CN109977846B - Living body detection method and system based on near-infrared monocular photography - Google Patents
Living body detection method and system based on near-infrared monocular photography Download PDFInfo
- Publication number
- CN109977846B CN109977846B CN201910221151.2A CN201910221151A CN109977846B CN 109977846 B CN109977846 B CN 109977846B CN 201910221151 A CN201910221151 A CN 201910221151A CN 109977846 B CN109977846 B CN 109977846B
- Authority
- CN
- China
- Prior art keywords
- infrared
- features
- image
- face
- infrared image
- 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.)
- Active
Links
Images
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
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
-
- 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
- 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
- G06V40/10—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
- G06V40/174—Facial expression recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/40—Spoof detection, e.g. liveness detection
- G06V40/45—Detection of the body part being alive
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention provides a living body detection method based on near-infrared monocular photography, which comprises the following steps: collecting near-infrared image information; detecting whether the near-infrared image contains a human face, and if the human face is not detected, judging that the identification object is a non-real person; if the face is detected, prompting the user to make a specified expression action; extracting the optical flow characteristics of the expression motions and extracting the facial image depth characteristics of the near-infrared images; inputting the optical flow features and the facial image depth features into a deep learning classifier; obtaining a face recognition result; the invention can effectively prevent the attack of videos and three-dimensional masks and improve the accuracy of in vivo detection.
Description
Technical Field
The invention relates to the field of security identification, in particular to a living body detection method and system based on near-infrared monocular photography.
Background
In recent years, the face recognition technology is widely commercialized, but faces are easily counterfeited by means of photos, videos, three-dimensional masks and the like, so that face living body detection is an important issue for safety of face recognition and authentication systems. From the type of image acquisition equipment for living body detection, the currently common living body detection mainly comprises visible light image acquisition and multispectral image acquisition, wherein the multispectral image acquisition comprises near infrared imaging equipment, far infrared imaging equipment, thermal infrared imaging equipment and the like; from the realization method of the living body detection, there are an interactive living body detection method and a non-interactive living body detection method, and the interactive living body detection method includes distinguishing whether a person is a real person through actions of blinking, opening a mouth and the like of a user. While non-interactive liveness detection need not be accomplished through user cooperation.
The living body detection method based on visible light has the advantages of low cost and no need of adding hardware equipment for living body detection of mobile users such as mobile phones; the method has the defects of poor robustness, high susceptibility to light change and the like, and incapability of judging high-definition video attack. The visible light-based in vivo sensing can only be used in a less secure setting.
The multispectral image processing method usually adopts binocular cameras, including a visible light camera and an infrared camera. The method has the advantages that multispectral information is provided, and the adaptability of the algorithm can be further improved; the disadvantage is that hardware cost and power consumption are increased and for some portable small devices it may not be possible to install two cameras at the same time.
Interactive living body detection usually uses a visible light camera to collect data, and uses a system to send an action instruction to a user to judge whether the user is a real person. The defect is that the common actions of blinking and opening the mouth cannot be judged whether the real person wears the mask or not, and then the action is performed through the holes of the mask. In addition, the action attack of the high-definition video cannot be judged.
The non-interactive live body detection mainly determines whether a live body is a human being or not from information of a single frame image. Its advantages are high reaction speed, low accuracy and easy attack.
Disclosure of Invention
In view of the problems in the prior art, the invention provides a living body detection method and system based on near-infrared monocular photography, and mainly solves the problems of poor robustness and high cost in the prior art.
In order to achieve the above and other objects, the present invention adopts the following technical solutions.
A living body detection method based on near-infrared monocular photography comprises the following steps:
collecting near-infrared image information;
detecting whether the near-infrared image contains a human face, and if the human face is not detected, judging that the identification object is a non-real person; if the face is detected, prompting the user to make a specified expression action;
extracting the optical flow characteristics of the expression actions and extracting the facial image depth characteristics of the near-infrared images;
inputting the optical flow features and the facial image depth features into a deep learning classifier;
and obtaining a living body detection result.
Optionally, a near-infrared monocular camera is used to collect the near-infrared image. The near-infrared monocular camera comprises a 850nm near-infrared monocular camera, only collects near-infrared images, does not need a visible light camera, and reduces equipment cost and power consumption.
Optionally, an infrared fill-in light source for filtering background light interference is introduced when the near-infrared image is collected. The effective distance of infrared light filling light source is shorter, but to a great extent filtering ambient light's interference improves the rate of accuracy that detects.
Optionally, the extracting the depth feature of the facial image specifically includes:
inputting the detected near-infrared image information containing the human face into a convolutional layer of a deep learning neural network to obtain near-infrared image characteristics; and activating the human face features in the near-infrared image features by acting on each convolution layer through a first activation function, and finally obtaining the facial image depth features.
Optionally, a specific implementation process of the deep learning classifier includes:
and combining the facial image depth features and the optical flow features, inputting the combined features into full-link layers of the deep learning classifier, activating corresponding facial expression and action features by acting on each full-link layer through a second activation function, and judging whether an identified object is a real face according to the facial expression and action features.
Optionally, the first activation function comprises:
wherein x is the near infrared image feature and y is the output of the activation function.
Optionally, the second activation function comprises:
wherein x is the combined feature of the depth feature and the optical flow feature of the face image, and y is the output of the activation function. The first activation function and the second activation function have strong expression capability and good convergence performance, and can effectively improve the accuracy of the deep neural network algorithm.
A living body detection system based on near-infrared monocular photography, comprising:
the near-infrared image acquisition module is used for acquiring a near-infrared image;
the detection module is used for detecting whether a human face exists in the near-infrared image;
the action prompting module is used for prompting a user to make a specified expression action;
the feature extraction module is used for extracting optical flow features of facial expression actions;
the deep learning identification module is used for identifying the facial image and the optical flow information of the facial expression and action;
the output end of the near-infrared image acquisition module is connected with the input ends of the detection module and the characteristic extraction module; the output end of the detection module is connected with the input ends of the action prompt module and the deep learning identification module, and the output end of the feature extraction module is connected with the deep learning identification module.
Optionally, the near-infrared image acquisition module includes a near-infrared monocular camera and an infrared supplementary lighting light source.
Optionally, the deep learning identification module includes a near-infrared face image feature extraction unit and a depth identification unit for identifying optical flow features and near-infrared face image features; the output end of the near-infrared face image feature extraction unit is connected with the input end of the depth recognition unit.
As described above, the method and system for detecting a living body based on near-infrared monocular imaging according to the present invention have the following advantageous effects.
An infrared light supplement light source is introduced, so that the interference of ambient light can be effectively filtered; by detecting the face information of the near-infrared image, the attack of a video or a photo can be effectively avoided; the monocular camera shooting is adopted to reduce the system cost and the power consumption; according to the optical flow characteristics of the expression actions, the attack of the three-dimensional mask can be prevented.
Drawings
Fig. 1 is a flowchart of a biopsy method based on near-infrared monocular photography according to the present invention.
Fig. 2 is a structural block diagram of a living body detection system based on near-infrared monocular photography according to the present invention.
Detailed Description
The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It should be noted that the features in the following embodiments and examples may be combined with each other without conflict.
It should be noted that the drawings provided in the following embodiments are only for illustrating the basic idea of the present invention, and the components related to the present invention are only shown in the drawings rather than drawn according to the number, shape and size of the components in actual implementation, and the type, quantity and proportion of the components in actual implementation may be changed freely, and the layout of the components may be more complicated.
Referring to fig. 1, in an embodiment, the present invention provides a living body detection method based on near-infrared monocular photography, including:
collecting near-infrared image information;
detecting whether the near-infrared image contains a human face, and if the human face is not detected, judging that the identification object is a non-real person; if the face is detected, prompting the user to make a specified expression action;
extracting the optical flow characteristics of the expression actions and extracting the facial image depth characteristics of the near-infrared images;
inputting the optical flow features and the facial image depth features into a deep learning classifier;
and obtaining a living body detection result.
The collected near-infrared image information is mainly matched with an infrared light supplementing light source through a near-infrared monocular camera; in one embodiment, the near-infrared monocular camera includes a 850nm near-infrared monocular camera, and other short-wave near-infrared cameras can be adopted to achieve the same effect. The infrared light supplementing light source with a short effective distance is adopted, so that the interference of ambient light can be effectively filtered, the effect of the collected near-infrared image is enhanced, and the misjudgment rate of the detection process is reduced.
And detecting the near-infrared image and judging whether a human face exists in the near-infrared image. The detection aims at preventing video attacks and other means, because the video attacks need to be displayed on a screen, and the screen can be a mobile phone, a computer monitor, a notebook, a television or other devices. And the displays can fully absorb near infrared light, so that pictures obtained after the screen is shot by the near infrared light are all black, and the human face cannot be detected. Therefore, if the face image cannot be detected in the acquired near-infrared image, it indicates that no face appears before the current camera, or the image is a video attack using a screen. If the face image information can be detected, it indicates that the current video or image which is not displayed through the screen is not in front of the camera.
When the collected near-infrared image information is detected to contain a human face, sending the corresponding near-infrared image to the deep learning neural network model, and inputting the near-infrared image into a convolution layer of the deep learning neural network model to obtain the characteristics of the near-infrared image; and activating the human face features in the near-infrared image features by acting on each layer of convolution layer through a first activation function, and finally obtaining the depth features of the face image. The first activation function includes:
wherein x is the near infrared image feature and y is the output of the activation function.
When the collected near-infrared image is detected to contain the face, prompt information is sent to the user to prompt the user to make a specified expression action. The prompt information comprises character display, voice prompt and the like; in one embodiment, the expressive actions mainly include smiling and frowning, which are selected rather than blinking and opening the mouth, because for blinking and opening the mouth, the system can be deceived by a real person wearing a mask with eyes and mouth holes in the hole to do the action. The two expressions of frown and smile involve more facial muscles whose tone cannot be simulated by the three-dimensional mask.
And after the near-infrared monocular camera collects the expression and the action of the user, calculating the sparse light stream characteristics between two interval frames. The sparse optical flow is a method for calculating motion information of an object between adjacent frames by finding out a corresponding relation between a previous frame and a current frame by using the change of pixels in an image sequence on a time domain and the correlation between the adjacent frames.
And inputting the obtained facial image depth features and the sparse optical flow features into a deep learning classifier of a depth neural network model, combining the facial image depth features and the optical flow features, inputting the combined features into a full connection layer of the deep learning classifier, and activating corresponding expression action features by acting on each full connection layer through a second activation function. And judging whether the acquired near-infrared image is a real image or not according to the expression action characteristics. In an embodiment, the deep neural network model is a deep learning model obtained by training a large number of near-infrared face images.
The second activation function includes:
wherein x is the combined feature of the depth feature and the optical flow feature of the face image, and y is the output of the activation function.
The first activation function and the second activation function have strong expression capability and good convergence performance, and can effectively improve the accuracy of the deep neural network algorithm.
Referring to fig. 2, in another embodiment, a living body detecting system based on near-infrared monocular photography according to the present invention includes:
the near-infrared image acquisition module is used for acquiring a near-infrared image;
the detection module is used for detecting whether a human face exists in the near-infrared image;
the action prompting module is used for prompting a user to make a specified expression action;
the feature extraction module is used for extracting the optical flow features of the facial expression actions;
the deep learning identification module is used for identifying the facial image and the optical flow information of the facial expression and action;
the output end of the near-infrared image acquisition module is connected with the input ends of the detection module and the characteristic extraction module; the output end of the detection module is connected with the input ends of the action prompt module and the deep learning identification module, and the output end of the feature extraction module is connected with the deep learning identification module.
The near-infrared image acquisition module comprises a near-infrared monocular camera and an infrared light supplementing light source. The near-infrared monocular camera comprises a 850nm near-infrared monocular camera, and other short-wave near-infrared cameras can be adopted to achieve the same effect. The infrared light supplementing light source with a short effective distance is adopted, so that the interference of ambient light can be effectively filtered, the effect of the collected near-infrared image is enhanced, and the misjudgment rate of the detection process is reduced.
The detection module receives the near-infrared image acquired by the near-infrared image acquisition module, detects whether the near-infrared image contains a face, and if the near-infrared image does not contain the face, judges that no face exists in front of the current monocular camera or a face video or image presented by a display screen in front of the camera is available. And if the detection result is that the human face is included, sending the corresponding near-infrared image to the deep learning identification module. The deep learning identification module is obtained by training a large number of near-infrared face images. The deep learning identification module comprises a near-infrared face image feature extraction unit and a deep identification unit for identifying optical flow features and infrared face image features.
Inputting the near-infrared image into the near-infrared face image feature extraction unit to obtain near-infrared image features; and activating the human face features in the near-infrared image features through a first activation function to obtain the depth features of the face image. The first activation function includes:
wherein x is the near infrared image feature and y is the output of the activation function.
The detection module also sends a detection result to the action prompt module, and if the collected near-infrared image contains the face, the action prompt module sends prompt information to the user according to the detection result of the detection module to prompt the user to make a specified expression action. In one embodiment, the prompt message includes a text display and a voice prompt. The specified expressive actions include smiling and frowning.
The near-infrared image acquisition module acquires facial expression and actions and sends near-infrared images corresponding to the expression and actions to the feature extraction module to obtain sparse light stream features.
And combining the sparse optical flow characteristics and the facial image depth characteristics, inputting the sparse optical flow characteristics and the facial image depth characteristics into the full-connection layers of the depth recognition unit, and then acting on each full-connection layer through a second activation function to activate corresponding expression and action characteristics. And judging whether the acquired near-infrared image is a real image or not according to the finally obtained expression and action characteristics.
The second activation function includes:
wherein x is the combined feature of the depth feature and the optical flow feature of the face image, and y is the output of the activation function.
In conclusion, the living body detection method and system based on the near-infrared monocular camera only use the near-infrared image acquired by the near-infrared monocular camera to carry out living body detection, and do not need visible light images, so that the system cost and power consumption are reduced; the infrared light supplement light source effectively filters background light interference, and the quality of the collected image is improved; the activation function with strong expression capability and good convergence is adopted, so that the identification accuracy can be effectively improved; the near-infrared image is combined with the sparse optical flow characteristic, so that the attack of the video and the three-dimensional mask can be effectively prevented. Therefore, the invention effectively overcomes various defects in the prior art and has high industrial utilization value.
The foregoing embodiments are merely illustrative of the principles and utilities of the present invention and are not intended to limit the invention. Those skilled in the art can modify or change the above-described embodiments without departing from the spirit and scope of the present invention. Accordingly, it is intended that all equivalent modifications or changes which can be made by those skilled in the art without departing from the spirit and technical spirit of the present invention be covered by the claims of the present invention.
Claims (8)
1. A living body detection method based on near-infrared monocular photography is characterized by comprising the following steps:
collecting near-infrared image information;
detecting whether the near-infrared image contains a face or not, and if the face is not detected, judging that the identification object is a non-real person; if the face is detected, prompting the user to make a specified expression action;
extracting the optical flow characteristics of the expression motions and extracting the facial image depth characteristics of the near-infrared images;
inputting the optical flow characteristics and the facial image depth characteristics into a deep learning classifier to obtain a living body detection result, wherein the specific execution process of the deep learning classifier comprises the following steps: and combining the facial image depth features and the optical flow features, inputting the combined facial image depth features and the optical flow features into full-link layers of the deep learning classifier, activating corresponding facial expression and action features by acting on each full-link layer through a second activation function, and judging whether the recognition object is a real face according to the finally obtained facial expression and action features.
2. The method of claim 1, wherein the near-infrared monocular camera is used to capture the near-infrared image.
3. The in-vivo detection method based on near-infrared monocular photography according to claim 2, wherein an infrared supplementary lighting source for filtering background light interference is introduced when the near-infrared image is collected.
4. The living body detection method based on near-infrared monocular photography according to claim 1, wherein the extracting of the facial image depth feature of the near-infrared image specifically comprises:
inputting the near-infrared image information including the detected face into a convolution layer of a deep learning neural network to obtain near-infrared image characteristics; and activating the human face features in the near-infrared image features by acting on each convolution layer through a first activation function, and finally obtaining the facial image depth features.
5. The near-infrared monocular camera-based liveness detection method of claim 4, wherein the first activation function comprises:
wherein x is the near infrared image feature and y is the output of the activation function.
6. The method of claim 1, wherein the second activation function comprises:
wherein x is the combined feature of the depth feature and the optical flow feature of the face image, and y is the output of the activation function.
7. A living body detection system based on near-infrared monocular photography, comprising:
the near-infrared image acquisition module is used for acquiring a near-infrared image;
the detection module is used for detecting whether a human face exists in the near-infrared image;
the action prompting module is used for prompting a user to make a specified expression action;
the characteristic extraction module is used for extracting the optical flow characteristics of the expression actions, inputting the near-infrared image information including the detected face into the convolution layer of the deep learning neural network, and obtaining the near-infrared image characteristics; activating the human face features in the near-infrared image features by acting on each layer of convolution layer through a first activation function, and finally obtaining the depth features of the facial image;
the deep learning identification module is used for identifying a face image in the near-infrared image and optical flow information of the expression action;
the output end of the near-infrared image acquisition module is connected with the input ends of the detection module and the feature extraction module; the output end of the detection module is connected with the input ends of the action prompt module and the deep learning identification module, and the output end of the feature extraction module is connected with the deep learning identification module; the deep learning identification module comprises a near-infrared face image feature extraction unit and a depth identification unit for identifying optical flow features and face image depth features; the output end of the near-infrared face image feature extraction unit is connected with the input end of the depth recognition unit, and the specific execution process of the depth recognition unit comprises the following steps: and combining the facial image depth features and the optical flow features, inputting the combined facial image depth features and the optical flow features into the full-connection layers of the depth recognition unit, activating corresponding facial expression and action features by acting on each full-connection layer through a second activation function, and judging whether the recognition object is a real face according to the finally obtained facial expression and action features.
8. The near-infrared monocular camera-based biopsy system of claim 7, wherein the near-infrared image acquisition module comprises a near-infrared monocular camera and an infrared fill-in light source.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910221151.2A CN109977846B (en) | 2019-03-22 | 2019-03-22 | Living body detection method and system based on near-infrared monocular photography |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910221151.2A CN109977846B (en) | 2019-03-22 | 2019-03-22 | Living body detection method and system based on near-infrared monocular photography |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109977846A CN109977846A (en) | 2019-07-05 |
| CN109977846B true CN109977846B (en) | 2023-02-10 |
Family
ID=67080001
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910221151.2A Active CN109977846B (en) | 2019-03-22 | 2019-03-22 | Living body detection method and system based on near-infrared monocular photography |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109977846B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110991307B (en) * | 2019-11-27 | 2023-09-26 | 北京锐安科技有限公司 | Face recognition method, device, equipment and storage medium |
| CN112597932A (en) * | 2020-12-28 | 2021-04-02 | 上海汽车集团股份有限公司 | Living body detection method and device and computer readable storage medium |
| CN113066237B (en) * | 2021-03-26 | 2022-12-23 | 中国工商银行股份有限公司 | Face living body detection and identification method for automatic teller machine and automatic teller machine |
| CN113691696A (en) * | 2021-07-23 | 2021-11-23 | 杭州魔点科技有限公司 | Face recognition method based on camera module and camera module |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2546996A1 (en) * | 2005-05-17 | 2006-11-17 | Spectratech Inc. | Optical coherence tomograph |
| CN108664922A (en) * | 2018-05-10 | 2018-10-16 | 东华大学 | A kind of infrared video Human bodys' response method based on personal safety |
| CN109308436A (en) * | 2017-07-28 | 2019-02-05 | 西南科技大学 | A kind of living body faces recognition methods based on active infrared video |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3161658B1 (en) * | 2014-12-19 | 2019-03-20 | SZ DJI Technology Co., Ltd. | Optical-flow imaging system and method using ultrasonic depth sensing |
| CN105787458B (en) * | 2016-03-11 | 2019-01-04 | 重庆邮电大学 | The infrared behavior recognition methods adaptively merged based on artificial design features and deep learning feature |
| CN106203369A (en) * | 2016-07-18 | 2016-12-07 | 三峡大学 | Active stochastic and dynamic for anti-counterfeiting recognition of face instructs generation system |
| CN206672320U (en) * | 2017-04-18 | 2017-11-24 | 中国科学院重庆绿色智能技术研究院 | A kind of reverse crowd regulation warning system in region |
| CN107358181A (en) * | 2017-06-28 | 2017-11-17 | 重庆中科云丛科技有限公司 | The infrared visible image capturing head device and method of monocular judged for face live body |
| CN107368798B (en) * | 2017-07-07 | 2019-11-29 | 四川大学 | A kind of crowd's Emotion identification method based on deep learning |
| CN108875509A (en) * | 2017-11-23 | 2018-11-23 | 北京旷视科技有限公司 | Biopsy method, device and system and storage medium |
| CN108062546B (en) * | 2018-02-11 | 2020-04-07 | 厦门华厦学院 | Computer face emotion recognition system |
| CN109145817A (en) * | 2018-08-21 | 2019-01-04 | 佛山市南海区广工大数控装备协同创新研究院 | A kind of face In vivo detection recognition methods |
-
2019
- 2019-03-22 CN CN201910221151.2A patent/CN109977846B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2546996A1 (en) * | 2005-05-17 | 2006-11-17 | Spectratech Inc. | Optical coherence tomograph |
| CN109308436A (en) * | 2017-07-28 | 2019-02-05 | 西南科技大学 | A kind of living body faces recognition methods based on active infrared video |
| CN108664922A (en) * | 2018-05-10 | 2018-10-16 | 东华大学 | A kind of infrared video Human bodys' response method based on personal safety |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109977846A (en) | 2019-07-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109977846B (en) | Living body detection method and system based on near-infrared monocular photography | |
| CN108197586B (en) | Face recognition method and device | |
| CN108764071B (en) | Real face detection method and device based on infrared and visible light images | |
| WO2018040307A1 (en) | Vivo detection method and device based on infrared visible binocular image | |
| da Silva Pinto et al. | Video-based face spoofing detection through visual rhythm analysis | |
| CN107370942B (en) | Photographing method, photographing device, storage medium and terminal | |
| CN104834901B (en) | A kind of method for detecting human face, apparatus and system based on binocular stereo vision | |
| US20150310259A1 (en) | Using facial data for device authentication or subject identification | |
| CN109190522B (en) | Living body detection method based on infrared camera | |
| WO2021027537A1 (en) | Method and apparatus for taking identification photo, device and storage medium | |
| CN108470169A (en) | Face identification system and method | |
| CN108229369A (en) | Image capturing method, device, storage medium and electronic equipment | |
| Wang et al. | InSight: recognizing humans without face recognition | |
| CN110837750B (en) | Face quality evaluation method and device | |
| CN116582741B (en) | Shooting method and equipment | |
| CN104361326A (en) | Method for distinguishing living human face | |
| CN108537131B (en) | Face recognition living body detection method based on face characteristic points and optical flow field | |
| CN108875468B (en) | Living body detection method, living body detection system, and storage medium | |
| WO2019011073A1 (en) | Human face live detection method and related product | |
| CN103731583A (en) | Integrated device for intelligent photograph synthesizing and printing and processing method for intelligent photograph synthesizing and printing | |
| CN111382592A (en) | Living body detection method and apparatus | |
| CN106412420B (en) | It is a kind of to interact implementation method of taking pictures | |
| CN109657627A (en) | Auth method, device and electronic equipment | |
| CN112434546A (en) | Face living body detection method and device, equipment and storage medium | |
| CN208351494U (en) | Face identification system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |