CN109684993B - Face recognition method, system and equipment based on nostril information - Google Patents
Face recognition method, system and equipment based on nostril information Download PDFInfo
- Publication number
- CN109684993B CN109684993B CN201811573339.5A CN201811573339A CN109684993B CN 109684993 B CN109684993 B CN 109684993B CN 201811573339 A CN201811573339 A CN 201811573339A CN 109684993 B CN109684993 B CN 109684993B
- Authority
- CN
- China
- Prior art keywords
- face
- nostril
- information
- images
- face recognition
- 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.)
- Expired - Fee Related
Links
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000004590 computer program Methods 0.000 claims description 18
- 238000001514 detection method Methods 0.000 claims description 13
- 238000001727 in vivo Methods 0.000 claims 2
- 238000005516 engineering process Methods 0.000 abstract description 26
- 230000008569 process Effects 0.000 description 13
- 230000006870 function Effects 0.000 description 9
- 239000000284 extract Substances 0.000 description 8
- 230000029058 respiratory gaseous exchange Effects 0.000 description 8
- 230000008859 change Effects 0.000 description 7
- 230000006872 improvement Effects 0.000 description 7
- 230000001815 facial effect Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 230000008921 facial expression Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 239000000654 additive Substances 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 210000003462 vein Anatomy 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
- G06V40/165—Detection; Localisation; Normalisation using facial parts and geometric relationships
-
- 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
- G06V40/171—Local features and components; Facial parts ; Occluding parts, e.g. glasses; Geometrical relationships
-
- 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
- G06V40/40—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)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention discloses a face recognition method based on nostril information, which comprises the following steps: when a face recognition instruction is responded, whether a face exists in the shooting range of the camera is detected; when the fact that a human face exists in the shooting range of the camera is detected, acquiring a plurality of human face images shot by the camera, and extracting nostril information in the human face images; performing living body identification on the nostril information according to a prestored nostril size threshold value, and judging whether a plurality of currently acquired face images are living body face images; and when the face image is a living body face image, extracting face information of the face image, and carrying out face identification on the face information according to a pre-stored face template. The invention also discloses a face recognition system based on the nostril information and a face recognition device based on the nostril information. By adopting the embodiment of the invention, the phenomena of false recognition and rejection of the face recognition system can be effectively solved, and the reliability of the face recognition technology is improved.
Description
Technical Field
The invention relates to the technical field of face recognition, in particular to a face recognition method, a face recognition system and face recognition equipment based on nostril information.
Background
With the development of technologies, biometric technologies are increasingly applied to intelligent terminals, such as fingerprint identification technologies and face identification technologies on mobile phones, and some biometric technologies are also gradually applied, such as finger vein identification technologies applied to access control systems. With the continuous popularization in practical application, the problems of the face recognition system are gradually highlighted. For example, the facial features have variability, such as various additives, changes of facial expressions, etc., and these changes may cause the rejection phenomenon of the face recognition system in practical applications. Although the embedded face recognition system collects the multi-directional features of the face by prompting information such as far, near, head raising, head turning and the like when a face template is input, the embedded face recognition system is beneficial to improving the recognition success rate, but the recognition rejection probability caused by the change of the face features is still not reduced enough. In addition, the illegal person utilizes the principle that the human face recognition system rejects due to the variability of the human face characteristics and adopts resources such as photos, videos and the like to crack the human face recognition technology, so that the human face recognition system misrecognizes and the reliability of the human face recognition technology is reduced.
Disclosure of Invention
The embodiment of the invention aims to provide a method, a system and equipment for face recognition based on nostril information, which can effectively solve the phenomena of false recognition and rejection of a face recognition system and improve the reliability of a face recognition technology.
In order to achieve the above object, an embodiment of the present invention provides a face recognition method based on nostril information, including:
when a face recognition instruction is responded, whether a face exists in the shooting range of the camera is detected;
when the fact that a human face exists in the shooting range of the camera is detected, acquiring a plurality of human face images shot by the camera, and extracting nostril information in the human face images;
performing living body identification on the nostril information according to a prestored nostril size threshold value, and judging whether a plurality of currently acquired face images are living body face images;
and when the face image is a living body face image, extracting face information of the face image, and carrying out face identification on the face information according to a pre-stored face template.
Compared with the prior art, the nostril information-based face recognition method disclosed by the invention comprises the steps of firstly detecting whether a face exists in the shooting range of a camera when responding to a face recognition instruction, and acquiring a plurality of face images when detecting that the face exists in the shooting range of the camera; extracting nostril information in a plurality of face images, and carrying out living body identification on the nostril information; and finally, when the face image is a living body face image, extracting face information of the face image, and carrying out face identification on the face information according to a pre-stored face template. The problems that in the prior art, the phenomenon of rejection of the face recognition system is possibly caused due to the fact that the face features have variability, meanwhile, the principle that the rejection of the face recognition system is caused due to the variability of the face features is utilized, the face recognition technology is cracked by the aid of the resources such as the pictures and the videos, the phenomenon of misidentification and the rejection of the face recognition system is caused, the reliability of the face recognition technology is reduced are solved, the phenomena of misidentification and the rejection of the face recognition system can be effectively solved, and the reliability of the face recognition technology is improved.
As an improvement of the above scheme, the extracting nostril information in a plurality of face images includes:
extracting the length of the left nostril from the leftmost end to the rightmost end in the left nostrils in the plurality of face images, and extracting the length of the right nostril from the leftmost end to the rightmost end in the right nostrils in the plurality of face images;
acquiring absolute values of differences between lengths of left nostrils in a plurality of face images, and acquiring absolute values of differences between lengths of right nostrils in the plurality of face images;
taking the maximum of the absolute value of the difference between the left nostril lengths and the absolute value of the difference between the right nostril lengths as the nostril information.
As an improvement of the above scheme, the performing living body identification on the nostril information according to a prestored nostril size threshold value, and determining whether a plurality of currently acquired face images are living body face images, includes:
judging whether the nostril information is larger than a prestored nostril size threshold value or not;
if yes, judging that the plurality of face images which are acquired currently are living face images; and if not, judging that the plurality of face images which are acquired currently are non-living body face images.
As an improvement of the above scheme, the performing face recognition on the face information according to a pre-stored face template includes:
if the matching degree of the face information and the face template is greater than or equal to a preset matching value, judging that the face recognition is successful;
and if the matching degree of the face information and the face template is smaller than the preset matching value, judging that the face recognition fails.
As an improvement of the above, the face information includes, but is not limited to, face contour, eye position information, nose contour, and nose position information.
In order to achieve the above object, an embodiment of the present invention further provides a face recognition system based on nostril information, including:
the human face detection unit is used for detecting whether a human face exists in the shooting range of the camera when responding to the human face recognition instruction;
the face image acquisition unit is used for acquiring a plurality of face images shot by the camera when the fact that a face exists in the shooting range of the camera is detected;
the nostril information acquisition unit is used for extracting nostril information in the plurality of face images;
the living body identification unit is used for carrying out living body identification on the nostril information according to a prestored nostril size threshold value and judging whether a plurality of currently acquired face images are living body face images or not;
and the face recognition unit is used for extracting the face information of the face image when the face image is a living body face image, and carrying out face recognition on the face information according to a pre-stored face template.
Compared with the prior art, the nostril information-based face recognition system disclosed by the invention comprises the steps of firstly detecting whether a face exists in the shooting range of a camera when a face detection unit responds to a face recognition instruction, and acquiring a plurality of face images by a face image acquisition unit when the face exists in the shooting range of the camera; then extracting nostril information in a plurality of face images by a nostril information acquisition unit, and carrying out living body identification on the nostril information by a living body identification unit; and finally, when the face image is a living body face image, the face recognition unit extracts face information of the face image and carries out face recognition on the face information according to a pre-stored face template. The problems that in the prior art, the phenomenon of rejection of the face recognition system is possibly caused due to the fact that the face features have variability, meanwhile, the principle that the rejection of the face recognition system is caused due to the variability of the face features is utilized, the face recognition technology is cracked by the aid of the resources such as the pictures and the videos, the phenomenon of misidentification and the rejection of the face recognition system is caused, the reliability of the face recognition technology is reduced are solved, the phenomena of misidentification and the rejection of the face recognition system can be effectively solved, and the reliability of the face recognition technology is improved.
As an improvement of the above solution, the nostril information acquiring unit is specifically configured to:
extracting the length of the left nostril from the leftmost end to the rightmost end in the left nostrils in the plurality of face images, and extracting the length of the right nostril from the leftmost end to the rightmost end in the right nostrils in the plurality of face images;
acquiring absolute values of differences between lengths of left nostrils in a plurality of face images, and acquiring absolute values of differences between lengths of right nostrils in the plurality of face images;
taking the maximum of the absolute value of the difference between the left nostril lengths and the absolute value of the difference between the right nostril lengths as the nostril information.
As an improvement of the above, the living body identification unit is specifically configured to:
judging whether the nostril information is larger than a prestored nostril size threshold value or not;
if yes, judging that the plurality of face images which are acquired currently are living face images; and if not, judging that the plurality of face images which are acquired currently are non-living body face images.
As an improvement of the above scheme, the face recognition unit is configured to determine that face recognition is successful if a matching degree of the face information and the face template is greater than or equal to a preset matching value; if the matching degree of the face information and the face template is smaller than the preset matching value, judging that face recognition fails;
the face information includes, but is not limited to, face contours, eye position information, nose contours, and nose position information.
In order to achieve the above object, an embodiment of the present invention further provides a face recognition device based on nostril information, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor, when executing the computer program, implements the method of face recognition based on nostril information as described in any of the above embodiments.
Drawings
Fig. 1 is a flowchart of a face recognition method based on nostril information according to an embodiment of the present invention;
fig. 2 is a flowchart of extracting nostril information in a method for face recognition based on nostril information according to an embodiment of the present invention;
fig. 3 is a block diagram of a face recognition system 10 based on nostril information according to an embodiment of the present invention;
fig. 4 is a block diagram of a face recognition device 20 based on nostril information according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. 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.
Example one
Referring to fig. 1, fig. 1 is a flowchart of a method for face recognition based on nostril information according to an embodiment of the present invention; the method comprises the following steps:
s1, when responding to the face recognition instruction, detecting whether a face exists in the shooting range of the camera;
s2, when the fact that a human face exists in the shooting range of the camera is detected, acquiring a plurality of human face images shot by the camera, and extracting nostril information in the plurality of human face images;
s3, performing living body identification on the nostril information according to a prestored nostril size threshold value, and judging whether the currently acquired face images are living body face images;
and S4, when the face image is a living body face image, extracting face information of the face image, and carrying out face recognition on the face information according to a pre-stored face template.
It should be noted that the face information according to the embodiment of the present invention does not include nostril information, and the face information includes, but is not limited to, face contour, eye position information, nose contour, and nose position information. The face recognition method based on nostril information provided by this embodiment can be implemented by a terminal device, which can be a mobile phone, a tablet computer or other terminal devices, wherein the terminal device includes a camera for collecting images.
Specifically, before the terminal device executes the nostril information-based face recognition method, a face template is established. In the process of establishing the face template, the face images of a plurality of users are collected through the camera, at the moment, nostril size information can be obtained from the face images, and in the process of collecting information through the camera, prompt information can be displayed on the terminal equipment to guide the users to collect information. For example, a character frame for correcting the shooting posture of the user appears in the display screen of the terminal device to guide the user to correct the posture, and meanwhile, voice or characters can be played to prompt the user to correct the posture, so that an effective recognizable image is obtained, the face information and the nostril size information are extracted, and the face template and the nostril size threshold are obtained.
In one embodiment, the calculation of the nostril size threshold includes: acquiring a plurality of face images, extracting the length of the left nostril from the leftmost end to the rightmost end in the left nostril of a user from the plurality of face images, and simultaneously extracting the length of the right nostril from the leftmost end to the rightmost end in the right nostril of the plurality of face images; obtaining the length of the left nostril and the length of the right nostril of each human face image, then obtaining the absolute value of the difference between the lengths of the left nostrils and obtaining the absolute value of the difference between the lengths of the right nostrils; taking the minimum of the absolute value of the difference between the left nostril lengths and the absolute value of the difference between the right nostril lengths as the nostril size threshold. Because the nose of the user changes along with breathing in the breathing process, the nostril size information is inconsistent in a plurality of face images continuously collected by the camera, so that the nostril size threshold value can be obtained.
In another embodiment, the nostril size threshold may be set to 0.
Specifically, in step S1, in response to the face recognition instruction, the face recognition instruction may be an instruction issued by the user when paying or unlocking the mobile phone. Preferably, when the control center responds to the face recognition instruction, the instruction is sent to the camera, so that the camera detects whether a face exists in the shooting range of the camera, and feeds back the detection result to the control center.
Specifically, in step S2, it is preferable that when it is detected that a human face exists in the shooting range of the camera, the infrared light source is turned on so that the infrared light source emits infrared rays to the human face. Specifically, infrared light source can make the camera also can acquire comparatively clear face image in the dark surrounds to can avoid being difficult to carry out face identification's problem in the dark surrounds. Preferably, the camera may be an infrared camera, and the infrared light source may be infrared light emitted by the infrared camera itself or infrared light emitted by another structural light source, which are within the protection scope of the present invention.
Specifically, a plurality of face images shot by the camera are acquired, and preferably, the camera can continuously shoot in a short time, for example, 5 face images in 3 seconds. In the process, the nostrils of the obtained face image are changed due to the breathing of the user, so that whether the face image is a living body can be judged according to the change condition of the nostrils of the user.
Specifically, after the face image is obtained, nostril information in a plurality of face images is extracted. Referring to fig. 2, fig. 2 is a flowchart illustrating extracting nostril information in a method for face recognition based on nostril information according to an embodiment of the present invention; the method comprises the following steps:
s21, extracting the lengths of the left nostrils from the leftmost end to the rightmost end in the left nostrils in the plurality of face images, and extracting the lengths of the right nostrils from the leftmost end to the rightmost end in the right nostrils in the plurality of face images;
s22, acquiring absolute values of differences between the lengths of the left nostrils in the plurality of face images, and acquiring absolute values of differences between the lengths of the right nostrils in the plurality of face images;
s23, taking the maximum value of the absolute value of the difference between the lengths of the left nostril and the absolute value of the difference between the lengths of the right nostril as the nostril information.
Specifically, in step S3, the nostril information is subjected to living body recognition according to a prestored nostril size threshold, and it is determined whether the plurality of face images currently acquired are living body face images. Preferably, whether the nostril information is larger than a prestored nostril size threshold value is judged; if the nostril information is larger than a prestored nostril size threshold value, judging that the currently acquired face image is a living body face image and the current user is a living body; if the nostril information is smaller than or equal to a prestored nostril size threshold value, the currently acquired face image is judged to be a non-living body face image, the current user is a non-living body, and the currently acquired face image may be shot by the camera according to a user picture. Whether the human face is a living body is judged according to the change condition of nostrils, the problem that the human face recognition system rejects due to the change of the facial expression is solved, the problem that the human face recognition system misrecognizes due to the fact that the human face recognition system rejects due to the variability of the facial features is solved, and the human face recognition technology is cracked by adopting the resources such as pictures and videos is solved.
Specifically, the nostril information cannot exceed the nostril size limit value, and because the camera continuously shoots the face in a short time, the distance between the user and the camera is kept unchanged in the process of carrying out face recognition by the user, so that the face images obtained by the camera are almost the same, and the user is in a breathing state in the shooting process of the camera, so that the nostril size can be slightly changed but cannot be greatly changed, and therefore, the situation that when the user carries out face recognition by using a picture from the outside, the nostril information of the user in the face images obtained by the camera is changed by moving the picture, so that the error recognition is caused can be eliminated by setting a nostril size limit value, and the reliability of the face recognition technology can be improved.
Specifically, in step S4, when the face image is a living body face image, face information of the face image is extracted, and face recognition is performed on the face information according to a face template stored in advance. Preferably, if the matching degree of the face information and the face template is greater than or equal to a preset matching value, it is determined that the face recognition is successful; and if the matching degree of the face information and the face template is smaller than the preset matching value, judging that the face recognition fails.
When the face recognition method is specifically implemented, firstly, when a face recognition instruction is responded, whether a face exists in the shooting range of a camera is detected, and when the face exists in the shooting range of the camera, a plurality of face images are obtained; extracting nostril information in a plurality of face images, and carrying out living body identification on the nostril information; and finally, when the face image is a living body face image, extracting face information of the face image, and carrying out face identification on the face information according to a pre-stored face template.
Compared with the prior art, the nostril information-based face recognition method solves the problems that the rejection phenomenon of a face recognition system can be caused due to the variability of the face characteristics in the prior art, and the reliability of the face recognition technology is reduced due to the fact that the face recognition system rejects due to the variability of the face characteristics and the face recognition technology is cracked by adopting the resources such as pictures and videos, so that the false recognition of the face recognition system is caused, and the false recognition and rejection phenomena of the face recognition system can be effectively solved, and the reliability of the face recognition technology is improved.
Example two
Referring to fig. 3, fig. 3 is a block diagram illustrating a structure of a face recognition system 10 based on nostril information according to an embodiment of the present invention; the method comprises the following steps:
the face detection unit 11 is used for detecting whether a face exists in a shooting range of the camera when responding to the face recognition instruction;
the face image acquiring unit 12 is configured to acquire a plurality of face images captured by the camera when it is detected that a face exists in a capturing range of the camera;
a nostril information obtaining unit 13, configured to extract nostril information in a plurality of face images;
the living body identification unit 14 is configured to perform living body identification on the nostril information according to a prestored nostril size threshold, and determine whether the currently acquired multiple face images are living body face images;
and the face recognition unit 15 is configured to, when the face image is a living body face image, extract face information of the face image, and perform face recognition on the face information according to a face template stored in advance.
It should be noted that the face information according to the embodiment of the present invention does not include nostril information, and the face information includes, but is not limited to, face contour, eye position information, nose contour, and nose position information. The nostril information-based face recognition system 10 provided in this embodiment may be a mobile phone, a tablet computer or other terminal devices, and the nostril information-based face recognition system 10 includes a camera for collecting images.
Specifically, before the nostril information-based face recognition system 10 performs the face recognition, a face template is established. In the process of establishing the face template, the face images of a plurality of users are acquired through the camera, at this time, the nostril size information can be acquired from the face images, and in the process of acquiring information through the camera, prompt information can be displayed on the face recognition system 10 based on the nostril information to guide the users to acquire information. For example, a character frame for correcting the shooting posture of the user appears on the display screen of the face recognition system 10 based on the nostril information to guide the user to correct the posture, and meanwhile, voice or characters can be played to prompt the user to correct the posture, so that an effective recognizable image is obtained, the face information and the nostril size information are further extracted, and the face template and the nostril size threshold are obtained.
In one embodiment, the calculation of the nostril size threshold includes: acquiring a plurality of face images, extracting the length of the left nostril from the leftmost end to the rightmost end in the left nostril of a user from the plurality of face images, and simultaneously extracting the length of the right nostril from the leftmost end to the rightmost end in the right nostril of the plurality of face images; obtaining the length of the left nostril and the length of the right nostril of each human face image, then obtaining the absolute value of the difference between the lengths of the left nostrils and obtaining the absolute value of the difference between the lengths of the right nostrils; taking the minimum of the absolute value of the difference between the left nostril lengths and the absolute value of the difference between the right nostril lengths as the nostril size threshold. Because the nose of the user changes along with breathing in the breathing process, the sizes of the nostrils in the plurality of face images continuously collected by the camera are inconsistent, and the size threshold of the nostrils can be obtained.
In another embodiment, the nostril size threshold may be set to 0.
Specifically, the face detection unit 11 responds to a face recognition instruction, where the face recognition instruction may be an instruction sent by a user when the user pays for or unlocks the mobile phone. Preferably, when the face detection unit 11 responds to the face recognition instruction, an instruction is sent to the camera, so that the camera detects whether a face exists in a shooting range of the camera, and feeds back a detection result to the face detection unit 11.
Preferably, when the face detection unit 11 detects that a face exists in the shooting range of the camera, the infrared light source is turned on, so that the infrared light source emits infrared rays to the face. Specifically, infrared light source can make the camera also can acquire comparatively clear face image in the dark surrounds to can avoid being difficult to carry out face identification's problem in the dark surrounds. Preferably, the camera may be an infrared camera, and the infrared light source may be infrared light emitted by the infrared camera itself or infrared light emitted by another structural light source, which are within the protection scope of the present invention.
Specifically, the facial image acquiring unit 12 acquires a plurality of facial images captured by the camera, and preferably, the camera can continuously capture 5 facial images within a short time, for example, within 3 seconds. In the process, the nostrils of the obtained face image are changed due to the breathing of the user, so that whether the face image is a living body can be judged according to the change condition of the nostrils of the user.
Specifically, after the face image obtaining unit 12 obtains the face image, the nostril information obtaining unit 13 extracts nostril information in a plurality of face images. Specifically, the nostril information obtaining unit 13 extracts the length of the left nostril from the leftmost end to the rightmost end of the left nostrils in the plurality of face images, and extracts the length of the right nostril from the leftmost end to the rightmost end of the right nostrils in the plurality of face images; the nostril information obtaining unit 13 obtains absolute values of differences between lengths of left nostrils in the plurality of face images, and obtains absolute values of differences between lengths of right nostrils in the plurality of face images; the nostril information obtaining unit 13 takes the maximum value of the absolute value of the difference between the lengths of the left and right nostrils as the nostril information.
Specifically, the living body identification unit 14 performs living body identification on the nostril information according to a prestored nostril size threshold, and determines whether the plurality of currently acquired face images are living body face images. Preferably, the living body identification unit 14 determines whether the nostril information is larger than a prestored nostril size threshold; if the nostril information is greater than a prestored nostril size threshold, the living body identification unit 14 determines that the currently acquired face image is a living body face image, and the current user is a living body; if the nostril information is smaller than or equal to a prestored nostril size threshold, the living body identification unit 14 determines that the currently acquired face image is a non-living body face image, the current user is a non-living body, and the currently acquired face image may be shot by the camera according to a user picture. Whether the human face is a living body is judged according to the change condition of nostrils, the problem that the human face recognition system rejects due to the change of the facial expression is solved, the problem that the human face recognition system misrecognizes due to the fact that the human face recognition system rejects due to the variability of the facial features is solved, and the human face recognition technology is cracked by adopting the resources such as pictures and videos is solved.
Specifically, the nostril information cannot exceed the nostril size limit value, and because the camera continuously shoots the face in a short time, the distance between the user and the camera is kept unchanged in the process of carrying out face recognition by the user, so that the face images obtained by the camera are almost the same, and the user is in a breathing state in the shooting process of the camera, so that the nostril size can be slightly changed but cannot be greatly changed, and therefore, the situation that when the user carries out face recognition by using a picture from the outside, the nostril information of the user in the face images obtained by the camera is changed by moving the picture, so that the error recognition is caused can be eliminated by setting a nostril size limit value, and the reliability of the face recognition technology can be improved.
Specifically, when the living body recognition unit 14 determines that the face image is a living body face image, the face recognition unit 15 extracts face information of the face image, and performs face recognition on the face information according to a face template stored in advance. Preferably, if the matching degree between the face information and the face template is greater than or equal to a preset matching value, the face recognition unit 15 determines that the face recognition is successful; if the matching degree of the face information and the face template is smaller than the preset matching value, the face recognition unit 15 determines that face recognition fails.
When the specific implementation is carried out, firstly, when the face detection unit 11 responds to a face recognition instruction, whether a face exists in the shooting range of the camera is detected, and when the face exists in the shooting range of the camera, the face image acquisition unit 12 acquires a plurality of face images; then, a nostril information acquisition unit 13 extracts nostril information in a plurality of face images, and a living body identification unit 14 carries out living body identification on the nostril information; and finally, when the face image is a living body face image, the face recognition unit 15 extracts face information of the face image, and performs face recognition on the face information according to a face template stored in advance.
Compared with the prior art, the nostril information-based face recognition system 10 solves the problems that the rejection phenomenon of the face recognition system can be caused due to the variability of the face characteristics in the prior art, and the reliability of the face recognition technology is reduced due to the fact that the face recognition technology is cracked by using the resources such as pictures, videos and the like by using the principle that the rejection phenomenon of the face recognition system is caused due to the variability of the face characteristics, and can effectively solve the false recognition and rejection phenomena of the face recognition system and improve the reliability of the face recognition technology.
EXAMPLE III
Referring to fig. 4, fig. 4 is a block diagram illustrating a structure of a face recognition device 20 based on nostril information according to an embodiment of the present invention; the nostril information-based face recognition apparatus 20 of this embodiment includes: a processor 21, a memory 22 and a computer program stored in said memory 22 and executable on said processor 21. The processor 21, when executing the computer program, implements the steps in the various screen control method embodiments described above, such as steps S1-S4 shown in fig. 1. Alternatively, the processor 21, when executing the computer program, implements the functions of the units in the above-described device embodiments, for example, the function of the face detection unit 11.
Illustratively, the computer program may be divided into one or more modules/units, which are stored in the memory and executed by the processor 21 to accomplish the present invention. The one or more modules/units may be a series of computer program instruction segments capable of performing specific functions, which are used to describe the execution process of the computer program in the nostril information based face recognition device 20. For example, the computer program may be divided into a face detection unit 11, a face image acquisition unit 12, a nostril information acquisition unit 13, a living body recognition unit 14 and a face recognition unit 15, and specific functions of the respective modules refer to functions of the respective modules in the nostril information-based face recognition system 10 in the second embodiment, which are not described herein again.
The nostril information-based face recognition device 20 may be a desktop computer, a notebook, a palm top computer, a cloud server, or other computing devices. The nostril information-based face recognition device 20 may include, but is not limited to, a processor 21 and a memory 22. It will be understood by those skilled in the art that the schematic diagram is merely an example of the nostril information based face recognition device 20, and does not constitute a limitation of the nostril information based face recognition device 20, and may include more or less components than those shown, or combine some components, or different components, for example, the nostril information based face recognition device 20 may further include an input-output device, a network access device, a bus, etc.
The Processor 21 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, discrete hardware component, etc. The general purpose processor may be a microprocessor or the processor may be any conventional processor, etc., and the processor 21 is a control center of the nostril information based face recognition device 20, and various interfaces and lines are used to connect various parts of the entire nostril information based face recognition device 20.
The memory 22 may be used to store the computer programs and/or modules, and the processor 22 may implement the various functions of the nostril information-based face recognition device 20 by running or executing the computer programs and/or modules stored in the memory and invoking the data stored in the memory. The memory 22 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating device, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data, a phonebook, etc.) created according to the use of the cellular phone, and the like. In addition, the memory 22 may include a high speed random access memory, and may also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device.
Wherein, the integrated module/unit of the face recognition device 20 based on nostril information can be stored in a computer readable storage medium if it is implemented in the form of software functional unit and sold or used as a stand-alone product. Based on such understanding, all or part of the flow of the method according to the embodiments of the present invention may also be implemented by a computer program, which may be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method embodiments may be implemented. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice.
It should be noted that the above-described device embodiments are merely illustrative, where the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. In addition, in the drawings of the embodiment of the apparatus provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, and may be specifically implemented as one or more communication buses or signal lines. One of ordinary skill in the art can understand and implement it without inventive effort.
While the foregoing is directed to the preferred embodiment of the present invention, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention.
Claims (8)
1. A face recognition method based on nostril information is characterized by comprising the following steps:
when a face recognition instruction is responded, whether a face exists in the shooting range of the camera is detected;
when the fact that a human face exists in the shooting range of the camera is detected, acquiring a plurality of human face images shot by the camera, and extracting nostril information in the human face images;
performing living body identification on the nostril information according to a prestored nostril size threshold value, and judging whether a plurality of currently acquired face images are living body face images;
when the face image is a living body face image, extracting face information of the face image, and carrying out face identification on the face information according to a pre-stored face template;
wherein, the extracting nostril information in a plurality of face images comprises:
extracting the length of the left nostril from the leftmost end to the rightmost end in the left nostrils in the plurality of face images, and extracting the length of the right nostril from the leftmost end to the rightmost end in the right nostrils in the plurality of face images;
acquiring absolute values of differences between lengths of left nostrils in a plurality of face images, and acquiring absolute values of differences between lengths of right nostrils in the plurality of face images;
taking the maximum of the absolute value of the difference between the left nostril lengths and the absolute value of the difference between the right nostril lengths as the nostril information.
2. The method of claim 1, wherein the in-vivo identification of the nostril information according to a prestored nostril size threshold value and the judgment of whether the currently acquired face images are in-vivo face images comprises:
judging whether the nostril information is larger than a prestored nostril size threshold value or not;
if yes, judging that the plurality of face images which are acquired currently are living face images; and if not, judging that the plurality of face images which are acquired currently are non-living body face images.
3. The method for recognizing a face based on nostril information as claimed in claim 1, wherein the face recognizing the face information according to a pre-stored face template comprises:
if the matching degree of the face information and the face template is greater than or equal to a preset matching value, judging that the face recognition is successful;
and if the matching degree of the face information and the face template is smaller than the preset matching value, judging that the face recognition fails.
4. The method of claim 1, wherein the face information includes, but is not limited to, face contour, eye position information, nose contour, and nose position information.
5. A face recognition system based on nostril information, comprising:
the human face detection unit is used for detecting whether a human face exists in the shooting range of the camera when responding to the human face recognition instruction;
the face image acquisition unit is used for acquiring a plurality of face images shot by the camera when the fact that a face exists in the shooting range of the camera is detected;
the nostril information acquisition unit is used for extracting nostril information in the plurality of face images;
the living body identification unit is used for carrying out living body identification on the nostril information according to a prestored nostril size threshold value and judging whether a plurality of currently acquired face images are living body face images or not;
the face recognition unit is used for extracting face information of the face image when the face image is a living body face image, and carrying out face recognition on the face information according to a pre-stored face template;
wherein, the nostril information obtaining unit is specifically configured to:
extracting the length of the left nostril from the leftmost end to the rightmost end in the left nostrils in the plurality of face images, and extracting the length of the right nostril from the leftmost end to the rightmost end in the right nostrils in the plurality of face images;
acquiring absolute values of differences between lengths of left nostrils in a plurality of face images, and acquiring absolute values of differences between lengths of right nostrils in the plurality of face images;
taking the maximum of the absolute value of the difference between the left nostril lengths and the absolute value of the difference between the right nostril lengths as the nostril information.
6. The nostril information based face recognition system of claim 5, wherein the living body recognition unit is specifically configured to:
judging whether the nostril information is larger than a prestored nostril size threshold value or not;
if yes, judging that the plurality of face images which are acquired currently are living face images; and if not, judging that the plurality of face images which are acquired currently are non-living body face images.
7. The nostril information-based face recognition system according to claim 5, wherein the face recognition unit is configured to determine that the face recognition is successful if the degree of matching between the face information and the face template is greater than or equal to a preset matching value; if the matching degree of the face information and the face template is smaller than the preset matching value, judging that face recognition fails;
the face information includes, but is not limited to, face contours, eye position information, nose contours, and nose position information.
8. A nostril information based face recognition device comprising a processor, a memory and a computer program stored in the memory and configured to be executed by the processor, the processor implementing the nostril information based face recognition method of any one of claims 1 to 4 when executing the computer program.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811573339.5A CN109684993B (en) | 2018-12-21 | 2018-12-21 | Face recognition method, system and equipment based on nostril information |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811573339.5A CN109684993B (en) | 2018-12-21 | 2018-12-21 | Face recognition method, system and equipment based on nostril information |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109684993A CN109684993A (en) | 2019-04-26 |
CN109684993B true CN109684993B (en) | 2021-04-27 |
Family
ID=66188837
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811573339.5A Expired - Fee Related CN109684993B (en) | 2018-12-21 | 2018-12-21 | Face recognition method, system and equipment based on nostril information |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109684993B (en) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112750221B (en) * | 2019-10-31 | 2023-05-12 | 深圳云天励飞技术有限公司 | Campus check-in method, device and check-in equipment |
CN111985438A (en) * | 2020-08-31 | 2020-11-24 | 杭州海康威视数字技术股份有限公司 | Static face processing method, device and equipment |
CN113158773B (en) * | 2021-03-05 | 2024-03-22 | 普联技术有限公司 | Training method and training device for living body detection model |
CN113723306B (en) * | 2021-08-31 | 2024-06-28 | 上海掌门科技有限公司 | Push-up detection method, push-up detection device and computer readable medium |
Family Cites Families (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104951743A (en) * | 2015-03-04 | 2015-09-30 | 苏州大学 | Active-shape-model-algorithm-based method for analyzing face expression |
CN105550671A (en) * | 2016-01-28 | 2016-05-04 | 北京麦芯科技有限公司 | Face recognition method and device |
CN107346422B (en) * | 2017-06-30 | 2020-09-08 | 成都大学 | Living body face recognition method based on blink detection |
CN107292290B (en) * | 2017-07-17 | 2021-02-19 | Oppo广东移动通信有限公司 | Face living body identification method and related product |
CN107451547A (en) * | 2017-07-17 | 2017-12-08 | 广东欧珀移动通信有限公司 | Identify the method and Related product of live body |
CN107590463A (en) * | 2017-09-12 | 2018-01-16 | 广东欧珀移动通信有限公司 | Face identification method and Related product |
CN107895155A (en) * | 2017-11-29 | 2018-04-10 | 五八有限公司 | A kind of face identification method and device |
-
2018
- 2018-12-21 CN CN201811573339.5A patent/CN109684993B/en not_active Expired - Fee Related
Also Published As
Publication number | Publication date |
---|---|
CN109684993A (en) | 2019-04-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109684993B (en) | Face recognition method, system and equipment based on nostril information | |
TWI751161B (en) | Terminal equipment, smart phone, authentication method and system based on face recognition | |
US10650259B2 (en) | Human face recognition method and recognition system based on lip movement information and voice information | |
CN105612533B (en) | Living body detection method, living body detection system, and computer program product | |
WO2019071664A1 (en) | Human face recognition method and apparatus combined with depth information, and storage medium | |
CN110612530B (en) | Method for selecting frames for use in face processing | |
CN109858337A (en) | A kind of face identification method based on pupil information, system and equipment | |
US9930525B2 (en) | Method and system for eyeprint recognition unlocking based on environment-filtering frames | |
CN110287918B (en) | Living body identification method and related product | |
US9449217B1 (en) | Image authentication | |
CN108108711B (en) | Face control method, electronic device and storage medium | |
WO2019011073A1 (en) | Human face live detection method and related product | |
KR101724971B1 (en) | System for recognizing face using wide angle camera and method for recognizing face thereof | |
WO2020244071A1 (en) | Neural network-based gesture recognition method and apparatus, storage medium, and device | |
CN108090340B (en) | Face recognition processing method, face recognition processing device and intelligent terminal | |
US11151398B2 (en) | Anti-counterfeiting processing method, electronic device, and non-transitory computer-readable storage medium | |
CN107710221B (en) | Method and device for detecting living body object and mobile terminal | |
CN111095268A (en) | User identity identification method and device and electronic equipment | |
CN110705356B (en) | Function control method and related equipment | |
CN114677607A (en) | Real-time pedestrian counting method and device based on face recognition | |
CN105825102A (en) | Terminal unlocking method and apparatus based on eye-print identification | |
CN111353364A (en) | Dynamic face identification method and device and electronic equipment | |
CN107545163B (en) | Unlocking control method and related product | |
CN105407069B (en) | Living body authentication method, apparatus, client device and server | |
CN113132801A (en) | Video playing control method, device, terminal and storage medium |
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 | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20210427 |
|
CF01 | Termination of patent right due to non-payment of annual fee |