system local；Database purchase, which refers to, is stored in video flowing in the database of system, database purchase
Need to install corresponding database；Distributed file system storage, which refers to, is stored in video flowing in distributed file system, point
Cloth file system storage needs to install distributed file system；Long-range storage refer to by video flowing transfer to other storage services into
Row storage.In other examples, the storage mode configured also may include the storage mode of other any suitable types, this hair
It is bright to this with no restriction.
Illustratively, the dog face image is by including to determined by each frame image progress dog face detection in video
There is the picture frame of dog face.Specifically, the various abilities such as template matching, SVM (support vector machines), neural network can be passed through
Common dog face detecting method determines the size and location of the dog face in the start image frame comprising target dog face in domain, thus
Determine include in video dog face each frame image.It is above by the processing that the detection determination of dog face includes the picture frame of dog face
Common processing in field of image processing, is no longer described in greater detail herein.
It should be noted that the dog face image be not necessarily in image data it is all include dog face image, and
It can be only parts of images frame therein；On the other hand, the dog face image can be single-frame images, can be continuous multiframe
Image is also possible to discontinuous, arbitrarily selected multiple image.
Illustratively, when not detecting that dog face then continues to the picture number of dog face to be identified in described image data
According to.
According to embodiments of the present invention, the method 200 further include: determine recognition property, wherein recognition property includes dog face
Attribute or dog noseprint attribute；Then, the dog face image to be identified and comparison reference picture are compared according to the recognition property
It is right；According to the recognition property by dog face image to be identified in dog number of elements according to being scanned in the library of bottom.
Wherein, dog noseprint is similar to mankind's fingerprint, will not because of the time passage and influence the shape of lines, every can be become
The unique identifier of dog.It is only compared using dog noseprint progress dog and/or dog only identifies and is conducive to further increase dog identity
The precision of verifying.
According to embodiments of the present invention, step 210 can further include:
Dog face image to be identified is compared with reference picture is compared according to the recognition property, determines dog face to be identified
Image and compare whether reference picture belongs to same dog, comprising:
Feature extraction is carried out respectively to the dog face image to be identified and comparison reference picture according to determining recognition property,
Obtain the feature to be compared of the dog face image to be identified and the fixed reference feature of the comparison reference picture；
It compares the feature to be compared and the fixed reference feature determines dog face image to be identified and whether compares reference picture
Belong to same dog.
Illustratively, according to the recognition property of the determination, the feature to be compared of the dog face image to be identified and described
The fixed reference feature for comparing reference picture can be dog face feature and/or dog noseprint feature.
Wherein, by dog face image to be identified with compare before reference picture is compared, the method 200 further include: obtain
Take the comparison reference picture.
Illustratively, described to obtain the comparison reference picture including acquiring the comparison reference picture and/or sheet in real time
Ground uploads the comparison reference picture.In one embodiment, the acquisition, which compares reference picture, can also receive other data
The comparison reference picture that source is sent.
Illustratively, the comparison feature to be compared and the fixed reference feature determine dog face image to be identified and compare
Whether reference picture belongs to same dog
The feature to be compared is calculated at a distance from the fixed reference feature；
If the distance, which is less than, compares distance threshold, confirm that the dog face image to be identified is with reference picture is compared
Belong to same dog.
Illustratively, the output of the Validation Mode includes: the dog in the image to be compared and comparison reference picture
A possibility that for same dog and/or similarity.Wherein, possibility can use percentage numeral system；Similarity can use percentage
Numeral system or similarity degree, similarity degree include: that height is similar, and moderate is similar or low similar.The possibility or similarity are equal
It can be obtained according to the distance.
Illustratively, the dog face image to be identified and comparison reference picture are carried out respectively according to determining recognition property
Feature extraction, the feature to be compared and the fixed reference feature for comparing reference picture for obtaining the dog face image to be identified include:
By the dog face image to be identified and reference picture input trained feature extraction network model is compared, is obtained
To the feature to be compared of the dog face image to be identified and the fixed reference feature of comparison reference picture.
Illustratively, the method 200 further include: if the feature to be compared is more than at a distance from the fixed reference feature
Distance threshold is compared, then confirm the dog face image to be identified and compares reference picture and is not belonging to same dog.
In one embodiment, as shown in figure 3, Fig. 3, which shows dog according to an embodiment of the present invention, only identifies management method
The exemplary schematic diagram of Validation Mode.Specifically, user select " Validation Mode ", and acquire respectively dog face image to be identified with
Reference picture is compared, " taking pictures in real time " mode or " local to upload " mode can be used in collection process.No matter which kind of is acquired
Mode can only carry out the identification of dog face and/or the identification of dog noseprint to the dog in current picture.If user has seen one before this
Living body dog only, want to verify certain of the dog only and in mobile phone photo album retain photo be same dog only, therefore, first to comparing dog only
Real-time acquisition has been carried out, and has uploaded the photo of dog to be compared only from local.Then by the comparison of dog face and/or dog noseprint ratio
It is right, the similar possibility of the two is given in real time.Similarly, user can also locally upload two dog photos or respectively into
The real-time collecting work of two dogs of row only, to achieve the purpose that dog only compares.
It should be noted that above-mentioned dog, which only compares, can be based on one of the identification of dog face feature or the identification of dog noseprint feature
It carries out, can also identify that dog noseprint feature identification of seeking peace is carried out based on dog face spy simultaneously；When simultaneously based on dog face feature identification and
The identification of dog noseprint feature carries out dog when only comparing, can be dog face image to be identified and compare the dog face feature of reference picture to
The distance between amount and picture to be compared and the distance between the dog noseprint feature vector for comparing picture meet simultaneously be less than or
When equal to comparing distance threshold, confirming the dog face image to be identified and comparing reference picture is to belong to same dog.
According to embodiments of the present invention, step 220 can further include:
Dog face image to be identified is scanned in dog number of elements according to bottom library according to the recognition property, obtains dog face to be identified
The identity identification information of image, comprising:
Feature extraction is carried out to the dog face image to be identified according to determining recognition property and obtains dog face image to be identified
Feature to be identified；
Search is compared according to the multiple template feature in the library of bottom with the dog number of elements based on the feature to be identified, will search
Identity identification information of the identity information corresponding to the template characteristic that rope obtains as dog face image to be identified.
Illustratively, it is compared with the dog number of elements according to the multiple template feature in the library of bottom based on the feature to be identified
It searches for, identity information corresponding to the template characteristic that search is obtained is as the identity identification information packet of dog face image to be identified
It includes:
The feature to be identified is calculated at a distance from the template characteristic；
Using the identity information corresponding to the smallest template characteristic as the identification of dog face image to be identified
Information.
Illustratively, the method 200 further include:
When the feature to be identified is all larger than identification distance threshold at a distance from template characteristic described in each,
By the dog face image to be identified and corresponding identity information typing to data bottom library.
It illustratively, can be to be described wait know when the dog face image to be identified being stored into the dog number of elements according to bottom library
Other dog face image distributes I D number and puts on record in dog database.Not only expand the covering of dog database in this way
Range, and be conducive to search/comparison operation of other users, enrich the data in dog database.
It should be noted that above-mentioned search pattern can be based on one of the identification of dog face feature or the identification of dog noseprint feature
It carries out, can also be carried out simultaneously based on the identification of dog face feature and the identification of dog noseprint feature；When simultaneously based on dog face feature identification and
When dog noseprint feature identification progress dog only identifies, the dog face of base map in the dog face feature vector of dog face picture to be identified and bottom library
The dog noseprint feature of base map in the distance between feature vector and the dog noseprint feature vector of dog face picture to be identified and bottom library
When the distance between vector while satisfaction are less than or equal to comparison distance threshold, confirm the dog recognition result for described in simultaneously
Meet the base map and/or base map I D of above-mentioned condition.
In one embodiment, as shown in figure 4, Fig. 4, which shows dog according to an embodiment of the present invention, only identifies management method
Exemplary schematic diagram.Specifically, user select " search pattern ", and by dog to be searched be merely placed at mobile phone camera it
Before.At this point, acquisition current picture, and the identification of dog face and authentication are only carried out to the dog in current picture.Specifically, once
It detects that there are dog face information in current picture, then carries out feature extraction and obtain corresponding dog face feature vector and/or dog noseprint
Feature vector is retrieved in well-established dog database based on the dog face feature vector and/or dog noseprint feature vector
The identity of the dog only, the identification result (such as dog image and/or dog I D) of dog described in rapid feedback only, and to user
It shows.Similarly, if user uploads dog face photo to be identified by local upper arq mode, user query knot can also be timely feedbacked
Fruit.
In one embodiment, as shown in figure 5, Fig. 5, which shows dog according to an embodiment of the present invention, only identifies management method
Exemplary schematic diagram.Specifically, user select " search pattern ", and by dog to be searched be merely placed at mobile phone camera it
Before.At this point, acquisition current picture, only carries out the identification of dog face and authentication to the dog in current picture；However when in dog number of elements
When according to not searching the identification result of the dog only in library, guidance user only carries out supplement record to the dog of current acquisition shooting
Enter, once typing success, then only distribute I D number for the dog and put on record in dog database, to expand dog only
The coverage area of database and the search/comparison operation for being conducive to other users, enrich the data in dog database.Together
Reason, if user uploads dog photo by local upper arq mode, user query can also be timely feedbacked as a result, and assist user into
Typing work of the row without search result dog only.
In one embodiment, as shown in fig. 6, Fig. 6, which shows dog according to an embodiment of the present invention, only identifies management method
Exemplary schematic diagram.Specifically, user selects " search pattern ", and dog to be searched is merely placed at the included network of computer
Before camera.At this point, only carrying out the identification of dog face and authentication to the dog in current picture.Once detecting in current picture
There are dog face information, then carry out feature extraction by the dog face image to be identified and obtain corresponding feature vector；Based on corresponding
Feature vector retrieve the identity of the dog only in well-established dog database, rapid feedback search result, and to user
It shows.Similarly, if user uploads dog photo by local upper arq mode, user query result can also be timely feedbacked.
It follows that dog according to an embodiment of the present invention only identifies management method, can be used for supporting acquired, is registered
A variety of dog pictures source management, and dog face and/or dog noseprint analysis module is assisted to complete real-time retrieval, dog only compares or body
The precision of part verifying, can be widely applied to various occasions and scene, greatly improves the reliability that dog only identifies.
In one embodiment, as shown in fig. 7, only identifying that management method is deployed in mobile phone with the dog of the embodiment of the present invention
Specific example on APP is come to being specifically described.Fig. 7 shows dog according to an embodiment of the present invention and only identifies management method
Exemplary schematic diagram.
Firstly, user opens App, selection operation mode: Validation Mode or search pattern (i.e. dog only identifies).Wherein, right
In Validation Mode, in order to realize that 1:1 dog is only verified, that is, provide two dog images and be judged as whether being same dog.
For search pattern (i.e. dog only identifies), in order to realize that 1:n dog is only retrieved, i.e., find given figure in dog database
Dog identity information as in registers in real time if not having, improves dog database.
It is then determined user needs to select real-time photographing mode or local upper arq mode, at this time system meeting after operation mode
It identifies the dog face and face feature of picture of the picture captured/locally upload, and provides Recognition feedback result.Wherein, in real time
Photographing mode has the function of " camera lens candid photograph ", its purpose is that user is assisted to grab the movement and expression of dog only.Only using dog
Face detection, camera lens can collect the current attribute of dog face in real time, once angle, light, position suitable, system are automatic
It presses shutter key and saves current collected picture, this can fill up the loophole of human eye, person's development speed to a certain extent
Time, preferably help user grab desired photo.
Wherein, when selecting operation mode is Validation Mode, real-time photographing mode or locally upper arq mode determine to be compared
Picture and comparison picture；Based on the images to be recognized and reference picture progress feature extraction is compared, obtains the dog to be identified
The feature to be compared of face image and the fixed reference feature for comparing reference picture calculate the feature to be compared and described with reference to special
The distance of sign confirms the dog face image to be identified and compares reference picture if the distance, which is less than, compares distance threshold
It is to belong to same dog.
When selecting operation mode is search pattern, dog to be identified is determined using real-time photographing mode or local upper arq mode
Face image；Feature extraction is carried out based on the images to be recognized, obtains feature to be identified；According to the feature to be identified in dog
It is scanned in database, calculates the feature to be identified at a distance from multiple template characteristics in dog database；It will
The identity identification information of the identity information as dog face image to be identified corresponding to the smallest template characteristic；When described
When feature to be identified is all larger than identification distance threshold at a distance from template characteristic described in each, by the dog face image to be identified
And corresponding identity information typing to the dog number of elements according to bottom library, to enrich the dog database.
In next step, final process result interaction is completed into this processing operation to display terminal.
Finally, judging whether to terminate application, application is exited if terminating application；Continuation is returned if not terminating to apply
Judge the dog face image to be identified with the presence or absence of dog face.
Fig. 8 shows the schematic block diagram that dog according to an embodiment of the present invention only identifies managing device 800.As shown in figure 8,
Dog according to an embodiment of the present invention only identifies that managing device 800 includes:
Image collection module 810, for obtaining dog face image to be identified；
Pattern recognition module 820, for determining that recognition mode, the recognition mode include: Validation Mode and search pattern；
Authentication module 830 determines dog face to be identified for dog face image to be identified to be compared with reference picture is compared
Image compares whether reference picture belongs to same dog with described；
Search module 840 obtains dog face to be identified for scanning for dog face image to be identified according to bottom library in dog number of elements
The identity information of image.
Dog according to an embodiment of the present invention only identifies managing device, and dog identity both may be implemented based on different recognition modes
Verifying determines that dog face image to be identified compares whether reference picture belongs to same dog with described, and can be realized identity search,
Dog management method providing system, meeting more demands is easy to operate, and recognition result is accurate.
According to embodiments of the present invention, image collection module 810 can further include:
Real-time acquisition module 811, for implementing acquisition image data；
Local uploading module 812 uploads image data for local；
Framing module 813, for being carried out to the video data in the image data implementing acquisition and/or locally uploading
Video image framing；
Dog face detection module 814 generates dog face image to be identified for carrying out the detection of dog face to every frame image.
According to embodiments of the present invention, dog face, which obtains module 810, to further include:
Image receiver module 815, for receiving the image data of other data sources.
Illustratively, the real-time acquisition module 811 is also used to: the environment attribute of acquisition dog only in real time；When the environment
Attribute meets scheduled acquisition when requiring, dog face image described in automatic collection.
Wherein, environment attribute includes the shooting angle of the dog only, shoots light, at least one of camera site.This
Sample can fill up the loophole time of human eye, person's development speed to a certain extent, and preferably help user, which grabs, collects
The image of high quality is as identification basis.Because the image based on high quality reduces the noise in image processing process, favorably
In the accuracy for further increasing the dog and only comparing or identify.
According to embodiments of the present invention, the dog only identifies managing device 800 further include:
Recognition property module 850, for determining recognition property, wherein recognition property includes dog face attribute or dog noseprint category
Property；Then, the dog face image to be identified and comparison reference picture are compared according to the recognition property；According to the identification
Attribute is by dog face image to be identified in dog number of elements according to scanning in the library of bottom.
Wherein, dog noseprint is similar to mankind's fingerprint, will not because of the time passage and influence the shape of lines, every can be become
The unique identifier of dog.It is only compared using dog noseprint progress dog and/or dog only identifies and is conducive to further increase dog identity
The precision of verifying.
According to embodiments of the present invention, the dog only identifies managing device 800 further include:
Characteristic extracting module 860, for the dog face image to be identified and/or comparing ginseng according to determining recognition property
It examines image and carries out feature extraction respectively, the feature to be compared for obtaining the dog face image to be identified and/or the comparison are with reference to figure
The fixed reference feature of picture.
Illustratively, the characteristic extracting module 860 can be further used for:
It is according to the recognition property that the dog face image to be identified and/or comparison reference picture input is trained
Feature extraction network model obtains the feature to be compared of the dog face image to be identified and/or compares the reference spy of reference picture
Sign.
Illustratively, according to the recognition property of the determination, the feature to be compared of the dog face image to be identified and described
The fixed reference feature for comparing reference picture can be dog face feature and/or dog noseprint feature.
Illustratively, authentication module 830 can be further used for:
It compares the feature to be compared and the fixed reference feature determines dog face image to be identified and whether compares reference picture
Belong to same dog.
Wherein, by dog face image to be identified with compare before reference picture is compared, described image obtains module 810 also
For: obtain the comparison reference picture.
Illustratively, described image obtains module 810 and can also be further used for acquiring the comparison reference picture in real time
And/or the local upload comparison reference picture.In one embodiment, image receiver module 815 is also used to receive other numbers
The comparison reference picture sent according to source.
Illustratively, authentication module 830 can further include:
Computing module 831 is verified, for calculating the feature to be compared at a distance from the fixed reference feature；
Judgment module 832 is verified, distance threshold is compared if be less than for the distance, confirms the dog face to be identified
Image and to compare reference picture be to belong to same dog.
Illustratively, verifying judgment module 832 is also used to: if the feature to be compared is at a distance from the fixed reference feature
More than comparing distance threshold, then confirm the dog face image to be identified and compare reference picture and be not belonging to same dog.
Illustratively, the output result of the Validation Mode includes: the dog face image to be identified and compares reference picture
A possibility that belonging to same dog and/or similarity.Wherein, possibility can use percentage numeral system；Similarity can use hundred
Score system or similarity degree, similarity degree include: that height is similar, and moderate is similar or low similar.The possibility or similarity
It can be obtained according to the distance.
According to embodiments of the present invention, described search module 840 is to be further used for:
Search is compared according to the multiple template feature in the library of bottom with the dog number of elements based on the feature to be identified, will search
Identity identification information of the identity information corresponding to the template characteristic that rope obtains as dog face image to be identified.
Illustratively, described device 800 may further include:
Dog Registration Module 870, for being all larger than at a distance from template characteristic described in each when the feature to be identified
When identifying distance threshold, by the dog face image to be identified and corresponding identity information typing to data bottom library.
Illustratively, the dog Registration Module 870 is also used to: the dog face image to be identified is stored into the dog only
When the library of bottom, I D number is distributed for the dog face picture to be identified and is put on record in dog database.Not only expand in this way
The coverage area of dog database, and be conducive to search/comparison operation of other users, enrich the number in dog database
According to.
Those of ordinary skill in the art may be aware that list described in conjunction with the examples disclosed in the embodiments of the present disclosure
Member and algorithm steps can be realized with the combination of electronic hardware or computer software and electronic hardware.These functions are actually
It is implemented in hardware or software, the specific application and design constraint depending on technical solution.Professional technician
Each specific application can be used different methods to achieve the described function, but this realization is it is not considered that exceed
The scope of the present invention.
Fig. 9 shows the schematic block diagram of dog identification and management system 900 according to an embodiment of the present invention.Dog only identifies pipe
Reason system 900 includes imaging sensor 910, storage device 920 and processor 930.
Imaging sensor 910 is for acquiring image data.
The storage of storage device 920 only identifies corresponding in management method for realizing dog according to an embodiment of the present invention
The program code of step.
The processor 930 is for running the program code stored in the storage device 920, to execute according to the present invention
The dog of embodiment only identifies the corresponding steps of management method, and only identifies management for realizing dog according to an embodiment of the present invention
Image collection module 810 in device, pattern recognition module 820, authentication module 830 and search module 840.
In addition, according to embodiments of the present invention, additionally providing a kind of storage medium, storing program on said storage
Instruction only identifies manager for executing the dog of the embodiment of the present invention when described program instruction is run by computer or processor
The corresponding steps of method, and only identify for realizing dog according to an embodiment of the present invention corresponding module in managing device.It is described
Storage medium for example may include the hard disk, read-only of the storage card of smart phone, the storage unit of tablet computer, personal computer
Memory (ROM), Erasable Programmable Read Only Memory EPROM (EPROM), portable compact disc read-only memory (CD-ROM), USB
Any combination of memory or above-mentioned storage medium.The computer readable storage medium can be one or more calculating
Any combination of machine readable storage medium storing program for executing, such as a computer readable storage medium include for being randomly generated action command
The computer-readable program code of sequence, another computer readable storage medium include only to identify management for carrying out dog
Computer-readable program code.
In one embodiment, the computer program instructions may be implemented real according to the present invention when being run by computer
The dog for applying example only identifies each functional module of managing device, and/or can execute dog according to an embodiment of the present invention only
Identify management method.
Each module in dog identification and management system according to an embodiment of the present invention can be by according to embodiments of the present invention
Dog only identify that the processor computer program instructions that store in memory of operation of the electronic equipment of management are realized, or
The computer instruction that can be stored in the computer readable storage medium of computer program product according to an embodiment of the present invention
Realization when being run by computer.
Dog according to an embodiment of the present invention only identifies management method, device, system and storage medium, is identified by dog face
Technology and dog noseprint identification technology realize that Millisecond dog only compares, dog only identifies, easy to operate, recognition result is accurate.
Although describing example embodiment by reference to attached drawing here, it should be understood that above example embodiment are only exemplary
, and be not intended to limit the scope of the invention to this.Those of ordinary skill in the art can carry out various changes wherein
And modification, it is made without departing from the scope of the present invention and spiritual.All such changes and modifications are intended to be included in appended claims
Within required the scope of the present invention.
Those of ordinary skill in the art may be aware that list described in conjunction with the examples disclosed in the embodiments of the present disclosure
Member and algorithm steps can be realized with the combination of electronic hardware or computer software and electronic hardware.These functions are actually
It is implemented in hardware or software, the specific application and design constraint depending on technical solution.Professional technician
Each specific application can be used different methods to achieve the described function, but this realization is it is not considered that exceed
The scope of the present invention.
In several embodiments provided herein, it should be understood that disclosed device and method can pass through it
Its mode is realized.For example, apparatus embodiments described above are merely indicative, for example, the division of the unit, only
Only a kind of logical function partition, there may be another division manner in actual implementation, such as multiple units or components can be tied
Another equipment is closed or is desirably integrated into, or some features can be ignored or not executed.
In the instructions provided here, numerous specific details are set forth.It is to be appreciated, however, that implementation of the invention
Example can be practiced without these specific details.In some instances, well known method, structure is not been shown in detail
And technology, so as not to obscure the understanding of this specification.
Similarly, it should be understood that in order to simplify the present invention and help to understand one or more of the various inventive aspects,
To in the description of exemplary embodiment of the present invention, each feature of the invention be grouped together into sometimes single embodiment, figure,
Or in descriptions thereof.However, the method for the invention should not be construed to reflect an intention that i.e. claimed
The present invention claims features more more than feature expressly recited in each claim.More precisely, such as corresponding power
As sharp claim reflects, inventive point is that the spy of all features less than some disclosed single embodiment can be used
Sign is to solve corresponding technical problem.Therefore, it then follows thus claims of specific embodiment are expressly incorporated in this specific
Embodiment, wherein each, the claims themselves are regarded as separate embodiments of the invention.
It will be understood to those skilled in the art that any combination pair can be used other than mutually exclusive between feature
All features disclosed in this specification (including adjoint claim, abstract and attached drawing) and so disclosed any method
Or all process or units of equipment are combined.Unless expressly stated otherwise, this specification (is wanted including adjoint right
Ask, make a summary and attached drawing) disclosed in each feature can be replaced with an alternative feature that provides the same, equivalent, or similar purpose.
In addition, it will be appreciated by those of skill in the art that although some embodiments described herein include other embodiments
In included certain features rather than other feature, but the combination of the feature of different embodiments mean it is of the invention
Within the scope of and form different embodiments.For example, in detail in the claims, embodiment claimed it is one of any
Can in any combination mode come using.
Various component embodiments of the invention can be implemented in hardware, or to run on one or more processors
Software module realize, or be implemented in a combination thereof.It will be understood by those of skill in the art that can be used in practice
Microprocessor or digital signal processor (DSP) realize some moulds in article analytical equipment according to an embodiment of the present invention
The some or all functions of block.The present invention is also implemented as a part or complete for executing method as described herein
The program of device (for example, computer program and computer program product) in portion.It is such to realize that program of the invention can store
On a computer-readable medium, it or may be in the form of one or more signals.Such signal can be from internet
Downloading obtains on website, is perhaps provided on the carrier signal or is provided in any other form.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and ability
Field technique personnel can be designed alternative embodiment without departing from the scope of the appended claims.In the claims,
Any reference symbol between parentheses should not be configured to limitations on claims.Word "comprising" does not exclude the presence of not
Element or step listed in the claims.Word "a" or "an" located in front of the element does not exclude the presence of multiple such
Element.The present invention can be by means of including the hardware of several different elements and being come by means of properly programmed computer real
It is existing.In the unit claims listing several devices, several in these devices can be through the same hardware branch
To embody.The use of word first, second, and third does not indicate any sequence.These words can be explained and be run after fame
Claim.
The above description is merely a specific embodiment or to the explanation of specific embodiment, protection of the invention
Range is not limited thereto, and anyone skilled in the art in the technical scope disclosed by the present invention, can be easily
Expect change or replacement, should be covered by the protection scope of the present invention.Protection scope of the present invention should be with claim
Subject to protection scope.
Claims (10)
1. a kind of dog only identifies management method, which is characterized in that the described method includes:
Dog face image to be identified is obtained, and determines recognition mode, recognition mode includes: Validation Mode and search pattern；
Under Validation Mode, dog face image to be identified is compared with reference picture is compared, determine dog face image to be identified with
Whether the comparison reference picture belongs to same dog；
Under search pattern, dog face image to be identified is scanned in dog number of elements according to bottom library, dog face image to be identified is obtained
Identity information.
2. the method as described in claim 1, which is characterized in that the method also includes: determine recognition property, wherein identification
Attribute includes dog face attribute or dog noseprint attribute；Then, ginseng by the dog face image to be identified and is compared according to the recognition property
Image is examined to be compared；According to the recognition property by dog face image to be identified in dog number of elements according to being scanned in the library of bottom.
3. method according to claim 2, which is characterized in that according to the recognition property by dog face image to be identified with compare
Reference picture is compared, and determines dog face image to be identified and compares whether reference picture belongs to same dog, comprising:
According to determining recognition property feature extraction is carried out to the dog face image to be identified and comparison reference picture respectively, obtained
The feature to be compared of the dog face image to be identified and the fixed reference feature for comparing reference picture；
It compares the feature to be compared and the fixed reference feature determines dog face image to be identified and compares whether reference picture belongs to
Same dog.
4. method as claimed in claim 3, which is characterized in that than it is described to feature to be compared and the fixed reference feature determine to
It identifies dog face image and compares whether reference picture belongs to same dog, comprising:
The feature to be compared is calculated at a distance from the fixed reference feature；
If the distance, which is less than, compares distance threshold, confirm that the dog face image to be identified with reference picture is compared is to belong to
Same dog.
5. method according to claim 2, which is characterized in that according to the recognition property by dog face image to be identified in dog
Data bottom library scans for, and obtains the identity identification information of dog face image to be identified, comprising:
According to determining recognition property to the dog face image to be identified carry out feature extraction obtain dog face image to be identified to
Identification feature；
Search is compared according to the multiple template feature in the library of bottom with the dog number of elements based on the feature to be identified, will search for
Identity identification information of the identity information corresponding to the template characteristic arrived as dog face image to be identified.
6. method as claimed in claim 5, which is characterized in that based on the feature to be identified and the dog number of elements according in the library of bottom
Multiple template feature search is compared, obtain the identity identification information of dog face image to be identified, comprising:
The feature to be identified is calculated at a distance from the template characteristic；
Using the identity information corresponding to the smallest template characteristic as the identity identification information of dog face image to be identified.
7. method as claimed in claim 6, which is characterized in that the method also includes:
When the feature to be identified is all larger than identification distance threshold at a distance from template characteristic described in each, by described wait know
Other dog face image and corresponding identity information typing are to data bottom library.
8. a kind of dog only identifies managing device, which is characterized in that described device includes:
Dog face obtains module, for obtaining dog face image to be identified；
Pattern recognition module, for determining that recognition mode, the recognition mode include: Validation Mode and search pattern；
Authentication module, for dog face image to be identified to be compared with reference picture is compared, determine dog face image to be identified with
Whether the comparison reference picture belongs to same dog；
Search module obtains dog face image to be identified for scanning for dog face image to be identified according to bottom library in dog number of elements
Identity information.
9. a kind of dog identification and management system, including memory, processor and it is stored on the memory and in the processing
The computer program run on device, which is characterized in that the processor realized when executing the computer program claim 1 to
The step of any one of 7 the method.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of any one of claims 1 to 7 the method is realized when being computer-executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811628347.5A CN109829381A (en) | 2018-12-28 | 2018-12-28 | A kind of dog only identifies management method, device, system and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811628347.5A CN109829381A (en) | 2018-12-28 | 2018-12-28 | A kind of dog only identifies management method, device, system and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109829381A true CN109829381A (en) | 2019-05-31 |
Family
ID=66861410
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811628347.5A Pending CN109829381A (en) | 2018-12-28 | 2018-12-28 | A kind of dog only identifies management method, device, system and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109829381A (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110414390A (en) * | 2019-07-13 | 2019-11-05 | 恒大智慧科技有限公司 | Canine recognition methods, system and readable storage medium storing program for executing in a kind of community |
| CN110765323A (en) * | 2019-10-24 | 2020-02-07 | 武汉菲旺软件技术有限责任公司 | Community pet dog identification method, device, equipment and medium |
| CN111144378A (en) * | 2019-12-30 | 2020-05-12 | 众安在线财产保险股份有限公司 | Target object identification method and device |
| CN111191066A (en) * | 2019-12-23 | 2020-05-22 | 厦门快商通科技股份有限公司 | Image recognition-based pet identity recognition method and device |
| CN111259832A (en) * | 2020-01-20 | 2020-06-09 | 上海依图网络科技有限公司 | Identification method, identification device, machine readable medium and system for dog |
| CN111291641A (en) * | 2020-01-20 | 2020-06-16 | 上海依图网络科技有限公司 | Image recognition method and device, computer readable medium and system |
| CN111310703A (en) * | 2020-02-26 | 2020-06-19 | 深圳市巨星网络技术有限公司 | Identity recognition method, device, equipment and medium based on convolutional neural network |
| CN112329573A (en) * | 2020-10-27 | 2021-02-05 | 苏州中科先进技术研究院有限公司 | Cat nasal print recognition method and device based on cat nasal print feature extraction model |
| CN112329575A (en) * | 2020-10-27 | 2021-02-05 | 苏州中科先进技术研究院有限公司 | Nose print detection method and device based on image quality evaluation |
| CN112784741A (en) * | 2021-01-21 | 2021-05-11 | 宠爱王国(北京)网络科技有限公司 | Pet identity recognition method and device and nonvolatile storage medium |
| CN112784742A (en) * | 2021-01-21 | 2021-05-11 | 宠爱王国(北京)网络科技有限公司 | Extraction method and device of nose print features and nonvolatile storage medium |
| WO2021103707A1 (en) * | 2019-11-25 | 2021-06-03 | 支付宝(杭州)信息技术有限公司 | Identity identification method and device for house animals |
| CN113722522A (en) * | 2021-09-02 | 2021-11-30 | 四川楠水农牧科技有限公司 | Cattle uniqueness identification method, terminal and readable storage medium |
| CN115546838A (en) * | 2022-10-20 | 2022-12-30 | 星宠王国(北京)科技有限公司 | Wedding system and method based on dog face image recognition technology |
| CN115587896A (en) * | 2022-10-13 | 2023-01-10 | 星宠王国(北京)科技有限公司 | Dog medical insurance data processing method, device and equipment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101271521A (en) * | 2008-05-13 | 2008-09-24 | 清华大学 | Human face recognition method based on anisotropic double-tree complex wavelet package transforms |
| CN102436578A (en) * | 2012-01-16 | 2012-05-02 | 宁波江丰生物信息技术有限公司 | Formation method for dog face characteristic detector as well as dog face detection method and device |
| CN202230509U (en) * | 2011-06-24 | 2012-05-23 | 常州锐驰电子科技有限公司 | Face identification data management system |
| CN107808118A (en) * | 2017-09-28 | 2018-03-16 | 平安科技（深圳）有限公司 | Personal identification method, electronic installation and computer-readable recording medium |
| CN108875341A (en) * | 2018-05-24 | 2018-11-23 | 北京旷视科技有限公司 | A kind of face unlocking method, device, system and computer storage medium |
| CN108921026A (en) * | 2018-06-01 | 2018-11-30 | 平安科技（深圳）有限公司 | Recognition methods, device, computer equipment and the storage medium of animal identification |
-
2018
- 2018-12-28 CN CN201811628347.5A patent/CN109829381A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101271521A (en) * | 2008-05-13 | 2008-09-24 | 清华大学 | Human face recognition method based on anisotropic double-tree complex wavelet package transforms |
| CN202230509U (en) * | 2011-06-24 | 2012-05-23 | 常州锐驰电子科技有限公司 | Face identification data management system |
| CN102436578A (en) * | 2012-01-16 | 2012-05-02 | 宁波江丰生物信息技术有限公司 | Formation method for dog face characteristic detector as well as dog face detection method and device |
| CN107808118A (en) * | 2017-09-28 | 2018-03-16 | 平安科技（深圳）有限公司 | Personal identification method, electronic installation and computer-readable recording medium |
| CN108875341A (en) * | 2018-05-24 | 2018-11-23 | 北京旷视科技有限公司 | A kind of face unlocking method, device, system and computer storage medium |
| CN108921026A (en) * | 2018-06-01 | 2018-11-30 | 平安科技（深圳）有限公司 | Recognition methods, device, computer equipment and the storage medium of animal identification |
Non-Patent Citations (1)
| Title |
|---|
| 斯坦利•科伦: "《狗智慧 他们在想什么？》", 31 July 2018 * |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110414390A (en) * | 2019-07-13 | 2019-11-05 | 恒大智慧科技有限公司 | Canine recognition methods, system and readable storage medium storing program for executing in a kind of community |
| CN110765323A (en) * | 2019-10-24 | 2020-02-07 | 武汉菲旺软件技术有限责任公司 | Community pet dog identification method, device, equipment and medium |
| WO2021103707A1 (en) * | 2019-11-25 | 2021-06-03 | 支付宝(杭州)信息技术有限公司 | Identity identification method and device for house animals |
| CN111191066A (en) * | 2019-12-23 | 2020-05-22 | 厦门快商通科技股份有限公司 | Image recognition-based pet identity recognition method and device |
| CN111144378A (en) * | 2019-12-30 | 2020-05-12 | 众安在线财产保险股份有限公司 | Target object identification method and device |
| CN111144378B (en) * | 2019-12-30 | 2023-10-31 | 众安在线财产保险股份有限公司 | Target object identification method and device |
| CN111291641B (en) * | 2020-01-20 | 2024-02-27 | 上海依图网络科技有限公司 | Image recognition method and device, computer readable medium and system |
| CN111259832B (en) * | 2020-01-20 | 2023-05-02 | 上海依图网络科技有限公司 | Method, device, machine-readable medium and system for identifying dogs |
| CN111291641A (en) * | 2020-01-20 | 2020-06-16 | 上海依图网络科技有限公司 | Image recognition method and device, computer readable medium and system |
| CN111259832A (en) * | 2020-01-20 | 2020-06-09 | 上海依图网络科技有限公司 | Identification method, identification device, machine readable medium and system for dog |
| CN111310703A (en) * | 2020-02-26 | 2020-06-19 | 深圳市巨星网络技术有限公司 | Identity recognition method, device, equipment and medium based on convolutional neural network |
| CN111310703B (en) * | 2020-02-26 | 2022-06-03 | 深圳市巨星网络技术有限公司 | Identity recognition method, device, equipment and medium based on convolutional neural network |
| CN112329573A (en) * | 2020-10-27 | 2021-02-05 | 苏州中科先进技术研究院有限公司 | Cat nasal print recognition method and device based on cat nasal print feature extraction model |
| CN112329575A (en) * | 2020-10-27 | 2021-02-05 | 苏州中科先进技术研究院有限公司 | Nose print detection method and device based on image quality evaluation |
| WO2022088626A1 (en) * | 2020-10-27 | 2022-05-05 | 苏州中科先进技术研究院有限公司 | Cat nose print identification method and apparatus based on cat nose print feature extraction model |
| CN112784742A (en) * | 2021-01-21 | 2021-05-11 | 宠爱王国(北京)网络科技有限公司 | Extraction method and device of nose print features and nonvolatile storage medium |
| CN112784741A (en) * | 2021-01-21 | 2021-05-11 | 宠爱王国(北京)网络科技有限公司 | Pet identity recognition method and device and nonvolatile storage medium |
| CN112784742B (en) * | 2021-01-21 | 2024-06-18 | 宠爱王国(北京)网络科技有限公司 | Nose pattern feature extraction method and device and nonvolatile storage medium |
| CN113722522A (en) * | 2021-09-02 | 2021-11-30 | 四川楠水农牧科技有限公司 | Cattle uniqueness identification method, terminal and readable storage medium |
| CN115587896A (en) * | 2022-10-13 | 2023-01-10 | 星宠王国(北京)科技有限公司 | Dog medical insurance data processing method, device and equipment |
| CN115587896B (en) * | 2022-10-13 | 2023-08-11 | 星宠王国(北京)科技有限公司 | Method, device and equipment for processing canine medical insurance data |
| CN115546838A (en) * | 2022-10-20 | 2022-12-30 | 星宠王国(北京)科技有限公司 | Wedding system and method based on dog face image recognition technology |
| CN115546838B (en) * | 2022-10-20 | 2023-11-24 | 星宠王国(北京)科技有限公司 | Wedding system and method based on dog face image recognition technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109829381A (en) | A kind of dog only identifies management method, device, system and storage medium | |
| CN106407914B (en) | Method and device for detecting human face and remote teller machine system | |
| CN109117714A (en) | A kind of colleague's personal identification method, apparatus, system and computer storage medium | |
| CN106599772B (en) | Living body verification method and device and identity authentication method and device | |
| CN109886078B (en) | Retrieval positioning method and device for target object | |
| WO2019127273A1 (en) | Multi-person face detection method, apparatus, server, system, and storage medium | |
| CN108269333A (en) | Face identification method, application server and computer readable storage medium | |
| CN106803289A (en) | A kind of false proof method and system of registering of intelligent mobile | |
| CN108875476B (en) | Automatic near-infrared face registration and recognition method, device and system and storage medium | |
| CN110709854A (en) | Identity information security monitoring method and system | |
| US9633272B2 (en) | Real time object scanning using a mobile phone and cloud-based visual search engine | |
| CN108846912A (en) | Work attendance method, terminal and server | |
| CN108881813A (en) | A kind of video data handling procedure and device, monitoring system | |
| CN108875509A (en) | Biopsy method, device and system and storage medium | |
| CN109598251A (en) | Testimony of a witness checking method, device, equipment and system and storage medium | |
| CN110765851A (en) | Registration method, device and equipment | |
| CN109618100A (en) | Judgment method, the apparatus and system of image is taken on site | |
| CN109857891A (en) | A kind of querying method and device | |
| CN110287867A (en) | Unmanned convenience store enters recognition methods, device, equipment and storage medium | |
| CN111291912A (en) | Number taking method, number taking machine and number taking system using witness verification | |
| CN110263830B (en) | Image processing method, device and system and storage medium | |
| CN110992500A (en) | Attendance checking method and device, storage medium and server | |
| JP2013046135A (en) | Image providing apparatus, image utilization apparatus, image providing system, image providing method, and computer program | |
| CN109583296A (en) | One kind preventing error detection method, apparatus, system and computer storage medium | |
| CN112307817B (en) | Face living body detection method, device, computing equipment and computer 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 |