CN109359634B - Face living body detection method based on binocular camera - Google Patents
Face living body detection method based on binocular camera Download PDFInfo
- Publication number
- CN109359634B CN109359634B CN201811513776.8A CN201811513776A CN109359634B CN 109359634 B CN109359634 B CN 109359634B CN 201811513776 A CN201811513776 A CN 201811513776A CN 109359634 B CN109359634 B CN 109359634B
- Authority
- CN
- China
- Prior art keywords
- face
- image
- face image
- real
- detection method
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 33
- 238000002329 infrared spectrum Methods 0.000 claims description 21
- 238000001727 in vivo Methods 0.000 claims description 9
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 2
- 238000000034 method Methods 0.000 abstract description 9
- 230000000694 effects Effects 0.000 abstract description 3
- 230000009471 action Effects 0.000 abstract description 2
- 230000008569 process Effects 0.000 abstract description 2
- 239000003086 colorant Substances 0.000 description 3
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004397 blinking Effects 0.000 description 1
- 230000001680 brushing effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000001815 facial effect Effects 0.000 description 1
- 210000003128 head Anatomy 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
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
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
- G06V10/12—Details of acquisition arrangements; Constructional details thereof
- G06V10/14—Optical characteristics of the device performing the acquisition or on the illumination arrangements
- G06V10/147—Details of sensors, e.g. sensor lenses
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Vascular Medicine (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Image Analysis (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Collating Specific Patterns (AREA)
Abstract
The embodiment of the invention discloses a face living body detection method based on a binocular camera, which relates to the technical field of biological feature recognition, and comprises the following steps: acquiring scene images of the identification area in real time by using a binocular camera; detecting whether the acquired scene image contains a face image, if not, continuously keeping a scene image real-time acquisition mode, and if so, judging the attribute of the face image; and performing face recognition or returning to a scene image real-time acquisition mode according to the judgment result. The invention can solve the problems of low recognition effect, poor real-time performance and the like caused by the fact that the existing face recognition technology cannot directly and accurately distinguish the living body and the non-living body of the face, not only greatly improves the accuracy of the face living body detection, but also meets the real-time requirement on the detection time, and ensures that the whole detection process does not need the action cooperation of a user, so that the application scene of the living body detection is more extensive and efficient.
Description
Technical Field
The embodiment of the invention relates to the technical field of biological feature recognition, in particular to a face living body detection method based on a binocular camera.
Background
With the gradual maturity of the application of the biometric identification technology, the face identification becomes a relatively universal individual identification method at present and is applied to various different scenes. With the gradual and extensive application, the safety of face recognition is also severely challenged, for example, most of cells adopt face recognition access control, and a user can enter the face by brushing the face, but the current face recognition technology mainly recognizes according to the facial features of the face and cannot distinguish the differences of face entities, photos and 3D masks, so that the problem of paying attention to and researching on how to distinguish whether the face to be recognized is a real living face is solved.
Although the face recognition anti-cheating method based on the user interaction form exists, the method is limited in scene application, and various cooperation of a user is required, such as eye blinking, head shaking left and right, character reading and the like. The method has the advantages of high real-time performance, high light requirement and long time consumption, and the user experience effect is greatly reduced in public occasions such as a gate and a community entrance guard. Therefore, how to complete real-time human face living body detection under the condition that the user does not need any cooperation is a difficulty for scientific research to break.
Disclosure of Invention
Therefore, the embodiment of the invention provides a face living body detection method based on a binocular camera, which aims to solve the problems of low recognition effect, poor real-time performance and the like caused by the fact that the existing face recognition technology cannot directly and accurately distinguish a face living body from a non-living body.
In order to achieve the above object, an embodiment of the present invention provides the following: a face living body detection method based on a binocular camera comprises the following steps: acquiring scene images of the identification area in real time by using a binocular camera; detecting whether the acquired scene image contains a face image, if not, continuously keeping a scene image real-time acquisition mode, and if so, judging the attribute of the face image; performing face recognition or returning to a scene image real-time acquisition mode according to a judgment result; the binocular camera comprises a visible light camera and a near-infrared camera.
In the embodiment of the present invention, the attributes of the face image include an RGB face image collected by the visible light camera and an infrared spectrum black and white face image collected by the near-infrared camera.
In an embodiment of the present invention, the detection method further includes: and returning to a scene image real-time acquisition mode when detecting that the attribute of the face image is only that the RGB face image is acquired by the visible light camera.
In an embodiment of the present invention, the detection method further includes: when the attribute of the face image is detected to be only the infrared spectrum black-and-white face image collected by the near-infrared camera, Fourier transformation is carried out on the infrared spectrum black-and-white face image, then the high-frequency information characteristic average value of the transformed image is extracted, and then the high-frequency information characteristic average value is compared with a set threshold value.
In the implementation mode of the invention, if the high-frequency information characteristic average value is smaller than a set threshold, returning to a scene image real-time acquisition mode; and if the high-frequency information characteristic average value is larger than a set threshold value, carrying out face recognition.
In an embodiment of the present invention, the detection method further includes: and when the attributes of the face image comprise RGB face images and infrared spectrum black-and-white face images, the characteristics of the RGB face images and the infrared spectrum black-and-white face images are integrated, and whether the detected face is a living face is judged.
In an embodiment of the present invention, the method for determining whether a detected face is a living human face includes: the method comprises the steps of carrying out feature matching on face regions of an RGB face image and an infrared spectrum black-and-white face image, extracting image depth information, carrying out convolution on the image depth information and texture and color information of different size regions of the RGB face image by using a depth convolution neural network, extracting feature information, and judging whether face recognition is carried out or not according to the feature information.
In the embodiment of the invention, if the characteristic information is not matched with the face information in the database, a scene image real-time acquisition mode is returned, and if the characteristic information is matched with the face information in the database, face recognition is carried out.
According to the embodiment of the invention, the face living body detection method based on the binocular camera has the following advantages:
(1) the invention adopts a binocular camera with a visible light camera and a near infrared camera to collect images, and combines RGB face images and infrared spectrum black and white face images to detect, thereby having high detection accuracy;
(2) according to the invention, the RGB face image and the infrared spectrum black-and-white face image are processed through threshold comparison and convolution algorithm, so that the detection result can be directly obtained, user cooperation is not needed, and the real-time performance is higher;
(3) the binocular camera with the visible light camera and the near infrared camera can solve the problem of identified scenes, can identify the scenes no matter day or night, and can improve the applicability of the identified scenes.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It should be apparent that the drawings in the following description are merely exemplary, and that other embodiments can be derived from the drawings provided by those of ordinary skill in the art without inventive effort.
Fig. 1 is a flow chart of basic steps of a binocular camera-based human face in-vivo detection method according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating steps of a binocular camera-based human face in-vivo detection method according to an embodiment of the present invention under a certain condition;
fig. 3 is a flowchart illustrating steps of another situation of a binocular camera-based face in-vivo detection method according to an embodiment of the present invention;
Detailed Description
The present invention is described in terms of particular embodiments, other advantages and features of the invention will become apparent to those skilled in the art from the following disclosure, and it is to be understood that the described embodiments are merely exemplary of the invention and that it is not intended to limit the invention to the particular embodiments disclosed. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The embodiment provides a face living body detection method based on a binocular camera, and with reference to fig. 1, the method specifically includes the following steps:
s1: acquiring scene images of the identification area in real time by using a binocular camera;
s2: detecting whether the acquired scene image contains a face image, if not, continuously keeping a scene image real-time acquisition mode, and if so, judging the attribute of the face image;
s3: performing face recognition or returning to a scene image real-time acquisition mode according to a judgment result;
wherein, binocular camera includes visible light camera and near-infrared camera.
Specifically, the attributes of the face image include an RGB face image collected by a visible light camera and an infrared spectrum black and white face image collected by a near-infrared camera, where RGB represents colors of three channels of red, green, and blue, and the standard almost includes all colors that can be perceived by human vision, that is, the RGB face image is a face image obtained by collecting colors and identical to an image seen by naked eyes, and the infrared spectrum black and white face image is a black and white image formed by generating different spectrum bands by using infrared rays, that is, heat rays.
Further, in this embodiment, when the binocular camera detects that the attribute of the face image is only that the visible light camera acquires an RGB face image, it means that the near-infrared camera cannot detect a change in the face temperature in the same scene, that is, the image acquired by the visible light camera may be a photograph or a statue or other things without vital signs, then face recognition is not performed, the scene image real-time acquisition mode is returned, and the image acquisition is continued.
Further, referring to fig. 2, in this embodiment, when it is detected that the attribute of the face image is only an infrared spectrum black-and-white face image collected by a near-infrared camera, a visible light camera does not collect an RGB face image, which may be because light in a scene is too dark or is blocked by a foreign object, at this time, preprocessing the infrared spectrum black-and-white face image is required, then performing fourier transform on the infrared spectrum black-and-white face image, extracting a high frequency information feature average value of the transformed image, and then comparing the high frequency information feature average value with a set threshold value, where the set threshold value is a feature critical value of a living body face with a vital sign obtained through data calculation. If the high-frequency information characteristic average value is smaller than a set threshold value, indicating that the scene is a non-living human face, and returning to a scene image real-time acquisition mode; and if the high-frequency information characteristic average value is larger than the set threshold value, indicating that the scene is a living human face, and then cutting the human face area in the infrared spectrum black-and-white human face image and then identifying the human face.
Further, referring to fig. 3, when the attributes of the detected face image include both RGB face images and infrared spectrum black and white face images, indicating that both the visible light camera and the near-infrared camera acquire the face image, the features of the RGB face images and the infrared spectrum black and white face images are integrated to determine whether the detected face is a living face. Specifically, feature matching is carried out on face regions of an RGB face image and an infrared spectrum black-and-white face image, image depth information is extracted, a depth convolution neural network is used for carrying out convolution on the image depth information and texture and color information of different size regions of the RGB face image, feature information is extracted, if the extracted feature information is not matched with face information in a database, a scene image real-time acquisition mode is returned, and if the feature information is matched with the face information in the database, face recognition is carried out.
The embodiment not only greatly improves the accuracy of the in-vivo detection, but also meets the real-time requirement on the detection time, and the whole detection process does not need the user to perform action coordination, so that the application scene of the in-vivo detection is more extensive and efficient.
Although the invention has been described in detail above with reference to a general description and specific examples, it will be apparent to one skilled in the art that modifications or improvements may be made thereto based on the invention. Accordingly, such modifications and improvements are intended to be within the scope of the invention as claimed.
Claims (6)
1. A face living body detection method based on a binocular camera is characterized by comprising the following steps:
acquiring scene images of the identification area in real time by using a binocular camera;
detecting whether the acquired scene image contains a face image, if not, continuously keeping a scene image real-time acquisition mode, and if so, judging the attribute of the face image;
performing face recognition or returning to a scene image real-time acquisition mode according to a judgment result;
the binocular camera comprises a visible light camera and a near infrared camera;
when the attributes of the face image comprise an RGB face image and an infrared spectrum black-and-white face image, performing feature matching on face regions of the RGB face image and the infrared spectrum black-and-white face image, extracting image depth information, performing convolution on the image depth information and texture and color information of different size regions of the RGB face image by using a depth convolution neural network, extracting feature information, and judging whether face recognition is performed or not according to the feature information.
2. The binocular camera-based living human face detection method of claim 1, wherein the attributes of the human face image comprise an RGB human face image collected by the visible light camera and an infrared band black and white human face image collected by the near infrared camera.
3. The binocular camera based human face in-vivo detection method of claim 1, wherein the detection method further comprises: and returning to a scene image real-time acquisition mode when detecting that the attribute of the face image is only that the RGB face image is acquired by the visible light camera.
4. The binocular camera based human face in-vivo detection method of claim 1, wherein the detection method further comprises: when the attribute of the face image is detected to be only the infrared spectrum black-and-white face image collected by the near-infrared camera, Fourier transformation is carried out on the infrared spectrum black-and-white face image, then the high-frequency information characteristic average value of the transformed image is extracted, and then the high-frequency information characteristic average value is compared with a set threshold value.
5. The binocular camera based human face in-vivo detection method of claim 4, wherein if the high frequency information feature average value is smaller than a set threshold, a scene image real-time acquisition mode is returned; and if the high-frequency information characteristic average value is larger than a set threshold value, carrying out face recognition.
6. The binocular camera based human face in-vivo detection method of claim 1, wherein if the feature information does not match with the human face information in the database, a real-time scene image acquisition mode is returned, and if the feature information matches with the human face information in the database, human face recognition is performed.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811513776.8A CN109359634B (en) | 2018-12-11 | 2018-12-11 | Face living body detection method based on binocular camera |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811513776.8A CN109359634B (en) | 2018-12-11 | 2018-12-11 | Face living body detection method based on binocular camera |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109359634A CN109359634A (en) | 2019-02-19 |
CN109359634B true CN109359634B (en) | 2021-11-16 |
Family
ID=65330424
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811513776.8A Active CN109359634B (en) | 2018-12-11 | 2018-12-11 | Face living body detection method based on binocular camera |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109359634B (en) |
Families Citing this family (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109961062A (en) * | 2019-04-16 | 2019-07-02 | 北京迈格威科技有限公司 | Image-recognizing method, device, terminal and readable storage medium storing program for executing |
CN110134233B (en) * | 2019-04-24 | 2022-07-12 | 福建联迪商用设备有限公司 | Intelligent sound box awakening method based on face recognition and terminal |
CN110363087B (en) * | 2019-06-12 | 2022-02-25 | 苏宁云计算有限公司 | Long-baseline binocular face in-vivo detection method and system |
CN110276301A (en) * | 2019-06-24 | 2019-09-24 | 泰康保险集团股份有限公司 | Face identification method, device, medium and electronic equipment |
CN110503023A (en) * | 2019-08-19 | 2019-11-26 | 深圳市商汤科技有限公司 | Biopsy method and device, electronic equipment and storage medium |
CN110909617B (en) * | 2019-10-28 | 2022-03-25 | 广州多益网络股份有限公司 | Living body face detection method and device based on binocular vision |
CN111063079B (en) * | 2019-11-27 | 2022-04-15 | 深圳云天励飞技术有限公司 | Binocular living body face detection method and device based on access control system |
CN110705530B (en) * | 2019-12-13 | 2020-05-15 | 珠海亿智电子科技有限公司 | Method, device and equipment for binocular live recognition of same face frame and storage medium |
CN112700557A (en) * | 2020-12-24 | 2021-04-23 | 北京慧同科技有限公司 | Self-service ticket taking and returning method |
CN113537233B (en) * | 2021-06-03 | 2023-07-18 | 北京航空航天大学 | Method and device for extracting typical target material attribute by combining visible light and near infrared information |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104143078A (en) * | 2013-05-09 | 2014-11-12 | 腾讯科技(深圳)有限公司 | Living body face recognition method and device and equipment |
CN107657248A (en) * | 2017-10-26 | 2018-02-02 | 广州云从信息科技有限公司 | A kind of infrared binocular In vivo detections of Android based on recognition of face certification |
CN108345818A (en) * | 2017-01-23 | 2018-07-31 | 北京中科奥森数据科技有限公司 | A kind of human face in-vivo detection method and device |
CN108764071A (en) * | 2018-05-11 | 2018-11-06 | 四川大学 | It is a kind of based on infrared and visible images real human face detection method and device |
CN108776786A (en) * | 2018-06-04 | 2018-11-09 | 北京京东金融科技控股有限公司 | Method and apparatus for generating user's truth identification model |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7103227B2 (en) * | 2003-03-19 | 2006-09-05 | Mitsubishi Electric Research Laboratories, Inc. | Enhancing low quality images of naturally illuminated scenes |
-
2018
- 2018-12-11 CN CN201811513776.8A patent/CN109359634B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104143078A (en) * | 2013-05-09 | 2014-11-12 | 腾讯科技(深圳)有限公司 | Living body face recognition method and device and equipment |
CN108345818A (en) * | 2017-01-23 | 2018-07-31 | 北京中科奥森数据科技有限公司 | A kind of human face in-vivo detection method and device |
CN107657248A (en) * | 2017-10-26 | 2018-02-02 | 广州云从信息科技有限公司 | A kind of infrared binocular In vivo detections of Android based on recognition of face certification |
CN108764071A (en) * | 2018-05-11 | 2018-11-06 | 四川大学 | It is a kind of based on infrared and visible images real human face detection method and device |
CN108776786A (en) * | 2018-06-04 | 2018-11-09 | 北京京东金融科技控股有限公司 | Method and apparatus for generating user's truth identification model |
Also Published As
Publication number | Publication date |
---|---|
CN109359634A (en) | 2019-02-19 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109359634B (en) | Face living body detection method based on binocular camera | |
CN107862299B (en) | Living body face detection method based on near-infrared and visible light binocular cameras | |
CN106874871B (en) | Living body face double-camera identification method and identification device | |
CN108229362B (en) | Binocular face recognition living body detection method based on access control system | |
CN101706874A (en) | Method for face detection based on features of skin colors | |
CN106503644B (en) | Glasses attribute detection method based on edge projection and color characteristic | |
CN104408780A (en) | Face recognition attendance system | |
Atharifard et al. | Robust component-based face detection using color feature | |
CN112818722A (en) | Modular dynamically configurable living body face recognition system | |
Zheng | Face detection and eyeglasses detection for thermal face recognition | |
Gritzman et al. | Comparison of colour transforms used in lip segmentation algorithms | |
CN111523344A (en) | Human body living body detection system and method | |
CN107862298B (en) | Winking living body detection method based on infrared camera device | |
CN110598574A (en) | Intelligent face monitoring and identifying method and system | |
CN111767788A (en) | Non-interactive monocular in vivo detection method | |
CN109308436B (en) | Living body face recognition method based on active infrared video | |
Supriyanti et al. | Detecting pupil and iris under uncontrolled illumination using fixed-Hough circle transform | |
Bakshi et al. | Optimized periocular template selection for human recognition | |
Azad et al. | A robust and adaptable method for face detection based on color probabilistic estimation technique | |
CN110069962A (en) | A kind of biopsy method and system | |
Kumar et al. | Skin color segmentation for detecting human face region in image | |
CN104573743A (en) | Filtering method for facial image detection | |
Moorhouse et al. | The nose on your face may not be so plain: Using the nose as a biometric | |
Borah et al. | A human face detection method based on connected component analysis | |
WO2015103953A1 (en) | Method and device for extracting iris image image under condition of non-uniform illumination |
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 | ||
PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A Face Live Detection Method Based on Binocular Cameras Granted publication date: 20211116 Pledgee: Industrial Bank Limited by Share Ltd. Xi'an branch Pledgor: XI'AN GLASSSIX NETWORK TECHNOLOGY CO.,LTD. Registration number: Y2024980010126 |
|
PE01 | Entry into force of the registration of the contract for pledge of patent right |