CN113011391A - Optical system and method for face recognition living body detection - Google Patents
Optical system and method for face recognition living body detection Download PDFInfo
- Publication number
- CN113011391A CN113011391A CN202110447263.7A CN202110447263A CN113011391A CN 113011391 A CN113011391 A CN 113011391A CN 202110447263 A CN202110447263 A CN 202110447263A CN 113011391 A CN113011391 A CN 113011391A
- Authority
- CN
- China
- Prior art keywords
- visible light
- carbon dioxide
- ybf
- zns
- band
- 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.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 55
- 230000003287 optical effect Effects 0.000 title claims abstract description 24
- 238000000034 method Methods 0.000 title claims description 17
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 claims abstract description 138
- 229910002092 carbon dioxide Inorganic materials 0.000 claims abstract description 69
- 239000001569 carbon dioxide Substances 0.000 claims abstract description 69
- 229910009520 YbF3 Inorganic materials 0.000 claims description 48
- 229910052984 zinc sulfide Inorganic materials 0.000 claims description 47
- 239000000463 material Substances 0.000 claims description 11
- PQXKHYXIUOZZFA-UHFFFAOYSA-M lithium fluoride Chemical compound [Li+].[F-] PQXKHYXIUOZZFA-UHFFFAOYSA-M 0.000 claims description 6
- 239000000758 substrate Substances 0.000 claims description 6
- 229910052594 sapphire Inorganic materials 0.000 claims description 5
- 239000010980 sapphire Substances 0.000 claims description 5
- PFNQVRZLDWYSCW-UHFFFAOYSA-N (fluoren-9-ylideneamino) n-naphthalen-1-ylcarbamate Chemical compound C12=CC=CC=C2C2=CC=CC=C2C1=NOC(=O)NC1=CC=CC2=CC=CC=C12 PFNQVRZLDWYSCW-UHFFFAOYSA-N 0.000 claims description 3
- 239000005083 Zinc sulfide Substances 0.000 claims description 3
- OYLGJCQECKOTOL-UHFFFAOYSA-L barium fluoride Chemical compound [F-].[F-].[Ba+2] OYLGJCQECKOTOL-UHFFFAOYSA-L 0.000 claims description 3
- 229910001632 barium fluoride Inorganic materials 0.000 claims description 3
- WUKWITHWXAAZEY-UHFFFAOYSA-L calcium difluoride Chemical compound [F-].[F-].[Ca+2] WUKWITHWXAAZEY-UHFFFAOYSA-L 0.000 claims description 3
- 229910001634 calcium fluoride Inorganic materials 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- ORUIBWPALBXDOA-UHFFFAOYSA-L magnesium fluoride Chemical compound [F-].[F-].[Mg+2] ORUIBWPALBXDOA-UHFFFAOYSA-L 0.000 claims description 3
- 229910001635 magnesium fluoride Inorganic materials 0.000 claims description 3
- DRDVZXDWVBGGMH-UHFFFAOYSA-N zinc;sulfide Chemical compound [S-2].[Zn+2] DRDVZXDWVBGGMH-UHFFFAOYSA-N 0.000 claims description 3
- 230000009977 dual effect Effects 0.000 claims description 2
- 239000011248 coating agent Substances 0.000 claims 6
- 238000000576 coating method Methods 0.000 claims 6
- 230000003595 spectral effect Effects 0.000 claims 3
- 238000005516 engineering process Methods 0.000 description 8
- 230000029058 respiratory gaseous exchange Effects 0.000 description 7
- 238000009792 diffusion process Methods 0.000 description 5
- 238000003384 imaging method Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 230000007547 defect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000010438 heat treatment Methods 0.000 description 2
- 238000000926 separation method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000001815 facial effect Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000012528 membrane Substances 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000001931 thermography Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 230000000007 visual effect Effects 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
- G06V10/145—Illumination specially adapted for pattern recognition, e.g. using gratings
-
- 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
-
- 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)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Vascular Medicine (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses an optical system for face recognition living body detection, which comprises a light splitting prism, wherein a light splitting film is arranged on the end face of an incident end of the light splitting prism, an infrared narrow-band filter film is arranged on the end face of a first emergent end of the light splitting prism, a visible light band-pass filter film is arranged on the end face of a second emergent end of the light splitting prism, a two-waveband lighting lens group for collecting visible light and medium-wave infrared is arranged in front of the light splitting film, a carbon dioxide detection processor is arranged in front of the infrared narrow-band filter film, a visible light detection processor is arranged in front of the visible light band-pass filter film, and the light splitting film reflects the visible light to the visible light band-pass filter film and transmits the infrared to the infrared narrow-band filter film; also discloses a detection method, which adopts carbon dioxide as a living body detection standard for detection. The invention can effectively resist face recognition deception means and greatly improve the safety of user face recognition.
Description
Technical Field
The invention relates to the technical field of face recognition technology and optics, in particular to an optical system and method for face recognition living body detection
Background
Face recognition is a biometric technology, and usually uses a camera (visible light or near infrared band range) to identify the features of the face. In the identification process, the camera can collect a face image or a video, detect and analyze the face image or the video, and judge the identity of an identified object by means of a relevant software algorithm and the like. The face recognition technology is widely applied to the fields of security protection, finance and the like at present. With the popularization of smart phones, the number of applications of face recognition in the payment field is increasing dramatically.
However, there are many techniques for spoofing and deceiving by using the defects and deficiencies of face recognition. At present, the representative technologies include means of printing face photos, recording related videos and the like. The current technology mainly adopts the actions of randomly requiring a user to perform nodding, twisting, opening a mouth and the like aiming at whether a picture or a video acquired by a camera is a living body, and judges whether an object meets related requirements according to acquired data to determine whether the object is the living body. The method has better applicability to the situation of photo forgery, but has lower recognition degree for the deception method of the recorded video. It is quite possible for a masquerading to successfully fool the system through multiple attempts (or special cases even only once), causing loss to the user. In order to deal with the deception methods, a thermal imaging or hyperspectral face recognition and visible light face recognition comparison technology is adopted, although the deception technology adopting a photographing or video recording mode can be resisted to a certain extent, the deception means for the 3D face mask is not high in reliability. Especially, for a 3D face mask with a heating system, infrared signals of a human face can be fully simulated, so that the purpose of impersonating a user can be achieved through judgment.
Therefore, the living body recognition technology in the prior art still has great recognition defects, and the recognition reliability and the safety are greatly reduced.
Disclosure of Invention
The invention aims to provide an optical system and an optical method for face recognition living body detection, which can effectively resist face recognition deception means and greatly improve the face recognition safety of a user.
In order to solve the technical problem, the invention provides an optical system for face recognition living body detection, which comprises a light splitting prism, wherein a light splitting film is arranged on the end face of an incident end of the light splitting prism, an infrared narrow-band filter film is arranged on the end face of a first emergent end of the light splitting prism, a visible light band-pass filter film is arranged on the end face of a second emergent end of the light splitting prism, a double-waveband lighting lens group for collecting visible light and medium-wave infrared is arranged in front of the light splitting film, a carbon dioxide detection processor is arranged in front of the infrared narrow-band filter film, a visible light detection processor is arranged in front of the visible light band-pass filter film, and the light splitting film reflects the visible light to the visible light band-pass filter film and transmits the infrared light to the infrared narrow-band filter film.
Furthermore, the lens material of the dual-band light collection lens group is one of magnesium fluoride, calcium fluoride, barium fluoride, lithium fluoride, sapphire, multispectral zinc sulfide and zinc selenide.
Furthermore, the material of the beam splitter prism is consistent with the lens material of the two-waveband lighting lens group.
Further, the central wavelength of the infrared narrow-band filter film is 4.3 microns.
Further, the surface of the lens is plated with a dual-band antireflection film, the wavelength of the first band of the dual-band antireflection film is 400-700nm, and the wavelength of the second band of the dual-band antireflection film is 4.3 μm.
Further, the film system design of the dual-band antireflection film sequentially comprises from the outer surface to the substrate: ZnS1.74nm, YbF377.35nm、ZnS 8.17nm、YbF3132.46nm and ZnS 10 nm.
Further, the light splittingThe film system design of the film is as follows from the outer surface to the substrate: ZnS 51.74nm, YbF396.59nm、ZnS 48.87nm、YbF386.99nm、ZnS 45.03nm、YbF388.81nm、ZnS 48.09nm、YbF393.03nm、ZnS 45.71nm、YbF391.76nm、ZnS 46.10nm、YbF3106.32nm、ZnS 51.22nm、YbF3154.01nm、ZnS 56.85nm、YbF3119.87nm、ZnS 54.13nm、YbF3145.10nm、ZnS 61.59nm、YbF3126.96nm、ZnS 55.54nm、YbF3157.25nm、ZnS 59.02nm、YbF3496.88nm、ZnS 11.16nm、YbF3190.55nm, ZnS42.52nm and YbF376.80nm。
A method for face recognition live body detection, comprising the optical system of any one of the above, the detection method comprising the steps of:
step 1) collecting visible light and infrared light of the face of a target person simultaneously through a double-waveband lighting lens group and guiding the visible light and the infrared light to a beam splitter prism;
step 2), the beam splitter prism guides visible light to the visible light band-pass filter film through the beam splitting film and captures the visible light by adopting a visible light detection processor; the beam splitter prism guides infrared light to the infrared narrow-band filter film through the beam splitting film for filtering, and only can transmit carbon dioxide characteristic infrared signals and capture the signals by adopting a carbon dioxide detection processor;
step 3), converting the visible light detection processor into a visible light image through a converter; the carbon dioxide detection processor converts the carbon dioxide into a carbon dioxide characteristic image through a converter;
and 4) carrying out face recognition through the visible light image and carrying out living body recognition through the matching of the carbon dioxide characteristic image to obtain a recognition result.
Further, the visible light image and the characteristic image are superposed, and the action analysis is carried out through the continuous carbon dioxide characteristic image, so that whether the characteristic is the carbon dioxide signal characteristic generated by the target respiration is judged.
Further, the carbon dioxide signal characteristics generated by the target breath include the starting location of carbon dioxide, the flow direction of carbon dioxide, the velocity of carbon dioxide, and the frequency of carbon dioxide.
The invention has the beneficial effects that:
through effectual light path design, on the general visible light wave band visual imaging of present face identification uses the system module basis, additionally increase a carbon dioxide gas and survey imaging and use the system module, whether can judge for the user through the facial detail information of visible light wave band imaging is responsible for gathering the people, and simultaneously, carbon dioxide gas surveys imaging and uses the system module then can pass through the mouth to the user, the carbon dioxide gas of nose exhalation carries out the imaging analysis and can judge whether this target is the live body, both cooperation can effectually carry out face identification and live body detection. The current mainstream deception means of face recognition such as photographing, video recording and even 3D face mask can be effectively resisted through detection, and the safety of the face recognition of a user is effectively ensured.
Drawings
FIG. 1 is a schematic diagram of the optical system of the present invention;
FIG. 2 is a schematic view of image overlay of the present invention;
FIG. 3 is a schematic view of the respiration dynamics of the superimposed frontal image of the present invention;
FIG. 4 is a schematic illustration of the exhalation position offset of the present invention;
FIG. 5 is a schematic illustration of the exhalation direction offset of the present invention;
FIG. 6 is a schematic diagram of the optical device of the present invention;
figure 7 is a schematic view from a first perspective of the adaptor sleeve of the present invention with a vertical rod;
figure 8 is a schematic view from a second perspective between the adaptor sleeve and the pole of the present invention.
Detailed Description
The present invention is further described below in conjunction with the following figures and specific examples so that those skilled in the art may better understand the present invention and practice it, but the examples are not intended to limit the present invention.
Referring to fig. 1, an embodiment of an optical system for human face recognition and living body detection according to the present invention includes a light splitting prism 1, a light splitting film B1 is disposed on an incident end face of the light splitting prism, an infrared narrowband filter film B3 is disposed on a first exit end face of the light splitting prism, a band-pass filter film B2 is disposed on a second exit end face of the light splitting prism, a dual-band light collecting lens group 2 for collecting visible light and infrared light is disposed in front of the light splitting film, a carbon dioxide detection processor 3 is disposed in front of the infrared narrowband filter film, a visible light detection processor 4 is disposed in front of the band-pass filter film, the light splitting film reflects the visible light to the band-pass filter film, and transmits infrared light to the infrared narrow-band filter film, the center wavelength of the infrared narrow-band filter film is 4.3 μm, so as to effectively filter, and only the characteristic peak of the carbon dioxide can be detected to obtain the image corresponding to the carbon dioxide.
When the dual-band daylighting lens group is used, visible light and medium wave infrared signals are collected by the dual-band daylighting lens group, a splitting film of the splitting prism is a film which is coated and reflects in a visible light range or a wider range and transmits in a medium wave range or a wider range under the condition of specific angle incidence, the splitting prism reflects the visible light to the band-pass filter film, the band-pass filter film is filtered and then is received and processed by the visible light detection processor and converted into a visible light image through the converter, and whether a user exists or not can be effectively identified through the visible light image; the beam splitter prism also transmits infrared light to the infrared narrow-band filter film, the infrared narrow-band filter film only transmits carbon dioxide infrared signals, and the rest infrared signals are filtered, received and processed by the carbon dioxide detection processor and converted into carbon dioxide characteristic images through the converter; when a user exists, the carbon dioxide characteristic image can be matched with living body identification, the carbon dioxide characteristics generated by the user in breathing cannot be simulated in the existing deception means, and the problems that a disguiser can deceive a face identification system in the modes of shooting pictures or recording videos, even self-heating a 3D face mask and the like under the existing general technical conditions, the property of the user is lost and the like are solved.
The lens material of the dual-band lighting lens group is one or more of magnesium fluoride, calcium fluoride, barium fluoride, lithium fluoride, sapphire, multispectral zinc sulfide and zinc selenide, the sapphire is preferably adopted, the effect is optimal, the material of the beam splitter prism is consistent with the lens material of the dual-band lighting lens group, and the sapphire is also selected. Also in duplex wavesThe surface of the lens of the section lighting lens group is plated with a dual-waveband antireflection film, the wavelength of a first waveband of the dual-waveband antireflection film is 400-700nm, and the wavelength of a second waveband of the dual-waveband antireflection film is 4.3 mu m, so that the effect of antireflection of both the dual wavebands is realized; specifically, the film system design of the dual-band antireflection film sequentially comprises from the outer surface to the substrate: ZnS1.74nm, YbF377.35nm、ZnS 8.17nm、YbF3132.46nm and ZnS 10nm, and by the design of material selection, layer number and thickness, the dual-waveband antireflection effect is effectively realized, and the visible light and infrared reflection loss is reduced. And the film system of the light splitting film is designed from the outer surface to the substrate as follows in sequence: ZnS 51.74nm, YbF396.59nm、ZnS 48.87nm、YbF386.99nm、ZnS 45.03nm、YbF388.81nm、ZnS 48.09nm、YbF393.03nm、ZnS 45.71nm、YbF391.76nm、ZnS 46.10nm、YbF3106.32nm、ZnS 51.22nm、YbF3154.01nm、ZnS 56.85nm、YbF3119.87nm、ZnS54.13nm、YbF3145.10nm、ZnS 61.59nm、YbF3126.96nm、ZnS 55.54nm、YbF3157.25nm、ZnS 59.02nm、YbF3496.88nm、ZnS 11.16nm、YbF3190.55nm, ZnS42.52nm and YbF376.80nm, and by the design of material selection, layer number and thickness, the dual-waveband antireflection effect is effectively realized, and the visible light and infrared reflection loss is further reduced. Through foretell membrane system design, can improve the precision and the stability that detect discernment greatly, improve and use experience and feel.
The application also discloses a method for detecting the human face recognition living body, the optical system is adopted, and during detection, visible light and infrared light of the face of a target person are simultaneously collected and guided to the beam splitter prism through the double-waveband light collecting lens group; the beam splitter prism guides the visible light to the visible light band-pass filter film through the beam splitting film and adopts a visible light detection processor for capture processing; the beam splitter prism guides infrared light to the infrared narrow-band filter film through the beam splitting film for filtering, and only can transmit carbon dioxide characteristic infrared signals and capture the signals by adopting a carbon dioxide detection processor; the visible light detection processor is converted into a visible light image through the converter; the carbon dioxide detection processor converts the carbon dioxide into a carbon dioxide characteristic image through a converter; because the existing deception means can not simulate the condition that a person breathes out carbon dioxide, the face recognition is carried out through the visible light image and the living body recognition is carried out through the matching of the carbon dioxide characteristic image, so that an accurate recognition result is effectively obtained.
In the process of the living body detection and identification, the visible light image and the characteristic image can be superposed, and as shown in fig. 2, the optical system is a single-lens double-optical-path light splitting structure, so that the visible light/infrared images are basically superposed in the same view frame. And (3) performing action analysis through continuous carbon dioxide characteristic images, referring to fig. 3, the breathing of the user has discontinuity, judging whether the carbon dioxide signal characteristics generated by the target breathing of the user are met or not through the discontinuous detection of the carbon dioxide, if so, judging that the carbon dioxide signal characteristics are a living body, and if not, possibly, a deceptive means exists and the detection needs to be performed again. Referring to fig. 4, the initial position of carbon dioxide exhaled by a user is determined through image coincidence analysis, and if a slight deviation occurs in the image processing process, the initial position of carbon dioxide can be determined to coincide with the position of the nostrils of the face of the user through fine adjustment, and the carbon dioxide is a living body. Referring to fig. 5, the exhalation direction of carbon dioxide can also be used as a basis for judgment, the trend of carbon dioxide during exhalation can be judged through the recognition of the human face in the visible light image, and when the initial position of carbon dioxide is the nostril position of the human face of the user but the directions are not consistent, a deception condition of externally connecting carbon dioxide occurs.
In the detection process, random action instructions can be sent to the user target, such as 2 times and 3 times of continuous breathing through the nose or breath in the front direction, the upper direction, the lower direction, the left direction or the right direction through the mouth, so that whether the living body or the deceptive means can be truly reflected through the random instructions. When the breath captures a carbon dioxide signal, the judgment can be carried out according to the matching change required to be made by the user target face organ in the corresponding instruction, for example, the breath is carried out by mouth-up, in the carbon dioxide characteristic image, the carbon dioxide airflow moves upwards, the mouth of the face of the visible light image has the action of breath-up, and the breath-up needs to be realized by matching with the lower lip; the mouth is used for downwards exhaling, the downwards exhaling needs to be realized by matching the upper lip, double judgment is realized, and the result is more accurate. When the re-detection is needed, the verification can be performed by adopting the random instruction mode. Of course, the detection can be performed by adopting a random instruction mode in the initial detection.
Secondly, the diffusion range and the diffusion speed of the carbon dioxide can be obtained through the carbon dioxide characteristic image, whether the flow characteristics of the carbon dioxide generated by normal expiration of the living body are met or not can be judged through the diffusion speed and the diffusion range, when the diffusion range is very narrow and the speed is high, a system can be deceived in a mode that a carbon dioxide tank body is connected to the outside, the outside carbon dioxide possibly has overlarge pressure and leads to the fact that the air outlet is too high, and effective identification can be achieved.
The judgment can also be carried out through the exhalation frequency of the carbon dioxide, and when the external carbon dioxide gives off air continuously, the normal interval time of the living body breathing is contradicted, so that the effective identification can be realized.
Referring to fig. 6 to 8, the optical device for face recognition living body detection is further disclosed, and comprises a recognition shell 5, wherein the optical system is arranged in the recognition shell, and a display screen is arranged on the surface of the recognition shell, so that user interaction can be performed through the display screen, and the use convenience is improved.
Because the installation angle is fixed when the locked optical equipment is installed for the first time, and the angle position of the identification shell is required to be adjusted frequently during debugging, the identification shell can only be adjusted by rotating up and down, the horizontal adjustment of the left and right needs to unlock the fixed structure, the operation is time-consuming and labor-consuming, the angle range of the adjustment cannot be fixed, the operation difficulty is greatly improved, the fixed structure is effectively improved, the back of the identification shell is provided with an upright post bracket 6 which comprises a connecting plate 7 and an adapter sleeve 8, a hinge 9 is arranged between the connecting plate and the adapter sleeve, a locking part 10 is arranged on the hinge, a rotation stopping ring 11 is arranged in the adapter sleeve, the adapter sleeve is sleeved on an upright post 12 and is fixed by a locking screw, the rotation stopping ring of the adapter sleeve is abutted against the end part of the upright post, and the end face of the rotation stopping ring and the end part of the upright post are respectively provided with a plurality of rotation stopping grooves, one end of the locking screw penetrates through the anti-rotation ring to be connected and fixed with a threaded part 15 in the end part of the upright rod. When the angle on the horizontal direction needs to be adjusted, locking screw is unscrewed firstly, then upwards lifts up the switching sleeve, makes the spline groove remove with spline convex part separation, rotates the switching sleeve after the separation, puts down the switching sleeve under suitable angle, spline groove once more with spline convex part cooperation spline, afterwards with the locking screw lock solid can, locking screw can be fixed the switching sleeve in the axial, and then fixed by spline groove and spline convex part cooperation in the week, improve the simple operation degree greatly. And the operation and the adjustment are all outside, the blocking limitation is small, the operation is smooth, and the operation difficulty is reduced.
The above-mentioned embodiments are merely preferred embodiments for fully illustrating the present invention, and the scope of the present invention is not limited thereto. The equivalent substitution or change made by the technical personnel in the technical field on the basis of the invention is all within the protection scope of the invention. The protection scope of the invention is subject to the claims.
Claims (10)
1. The utility model provides an optical system for face identification live body detection, its characterized in that, includes beam splitter prism, be provided with the spectral film on beam splitter prism's the incident end terminal surface, be provided with infrared narrowband filter coating on beam splitter prism's the first exit end terminal surface, be provided with visible light on beam splitter prism's the second exit end terminal surface and lead to the filter coating, be provided with the dual waveband daylighting lens group of gathering visible light and medium wave infrared before the spectral film, be provided with carbon dioxide detection treater before the infrared narrowband filter coating, visible light leads to and is provided with visible light detection treater before the filter coating, the spectral film reflects visible light to band-pass filter coating, and sees through infrared narrowband filter coating with infrared light.
2. The optical system for face recognition liveness detection according to claim 1, wherein the lens material of said two-band collection lens set is one of magnesium fluoride, calcium fluoride, barium fluoride, lithium fluoride, sapphire, multispectral zinc sulfide and zinc selenide.
3. The optical system for human face recognition live body detection as claimed in claim 1, wherein the material of the beam splitter prism is the same as the lens material of the dual-band light collection lens group.
4. The optical system for face recognition live detection as claimed in claim 1, wherein the infrared narrowband filter has a center wavelength of 4.3 microns.
5. The optical system as claimed in claim 1, wherein the surface of the lens is coated with a dual-band antireflection film, the wavelength of the first band of the dual-band antireflection film is 400-700nm, and the wavelength of the second band of the dual-band antireflection film is 4.3 μm.
6. The optical system for human face recognition live body detection as claimed in claim 1, wherein the film system design of the dual-band antireflection film is as follows from the outer surface to the substrate: ZnS1.74nm, YbF377.35nm、ZnS 8.17nm、YbF3132.46nm and ZnS 10 nm.
7. The optical system for human face recognition live body detection as claimed in claim 1, wherein the film system design of the light splitting film is as follows from the outer surface to the substrate: ZnS 51.74nm, YbF3 96.59nm、ZnS 48.87nm、YbF386.99nm、ZnS 45.03nm、YbF3 88.81nm、ZnS 48.09nm、YbF3 93.03nm、ZnS 45.71nm、YbF391.76nm、ZnS 46.10nm、YbF3 106.32nm、ZnS 51.22nm、YbF3 154.01nm、ZnS 56.85nm、YbF3119.87nm、ZnS 54.13nm、YbF3 145.10nm、ZnS 61.59nm、YbF3 126.96nm、ZnS 55.54nm、YbF3157.25nm、ZnS 59.02nm、YbF3 496.88nm、ZnS 11.16nm、YbF3190.55nm, ZnS42.52nm and YbF3 76.80nm。
8. A method for face recognition live detection, comprising the optical system of any one of claims 1 to 7, the detection method comprising the steps of:
step 1) collecting visible light and infrared light of the face of a target person simultaneously through a double-waveband lighting lens group and guiding the visible light and the infrared light to a beam splitter prism;
step 2), the beam splitter prism guides visible light to the visible light band-pass filter film through the beam splitting film and captures the visible light by adopting a visible light detection processor; the beam splitter prism guides infrared light to the infrared narrow-band filter film through the beam splitting film for filtering, and only can transmit carbon dioxide characteristic infrared signals and capture the signals by adopting a carbon dioxide detection processor;
step 3), converting the visible light detection processor into a visible light image through a converter; the carbon dioxide detection processor converts the carbon dioxide into a carbon dioxide characteristic image through a converter;
and 4) carrying out face recognition through the visible light image and carrying out living body recognition through the matching of the carbon dioxide characteristic image to obtain a recognition result.
9. The method for face recognition live detection as claimed in claim 8, wherein the visible light image and the characteristic image are overlapped, and motion analysis is performed through the continuous carbon dioxide characteristic image to judge whether the characteristic is the carbon dioxide signal generated by the target breath.
10. The method for face recognition live detection as recited in claim 9, wherein the carbon dioxide signal features generated by the target breath include a starting location of carbon dioxide, a flow direction of carbon dioxide, a velocity of carbon dioxide, and a frequency of carbon dioxide.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110447263.7A CN113011391B (en) | 2021-04-25 | 2021-04-25 | Optical system and method for human face recognition living body detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110447263.7A CN113011391B (en) | 2021-04-25 | 2021-04-25 | Optical system and method for human face recognition living body detection |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113011391A true CN113011391A (en) | 2021-06-22 |
| CN113011391B CN113011391B (en) | 2024-04-26 |
Family
ID=76389220
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110447263.7A Active CN113011391B (en) | 2021-04-25 | 2021-04-25 | Optical system and method for human face recognition living body detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113011391B (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2011117572A1 (en) * | 2010-03-25 | 2011-09-29 | Isis Innovation Limited | Analysis of breath |
| CN102323670A (en) * | 2011-09-06 | 2012-01-18 | 中国科学院长春光学精密机械与物理研究所 | Ultraviolet, visible and near-infrared light three-band optical imaging system |
| CN102567707A (en) * | 2010-12-27 | 2012-07-11 | 北京北科慧识科技股份有限公司 | Biological identification sensor and biological identification system |
| CN105718925A (en) * | 2016-04-14 | 2016-06-29 | 苏州优化智能科技有限公司 | Real person living body authentication terminal equipment based on near infrared and facial micro expression |
| CN106355169A (en) * | 2016-11-11 | 2017-01-25 | 成都优势互动科技有限公司 | Infrared living body face image acquisition device, identification device and treatment method thereof |
| CN206650741U (en) * | 2017-02-14 | 2017-11-17 | 浙江大华技术股份有限公司 | A kind of coaxial image fusion device |
| CN109584502A (en) * | 2018-11-13 | 2019-04-05 | 武汉科技大学 | A kind of car life body intelligent safety monitoring warning device and method |
| CN109606065A (en) * | 2019-01-18 | 2019-04-12 | 广州小鹏汽车科技有限公司 | Environment control method, device and automobile |
| CN109998496A (en) * | 2019-01-31 | 2019-07-12 | 中国人民解放军海军工程大学 | A kind of autonomous type body temperature automatic collection and respiratory monitoring system and method |
| US20200150662A1 (en) * | 2017-09-28 | 2020-05-14 | SZ DJI Technology Co., Ltd. | Flying body, living body detection system, living body detection method, program and recording medium |
| CN111611977A (en) * | 2020-06-05 | 2020-09-01 | 吉林求是光谱数据科技有限公司 | Face recognition monitoring system and recognition method based on spectrum and multiband fusion |
| CN111772633A (en) * | 2020-07-16 | 2020-10-16 | 韩锋 | Remote sensing respiratory function monitoring device and method |
| CN214623689U (en) * | 2021-04-25 | 2021-11-05 | 秦皇岛本征晶体科技有限公司 | Optical system and equipment for face recognition living body detection |
-
2021
- 2021-04-25 CN CN202110447263.7A patent/CN113011391B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2011117572A1 (en) * | 2010-03-25 | 2011-09-29 | Isis Innovation Limited | Analysis of breath |
| CN102567707A (en) * | 2010-12-27 | 2012-07-11 | 北京北科慧识科技股份有限公司 | Biological identification sensor and biological identification system |
| CN102323670A (en) * | 2011-09-06 | 2012-01-18 | 中国科学院长春光学精密机械与物理研究所 | Ultraviolet, visible and near-infrared light three-band optical imaging system |
| CN105718925A (en) * | 2016-04-14 | 2016-06-29 | 苏州优化智能科技有限公司 | Real person living body authentication terminal equipment based on near infrared and facial micro expression |
| CN106355169A (en) * | 2016-11-11 | 2017-01-25 | 成都优势互动科技有限公司 | Infrared living body face image acquisition device, identification device and treatment method thereof |
| CN206650741U (en) * | 2017-02-14 | 2017-11-17 | 浙江大华技术股份有限公司 | A kind of coaxial image fusion device |
| US20200150662A1 (en) * | 2017-09-28 | 2020-05-14 | SZ DJI Technology Co., Ltd. | Flying body, living body detection system, living body detection method, program and recording medium |
| CN109584502A (en) * | 2018-11-13 | 2019-04-05 | 武汉科技大学 | A kind of car life body intelligent safety monitoring warning device and method |
| CN109606065A (en) * | 2019-01-18 | 2019-04-12 | 广州小鹏汽车科技有限公司 | Environment control method, device and automobile |
| CN109998496A (en) * | 2019-01-31 | 2019-07-12 | 中国人民解放军海军工程大学 | A kind of autonomous type body temperature automatic collection and respiratory monitoring system and method |
| CN111611977A (en) * | 2020-06-05 | 2020-09-01 | 吉林求是光谱数据科技有限公司 | Face recognition monitoring system and recognition method based on spectrum and multiband fusion |
| CN111772633A (en) * | 2020-07-16 | 2020-10-16 | 韩锋 | Remote sensing respiratory function monitoring device and method |
| CN214623689U (en) * | 2021-04-25 | 2021-11-05 | 秦皇岛本征晶体科技有限公司 | Optical system and equipment for face recognition living body detection |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113011391B (en) | 2024-04-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2021244414A1 (en) | Facial recognition monitoring system based on spectrum and multi-band fusion, and recognition method | |
| US10762334B2 (en) | System and method for entity recognition | |
| US20190138807A1 (en) | Iris liveness detection for mobile devices | |
| CN109389719B (en) | Community door access control system and door opening method | |
| CN111881726B (en) | Living body detection method and device and storage medium | |
| US10445556B2 (en) | Optical system for biometric identification of a user | |
| CN104881632A (en) | Hyperspectral face recognition method | |
| JP2018501586A (en) | Image identification system and method | |
| JP2006510109A (en) | Facial expression invariant face recognition method and apparatus | |
| JP2007516525A (en) | Method and system for facial image acquisition and identification | |
| KR20050048413A (en) | Apparatus and method for discriminating person using infrared rays | |
| CN103136505A (en) | System and method for identifying identity by using multiple physiological information in mixed mode | |
| JP2000107156A (en) | Authentication device | |
| CN209118424U (en) | Utilize the client identity identifying system of the withdrawal circulation all-in-one machine of recognition of face | |
| US20140071293A1 (en) | Method and device for authintication of live human faces using infra red images | |
| CN105930780A (en) | Near infrared and micro expression based living body identity verification method | |
| CN109726694A (en) | A kind of iris image acquiring method and device | |
| WO2012083860A1 (en) | Face recognition device and method | |
| WO2014119503A1 (en) | Authentication device, prism body for authentication, and authentication method | |
| JP6321289B2 (en) | Apparatus and method for acquiring iris image outside and inside | |
| CN111462417A (en) | Multi-information verification system and multi-information verification method for unmanned bank | |
| CN214623689U (en) | Optical system and equipment for face recognition living body detection | |
| CN113011391A (en) | Optical system and method for face recognition living body detection | |
| CN109801462A (en) | The burglar alarm of intelligent mobile rack | |
| KR100711110B1 (en) | System for iris recognition against counterfeit attack using gradient based fusion of multi-spectral images and method thereof |
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 | ||
| CB03 | Change of inventor or designer information |
Inventor after: Liu Chang Inventor after: Jiang Shaohua Inventor after: Zhu Fengrui Inventor after: Zhu Fengxu Inventor after: Zhou Fang Inventor after: Xu Wusheng Inventor after: Yang Chunhui Inventor before: Liu Chang Inventor before: Jiang Shaohua Inventor before: Zhu Fengrui Inventor before: Zhu Fengxu Inventor before: Zhou Fang Inventor before: Xu Wusheng Inventor before: Yang Chunhui |
|
| CB03 | Change of inventor or designer information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |