CN107103313A - The casualty insurance fee payment method and device of a kind of utilization recognition of face people at highest risk - Google Patents
The casualty insurance fee payment method and device of a kind of utilization recognition of face people at highest risk Download PDFInfo
- Publication number
- CN107103313A CN107103313A CN201710444870.1A CN201710444870A CN107103313A CN 107103313 A CN107103313 A CN 107103313A CN 201710444870 A CN201710444870 A CN 201710444870A CN 107103313 A CN107103313 A CN 107103313A
- Authority
- CN
- China
- Prior art keywords
- face
- people
- person
- highest risk
- information
- 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 32
- 238000000605 extraction Methods 0.000 claims abstract description 37
- 230000001815 facial effect Effects 0.000 claims abstract description 16
- 238000009472 formulation Methods 0.000 claims abstract description 6
- 239000000203 mixture Substances 0.000 claims abstract description 6
- 238000012545 processing Methods 0.000 claims description 20
- 238000013135 deep learning Methods 0.000 claims description 13
- 238000012549 training Methods 0.000 claims description 10
- 206010039203 Road traffic accident Diseases 0.000 claims description 9
- 230000004069 differentiation Effects 0.000 claims 1
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 210000004709 eyebrow Anatomy 0.000 description 1
- 210000004209 hair Anatomy 0.000 description 1
- 230000037308 hair color Effects 0.000 description 1
- 230000013016 learning Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
Abstract
The present invention relates to insurance, Internet of Things, field of cloud calculation, more particularly to a kind of accident insurance fee payment method of utilization recognition of face people at highest risk, including, it is determined that treating into dangerous personnel；Pass through Face datection model extraction this person's facial information；This person's face feature information is extracted by face characteristic extraction model；By treating to judge whether this person belongs to unexpected people at highest risk into dangerous personnel's face feature information；Harmful grade is assert according to above-mentioned judgement；If this person's harmful grade is assert in unexpected people at highest risk, then identification；If it is not, then harmful grade is set to 0；Corresponding payment is formulated according to this person's harmful grade and standard is compensated.The invention also discloses a kind of accident insurance paying device of utilization recognition of face people at highest risk, including, extraction module；Judge module；Standard formulation module.The present invention realizes the purpose that insurance company and insurer's common interest are protected using decision data by way of to recognizing that the method progress staged of people at highest risk collects accident insurance expense.
Description
Technical field
The present invention relates to Internet of Things and insurance field, the unexpected guarantor of more particularly to a kind of utilization recognition of face people at highest risk
Dangerous fee payment method and device.
Background technology
In actual life, the frequency of drop-in is more and more, and many accidents are due to not observe traffic rules and regulations and cause
, some are due to surprisingly often to be caused to dangerous place.Often do not observed traffic rules and regulations for these, or often go one
The people of a little danger zones, the unexpected probability of generation is very big, therefore formulates a kind of scientific and reasonable casualty insurance payment, compensation side
Formula, which seems, to be even more important.
The content of the invention
It is an object of the present invention to provide the casualty insurance fee payment method of utilization recognition of face people at highest risk a kind of and device, this hair
It is bright to recognizing that the method for people at highest risk by way of staged collects casualty insurance expense, realize and determined using science
Plan, at utmost protects the purpose of insurance company and the interests of the insurer.
To achieve these goals, the present invention uses following technical scheme.
A kind of casualty insurance fee payment method of utilization recognition of face people at highest risk, its step is as follows：
It is determined that treating into dangerous personnel；
Pass through Face datection model extraction this person's facial information；This person's facial characteristics is extracted by face characteristic extraction model to believe
Breath；
By treating to judge whether this person belongs to unexpected people at highest risk into dangerous personnel's face feature information；
Harmful grade is assert according to above-mentioned judgement；If this person's harmful grade is assert in unexpected people at highest risk, then identification；If it is not, then
Harmful grade is set to 0；
Corresponding payment is formulated according to this person's harmful grade and standard is compensated.
Further, Face datection model extraction this person's facial information is passed through；This is extracted by face characteristic extraction model
Human face's characteristic information, before, in addition to, based on deep learning framework and the network architecture, training obtain Face datection model and
Face characteristic extraction model.
Further, by treating to judge whether this person belongs to traffic accident people at highest risk into dangerous personnel's face feature information,
Before, in addition to, set up and obtain unexpected people at highest risk's information bank.
Further, Face datection model extraction this person's facial information is passed through；This is extracted by face characteristic extraction model
Human face's characteristic information, before, in addition to, it is that this person shoots photo and/or obtains this person's photo and/or obtain identity card.
Further, it is that this person shoots photo and/or obtains this person's photo and/or obtain identity card, in addition to, to identity
Photo does age gap alienation processing on card.
Further, age gap alienation processing is done to photo on identity card, before, in addition to, set up photo age differences
Change processing model.
Further, by treating to judge whether this person belongs to traffic accident people at highest risk into dangerous personnel's face feature information,
Before, in addition to, the phase for treating the face feature information into dangerous personnel's face feature information and unexpected people at highest risk's information bank is set
Like degree threshold value.
A kind of casualty insurance paying device of utilization recognition of face people at highest risk, including：
Determining module：For determining to treat into dangerous personnel；
Extraction module：For passing through Face datection model extraction this person's facial information；This is extracted by face characteristic extraction model
Human face's characteristic information；
Judge module：For by treating to judge whether this person belongs to unexpected people at highest risk into dangerous personnel's face feature information；
Harmful grade assert module：For assert harmful grade according to above-mentioned judgement；If unexpected people at highest risk, then identification is assert
This person's harmful grade；If it is not, then harmful grade is set to 0；
Standard formulation module：For formulating corresponding payment according to this person's harmful grade and compensating standard.
Further, in addition to：
Modeling module：For based on deep learning framework and the network architecture, training obtains Face datection model and face characteristic is carried
Modulus type.
Further, in addition to：
Acquisition module：For setting up and obtaining people at highest risk's information bank；
Differential model module：For setting up photo age gap alienation processing model；
Further, in addition to, processing module：For doing age gap alienation processing to photo on identity card.
Compared with prior art, the present invention has advantages below：
It is an object of the present invention to provide the casualty insurance fee payment method of utilization recognition of face people at highest risk a kind of and device, the present invention is logical
Cross and the mode that staged collects casualty insurance expense is carried out to the method for recognizing people at highest risk, realize and utilize science decision, most
The purpose of the interests of big degree protection insurance company and the insurer.
Brief description of the drawings
Fig. 1 is a kind of schematic flow sheet 1 of the casualty insurance fee payment method of utilization recognition of face people at highest risk of the invention；
Fig. 2 is a kind of schematic flow sheet 2 of the casualty insurance fee payment method of utilization recognition of face people at highest risk of the invention；
Fig. 3 is a kind of schematic flow sheet 3 of the casualty insurance fee payment method of utilization recognition of face people at highest risk of the invention；
Fig. 4 is a kind of structural representation Fig. 1 of the casualty insurance paying device of utilization recognition of face people at highest risk of the invention；
Fig. 5 is a kind of structural representation Fig. 2 of the casualty insurance paying device of utilization recognition of face people at highest risk of the invention.
Embodiment
With reference to the accompanying drawings and examples, the embodiment to the present invention is described in further detail：
A kind of casualty insurance fee payment method of utilization recognition of face people at highest risk, comprises the following steps：
Embodiment 1
Fig. 1 is refer to, Fig. 1 illustrates for a kind of flow of casualty insurance fee payment method of utilization recognition of face people at highest risk of the invention
Figure；The present embodiment comprises the following steps there is provided a kind of casualty insurance fee payment method of utilization recognition of face people at highest risk：
Step S101, it is determined that treating into dangerous personnel；
Step S102, passes through Face datection model extraction this person's facial information；This person face is extracted by face characteristic extraction model
Portion's characteristic information；
Step S103, by treating to judge whether this person belongs to unexpected people at highest risk into dangerous personnel's face feature information；
Step S104, harmful grade is assert according to above-mentioned judgement；If this person's hazard class is assert in unexpected people at highest risk, then identification
Not；If it is not, then harmful grade is set to 0；
Step S105, formulates corresponding payment according to this person's harmful grade and compensates standard.
Embodiment 2
Fig. 2 is refer to, Fig. 2 is that the flow for the casualty insurance fee payment method for being a kind of utilization recognition of face people at highest risk of the invention is shown
It is intended to 2；The present embodiment comprises the following steps there is provided the casualty insurance fee payment method of another utilization recognition of face people at highest risk：
Step S201, based on deep learning framework and the network architecture, training obtains Face datection model and face characteristic extracts mould
Type；
Face datection model uses caffe deep learnings framework and the Faster-RCNN network architectures, but is not limited to use this depth
Learning method and this network architecture；As Caffe, the Theano of the Montreal Institute of Technology, the Swiss of California Berkeley
Work Development of intelligent laboratory IDSIA Brainstorm, it is that any one method such as Princeton University Marvin can serve as this depth
Spend the framework of study；The network architecture that can be modeled as SSD, Faster-RCNN etc. as this；
Face characteristic extraction model, which is used, is based on caffe deep learnings framework and the VGGFACE network architectures, but is not limited to use this
Deep learning method and this network architecture；
Multigroup certificate face picture is extracted, deep learning is carried out, each face feature point is exported；Every face feature point, bag are set
Include the shape of face, size, skin, hair color, facial central point information and the boundary point letter of boundary point information and face
Breath, in addition to local feature information, such as nose, face, left eye, right eye, Zuo Mei, right eyebrow and mutual range information；It is defeated
Enter face picture, output characteristic point information, untill training reaches requirement.
Step S202, it is determined that treating into dangerous personnel.
Step S203, obtains this person's photographic intelligence；
Photo can be with shooting, or obtains from video recording, the photo that preserved originally.
Step S204, passes through Face datection model extraction this person's facial information；This is extracted by face characteristic extraction model
Human face's characteristic information.
Step S205, sets up and obtains people at highest risk's information bank；
Set up people at highest risk's information bank method as follows, unexpected type is classified first, different types of accident sets different
Weight coefficient.In having occurred, unexpected record information is gathered data source and the information gathering of emergency risk occurs for presence.
By taking traffic accident as an example, illustrate.Method is as follows：
A) act of violating regulations is predefined, different weight coefficients is set to different acts of violating regulations；
B) act of violating regulations to Pedestrians and vehicles enters Mobile state seizure, obtains act of violating regulations record；
Different acquisition modes are used to different acts of violating regulations；
C) deep learning framework and the network architecture are based on, training obtains the model of Face datection；
D) personnel's dynamic picture human face picture violating the regulations is obtained by Face datection model；
E) deep learning framework and the network architecture are based on, training obtains face characteristic extraction model；
F) face feature information of face picture is extracted by face characteristic extraction model；
G) judge to record with the presence or absence of violating the regulations before the personnel violating the regulations by above-mentioned face feature information；
H) respective record is done according to judged result；If there is record violating the regulations, this person's dangerous values are weighted by danger coefficient
Number of times accumulative and violating the regulations adds 1；If in the absence of record of breaking rules and regulations, creating this person record violating the regulations, recording this person's dangerous values and disobey
Chapter number of times adds 1；
I) number of times violating the regulations and dangerous values are reached to personnel's typing traffic accident people at highest risk's information bank of threshold value.
Step S206, sets the face feature information treated into dangerous personnel's face feature information and unexpected people at highest risk's information bank
Similarity threshold；
When the similarity for treating dangerous personnel's face feature information and a certain face feature information in unexpected people at highest risk's information bank
During more than threshold value, it is judged as same people；If similarity is less than threshold value, judgement is not same people.
Step S207, by treating to judge whether this person belongs to traffic accident people at highest risk into dangerous personnel's face feature information.
Step S208, harmful grade is assert according to above-mentioned judgement；If unexpected people at highest risk, then identification assert that this person is dangerous
Rank；If it is not, then harmful grade is set to 0；
By traffic accident people at highest risk's information bank, this person's traffic accident dangerous values are found, according to the value, this person's hazard class are assert
Not.
Step S209, formulates corresponding payment according to this person's harmful grade and compensates standard；
According to the different payment of different harmful grade formulations and compensation standard, stepped charging mode is carried out.Danger coefficient
Lower charge is lower.The mode that setting is compensated when surprisingly occurring, has record violating the regulations and without two kinds of record violating the regulations；There is record violating the regulations,
It is divided into tort-feasor and non-tort-feasor again, it is in full to compensate if being non-tort-feasor, if tort-feasor, then by mistake size, carry out
Discount compensates mode；Always without record violating the regulations, tort-feasor, then by mistake size, progress discount compensation mode, non-tort-feasor,
Excess is compensated；
Such as, danger coefficient is 0,100 yuan of premium, and tort-feasor compensates 70% ~ 90%, and non-tort-feasor compensates 110%；Such as, it is dangerous
Coefficient is 5,180 yuan of premium, and tort-feasor compensates 40% ~ 80%, and non-tort-feasor compensates 100%.
Embodiment 3
Fig. 3 is refer to, Fig. 3 is that a kind of flow of the casualty insurance fee payment method of utilization recognition of face people at highest risk of the invention is shown
It is intended to 3；
Difference from Example 2 is that step S303 obtains this person's identity card picture.
Step S304, sets up photo age gap alienation processing model;
Based on deep learning framework and the network architecture, age gap alienation processing age gap alienation processing model is set up；Training study
In all ages and classes human face characteristic point difference, ideal process purpose is reached.
Step S305, age gap alienation processing is done to photo on identity card；
Age gap alienation processing is done to photo on identity card.
Embodiment 4
Fig. 4 is refer to, Fig. 4 is a kind of structural representation of the casualty insurance paying device of utilization recognition of face people at highest risk of the invention
Fig. 1；The present embodiment there is provided a kind of casualty insurance paying device of utilization recognition of face people at highest risk, including：
Extraction module 11：For passing through Face datection model extraction this person's facial information；Extracted by face characteristic extraction model
This person's face feature information；
Judge module 12：For by treating to judge whether this person belongs to unexpected people at highest risk into dangerous personnel's face feature information；
Harmful grade assert module 13：Harmful grade is assert according to above-mentioned judgement；If unexpected people at highest risk, then identification assert this
People's harmful grade；If it is not, then harmful grade is set to 0；
Standard formulation module 14：For formulating corresponding payment according to this person's harmful grade and compensating standard.
Embodiment 5
Fig. 5 is refer to, Fig. 5 is a kind of structural representation of the casualty insurance paying device of utilization recognition of face people at highest risk of the invention
Fig. 2；The present embodiment there is provided a kind of casualty insurance paying device of utilization recognition of face people at highest risk, including：
Modeling module 21：For based on deep learning framework and the network architecture, the model and face that training obtains Face datection to be special
Levy extraction model；
Extraction module 22：For passing through Face datection model extraction this person's facial information；Extracted by face characteristic extraction model
This person's face feature information；
Differential model module 23：For setting up photo age gap alienation processing model；
Processing module 24：For doing age gap alienation processing to photo on identity card；
Acquisition module 25：For setting up and obtaining people at highest risk's information bank；
Judge module 26：For by treating to judge whether this person belongs to unexpected people at highest risk into dangerous personnel's face feature information；
Harmful grade assert module 27：Harmful grade is assert according to above-mentioned judgement；If unexpected people at highest risk, then identification assert this
People's harmful grade；If it is not, then harmful grade is set to 0；
Standard formulation module 28：For formulating corresponding payment according to this person's harmful grade and compensating standard.
Illustrated above is only the preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
For member, under the premise without departing from the principles of the invention, some improvements and modifications can also be made, these improvements and modifications also should
It is considered as protection scope of the present invention.
Claims (10)
1. a kind of casualty insurance fee payment method of utilization recognition of face people at highest risk, it is characterised in that including：
It is determined that treating into dangerous personnel；
Pass through Face datection model extraction this person's facial information；This person's facial characteristics is extracted by face characteristic extraction model to believe
Breath；
By treating to judge whether this person belongs to unexpected people at highest risk into dangerous personnel's face feature information；
Harmful grade is assert according to above-mentioned judgement；If this person's harmful grade is assert in unexpected people at highest risk, then identification；If it is not, then
Harmful grade is set to 0；
Corresponding payment is formulated according to this person's harmful grade and standard is compensated.
2. a kind of casualty insurance fee payment method of utilization recognition of face people at highest risk according to claim 1, its feature exists
In passing through Face datection model extraction this person's facial information；This person's face feature information is extracted by face characteristic extraction model,
Before, in addition to,
Based on deep learning framework and the network architecture, training obtains Face datection model and face characteristic extraction model.
3. a kind of casualty insurance fee payment method of utilization recognition of face people at highest risk according to claim 1, its feature exists
In, by treating to judge whether this person belongs to traffic accident people at highest risk into dangerous personnel's face feature information, before, in addition to, build
Stand and obtain unexpected people at highest risk's information bank.
4. a kind of casualty insurance fee payment method of utilization recognition of face people at highest risk according to claim 1, its feature exists
In passing through Face datection model extraction this person's facial information；This person's face feature information is extracted by face characteristic extraction model,
Before, in addition to, be this person shoot photo and/or obtain this person's photo and/or obtain identity card.
5. a kind of casualty insurance fee payment method of utilization recognition of face people at highest risk according to claim 4, its feature exists
In, it is that this person shoots photo and/or obtains this person's photo and/or obtain identity card, in addition to, the age is done to photo on identity card
Differentiation processing.
6. a kind of casualty insurance fee payment method of utilization recognition of face people at highest risk according to claim 5, its feature exists
In, age gap alienation processing is done to photo on identity card, before, in addition to, set up photo age gap alienation processing model.
7. a kind of casualty insurance fee payment method of utilization recognition of face people at highest risk according to claim 1, its feature exists
In, by treating to judge whether this person belongs to traffic accident people at highest risk into dangerous personnel's face feature information, before, in addition to, if
Put the similarity threshold treated into dangerous personnel's face feature information and the face feature information of unexpected people at highest risk's information bank.
8. a kind of casualty insurance paying device of utilization recognition of face people at highest risk, it is characterised in that including：
Determining module：For determining to treat into dangerous personnel；
Extraction module：For passing through Face datection model extraction this person's facial information；This is extracted by face characteristic extraction model
Human face's characteristic information；
Judge module：For by treating to judge whether this person belongs to unexpected people at highest risk into dangerous personnel's face feature information；
Harmful grade assert module：For assert harmful grade according to above-mentioned judgement；If unexpected people at highest risk, then identification is assert
This person's harmful grade；If it is not, then harmful grade is set to 0；
Standard formulation module：For formulating corresponding payment according to this person's harmful grade and compensating standard.
9. a kind of casualty insurance paying device of utilization recognition of face people at highest risk according to claim 8, its feature exists
In, in addition to：
Modeling module：For based on deep learning framework and the network architecture, training obtains Face datection model and face characteristic is carried
Modulus type.
10. a kind of casualty insurance paying device of utilization recognition of face people at highest risk according to claim 8, its feature exists
In, in addition to：
Acquisition module：For setting up and obtaining people at highest risk's information bank；
Further, in addition to, differential model module：For setting up photo age gap alienation processing model；
Further, in addition to, processing module：For doing age gap alienation processing to photo on identity card.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710444870.1A CN107103313A (en) | 2017-06-14 | 2017-06-14 | The casualty insurance fee payment method and device of a kind of utilization recognition of face people at highest risk |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710444870.1A CN107103313A (en) | 2017-06-14 | 2017-06-14 | The casualty insurance fee payment method and device of a kind of utilization recognition of face people at highest risk |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107103313A true CN107103313A (en) | 2017-08-29 |
Family
ID=59659358
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710444870.1A Pending CN107103313A (en) | 2017-06-14 | 2017-06-14 | The casualty insurance fee payment method and device of a kind of utilization recognition of face people at highest risk |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107103313A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109063751A (en) * | 2018-07-16 | 2018-12-21 | 江苏智通交通科技有限公司 | The traffic high-risk personnel recognition methods of decision Tree algorithms is promoted based on gradient |
| CN111292146A (en) * | 2018-12-07 | 2020-06-16 | 泰康保险集团股份有限公司 | Insurance recommendation method and device, computer storage medium and electronic equipment |
| CN113256865A (en) * | 2020-11-06 | 2021-08-13 | 上海兴容信息技术有限公司 | Control method and system of intelligent access control |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030187704A1 (en) * | 2002-03-26 | 2003-10-02 | Fujitsu Limited | Method of and apparatus for setting insurance premium, and computer product |
| JP2009128486A (en) * | 2007-11-21 | 2009-06-11 | Hitachi Ltd | Safe driving diagnostic system and automobile insurance premium setting system |
| JP2015071318A (en) * | 2013-10-01 | 2015-04-16 | 株式会社オートネットワーク技術研究所 | Insurance fee calculation system |
| CN105225155A (en) * | 2015-09-25 | 2016-01-06 | 中国人民财产保险股份有限公司 | A kind of insurance risk management-control method based on biological identification technology |
| CN106846153A (en) * | 2016-06-28 | 2017-06-13 | 郑鑫 | A kind of vehicle insurance compensates method and system |
-
2017
- 2017-06-14 CN CN201710444870.1A patent/CN107103313A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030187704A1 (en) * | 2002-03-26 | 2003-10-02 | Fujitsu Limited | Method of and apparatus for setting insurance premium, and computer product |
| JP2009128486A (en) * | 2007-11-21 | 2009-06-11 | Hitachi Ltd | Safe driving diagnostic system and automobile insurance premium setting system |
| JP2015071318A (en) * | 2013-10-01 | 2015-04-16 | 株式会社オートネットワーク技術研究所 | Insurance fee calculation system |
| CN105225155A (en) * | 2015-09-25 | 2016-01-06 | 中国人民财产保险股份有限公司 | A kind of insurance risk management-control method based on biological identification technology |
| CN106846153A (en) * | 2016-06-28 | 2017-06-13 | 郑鑫 | A kind of vehicle insurance compensates method and system |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109063751A (en) * | 2018-07-16 | 2018-12-21 | 江苏智通交通科技有限公司 | The traffic high-risk personnel recognition methods of decision Tree algorithms is promoted based on gradient |
| CN109063751B (en) * | 2018-07-16 | 2021-09-17 | 江苏智通交通科技有限公司 | Traffic high-risk personnel identification method based on gradient lifting decision tree algorithm |
| CN111292146A (en) * | 2018-12-07 | 2020-06-16 | 泰康保险集团股份有限公司 | Insurance recommendation method and device, computer storage medium and electronic equipment |
| CN113256865A (en) * | 2020-11-06 | 2021-08-13 | 上海兴容信息技术有限公司 | Control method and system of intelligent access control |
| CN113256865B (en) * | 2020-11-06 | 2023-01-06 | 上海兴容信息技术有限公司 | Control method and system of intelligent access control |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Mirjalili et al. | Semi-adversarial networks: Convolutional autoencoders for imparting privacy to face images | |
| CN108509862B (en) | Rapid face recognition method capable of resisting angle and shielding interference | |
| CN105139003B (en) | A kind of dynamic human face recognition system and method | |
| CN107194341A (en) | The many convolution neural network fusion face identification methods of Maxout and system | |
| CN105913051B (en) | A kind of updating device and method of the template library identifying facial image | |
| CN103473564B (en) | A kind of obverse face detection method based on sensitizing range | |
| CN108256459A (en) | Library algorithm is built in detector gate recognition of face and face based on multiple-camera fusion automatically | |
| CN107273822A (en) | A kind of method for secret protection based on monitor video multiple target tracking and recognition of face | |
| CN107103313A (en) | The casualty insurance fee payment method and device of a kind of utilization recognition of face people at highest risk | |
| CN108573243A (en) | A kind of comparison method of the low quality face based on depth convolutional neural networks | |
| CN106156765A (en) | safety detection method based on computer vision | |
| Tan et al. | Legitimate adversarial patches: Evading human eyes and detection models in the physical world | |
| CN105160299A (en) | Human face emotion identifying method based on Bayes fusion sparse representation classifier | |
| Cho et al. | Dapas: Denoising autoencoder to prevent adversarial attack in semantic segmentation | |
| CN107392222A (en) | A kind of face cluster method, apparatus and storage medium | |
| CN110298257A (en) | A kind of driving behavior recognition methods based on human body multiple location feature | |
| CN111914748A (en) | Face recognition method and device, electronic equipment and computer readable storage medium | |
| CN108108711A (en) | Face supervision method, electronic equipment and storage medium | |
| CN112818901A (en) | Wearing mask face recognition method based on eye attention mechanism | |
| CN101719223B (en) | Identification method for stranger facial expression in static image | |
| CN109101925A (en) | Biopsy method | |
| CN106971161A (en) | Face In vivo detection system based on color and singular value features | |
| Hernandez-Diaz et al. | Cross spectral periocular matching using resnet features | |
| CN106778797A (en) | A kind of identity intelligent identification Method | |
| Rauf et al. | Pedestrian detection using HOG, LUV and optical flow as features with AdaBoost as classifier |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170829 |
|
| WD01 | Invention patent application deemed withdrawn after publication |