CN113807144A - Testing method of living body detection equipment - Google Patents
Testing method of living body detection equipment Download PDFInfo
- Publication number
- CN113807144A CN113807144A CN202010541380.5A CN202010541380A CN113807144A CN 113807144 A CN113807144 A CN 113807144A CN 202010541380 A CN202010541380 A CN 202010541380A CN 113807144 A CN113807144 A CN 113807144A
- Authority
- CN
- China
- Prior art keywords
- human face
- identification
- test
- living body
- dimensional
- 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
- 238000012360 testing method Methods 0.000 title claims abstract description 80
- 238000001514 detection method Methods 0.000 title claims abstract description 46
- 238000005286 illumination Methods 0.000 claims abstract description 15
- 238000013095 identification testing Methods 0.000 claims abstract description 4
- 238000007619 statistical method Methods 0.000 claims abstract description 4
- 230000003068 static effect Effects 0.000 claims description 20
- 238000000034 method Methods 0.000 claims description 17
- 238000012545 processing Methods 0.000 claims description 14
- 238000004088 simulation Methods 0.000 claims description 12
- VYPSYNLAJGMNEJ-UHFFFAOYSA-N Silicium dioxide Chemical compound O=[Si]=O VYPSYNLAJGMNEJ-UHFFFAOYSA-N 0.000 claims description 5
- 238000010998 test method Methods 0.000 claims description 5
- 230000014509 gene expression Effects 0.000 claims description 4
- 230000002194 synthesizing effect Effects 0.000 claims description 4
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 claims description 3
- 239000006004 Quartz sand Substances 0.000 claims description 3
- 229910052802 copper Inorganic materials 0.000 claims description 3
- 239000010949 copper Substances 0.000 claims description 3
- 239000006260 foam Substances 0.000 claims description 3
- 239000000843 powder Substances 0.000 claims description 3
- 239000011347 resin Substances 0.000 claims description 3
- 229920005989 resin Polymers 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 2
- 229920001296 polysiloxane Polymers 0.000 claims 1
- 210000003128 head Anatomy 0.000 description 14
- 238000001727 in vivo Methods 0.000 description 5
- 210000001508 eye Anatomy 0.000 description 3
- 210000000214 mouth Anatomy 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 210000001331 nose Anatomy 0.000 description 2
- 239000000741 silica gel Substances 0.000 description 2
- 229910002027 silica gel Inorganic materials 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000001574 biopsy Methods 0.000 description 1
- 230000004397 blinking Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000010985 leather Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Landscapes
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses a testing method of a living body testing device, which comprises the following steps: making a plurality of test models, wherein the test models are prostheses or living bodies; controlling different illumination intensities, carrying out identification test on each test model in living body detection equipment to be tested, and respectively recording identification correctness or identification errors, wherein identification correctness means that the test model received by the living body detection equipment to be tested is the same as the test model output after identification; the identification error means that the test model received by the living body detection equipment to be tested is different from the test model output after identification; and carrying out statistical analysis on the identification errors, the corresponding illumination intensity and the types of the test models.
Description
Technical Field
The invention relates to the technical field of in-vivo detection, in particular to a testing method of in-vivo detection equipment.
Background
With the gradual update of the authentication mode, more and more authentication technologies are highlighted, more and more emerging payment authentication modes such as face recognition and face payment are around people, but with the more and more authentication modes, the security problem becomes a problem to be considered, and the equipment should have some functions of most basic security guarantee to guarantee the security of the authentication.
Face recognition systems are increasingly used in security, finance and other fields where identity authentication is required, such as remote bank account opening, access control systems, remote transaction operation authentication and the like. It is necessary not only to ensure that the face similarity of the authenticatee conforms to the base database stored in the database, but also to confirm that the authenticatee is a legitimate living organism. Therefore, the face recognition system needs to be able to prevent an attacker from attacking the face by using a picture, a 3D face model, a mask, or the like.
Moreover, at present, no effective detection method exists, more test methods are to use the real person and the photo for testing, or only use the real person for testing, the test methods are more that the test by taking the photo should be rejected, the test by the real person should be accepted, and no good test method exists for the non-real person and the medium between the real person and the non-real person. The non-real person is a non-real person with most of real conditions such as a head pattern wax image, the leather mask is worn by the real person between the real person and the non-real person, the conditions of the real person are such as blinking, but the face appearance is not the face appearance of the real person. The face recognition system has low detection accuracy and certain risk coefficient.
The invention is therefore proposed.
Disclosure of Invention
In order to achieve the above object, the present invention provides a testing method of a living body testing apparatus, the method comprising:
making a plurality of test models, wherein the test models are prostheses or living bodies;
controlling different illumination intensities, performing identification test on each test model in the living body detection equipment to be tested, and respectively recording whether the identification is correct or wrong, wherein,
the identification is correct, namely the test model received by the living body detection equipment to be tested is the same as the test model output after identification;
the identification error means that the test model received by the living body detection equipment to be tested is different from the test model output after identification;
and carrying out statistical analysis on the identification errors, the corresponding illumination intensity and the types of the test models.
Preferably, the illumination intensity includes strong light, weak light, sunshine, backlight and normal light.
Preferably, the making of the plurality of test models further comprises:
acquiring a human face, simulating the human face by using two dimensions or three dimensions, and testing the test model of the living body detection equipment; wherein the face is stored in a face database.
Preferably, the simulating the human face by using two dimensions further includes:
and performing simulation processing on the human face through two-dimensional static paper or two-dimensional static electrons or two-dimensional dynamic electrons.
Preferably, the simulation processing of the human face through two-dimensional static paper or two-dimensional static electronics further includes:
and printing the human face on paper or displaying the human face on electronic equipment to obtain a human face static picture.
Preferably, the simulating processing of the human face through two-dimensional dynamic electrons further includes:
and recording or synthesizing the human face into a video with various expressions to obtain a human face video.
Preferably, the simulating the human face by using three dimensions further includes:
carrying out simulation processing on the human face through a three-dimensional mask to obtain a human skin mask which can be sleeved on the head of a human; or
And carrying out simulation processing on the human face through a three-dimensional head model to obtain a simulated statue/wax figure.
Preferably, the paper comprises printing paper, matte photographic paper, highlight photographic paper, suede photographic paper, matte powder and polished copper.
Preferably, the three-dimensional mask comprises a plastic mask, a 3D paper mask and a silica gel mask.
Preferably, the three-dimensional head die is made of foam, resin, full-color sandstone and quartz sand.
Has the advantages that:
the invention verifies the defects of the living body detection equipment by setting a series of test models, and the provided verification method can more comprehensively simulate that the equipment is judged as a living body real person in the modes of photo/human skin mask/head model/video playback and the like in the actual application scene, so that the living body detection equipment has higher detection accuracy and higher safety on the living body.
Drawings
Fig. 1 is a flowchart of a testing method of a living body testing apparatus according to an embodiment of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The present invention will be described in detail with reference to the following examples.
Referring to fig. 1, a flow chart of a testing method of a living body testing apparatus according to an embodiment of the present invention is shown. A method of testing a living subject testing device, comprising:
making a plurality of test models, wherein the test models are prostheses or living bodies;
controlling different illumination intensities, performing identification test on each test model in the living body detection equipment to be tested, and respectively recording whether the identification is correct or wrong, wherein,
the identification is correct, namely the test model received by the living body detection equipment to be tested is the same as the test model output after identification; at least comprises the following steps:
the identification is correct, namely the to-be-tested living body detection device identifies the test model, and the to-be-tested living body detection device identifies the test model to be a prosthesis when detecting the prosthesis, or identifies the test model to be a living body when detecting the living body.
The identification error means that the test model received by the living body detection equipment to be tested is different from the test model output after identification; at least comprises the following steps:
the identification error means that the living body detection device to be tested identifies that the test model includes that the living body detection device to be tested identifies the prosthesis as a living body when detecting the prosthesis, or that the living body detection device to be tested identifies the prosthesis when detecting the living body.
And carrying out statistical analysis on the identification errors, the corresponding illumination intensity and the types of the test models.
Preferably, the illumination intensity includes strong light, weak light, sunshine, backlight and normal light.
Because the identification of the test living body detection equipment to the test model can be influenced by the illumination intensity under different illumination conditions, the type of the test model corresponding to the identification error is recorded in the data obtained by testing under various illumination intensities for statistics, so that later analysis and further correction and adjustment of the test living body detection equipment are facilitated. In addition, a judgment error easily occurs to equipment without depth data under strong light or weak light; the device with the binocular rgb has a high requirement for the image effect and, if the algorithms in the device are not perfect, also in case of strong or weak light, a judgment error may occur.
Preferably, the making of the plurality of test models further comprises:
acquiring a human face, simulating the human face by using two dimensions or three dimensions, and testing the test model of the living body detection equipment; wherein the face is stored in a face database.
Preferably, the simulating the human face by using two dimensions further includes:
and performing simulation processing on the human face through two-dimensional static paper or two-dimensional static electrons or two-dimensional dynamic electrons.
Preferably, the simulation processing of the human face through two-dimensional static paper or two-dimensional static electronics further includes:
and printing the human face on paper or displaying the human face on electronic equipment to obtain a human face static picture. The electronic equipment for displaying the human face comprises a computer terminal, a smart phone, a tablet and the like.
Preferably, the simulating processing of the human face through two-dimensional dynamic electrons further includes:
and recording or synthesizing the human face into a video with various expressions to obtain a human face video.
Preferably, the simulating the human face by using three dimensions further includes:
carrying out simulation processing on the human face through a three-dimensional mask to obtain a human skin mask which can be sleeved on the head of a human; or
And carrying out simulation processing on the human face through a three-dimensional head model to obtain a simulated statue/wax figure.
Preferably, the paper comprises printing paper, matte photographic paper, highlight photographic paper, suede photographic paper, matte powder and polished copper.
Preferably, the three-dimensional mask comprises a plastic mask, a 3D paper mask and a silica gel mask.
Preferably, the three-dimensional head die is made of foam, resin, full-color sandstone and quartz sand.
Another embodiment provided by the present invention comprises:
a series of test models are designed to test the in-vivo detection performance of the equipment with in-vivo detection, namely the test models are utilized to attack the equipment with in-vivo detection, and the attacking prop has two-dimensional static paper, two-dimensional dynamic electron, two-dimensional static electron, three-dimensional mask and three-dimensional head model.
Printing the human face on paper, wherein the paper is provided with the whole paper, cut according to the head shape, or respectively and independently dig out eyes, noses or mouth parts, or combined/completely dig out, wearing the printed human face static picture on the human face, and using the movable mouths, noses and eyes to ensure that the tested living body detection equipment verifies that the human face static picture is a real living body. Therefore, attack success of the test model on the tested living body detection device is obtained.
Two-dimensional static electrons are adopted, namely an electronic screen or an electronic ink screen is used for displaying the human face, wherein the displayed human face comprises a colorful human face/black and white human face/infrared human face image, and the infrared human face image is a punctiform infrared human face image; or two-dimensional dynamic electronics, namely recording or synthesizing expression and action of a person in a video playing mode is adopted, and the tested living body detection equipment verifies that the face video is a real living body. Therefore, attack success of the test model on the tested living body detection device is obtained.
A three-dimensional mask is adopted, namely the mask is the same as a human skin mask and is sleeved on the head of a test prosthesis, and eyes and mouths are exposed; or a three-dimensional head model, i.e., a wax or statue, is used to verify that the wax or statue is a genuine living subject by the biopsy device being tested. Therefore, attack success of the test model on the tested living body detection device is obtained.
The above test model was performed under different conditions: for example, the test models are tested under different illumination conditions, strong light conditions, weak light conditions, sunshine conditions, backlight conditions and normal light conditions, so that the test models under different conditions are obtained, and the tested equipment can not be used as a living body.
The method provided by the embodiment can comprehensively simulate the condition of living body detection judgment error in the process of face detection, and avoid the situation that equipment is judged to be a real person in the modes of photo/human skin mask/head model/video playback and the like in the actual application scene. For example, there are real cases in reality: a child uses a parent photo to display in a mobile phone to go to an express cabinet with face recognition to take express; when the payer or the WeChat is used for calling the personal information, face recognition verification or login may be needed, video is used for returning, or a head model or a human skin mask of other people is made to log in the account of other people, and fund/privacy information and the like are stolen.
The method provided by the invention is used for testing the face recognition live body detection function by taking an attack method which is easy to realize as a basic face recognition live body detection case. The invention verifies the defects of the living body detection equipment by setting a series of test models, thereby leading the living body detection equipment to have higher detection accuracy and higher safety on the living body.
The embodiments in the above embodiments can be further combined or replaced, and the embodiments are only used for describing the preferred embodiments of the present invention, and do not limit the concept and scope of the present invention, and various changes and modifications made to the technical solution of the present invention by those skilled in the art without departing from the design idea of the present invention belong to the protection scope of the present invention.
Claims (10)
1. A method of testing a living subject testing device, the method comprising:
making a plurality of test models, wherein the test models are prostheses or living bodies;
controlling different illumination intensities, performing identification test on each test model in the living body detection equipment to be tested, and respectively recording whether the identification is correct or wrong, wherein,
the identification is correct, namely the test model received by the living body detection equipment to be tested is the same as the test model output after identification;
the identification error means that the test model received by the living body detection equipment to be tested is different from the test model output after identification;
and carrying out statistical analysis on the identification errors, the corresponding illumination intensity and the types of the test models.
2. The method as claimed in claim 1, wherein the illumination intensity includes strong light, weak light, shade, backlight and normal light.
3. The method of claim 1, wherein the step of creating a plurality of test patterns further comprises:
acquiring a human face, simulating the human face by using two dimensions or three dimensions, and testing the test model of the living body detection equipment; wherein the face is stored in a face database.
4. The method as claimed in claim 3, wherein the simulating the human face with two dimensions further comprises:
and performing simulation processing on the human face through two-dimensional static paper or two-dimensional static electrons or two-dimensional dynamic electrons.
5. The method as claimed in claim 4, wherein the simulation processing of the human face by two-dimensional static paper or two-dimensional static electronics further comprises:
and printing the human face on paper or displaying the human face on electronic equipment to obtain a human face static picture.
6. The method as claimed in claim 4, wherein the simulating process of the human face by two-dimensional dynamic electrons further comprises:
and recording or synthesizing the human face into a video with various expressions to obtain a human face video.
7. The method as claimed in claim 3, wherein the simulating the human face with three dimensions further comprises:
carrying out simulation processing on the human face through a three-dimensional mask to obtain a human skin mask which can be sleeved on the head of a human; or
And carrying out simulation processing on the human face through a three-dimensional head model to obtain a simulated statue/wax figure.
8. The method as claimed in claim 5, wherein the paper comprises printing paper, matte photo paper, high gloss photo paper, suede photo paper, matte powder and copper.
9. The method as claimed in claim 7, wherein the three-dimensional mask comprises a plastic mask, a 3D paper mask and a silicone mask.
10. The method as claimed in claim 7, wherein the three-dimensional head mold is made of foam, resin, full-color sandstone and quartz sand.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010541380.5A CN113807144A (en) | 2020-06-15 | 2020-06-15 | Testing method of living body detection equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010541380.5A CN113807144A (en) | 2020-06-15 | 2020-06-15 | Testing method of living body detection equipment |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113807144A true CN113807144A (en) | 2021-12-17 |
Family
ID=78892361
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010541380.5A Pending CN113807144A (en) | 2020-06-15 | 2020-06-15 | Testing method of living body detection equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113807144A (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101770613A (en) * | 2010-01-19 | 2010-07-07 | 北京智慧眼科技发展有限公司 | Social insurance identity authentication method based on face recognition and living body detection |
CN101999900A (en) * | 2009-08-28 | 2011-04-06 | 南京壹进制信息技术有限公司 | Living body detecting method and system applied to human face recognition |
CN106295571A (en) * | 2016-08-11 | 2017-01-04 | 深圳市赛为智能股份有限公司 | The face identification method of illumination adaptive and system |
CN107808115A (en) * | 2017-09-27 | 2018-03-16 | 联想(北京)有限公司 | A kind of biopsy method, device and storage medium |
CN109034102A (en) * | 2018-08-14 | 2018-12-18 | 腾讯科技(深圳)有限公司 | Human face in-vivo detection method, device, equipment and storage medium |
CN110059673A (en) * | 2019-05-05 | 2019-07-26 | 重庆中科云从科技有限公司 | A kind of recognition of face premises automation test macro and method |
CN111222433A (en) * | 2019-12-30 | 2020-06-02 | 新大陆数字技术股份有限公司 | Automatic face auditing method, system, equipment and readable storage medium |
-
2020
- 2020-06-15 CN CN202010541380.5A patent/CN113807144A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101999900A (en) * | 2009-08-28 | 2011-04-06 | 南京壹进制信息技术有限公司 | Living body detecting method and system applied to human face recognition |
CN101770613A (en) * | 2010-01-19 | 2010-07-07 | 北京智慧眼科技发展有限公司 | Social insurance identity authentication method based on face recognition and living body detection |
CN106295571A (en) * | 2016-08-11 | 2017-01-04 | 深圳市赛为智能股份有限公司 | The face identification method of illumination adaptive and system |
CN107808115A (en) * | 2017-09-27 | 2018-03-16 | 联想(北京)有限公司 | A kind of biopsy method, device and storage medium |
US20190095701A1 (en) * | 2017-09-27 | 2019-03-28 | Lenovo (Beijing) Co., Ltd. | Living-body detection method, device and storage medium |
CN109034102A (en) * | 2018-08-14 | 2018-12-18 | 腾讯科技(深圳)有限公司 | Human face in-vivo detection method, device, equipment and storage medium |
CN110059673A (en) * | 2019-05-05 | 2019-07-26 | 重庆中科云从科技有限公司 | A kind of recognition of face premises automation test macro and method |
CN111222433A (en) * | 2019-12-30 | 2020-06-02 | 新大陆数字技术股份有限公司 | Automatic face auditing method, system, equipment and readable storage medium |
Non-Patent Citations (1)
Title |
---|
李浩;张玲;崔小利;: "生物识别中"活体检测"专利技术分析", 河南科技, no. 09 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107886032B (en) | Terminal device, smart phone, authentication method and system based on face recognition | |
CN109657554B (en) | Image identification method and device based on micro expression and related equipment | |
CN108319953B (en) | Occlusion detection method and device, electronic equipment and the storage medium of target object | |
CN112818767B (en) | Data set generation and forgery detection methods and devices, electronic equipment and storage medium | |
CN108549854A (en) | A kind of human face in-vivo detection method | |
CN110287671A (en) | Verification method and device, electronic equipment and storage medium | |
CN108900700A (en) | Authentication method and system based on the double verification that recognition of face and sight position | |
CN110428399A (en) | Method, apparatus, equipment and storage medium for detection image | |
CN109934187B (en) | Random challenge response method based on face activity detection-eye sight | |
WO2019017178A1 (en) | Method and apparatus for dynamically identifying a user of an account for posting images | |
CN208351494U (en) | Face identification system | |
Farrukh et al. | FaceRevelio: a face liveness detection system for smartphones with a single front camera | |
CN110599187A (en) | Payment method and device based on face recognition, computer equipment and storage medium | |
Nguyen et al. | Master face attacks on face recognition systems | |
CN109670285A (en) | Face recognition login method, device, computer equipment and storage medium | |
CN113642003A (en) | Safety detection method of face recognition system based on high-robustness confrontation sample generation | |
Di Martino et al. | Rethinking shape from shading for spoofing detection | |
CN113632137A (en) | System and method for adaptively constructing three-dimensional face model based on two or more inputs of two-dimensional face image | |
CN109886084B (en) | Face authentication method based on gyroscope, electronic equipment and storage medium | |
KR102581415B1 (en) | UBT system using face contour recognition AI to prevent the cheating behaviour and method thereof | |
CN113807144A (en) | Testing method of living body detection equipment | |
Shi et al. | Shield: An evaluation benchmark for face spoofing and forgery detection with multimodal large language models | |
CN115984978A (en) | Face living body detection method and device and computer readable storage medium | |
CN115082992A (en) | Face living body detection method and device, electronic equipment and readable storage medium | |
CN110162949B (en) | Method and device for controlling image display |
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 |