CN110298230A - Silent biopsy method, device, computer equipment and storage medium - Google Patents
Silent biopsy method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN110298230A CN110298230A CN201910372163.5A CN201910372163A CN110298230A CN 110298230 A CN110298230 A CN 110298230A CN 201910372163 A CN201910372163 A CN 201910372163A CN 110298230 A CN110298230 A CN 110298230A
- Authority
- CN
- China
- Prior art keywords
- convolutional neural
- neural networks
- image data
- data
- deep learning
- 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
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000001574 biopsy Methods 0.000 title claims abstract description 24
- 238000001514 detection method Methods 0.000 claims abstract description 97
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 96
- 238000012549 training Methods 0.000 claims abstract description 48
- 238000001727 in vivo Methods 0.000 claims abstract description 43
- 238000013136 deep learning model Methods 0.000 claims abstract description 36
- 241001269238 Data Species 0.000 claims abstract description 12
- 238000013135 deep learning Methods 0.000 claims abstract description 11
- 230000006870 function Effects 0.000 claims description 39
- 238000004590 computer program Methods 0.000 claims description 22
- 238000000926 separation method Methods 0.000 claims description 6
- 238000013528 artificial neural network Methods 0.000 claims description 5
- 238000013481 data capture Methods 0.000 claims description 3
- 238000007689 inspection Methods 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 9
- 230000000875 corresponding effect Effects 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 108010001267 Protein Subunits Proteins 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- 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
- G06V40/172—Classification, e.g. identification
-
- 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
- G06V40/40—Spoof detection, e.g. liveness detection
- G06V40/45—Detection of the body part being alive
Abstract
The present invention relates to silent biopsy method, device, computer equipment and storage medium, this method includes obtaining multiple image datas；Face datection is carried out to image data, to obtain Preliminary detection result；Judge in Preliminary detection result whether to be with the presence of face；If so, In vivo detection is carried out to image data using convolutional neural networks deep learning model, to obtain secondary detection result；Judge whether secondary detection result meets setting condition；If so, image data is exported to terminal, so that image data is shown in terminal.The present invention uses CAFFE deep learning framework establishment convolutional neural networks, and the convolutional neural networks become convolutional neural networks deep learning model using the training of great amount of samples data, silent In vivo detection can be carried out using the convolutional neural networks deep learning model, realize that In vivo detection is more accurate, it is quicker to detect speed, model lightweight makes model be easier to promote.
Description
Technical field
The present invention relates to biopsy methods, more specifically refer to silent biopsy method, device, computer equipment
And storage medium.
Background technique
In vivo detection refers to that user makes corresponding movement according to system instruction, prevents user from using under some important environment
Photo out-trick system complete verifying.User according to system prompt complete corresponding actions after, from the background to user complete movement into
Row identification, and prompt whether user's In vivo detection passes through.
In vivo detection important events of opening an account etc. in social security, on the net have its application.Determine that the elderly's identity is true by verifying
It just can be carried out getting for old-age pension after real and alive.User's checking is needed when opening an account on the net, it was demonstrated that and non-user is completed with photo
Verifying, to guarantee the true, effectively and safely of user information.
Existing accurate In vivo detection model, mostly movement formula In vivo detection, user's interaction are unfriendly；It is existing
Having silent In vivo detection system is mostly monocular In vivo detection, and detection time is long, and accuracy rate is lower, is easy to be attacked.
Therefore, it is necessary to design a kind of new method, realize that In vivo detection is more accurate, detection speed is quicker, mould
Type lightweight makes model be easier to promote.
Summary of the invention
It is an object of the invention to overcome the deficiencies of existing technologies, silent biopsy method, device, computer are provided and set
Standby and storage medium.
To achieve the above object, the invention adopts the following technical scheme: silent biopsy method, comprising:
Obtain multiple image datas；
Face datection is carried out to image data, to obtain Preliminary detection result；
Judge in the Preliminary detection result whether to be with the presence of face；
If so, In vivo detection is carried out to image data using convolutional neural networks deep learning model, it is secondary to obtain
Testing result；
Judge whether the secondary detection result meets setting condition；
If so, described image data are exported to terminal, so that image data is shown in terminal.
Its further technical solution are as follows: described multiple image datas of acquisition, comprising:
Image data is obtained using RGB binocular camera.
Its further technical solution are as follows: the convolutional neural networks deep learning model is high by multiple groups true man and personage
Clear picture data is as the resulting model of training data training convolutional neural networks.
Its further technical solution are as follows: the convolutional neural networks deep learning model is high by multiple groups true man and personage
Clear picture data is as the resulting model of training data training convolutional neural networks, comprising:
Multiple groups true man and personage's high definition picture data are obtained, to obtain sample data；
Use CAFFE deep learning framework establishment convolutional neural networks；
Two classification based trainings are carried out to sample data using convolutional neural networks, to obtain classification and loss function；
Judge the loss function whether within the set range；
If it is not, then using the parameter of loss function and sample data adjustment convolutional neural networks, and return to the utilization
Convolutional neural networks carry out two classification based trainings to sample data, to obtain classification and loss function；
If so, using current convolutional neural networks as convolutional neural networks deep learning model.
Its further technical solution are as follows: it is described that two classification based trainings are carried out to sample data using convolutional neural networks, with
To classification and loss function, comprising:
Convolution and/or point separation convolution is separated using the depth of convolutional neural networks to instruct two classification of sample data progress
Practice, to obtain loss function.
Its further technical solution are as follows: described to judge in the Preliminary detection result whether to be gone back with the presence of after face
Include:
If it is not, then entering end step.
The present invention also provides silent living body detection devices, comprising:
Data capture unit, for obtaining multiple image datas；
Face datection unit, for carrying out Face datection to image data, to obtain Preliminary detection result；
First judging unit, for judging in the Preliminary detection result whether to be with the presence of face；
In vivo detection unit, for if so, being lived using convolutional neural networks deep learning model to image data
Physical examination is surveyed, to obtain secondary detection result；
Second judgment unit, for judging whether the secondary detection result meets setting condition；
Data outputting unit, for if so, described image data are exported to terminal, so that image data is aobvious in terminal
Show.
The present invention also provides a kind of computer equipment, the computer equipment includes memory and processor, described to deposit
Computer program is stored on reservoir, the processor realizes above-mentioned method when executing the computer program.
The present invention also provides a kind of storage medium, the storage medium is stored with computer program, the computer journey
Sequence can realize above-mentioned method when being executed by processor.
Compared with the prior art, the invention has the advantages that: the present invention obtains image data by RGB binocular camera,
Face datection is first done for image data, to shorten the subsequent In vivo detection time, is rolled up using CAFFE deep learning framework establishment
Product neural network, and the convolutional neural networks become convolutional neural networks deep learning mould using the training of great amount of samples data
Type can carry out silent In vivo detection using the convolutional neural networks deep learning model, realize that In vivo detection is more accurate, inspection
Degree of testing the speed is quicker, and model lightweight makes model be easier to promote.
The invention will be further described in the following with reference to the drawings and specific embodiments.
Detailed description of the invention
Technical solution in order to illustrate the embodiments of the present invention more clearly, below will be to needed in embodiment description
Attached drawing is briefly described, it should be apparent that, drawings in the following description are some embodiments of the invention, general for this field
For logical technical staff, without creative efforts, it is also possible to obtain other drawings based on these drawings.
Fig. 1 is the application scenarios schematic diagram of silent biopsy method provided in an embodiment of the present invention；
Fig. 2 is the flow diagram of silent biopsy method provided in an embodiment of the present invention；
Fig. 3 is the sub-process schematic diagram of silent biopsy method provided in an embodiment of the present invention；
Fig. 4 is convolutional neural networks deep learning model provided in an embodiment of the present invention；
Fig. 5 is the schematic block diagram of silent living body detection device provided in an embodiment of the present invention；
Fig. 6 is the schematic block diagram of computer equipment provided in an embodiment of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are some of the embodiments of the present invention, instead of all the embodiments.Based on this hair
Embodiment in bright, every other implementation obtained by those of ordinary skill in the art without making creative efforts
Example, shall fall within the protection scope of the present invention.
It should be appreciated that ought use in this specification and in the appended claims, term " includes " and "comprising" instruction
Described feature, entirety, step, operation, the presence of element and/or component, but one or more of the other feature, whole is not precluded
Body, step, operation, the presence or addition of element, component and/or its set.
It is also understood that mesh of the term used in this description of the invention merely for the sake of description specific embodiment
And be not intended to limit the present invention.As description of the invention and it is used in the attached claims, unless on
Other situations are hereafter clearly indicated, otherwise " one " of singular, "one" and "the" are intended to include plural form.
It will be further appreciated that the term "and/or" used in description of the invention and the appended claims is
Refer to any combination and all possible combinations of one or more of associated item listed, and including these combinations.
Fig. 1 and Fig. 2 are please referred to, Fig. 1 is the application scenarios signal of silent biopsy method provided in an embodiment of the present invention
Figure.Fig. 2 is the schematic flow chart of silent biopsy method provided in an embodiment of the present invention.The application scenarios include user's end
End and server.
Wherein, user terminal can be smart phone, tablet computer, laptop, desktop computer, personal digital assistant
With the electronic equipments such as wearable device；Server can be independent server, be also possible to the service of multiple server compositions
Device cluster.
Specifically, silent In vivo detection platform and silent In vivo detection can be developed according to the silence biopsy method
App.Silent In vivo detection platform is mountable in the server, and silent In vivo detection App is mountable in the user terminal, utilizes use
The interaction of family terminal and server is completed to carry out user silent In vivo detection.
Fig. 2 is the flow diagram of silent biopsy method provided in an embodiment of the present invention.As shown in Fig. 2, this method
Include the following steps S110 to S160.
S110, multiple image datas are obtained.
In the present embodiment, it is acquired to refer to that face that detection zone occurs or photo shoot for image data
Image.
Specifically, image data is obtained using RGB binocular camera.Utilize RGB binocular camera pair at regular intervals
Face is captured, and carries out In vivo detection using RGB binocular camera simultaneously, is provided better data for In vivo detection, is made
Image data is captured with RGB binocular camera, two 18 millimeters of camera spacing, can be used for the small devices such as mobile terminal.
S120, Face datection is carried out to image data, to obtain Preliminary detection result.
In the present embodiment, Preliminary detection result, which refers to, carries out Face datection to image, has detected whether existing for face
As a result.
Specifically, can using SSD human face detection tech, S3FD human face detection tech, MTCNN human face detection tech etc. into
Row Face datection.
S130, judge in the Preliminary detection result whether to be with the presence of face.
Can just In vivo detection be carried out to image data when detected existing for face when, if it does not exist face, then
It is directly entered end step.
S140, if so, using convolutional neural networks deep learning model to image data carry out In vivo detection, to obtain
Secondary detection result.
In the present embodiment, secondary detection carries out In vivo detection, judgement for the image data with face the result is that referring to
With the presence or absence of living body, silent living body can be detected simultaneously in this way, improve the accuracy of In vivo detection.
The convolutional neural networks deep learning model is by multiple groups true man and personage's high definition picture data as training
The resulting model of data training convolutional neural networks.The convolutional neural networks deep learning model can be found in Fig. 4.
Specifically, above-mentioned convolutional neural networks deep learning model as following steps training obtained by,
S141, multiple groups true man and personage's high definition picture data are obtained, to obtain sample data.
To carry out In vivo detection, acquired by binocular RGB camera more than 100,000 groups of true man and personage's high definition number of pictures
According to as sample data training convolutional neural networks.
S142, CAFFE deep learning framework establishment convolutional neural networks are used.
With one 16 layers of convolutional neural networks of CAFFE deep learning framework establishment, which mainly includes convolutional layer, complete
Articulamentum；Convolutional layer can carry out depth and separate the separable convolutional calculation of convolution sum point.
S143, two classification based trainings are carried out to sample data using convolutional neural networks, to obtain classification and loss function；
Two classification based trainings are carried out to sample data using convolutional neural networks, to obtain loss function, including use convolution
The depth of neural network separates convolution and/or point separation convolution carries out two classification based trainings to sample data, to obtain each sample
The classification of notebook data generally comprises living body classification and non-living body classification, is made in the output layer of convolutional neural networks using cross entropy
For loss function, two classification based trainings are carried out according to face part of the binocular RGB image to true man and high definition photo, the volume after training
Product neural network deep learning model can be used for predicting that photo is the classification of true man or dummy.
S144, judge the loss function whether within the set range.
In the present embodiment, setting range can be 0~0.001, of course, it is possible to depending on according to actual conditions.
S145, if it is not, then using loss function and sample data adjustment convolutional neural networks parameter, and return described in
Two classification based trainings are carried out to sample data using convolutional neural networks, to obtain classification and loss function；
When loss function not within the set range when, need to be adjusted the parameter of convolutional neural networks, just may not be used
Disconnected ground training convolutional neural networks, so that the output of model more closing to reality, to improve the accuracy entirely detected.
S146, if so, using current convolutional neural networks as convolutional neural networks deep learning model.
If it is not, then entering end step；
S150, judge whether the secondary detection result meets setting condition.
In the present embodiment, setting condition refers to that the secondary detection result of convolutional neural networks deep learning model output is
Living body classification.
S160, if so, described image data are exported to terminal, so that image data is shown in terminal；
If it is not, then entering end step.
Living body judgement is carried out according to the classification results, to achieve the purpose that In vivo detection.Successfully pass In vivo detection
Face can travel further into face alignment and recognition of face.To realize effective performance that the model is calculated in mobile terminal, in convolution
The light-weighted convolutional calculation sides such as convolution sum point separation convolution are separated using including depth in neural network deep learning model
Convolutional neural networks deep learning model is not only accomplished that lightweight, speed are fast, but also has high standard for In vivo detection by formula
True rate.In order to enable the convolutional neural networks deep learning model, which has, is more widely applied scene, it can be by the convolutional Neural
Network depth learning model is deployed to server end, the end PC and mobile terminal, so that the convolutional neural networks deep learning model
Can preferably it be applied in real life.
Above-mentioned silent biopsy method obtains image data by RGB binocular camera, first does for image data
Face datection, to shorten the subsequent In vivo detection time, using CAFFE deep learning framework establishment convolutional neural networks, and benefit
With the training of great amount of samples data, the convolutional neural networks become convolutional neural networks deep learning model, utilize convolution mind
Silent In vivo detection can be carried out through network depth learning model, realizes that In vivo detection is more accurate, detection speed is quicker,
Model lightweight makes model be easier to promote.
Fig. 5 is a kind of schematic block diagram of silent living body detection device 300 provided in an embodiment of the present invention.As shown in figure 5,
Corresponding to the above silent biopsy method, the present invention also provides a kind of silent living body detection devices 300.The silence In vivo detection
Device 300 includes the unit for executing above-mentioned silent biopsy method, which can be configured in server.
Specifically, referring to Fig. 5, the silence living body detection device 300 includes:
Data capture unit 301, for obtaining multiple image datas；
Face datection unit 302, for carrying out Face datection to image data, to obtain Preliminary detection result；
First judging unit 303, for judging in the Preliminary detection result whether to be with the presence of face；
In vivo detection unit 304 is used for if so, being carried out using convolutional neural networks deep learning model to image data
In vivo detection, to obtain secondary detection result；
Second judgment unit 305, for judging whether the secondary detection result meets setting condition；
Data outputting unit 306, for if so, described image data are exported to terminal, so that image data is at end
End display.
In one embodiment, described device includes:
Model acquiring unit, for obtaining the convolutional neural networks deep learning model, particular by multiple groups true man
And personage's high definition picture data is as the resulting model of training data training convolutional neural networks.
The model acquiring unit includes:
Sample data obtains subelement, for obtaining multiple groups true man and personage's high definition picture data, to obtain sample data；
Network struction subelement, for using CAFFE deep learning framework establishment convolutional neural networks；
Training subelement, for using convolutional neural networks to sample data carry out two classification based trainings, with obtain classification with
Loss function；
Judgment sub-unit, for judging the loss function whether within the set range；
Adjust subelement, for if it is not, then using loss function and sample data adjustment convolutional neural networks parameter,
And return it is described using convolutional neural networks to sample data carry out two classification based trainings, to obtain classification and loss function；
Model forms subelement, for if so, using current convolutional neural networks as convolutional neural networks depth
Practise model.
It should be noted that it is apparent to those skilled in the art that, above-mentioned silent In vivo detection dress
The specific implementation process of 300 and each unit is set, it can be with reference to the corresponding description in preceding method embodiment, for convenience of description
With it is succinct, details are not described herein.
Above-mentioned silent living body detection device 300 can be implemented as a kind of form of computer program, the computer program
It can be run in computer equipment as shown in FIG. 6.
Referring to Fig. 6, a kind of Fig. 6 schematic block diagram of computer equipment provided by the embodiments of the present application.The computer is set
Standby 500 can be server.
Refering to Fig. 6, which includes processor 502, memory and the net connected by system bus 501
Network interface 505, wherein memory may include non-volatile memory medium 503 and built-in storage 504.
The non-volatile memory medium 503 can storage program area 5031 and computer program 5032.The computer program
5032 include program instruction, which is performed, and processor 502 may make to execute a kind of silent In vivo detection side
Method.
The processor 502 is for providing calculating and control ability, to support the operation of entire computer equipment 500.
The built-in storage 504 provides environment for the operation of the computer program 5032 in non-volatile memory medium 503, should
When computer program 5032 is executed by processor 502, processor 502 may make to execute a kind of silent biopsy method.
The network interface 505 is used to carry out network communication with other equipment.It will be understood by those skilled in the art that in Fig. 6
The structure shown, only the block diagram of part-structure relevant to application scheme, does not constitute and is applied to application scheme
The restriction of computer equipment 500 thereon, specific computer equipment 500 may include more more or fewer than as shown in the figure
Component perhaps combines certain components or with different component layouts.
Wherein, the processor 502 is for running computer program 5032 stored in memory, to realize following step
It is rapid:
Obtain multiple image datas；
Face datection is carried out to image data, to obtain Preliminary detection result；
Judge in the Preliminary detection result whether to be with the presence of face；
If so, In vivo detection is carried out to image data using convolutional neural networks deep learning model, it is secondary to obtain
Testing result；
Judge whether the secondary detection result meets setting condition；
If so, described image data are exported to terminal, so that image data is shown in terminal.
Wherein, the convolutional neural networks deep learning model is by multiple groups true man and personage's high definition picture data conduct
The resulting model of training data training convolutional neural networks.
In one embodiment, processor 502 is implemented as follows step when realizing described multiple IMAGE DATA steps of acquisition
It is rapid:
Image data is obtained using RGB binocular camera.
In one embodiment, processor 502 is realizing that the convolutional neural networks deep learning model is true by multiple groups
People and when resulting as the training data training convolutional neural networks model step of personage's high definition picture data, is implemented as follows
Step:
Multiple groups true man and personage's high definition picture data are obtained, to obtain sample data；
Use CAFFE deep learning framework establishment convolutional neural networks；
Two classification based trainings are carried out to sample data using convolutional neural networks, to obtain classification and loss function；
Judge the loss function whether within the set range；
If it is not, then using the parameter of loss function and sample data adjustment convolutional neural networks, and return to the utilization
Convolutional neural networks carry out two classification based trainings to sample data, to obtain classification and loss function；
If so, using current convolutional neural networks as convolutional neural networks deep learning model.
In one embodiment, processor 502 realize it is described using convolutional neural networks to sample data carry out two classify
Training, when obtaining classification and loss function step, is implemented as follows step:
Convolution and/or point separation convolution is separated using the depth of convolutional neural networks to instruct two classification of sample data progress
Practice, to obtain loss function.
In one embodiment, whether processor 502 described judges in the Preliminary detection result to be to have face to deposit realizing
After step, following steps are also realized:
If it is not, then entering end step.
It should be appreciated that in the embodiment of the present application, processor 502 can be central processing unit (Central
Processing Unit, CPU), which can also be other general processors, digital signal processor (Digital
Signal Processor, DSP), specific integrated circuit (Application Specific Integrated Circuit,
ASIC), ready-made programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic
Device, discrete gate or transistor logic, discrete hardware components etc..Wherein, general processor can be microprocessor or
Person's processor is also possible to any conventional processor etc..
Those of ordinary skill in the art will appreciate that be realize above-described embodiment method in all or part of the process,
It is that relevant hardware can be instructed to complete by computer program.The computer program includes program instruction, computer journey
Sequence can be stored in a storage medium, which is computer readable storage medium.The program instruction is by the department of computer science
At least one processor in system executes, to realize the process step of the embodiment of the above method.
Therefore, the present invention also provides a kind of storage mediums.The storage medium can be computer readable storage medium.This is deposited
Storage media is stored with computer program, and processor is made to execute following steps when wherein the computer program is executed by processor:
Obtain multiple image datas；
Face datection is carried out to image data, to obtain Preliminary detection result；
Judge in the Preliminary detection result whether to be with the presence of face；
If so, In vivo detection is carried out to image data using convolutional neural networks deep learning model, it is secondary to obtain
Testing result；
Judge whether the secondary detection result meets setting condition；
If so, described image data are exported to terminal, so that image data is shown in terminal.
Wherein, the convolutional neural networks deep learning model is by multiple groups true man and personage's high definition picture data conduct
The resulting model of training data training convolutional neural networks.
In one embodiment, the processor realizes described multiple image datas of acquisition executing the computer program
When step, it is implemented as follows step:
Image data is obtained using RGB binocular camera.
In one embodiment, the processor realizes the convolutional neural networks depth executing the computer program
Learning model is by multiple groups true man and personage's high definition picture data as the resulting mould of training data training convolutional neural networks
When type step, it is implemented as follows step:
Multiple groups true man and personage's high definition picture data are obtained, to obtain sample data；
Use CAFFE deep learning framework establishment convolutional neural networks；
Two classification based trainings are carried out to sample data using convolutional neural networks, to obtain classification and loss function；
Judge the loss function whether within the set range；
If it is not, then using the parameter of loss function and sample data adjustment convolutional neural networks, and return to the utilization
Convolutional neural networks carry out two classification based trainings to sample data, to obtain classification and loss function；
If so, using current convolutional neural networks as convolutional neural networks deep learning model.
In one embodiment, the processor is realized and described utilizes convolutional neural networks executing the computer program
Two classification based trainings are carried out to sample data and are implemented as follows step when obtaining classification and loss function step:
Convolution and/or point separation convolution is separated using the depth of convolutional neural networks to instruct two classification of sample data progress
Practice, to obtain loss function.
In one embodiment, the processor realizes the judgement Preliminary detection executing the computer program
As a result whether it is also to realize following steps with the presence of after face step in:
If it is not, then entering end step.
The storage medium can be USB flash disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), magnetic disk
Or the various computer readable storage mediums that can store program code such as CD.
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 electronic hardware, computer software, or a combination of the two, in order to clearly demonstrate hardware
With the interchangeability of software, each exemplary composition and step are generally described according to function in the above description.This
A little functions are implemented in hardware or software actually, the specific application and design constraint depending on technical solution.Specially
Industry technical staff can use different methods to achieve the described function each specific application, but this realization is not
It is considered as beyond the scope of this invention.
In several embodiments provided by the present invention, it should be understood that disclosed device and method can pass through it
Its mode is realized.For example, the apparatus embodiments described above are merely exemplary.For example, the division of each 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 system is closed or is desirably integrated into, or some features can be ignored or not executed.
The steps in the embodiment of the present invention can be sequentially adjusted, merged and deleted according to actual needs.This hair
Unit in bright embodiment device can be combined, divided and deleted according to actual needs.In addition, in each implementation of the present invention
Each functional unit in example can integrate in one processing unit, is also possible to each unit and physically exists alone, can also be with
It is that two or more units are integrated in one unit.
If the integrated unit is realized in the form of SFU software functional unit and when sold or used as an independent product,
It can store in one storage medium.Based on this understanding, technical solution of the present invention is substantially in other words to existing skill
The all or part of part or the technical solution that art contributes can be embodied in the form of software products, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be a
People's computer, terminal or network equipment etc.) it performs all or part of the steps of the method described in the various embodiments of the present invention.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
Those familiar with the art in the technical scope disclosed by the present invention, can readily occur in various equivalent modifications or replace
It changes, these modifications or substitutions should be covered by the protection scope of the present invention.Therefore, protection scope of the present invention should be with right
It is required that protection scope subject to.
Claims (9)
1. silent biopsy method characterized by comprising
Obtain multiple image datas；
Face datection is carried out to image data, to obtain Preliminary detection result；
Judge in the Preliminary detection result whether to be with the presence of face；
If so, In vivo detection is carried out to image data using convolutional neural networks deep learning model, to obtain secondary detection
As a result；
Judge whether the secondary detection result meets setting condition；
If so, described image data are exported to terminal, so that image data is shown in terminal.
2. silence biopsy method according to claim 1, which is characterized in that described multiple image datas of acquisition, packet
It includes:
Image data is obtained using RGB binocular camera.
3. silence biopsy method according to claim 1, which is characterized in that the convolutional neural networks deep learning
Model is by multiple groups true man and personage's high definition picture data as the resulting model of training data training convolutional neural networks.
4. silence biopsy method according to claim 3, which is characterized in that the convolutional neural networks deep learning
Model is by multiple groups true man and personage's high definition picture data as the resulting model of training data training convolutional neural networks, packet
It includes:
Multiple groups true man and personage's high definition picture data are obtained, to obtain sample data；
Use CAFFE deep learning framework establishment convolutional neural networks；
Two classification based trainings are carried out to sample data using convolutional neural networks, to obtain classification and loss function；
Judge the loss function whether within the set range；
If it is not, then using the parameter of loss function and sample data adjustment convolutional neural networks, and return described using convolution
Neural network carries out two classification based trainings to sample data, to obtain classification and loss function；
If so, using current convolutional neural networks as convolutional neural networks deep learning model.
5. silence biopsy method according to claim 4, which is characterized in that described to utilize convolutional neural networks to sample
Notebook data carries out two classification based trainings, to obtain classification and loss function, comprising:
Convolution is separated using the depth of convolutional neural networks and/or point separation convolution carries out two classification based trainings to sample data,
To obtain loss function.
6. silence biopsy method according to claim 1, which is characterized in that the judgement Preliminary detection result
In whether be with the presence of after face, further includes:
If it is not, then entering end step.
7. silent living body detection device characterized by comprising
Data capture unit, for obtaining multiple image datas；
Face datection unit, for carrying out Face datection to image data, to obtain Preliminary detection result；
First judging unit, for judging in the Preliminary detection result whether to be with the presence of face；
In vivo detection unit is used for if so, carrying out living body inspection to image data using convolutional neural networks deep learning model
It surveys, to obtain secondary detection result；
Second judgment unit, for judging whether the secondary detection result meets setting condition；
Data outputting unit, for if so, described image data are exported to terminal, so that image data is shown in terminal.
8. a kind of computer equipment, which is characterized in that the computer equipment includes memory and processor, on the memory
It is stored with computer program, the processor is realized as described in any one of claims 1 to 6 when executing the computer program
Method.
9. a kind of storage medium, which is characterized in that the storage medium is stored with computer program, and the computer program is located
Reason device can be realized when executing such as method described in any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910372163.5A CN110298230A (en) | 2019-05-06 | 2019-05-06 | Silent biopsy method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910372163.5A CN110298230A (en) | 2019-05-06 | 2019-05-06 | Silent biopsy method, device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110298230A true CN110298230A (en) | 2019-10-01 |
Family
ID=68026639
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910372163.5A Pending CN110298230A (en) | 2019-05-06 | 2019-05-06 | Silent biopsy method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110298230A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110826519A (en) * | 2019-11-14 | 2020-02-21 | 深圳市华付信息技术有限公司 | Face occlusion detection method and device, computer equipment and storage medium |
| CN111027400A (en) * | 2019-11-15 | 2020-04-17 | 烟台市广智微芯智能科技有限责任公司 | Living body detection method and device |
| CN111209863A (en) * | 2020-01-07 | 2020-05-29 | 北京旷视科技有限公司 | Living body model training and human face living body detection method, device and electronic equipment |
| CN111325175A (en) * | 2020-03-03 | 2020-06-23 | 北京三快在线科技有限公司 | Living body detection method, living body detection device, electronic apparatus, and storage medium |
| CN111368731A (en) * | 2020-03-04 | 2020-07-03 | 上海东普信息科技有限公司 | Silent in-vivo detection method, silent in-vivo detection device, silent in-vivo detection equipment and storage medium |
| CN111401127A (en) * | 2020-01-16 | 2020-07-10 | 创意信息技术股份有限公司 | Human face living body detection joint judgment method |
| CN111597938A (en) * | 2020-05-07 | 2020-08-28 | 马上消费金融股份有限公司 | Living body detection and model training method and device |
| CN112115852A (en) * | 2020-09-17 | 2020-12-22 | 广东光速智能设备有限公司 | Living body detection method using RGB infrared camera |
| CN112668631A (en) * | 2020-12-24 | 2021-04-16 | 哈尔滨理工大学 | Mobile terminal community pet identification method based on convolutional neural network |
| WO2021114916A1 (en) * | 2019-12-13 | 2021-06-17 | 支付宝(杭州)信息技术有限公司 | Risk detection method, apparatus and device |
| CN113688768A (en) * | 2021-08-31 | 2021-11-23 | 中国平安人寿保险股份有限公司 | Human face detection method, device, equipment and medium based on artificial intelligence |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105023010A (en) * | 2015-08-17 | 2015-11-04 | 中国科学院半导体研究所 | Face living body detection method and system |
| CN106845374A (en) * | 2017-01-06 | 2017-06-13 | 清华大学 | Pedestrian detection method and detection means based on deep learning |
| CN107066942A (en) * | 2017-03-03 | 2017-08-18 | 上海斐讯数据通信技术有限公司 | A kind of living body faces recognition methods and system |
| CN108470169A (en) * | 2018-05-23 | 2018-08-31 | 国政通科技股份有限公司 | Face identification system and method |
| CN108537776A (en) * | 2018-03-12 | 2018-09-14 | 维沃移动通信有限公司 | A kind of image Style Transfer model generating method and mobile terminal |
| CN108875488A (en) * | 2017-09-29 | 2018-11-23 | 北京旷视科技有限公司 | Method for tracing object, object tracking device and computer readable storage medium |
| CN109101925A (en) * | 2018-08-14 | 2018-12-28 | 成都智汇脸卡科技有限公司 | Biopsy method |
| CN109255322A (en) * | 2018-09-03 | 2019-01-22 | 北京诚志重科海图科技有限公司 | A kind of human face in-vivo detection method and device |
| CN109660699A (en) * | 2019-01-17 | 2019-04-19 | 深圳市迪威泰实业有限公司 | A kind of AI intelligent imaging identification In vivo detection video camera |
-
2019
- 2019-05-06 CN CN201910372163.5A patent/CN110298230A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105023010A (en) * | 2015-08-17 | 2015-11-04 | 中国科学院半导体研究所 | Face living body detection method and system |
| CN106845374A (en) * | 2017-01-06 | 2017-06-13 | 清华大学 | Pedestrian detection method and detection means based on deep learning |
| CN107066942A (en) * | 2017-03-03 | 2017-08-18 | 上海斐讯数据通信技术有限公司 | A kind of living body faces recognition methods and system |
| CN108875488A (en) * | 2017-09-29 | 2018-11-23 | 北京旷视科技有限公司 | Method for tracing object, object tracking device and computer readable storage medium |
| CN108537776A (en) * | 2018-03-12 | 2018-09-14 | 维沃移动通信有限公司 | A kind of image Style Transfer model generating method and mobile terminal |
| CN108470169A (en) * | 2018-05-23 | 2018-08-31 | 国政通科技股份有限公司 | Face identification system and method |
| CN109101925A (en) * | 2018-08-14 | 2018-12-28 | 成都智汇脸卡科技有限公司 | Biopsy method |
| CN109255322A (en) * | 2018-09-03 | 2019-01-22 | 北京诚志重科海图科技有限公司 | A kind of human face in-vivo detection method and device |
| CN109660699A (en) * | 2019-01-17 | 2019-04-19 | 深圳市迪威泰实业有限公司 | A kind of AI intelligent imaging identification In vivo detection video camera |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110826519A (en) * | 2019-11-14 | 2020-02-21 | 深圳市华付信息技术有限公司 | Face occlusion detection method and device, computer equipment and storage medium |
| CN110826519B (en) * | 2019-11-14 | 2023-08-18 | 深圳华付技术股份有限公司 | Face shielding detection method and device, computer equipment and storage medium |
| CN111027400A (en) * | 2019-11-15 | 2020-04-17 | 烟台市广智微芯智能科技有限责任公司 | Living body detection method and device |
| WO2021114916A1 (en) * | 2019-12-13 | 2021-06-17 | 支付宝(杭州)信息技术有限公司 | Risk detection method, apparatus and device |
| CN111209863A (en) * | 2020-01-07 | 2020-05-29 | 北京旷视科技有限公司 | Living body model training and human face living body detection method, device and electronic equipment |
| CN111209863B (en) * | 2020-01-07 | 2023-12-15 | 北京旷视科技有限公司 | Living model training and human face living body detection method and device and electronic equipment |
| CN111401127A (en) * | 2020-01-16 | 2020-07-10 | 创意信息技术股份有限公司 | Human face living body detection joint judgment method |
| CN111325175A (en) * | 2020-03-03 | 2020-06-23 | 北京三快在线科技有限公司 | Living body detection method, living body detection device, electronic apparatus, and storage medium |
| CN111368731B (en) * | 2020-03-04 | 2023-06-09 | 上海东普信息科技有限公司 | Silence living body detection method, silence living body detection device, silence living body detection equipment and storage medium |
| CN111368731A (en) * | 2020-03-04 | 2020-07-03 | 上海东普信息科技有限公司 | Silent in-vivo detection method, silent in-vivo detection device, silent in-vivo detection equipment and storage medium |
| CN111597938A (en) * | 2020-05-07 | 2020-08-28 | 马上消费金融股份有限公司 | Living body detection and model training method and device |
| CN112115852A (en) * | 2020-09-17 | 2020-12-22 | 广东光速智能设备有限公司 | Living body detection method using RGB infrared camera |
| CN112668631A (en) * | 2020-12-24 | 2021-04-16 | 哈尔滨理工大学 | Mobile terminal community pet identification method based on convolutional neural network |
| CN112668631B (en) * | 2020-12-24 | 2022-06-24 | 哈尔滨理工大学 | Mobile terminal community pet identification method based on convolutional neural network |
| CN113688768A (en) * | 2021-08-31 | 2021-11-23 | 中国平安人寿保险股份有限公司 | Human face detection method, device, equipment and medium based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110298230A (en) | Silent biopsy method, device, computer equipment and storage medium | |
| US10726244B2 (en) | Method and apparatus detecting a target | |
| CN107862270B (en) | Face classifier training method, face detection method and device and electronic equipment | |
| CN107742100B (en) | A kind of examinee's auth method and terminal device | |
| CN109214343A (en) | Method and apparatus for generating face critical point detection model | |
| CN108229262B (en) | Pornographic video detection method and device | |
| CN110458154A (en) | Face identification method, device and computer readable storage medium | |
| CN110443110A (en) | Face identification method, device, terminal and storage medium based on multichannel camera shooting | |
| CN106997452B (en) | Living body verification method and device | |
| CN107590473B (en) | Human face living body detection method, medium and related device | |
| TWI707243B (en) | Method, apparatus, and system for detecting living body based on eyeball tracking | |
| Wang et al. | Using opportunistic face logging from smartphone to infer mental health: challenges and future directions | |
| WO2021051547A1 (en) | Violent behavior detection method and system | |
| CN111241883B (en) | Method and device for preventing cheating of remote tested personnel | |
| WO2023005468A1 (en) | Respiratory rate measurement method and apparatus, storage medium, and electronic device | |
| WO2021120961A1 (en) | Brain addiction structure map evaluation method and apparatus | |
| CN111563480A (en) | Conflict behavior detection method and device, computer equipment and storage medium | |
| WO2021068781A1 (en) | Fatigue state identification method, apparatus and device | |
| CN109766755A (en) | Face identification method and Related product | |
| CN110287767A (en) | Can attack protection biopsy method, device, computer equipment and storage medium | |
| CN109460733A (en) | Recognition of face in-vivo detection method and system based on single camera, storage medium | |
| CN108875509A (en) | Biopsy method, device and system and storage medium | |
| KR20150128510A (en) | Apparatus and method for liveness test, and apparatus and method for image processing | |
| CN110807117B (en) | User relation prediction method and device and computer readable storage medium | |
| CN112052815A (en) | Behavior detection method and device and electronic equipment |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191001 |