CN113298008A - Living body detection-based driver face identification qualification authentication method and device - Google Patents
Living body detection-based driver face identification qualification authentication method and device Download PDFInfo
- Publication number
- CN113298008A CN113298008A CN202110624048.XA CN202110624048A CN113298008A CN 113298008 A CN113298008 A CN 113298008A CN 202110624048 A CN202110624048 A CN 202110624048A CN 113298008 A CN113298008 A CN 113298008A
- Authority
- CN
- China
- Prior art keywords
- face
- image
- driver
- video
- feature vector
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 142
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000012797 qualification Methods 0.000 title claims abstract description 31
- 238000003062 neural network model Methods 0.000 claims abstract description 65
- 239000013598 vector Substances 0.000 claims description 96
- 230000009466 transformation Effects 0.000 claims description 20
- 230000008859 change Effects 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 10
- 238000005520 cutting process Methods 0.000 claims description 4
- 238000003860 storage Methods 0.000 claims description 4
- 238000004891 communication Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000001727 in vivo Methods 0.000 description 3
- 238000007781 pre-processing Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 210000000887 face Anatomy 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000004519 manufacturing process 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
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- 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
Abstract
The invention provides a driver face identification qualification authentication method and device based on living body detection, which comprises the following steps: determining face frame coordinates and key point coordinates corresponding to the image converted from the face video based on a face detection neural network model; obtaining a region image for living body detection based on the key point coordinates; detecting based on a living body detection neural network model, and determining the real face situation of a driver in a cab of the vehicle A; if the real face situation of the driver in the cab is real, obtaining an image with the aligned face; and inputting the image after the face alignment into a face recognition neural network model for recognition, and determining whether a driver in a cab of the vehicle A has the driving permission of the vehicle A. On one hand, the method can cope with various false body attacks based on the living body detection, and on the other hand, whether a driver in a cab of the current vehicle A has the driving permission of the vehicle A can be accurately determined, so that safety guarantee is provided.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a driver face identification qualification authentication method and device based on living body detection.
Background
With the improvement of hardware computing power, more and more methods for solving the face recognition problem based on the neural network are provided. Face recognition technology is widely used in life and work. However, the method is not widely applied to the field of commercial vehicles, and the prior art cannot verify whether a driver has a driving permission qualification through face recognition, so that the occurrence of potential accidents cannot be reduced. Meanwhile, the prior art cannot prevent a driver from attacking the face recognition technology by using a prosthesis such as a picture.
Disclosure of Invention
Aiming at the problems in the prior art, the embodiment of the invention provides a driver face identification qualification authentication method and device based on living body detection.
In a first aspect, an embodiment of the present invention provides a method for identifying qualification of a driver's face based on live body detection, including:
acquiring a face video of a driver in a cab of a vehicle A, and converting the face video into an image;
inputting the image converted from the face video into a face detection neural network model for detection, and determining face frame coordinates corresponding to the image converted from the face video and key point coordinates corresponding to the image converted from the face video;
clipping the image converted by the face video based on the key point coordinates corresponding to the image converted by the face video to obtain a region image for living body detection;
inputting the area image for living body detection into a living body detection neural network model for detection, and determining the real face situation of a driver in a cab of the vehicle A;
if the real face situation of the driver in the cab is real, determining a face area image based on face frame coordinates corresponding to the image converted from the face video, and performing face alignment by adopting perspective change based on the face area image to obtain an image after face alignment;
and inputting the image after the face alignment into a face recognition neural network model for recognition, and determining whether a driver in a cab of the vehicle A has the driving permission of the vehicle A.
Further, inputting the image converted from the face video into a face detection neural network model for detection, and determining a face frame coordinate corresponding to the image converted from the face video and a key point coordinate corresponding to the image converted from the face video, specifically comprising:
inputting the image converted by the face video into a face detection neural network model for detection, and determining face frame coordinates (x, y, w, h) corresponding to the image converted by the face video and key point coordinates corresponding to the image converted by the face video
Wherein x represents the horizontal coordinate of the top left corner of the face frame, y represents the vertical coordinate of the top left corner of the face frame, w represents the width of the face frame, and h represents the height of the face frame;
the abscissa and ordinate representing the center of the left eye of the face,
the abscissa and ordinate representing the center of the right eye of the face,
the horizontal coordinate and the vertical coordinate of the nose tip of the human face are shown,
the abscissa and ordinate of the left mouth corner of the face are indicated,
the abscissa and ordinate of the right mouth angle of the face are indicated.
Further, still include:
and if the real face situation of the driver in the cab is not real, prompting that the face is forged by voice.
Further, inputting the image with the aligned face into a face recognition neural network model for recognition, and determining whether a driver in a cab of a vehicle a has a driving permission of the vehicle a, specifically comprising:
inputting the image after the face alignment into a face recognition neural network model for recognition to determine a first face characteristic vector;
carrying out mirror image transformation on the image after the face is aligned to determine an image after mirror image transformation, and inputting the image after mirror image transformation into a face recognition neural network model for recognition to determine a second face characteristic vector;
determining a third face feature vector based on the first face feature vector and the second face feature vector;
comparing a third face feature vector with a face feature vector set recorded in the face recognition neural network model to obtain a face feature vector corresponding to the third face feature vector in the recorded face feature vector set;
and determining an ID (identity) based on a face feature vector corresponding to a third face feature vector in the input face feature vector set, and determining whether a driver in a cab of the vehicle A has the driving permission of the vehicle A based on the driver represented by the ID.
In a second aspect, an embodiment of the present invention provides a driver face identification qualification authentication apparatus based on living body detection, including:
the system comprises an acquisition module, a display module and a control module, wherein the acquisition module is used for acquiring a face video of a driver in a cab of a vehicle A and converting the face video into an image;
the face detection module is used for inputting the image converted from the face video into a face detection neural network model for detection, and determining face frame coordinates corresponding to the image converted from the face video and key point coordinates corresponding to the image converted from the face video;
the cutting module is used for cutting the image converted by the face video based on the key point coordinates corresponding to the image converted by the face video to obtain an area image used for living body detection;
the living body detection module is used for inputting the area image for living body detection into a living body detection neural network model for detection and determining the real situation of the face of a driver in a cab of the vehicle A;
the determining module is used for determining a face area image based on face frame coordinates corresponding to the image converted from the face video if the real face situation of the driver in the cab is real, and performing face alignment by adopting perspective change based on the face area image to obtain an image after face alignment;
and the face recognition module is used for inputting the image after the face alignment into a face recognition neural network model for recognition and determining whether a driver in a cab of the vehicle A has the driving permission of the vehicle A.
Further, the face detection module is specifically configured to:
inputting the image converted by the face video into a face detection neural network model for detection, and determining face frame coordinates (x, y, w, h) corresponding to the image converted by the face video and key point coordinates corresponding to the image converted by the face video
Wherein x represents the horizontal coordinate of the top left corner of the face frame, y represents the vertical coordinate of the top left corner of the face frame, w represents the width of the face frame, and h represents the height of the face frame;
the abscissa and ordinate representing the center of the left eye of the face,
the abscissa and ordinate representing the center of the right eye of the face,
the horizontal coordinate and the vertical coordinate of the nose tip of the human face are shown,
the abscissa and ordinate of the left mouth corner of the face are indicated,
the abscissa and ordinate of the right mouth angle of the face are indicated.
Further, still include: a voice prompt module for sending a voice prompt to a user,
and the voice prompt module is used for prompting that the face of the driver is forged if the real face condition of the driver in the cab is not real.
Further, the face recognition module is specifically configured to:
inputting the image after the face alignment into a face recognition neural network model for recognition to determine a first face characteristic vector;
carrying out mirror image transformation on the image after the face is aligned to determine an image after mirror image transformation, and inputting the image after mirror image transformation into a face recognition neural network model for recognition to determine a second face characteristic vector;
determining a third face feature vector based on the first face feature vector and the second face feature vector;
comparing a third face feature vector with a face feature vector set recorded in the face recognition neural network model to obtain a face feature vector corresponding to the third face feature vector in the recorded face feature vector set;
and determining an ID (identity) based on a face feature vector corresponding to a third face feature vector in the input face feature vector set, and determining whether a driver in a cab of the vehicle A has the driving permission of the vehicle A based on the driver represented by the ID.
In a third aspect, an embodiment of the present invention further provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the steps of the living body detection-based driver face identification qualification authentication method according to the first aspect when executing the program.
In a fourth aspect, the present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the method for authenticating driver face identification based on living body detection according to the first aspect.
According to the technical scheme, the driver face identification qualification authentication method and device based on the living body detection, provided by the embodiment of the invention, are characterized in that the face video of the driver in the cab of the vehicle A is collected and converted into an image; inputting the image converted from the face video into a face detection neural network model for detection, and determining face frame coordinates corresponding to the image converted from the face video and key point coordinates corresponding to the image converted from the face video; clipping the image converted by the face video based on the key point coordinates corresponding to the image converted by the face video to obtain a region image for living body detection; inputting the area image for living body detection into a living body detection neural network model for detection, and determining the real face situation of a driver in a cab of the vehicle A; if the real face situation of the driver in the cab is real, determining a face area image based on face frame coordinates corresponding to the image converted from the face video, and performing face alignment by adopting perspective change based on the face area image to obtain an image after face alignment; the image after the face alignment is input into a face recognition neural network model for recognition, and whether the driver in the cab of the vehicle A has the driving permission of the vehicle A is determined.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a schematic flow chart of a method for identifying qualification of a driver's face based on living body detection according to an embodiment of the present invention;
fig. 2 is a schematic view of a face recognition process according to an embodiment of the present invention;
fig. 3 is a schematic view of a face recognition entry provided in an embodiment of the present invention;
FIG. 4 is a schematic diagram of a region image for in vivo detection according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a driver face identification qualification authentication apparatus based on living body detection according to an embodiment of the present invention;
fig. 6 is a schematic physical structure diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some embodiments, but not all embodiments, of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention. The method for identifying and certifying the face of a driver based on living body detection according to the present invention will be explained and illustrated in detail by specific embodiments.
Fig. 1 is a schematic flow chart of a method for identifying qualification of a driver's face based on living body detection according to an embodiment of the present invention; as shown in fig. 1, the method includes:
step 101: acquiring a face video of a driver in a cab of a vehicle A, and converting the face video into an image;
step 102: inputting the image converted from the face video into a face detection neural network model for detection, and determining face frame coordinates corresponding to the image converted from the face video and key point coordinates corresponding to the image converted from the face video;
step 103: clipping the image converted by the face video based on the key point coordinates corresponding to the image converted by the face video to obtain a region image for living body detection;
step 104: inputting the area image for living body detection into a living body detection neural network model for detection, and determining the real face situation of a driver in a cab of the vehicle A;
step 105: if the real face situation of the driver in the cab is real, determining a face area image based on face frame coordinates corresponding to the image converted from the face video, and performing face alignment by adopting perspective change based on the face area image to obtain an image after face alignment;
step 106: and inputting the image after the face alignment into a face recognition neural network model for recognition, and determining whether a driver in a cab of the vehicle A has the driving permission of the vehicle A.
In the embodiment, it should be noted that the face recognition is used to verify whether the driver is qualified for driving, so as to help reduce the occurrence of potential accidents; on the basis of verifying whether a driver has a driving permission or not through face recognition, in order to prevent the driver from attacking a face recognition technology by using a false body such as a picture and the like, the attack means such as a picture, a video, a printed picture, a three-dimensional false face and the like recorded on a screen can be effectively resisted by combining a living body detection mode, so that the face recognition can be quickly and accurately operated on an embedded device and can cope with various false body attacks, the embodiment of the invention provides a driver face recognition qualification authentication method based on the living body detection.
In this embodiment, it can be understood that the infrared camera is used to collect the face video of the driver in the cab of the vehicle a, that is, the infrared camera is used to monitor the environment in the cab in real time, and at the same time, convert the collected face video into an image (that is, convert the face video into an image), determine whether there is a real face according to a preset software logic (that is, input the area image for in-vivo detection into the in-vivo detection neural network model for detection, and determine the real situation of the face of the driver in the cab of the vehicle a), and if there is a real face (that is, if the real situation of the face of the driver in the cab is real), immediately identify whether the person is a person with the vehicle driving permission through the next software logic (that is, input the image after the face is aligned into the face recognition neural network model for identification, and determine whether the driver in the cab of the vehicle a has the driving permission of the vehicle a), and the electronic system transmits the judgment information to the vehicle-mounted host or the server. The vehicle-mounted host gives voice prompt to the driver.
In order to better understand the present invention, the following examples are further provided to illustrate the content of the present invention, but the present invention is not limited to the following examples.
For example: referring to fig. 2 and fig. 3, a picture is collected in real time by a camera device (for example, in step one in fig. 2, a photo is taken to input a picture) to judge whether a current input frame is a real face (i.e., live body detection, and then whether the current input frame is a real face is judged, and referring to fig. 2), if the current input frame is a real face, whether a person in the image has the vehicle driving qualification is continuously judged (referring to fig. 3, picture preprocessing such as face alignment and image scaling, and then a trained face recognition convolutional neural network is input, that is, the image after face alignment is input to a face recognition neural network model for recognition, feature vectors (a first face feature vector, a second face feature vector and a third face feature vector) of a current driver are further determined, and finally, an ID is determined based on a face feature vector corresponding to the third face feature vector in an input face feature vector set, and whether the driver in the cab of the vehicle a has the driving permission of the vehicle a is determined based on the driver represented by the ID, that is, the feature vector and the ID corresponding thereto are stored in the server side in fig. 3), and finally, the determination result is prompted or uploaded to the server side for backup in a voice broadcast form or a display screen text display mode, specifically, network training, face entry and face recognition are required in the embodiment, wherein:
network training: deep convolution neural network needing training and comprising human face detection network module NetdThe method is mainly used for executing the step 102, inputting the image converted from the face video into a face detection neural network model for detection, and determining face frame coordinates corresponding to the image converted from the face video and key point coordinates corresponding to the image converted from the face video; living body detection network module NetlThe method is mainly used for executing step 104, inputting the area image for living body detection into a living body detection neural network model for detection, and determining the real situation of the face of a driver in a cab of the vehicle A; face recognition network module NetrThe method is mainly used for executing step 106 and inputting the image with the aligned human face into a human face recognition neural network model for recognition, and determining whether a driver in a cab of the vehicle A has the driving permission of the vehicle A. If the input of the face detection network module is 300 x 300 pictures, the output is face frame coordinates (x, y, w, h) (only one face is compared by face recognition each time) and key point coordinates
Wherein x is the horizontal coordinate of the upper left corner of the face frame, y is the vertical coordinate of the upper left corner of the face frame, w is the width of the face frame, and h is the height of the face frame;
the abscissa and ordinate of the center of the left eye of the face,
is the abscissa and ordinate of the center of the right eye of the human face,
the horizontal coordinate and the vertical coordinate of the nose tip of the human face,
the horizontal coordinate and the vertical coordinate of the left mouth corner of the human face,
the abscissa and ordinate of the right mouth corner of the human face are shown. The living body detection network module inputs an image area (namely an interested area) and adopts the positions of two eyes and the center position of the nose tip to obtain an image with the height from the center position of the higher eye of the two eyes to the nose tip and the width from the center of the left eye to the center of the right eye as a training image, as shown in fig. 4, the image is input into the living body detection network module after being zoomed to 24 × 24, and the confidence conf of true classification is outputtrueAnd false confidence conffalse. The input of the face recognition network module is a picture which adopts perspective transformation and is subjected to face correspondence, and the image is zoomed to 112 × 96. The output is a face feature vector of 512 x 1.
Face inputting: according to the text voice prompt of the display screen, picture preprocessing is carried out on the front face image of the face of the driver with the driving qualification of the vehicle, the preprocessing comprises face detection, face detection outputs face frames and five key point coordinates, a face area is cut according to the face frames, face alignment is carried out by adopting perspective transformation, and the picture after face alignment is zoomed to 112 × 96. Input to the face recognition network module NetrObtaining 512 x 1 face feature vector corresponding to the face, carrying out mirror image transformation on the 112 x 96 face alignment picture, and inputting the picture into a face recognition network module NetrAlso obtain the corresponding 512 x 1 face feature vector of the face after mirroring, connect the two face feature vectors together to form 1024 x 1 feature vector, which is the feature vector in this example
And storing the feature vector and the face ID corresponding to the feature vector in a server side.
Face recognition: according to the text voice prompt of the display screen, the testee collects a face front image facing the infrared camera, outputs a face frame and key point coordinates according to the image, cuts out a living body detection area according to the key point coordinates, and inputs the living body detection area image to a living body detection network module NetlIf the face is a real face, the judgment is based on the output result confidence coefficient value, namely max { conftrue,conffalseIf not, the human face is prompted to be forged by voice, if so, the human face is aligned by adopting perspective transformation to the human face area, and the image is input to the human face recognition network module Net after being zoomed to 112 × 96rObtaining 512 x 1 face characteristic vector of the tested person, carrying out mirror image transformation on the image scaled to 112 x 96, and then sending the image to a face identification network module NetrAlso obtain the corresponding 512 x 1 face feature vector of the face after mirroring, connect the two face feature vectors together to form 1024 x 1 feature vector, which is the feature vector in this example
Inputting the feature vector
Comparing with all the face feature vectors recorded, wherein the number of the face feature vectors recorded in the example is m, and all the face feature vectors recorded in the example are
And representing the feature vector of the mth input human face. Respectively calculate
And
cosine similarity, the calculation formula of cosine similarity is
The cosine similarity value range is calculated to be [ -1,1]So it is normalized to [0,1 ]]Normalized formula is
Assume that the lowest confidence score is considered confxN number of satisfy
Feature vector of (2), using set
And (4) showing.
And expressing the score of the nth characteristic vector meeting the confidence requirement, taking the ID corresponding to the characteristic vector with the maximum score in the n characteristic vectors as an identification result, and prompting the driver to log in the vehicle and open the driving authority by voice if the driver represented by the ID has the vehicle permission. If the driver represented by the ID does not have the vehicle permission, the driver is prompted to log in the vehicle by voice but does not have the vehicle driving qualification and does not have the permission to open, and the picture is reported by a background. If the face recorded does not have the characteristic vector similar to the tested person, the voice prompts that an unknown person logs in the driving system, and the background reports the picture.
According to the technical scheme, the driver face identification qualification authentication method based on the living body detection provided by the embodiment of the invention comprises the steps of collecting a face video of a driver in a cab of a vehicle A, and converting the face video into an image; inputting the image converted from the face video into a face detection neural network model for detection, and determining face frame coordinates corresponding to the image converted from the face video and key point coordinates corresponding to the image converted from the face video; clipping the image converted by the face video based on the key point coordinates corresponding to the image converted by the face video to obtain a region image for living body detection; inputting the area image for living body detection into a living body detection neural network model for detection, and determining the real face situation of a driver in a cab of the vehicle A; if the real face situation of the driver in the cab is real, determining a face area image based on face frame coordinates corresponding to the image converted from the face video, and performing face alignment by adopting perspective change based on the face area image to obtain an image after face alignment; the image after the face alignment is input into a face recognition neural network model for recognition, and whether the driver in the cab of the vehicle A has the driving permission of the vehicle A is determined.
On the basis of the foregoing embodiment, in this embodiment, inputting the image converted from the face video into a face detection neural network model for detection, and determining coordinates of a face frame corresponding to the image converted from the face video and coordinates of a key point corresponding to the image converted from the face video specifically include:
inputting the image converted by the face video into a face detection neural network model for detection, and determining face frame coordinates (x, y, w, h) corresponding to the image converted by the face video and key point coordinates corresponding to the image converted by the face video
Wherein x represents the horizontal coordinate of the top left corner of the face frame, y represents the vertical coordinate of the top left corner of the face frame, w represents the width of the face frame, and h represents the height of the face frame;
the abscissa and ordinate representing the center of the left eye of the face,
the abscissa and ordinate representing the center of the right eye of the face,
the horizontal coordinate and the vertical coordinate of the nose tip of the human face are shown,
the abscissa and ordinate of the left mouth corner of the face are indicated,
the abscissa and ordinate of the right mouth angle of the face are indicated.
On the basis of the above embodiment, in this embodiment, the method further includes:
and if the real face situation of the driver in the cab is not real, prompting that the face is forged by voice.
On the basis of the foregoing embodiment, in this embodiment, the inputting the image with aligned human faces to a human face recognition neural network model for recognition, and determining whether a driver in a cab of a vehicle a has a driving permission of the vehicle a specifically includes:
inputting the image after the face alignment into a face recognition neural network model for recognition to determine a first face characteristic vector;
carrying out mirror image transformation on the image after the face is aligned to determine an image after mirror image transformation, and inputting the image after mirror image transformation into a face recognition neural network model for recognition to determine a second face characteristic vector;
determining a third face feature vector based on the first face feature vector and the second face feature vector;
comparing a third face feature vector with a face feature vector set recorded in the face recognition neural network model to obtain a face feature vector corresponding to the third face feature vector in the recorded face feature vector set;
and determining an ID (identity) based on a face feature vector corresponding to a third face feature vector in the input face feature vector set, and determining whether a driver in a cab of the vehicle A has the driving permission of the vehicle A based on the driver represented by the ID.
According to the technical scheme, the living body detection-based driver face identification qualification authentication method provided by the embodiment of the invention can be used for dealing with various false body attacks on the basis of the living body detection on one hand, and can be used for accurately determining whether a driver in a cab of a current vehicle A has the driving permission of the vehicle A on the other hand, so that safety guarantee is provided.
Fig. 5 is a schematic structural diagram of a living body detection-based driver face identification qualification authentication apparatus according to an embodiment of the present invention, as shown in fig. 5, the apparatus includes: an acquisition module 201, a face detection module 202, a cropping module 203, a liveness detection module 204, a determination module 205, and a face recognition module 206, wherein:
the system comprises an acquisition module 201, a display module and a control module, wherein the acquisition module 201 is used for acquiring a face video of a driver in a cab of a vehicle A and converting the face video into an image;
a face detection module 202, configured to input the image converted from the face video into a face detection neural network model for detection, and determine face frame coordinates corresponding to the image converted from the face video and key point coordinates corresponding to the image converted from the face video;
the cropping module 203 is used for cropping the image converted from the face video based on the key point coordinates corresponding to the image converted from the face video to obtain an area image for living body detection;
the living body detection module 204 is used for inputting the area image for living body detection into a living body detection neural network model for detection, and determining the real situation of the face of a driver in a cab of the vehicle A;
a determining module 205, configured to determine a face region image based on face frame coordinates corresponding to the image converted from the face video if the real face situation of the driver in the cab is real, and perform face alignment based on the face region image by using perspective change to obtain an image after face alignment;
and the face recognition module 206 is configured to input the image after the face alignment to a face recognition neural network model for recognition, and determine whether a driver in a cab of the vehicle a has a driving permission of the vehicle a.
The driver face identification qualification authentication device based on living body detection provided by the embodiment of the invention can be specifically used for executing the driver face identification qualification authentication method based on living body detection of the embodiment, the technical principle and the beneficial effect are similar, and the embodiment can be specifically referred to, and the details are not repeated herein.
Based on the same inventive concept, an embodiment of the present invention provides an electronic device, which specifically includes the following components, with reference to fig. 6: a processor 301, a communication interface 303, a memory 302, and a communication bus 304;
the processor 301, the communication interface 303 and the memory 302 complete mutual communication through the communication bus 304; the communication interface 303 is used for realizing information transmission between related devices such as modeling software, an intelligent manufacturing equipment module library and the like; the processor 301 is used for calling the computer program in the memory 302, and the processor executes the computer program to implement the method provided by the above method embodiments, for example, the processor executes the computer program to implement the following steps: acquiring a face video of a driver in a cab of a vehicle A, and converting the face video into an image; inputting the image converted from the face video into a face detection neural network model for detection, and determining face frame coordinates corresponding to the image converted from the face video and key point coordinates corresponding to the image converted from the face video; clipping the image converted by the face video based on the key point coordinates corresponding to the image converted by the face video to obtain a region image for living body detection; inputting the area image for living body detection into a living body detection neural network model for detection, and determining the real face situation of a driver in a cab of the vehicle A; if the real face situation of the driver in the cab is real, determining a face area image based on face frame coordinates corresponding to the image converted from the face video, and performing face alignment by adopting perspective change based on the face area image to obtain an image after face alignment; and inputting the image after the face alignment into a face recognition neural network model for recognition, and determining whether a driver in a cab of the vehicle A has the driving permission of the vehicle A.
Based on the same inventive concept, yet another embodiment of the present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, is implemented to perform the methods provided by the above method embodiments, for example, capturing a video of a face of a driver in a cab of a vehicle a, and converting the video of the face into an image; inputting the image converted from the face video into a face detection neural network model for detection, and determining face frame coordinates corresponding to the image converted from the face video and key point coordinates corresponding to the image converted from the face video; clipping the image converted by the face video based on the key point coordinates corresponding to the image converted by the face video to obtain a region image for living body detection; inputting the area image for living body detection into a living body detection neural network model for detection, and determining the real face situation of a driver in a cab of the vehicle A; if the real face situation of the driver in the cab is real, determining a face area image based on face frame coordinates corresponding to the image converted from the face video, and performing face alignment by adopting perspective change based on the face area image to obtain an image after face alignment; and inputting the image after the face alignment into a face recognition neural network model for recognition, and determining whether a driver in a cab of the vehicle A has the driving permission of the vehicle A.
The above-described embodiments of the apparatus are merely illustrative, and 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 a plurality of 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. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods of the various embodiments or some parts of the embodiments.
In addition, in the present invention, terms such as "first" and "second" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "a plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
Moreover, in the present invention, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
Furthermore, in the description herein, reference to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A face recognition qualification authentication method for a driver based on living body detection is characterized by comprising the following steps:
acquiring a face video of a driver in a cab of a vehicle A, and converting the face video into an image;
inputting the image converted from the face video into a face detection neural network model for detection, and determining face frame coordinates corresponding to the image converted from the face video and key point coordinates corresponding to the image converted from the face video;
clipping the image converted by the face video based on the key point coordinates corresponding to the image converted by the face video to obtain a region image for living body detection;
inputting the area image for living body detection into a living body detection neural network model for detection, and determining the real face situation of a driver in a cab of the vehicle A;
if the real face situation of the driver in the cab is real, determining a face area image based on face frame coordinates corresponding to the image converted from the face video, and performing face alignment by adopting perspective change based on the face area image to obtain an image after face alignment;
and inputting the image after the face alignment into a face recognition neural network model for recognition, and determining whether a driver in a cab of the vehicle A has the driving permission of the vehicle A.
2. The living body detection-based driver face identification qualification authentication method according to claim 1, wherein the image converted from the face video is input into a face detection neural network model for detection, and face frame coordinates corresponding to the image converted from the face video and key point coordinates corresponding to the image converted from the face video are determined, specifically comprising:
inputting the image converted by the face video into a face detection neural network model for detection, and determining face frame coordinates (x, y, w, h) corresponding to the image converted by the face video and key point coordinates corresponding to the image converted by the face video
Wherein x represents the horizontal coordinate of the top left corner of the face frame, y represents the vertical coordinate of the top left corner of the face frame, w represents the width of the face frame, and h represents the height of the face frame;
the abscissa and ordinate representing the center of the left eye of the face,
the abscissa and ordinate representing the center of the right eye of the face,
the horizontal coordinate and the vertical coordinate of the nose tip of the human face are shown,
the abscissa and ordinate of the left mouth corner of the face are indicated,
the abscissa and ordinate of the right mouth angle of the face are indicated.
3. The living body detection-based face recognition qualification authentication method for the driver according to claim 1, further comprising:
and if the real face situation of the driver in the cab is not real, prompting that the face is forged by voice.
4. The living body detection-based driver face identification qualification authentication method according to claim 1, wherein the image obtained by aligning the faces is input to a face identification neural network model for identification, and whether a driver in a cab of a vehicle a has the permission of driving of the vehicle a is determined, specifically comprising:
inputting the image after the face alignment into a face recognition neural network model for recognition to determine a first face characteristic vector;
carrying out mirror image transformation on the image after the face is aligned to determine an image after mirror image transformation, and inputting the image after mirror image transformation into a face recognition neural network model for recognition to determine a second face characteristic vector;
determining a third face feature vector based on the first face feature vector and the second face feature vector;
comparing a third face feature vector with a face feature vector set recorded in the face recognition neural network model to obtain a face feature vector corresponding to the third face feature vector in the recorded face feature vector set;
and determining an ID (identity) based on a face feature vector corresponding to a third face feature vector in the input face feature vector set, and determining whether a driver in a cab of the vehicle A has the driving permission of the vehicle A based on the driver represented by the ID.
5. A driver face identification qualification authentication device based on living body detection is characterized by comprising:
the system comprises an acquisition module, a display module and a control module, wherein the acquisition module is used for acquiring a face video of a driver in a cab of a vehicle A and converting the face video into an image;
the face detection module is used for inputting the image converted from the face video into a face detection neural network model for detection, and determining face frame coordinates corresponding to the image converted from the face video and key point coordinates corresponding to the image converted from the face video;
the cutting module is used for cutting the image converted by the face video based on the key point coordinates corresponding to the image converted by the face video to obtain an area image used for living body detection;
the living body detection module is used for inputting the area image for living body detection into a living body detection neural network model for detection and determining the real situation of the face of a driver in a cab of the vehicle A;
the determining module is used for determining a face area image based on face frame coordinates corresponding to the image converted from the face video if the real face situation of the driver in the cab is real, and performing face alignment by adopting perspective change based on the face area image to obtain an image after face alignment;
and the face recognition module is used for inputting the image after the face alignment into a face recognition neural network model for recognition and determining whether a driver in a cab of the vehicle A has the driving permission of the vehicle A.
6. The living body detection-based driver face identification qualification authentication device according to claim 5, wherein the face detection module is specifically configured to:
looking at the human faceInputting the frequency-converted image into a face detection neural network model for detection, and determining face frame coordinates (x, y, w, h) corresponding to the image converted from the face video and key point coordinates (x, y, w, h) corresponding to the image converted from the face video
Wherein x represents the horizontal coordinate of the top left corner of the face frame, y represents the vertical coordinate of the top left corner of the face frame, w represents the width of the face frame, and h represents the height of the face frame;
the abscissa and ordinate representing the center of the left eye of the face,
the abscissa and ordinate representing the center of the right eye of the face,
the horizontal coordinate and the vertical coordinate of the nose tip of the human face are shown,
the abscissa and ordinate of the left mouth corner of the face are indicated,
the abscissa and ordinate of the right mouth angle of the face are indicated.
7. The living body detection-based driver face identification qualification authentication device according to claim 5, further comprising: a voice prompt module for sending a voice prompt to a user,
and the voice prompt module is used for prompting that the face of the driver is forged if the real face condition of the driver in the cab is not real.
8. The living body detection-based driver face identification qualification authentication device according to claim 5, wherein the face identification module is specifically configured to:
inputting the image after the face alignment into a face recognition neural network model for recognition to determine a first face characteristic vector;
carrying out mirror image transformation on the image after the face is aligned to determine an image after mirror image transformation, and inputting the image after mirror image transformation into a face recognition neural network model for recognition to determine a second face characteristic vector;
determining a third face feature vector based on the first face feature vector and the second face feature vector;
comparing a third face feature vector with a face feature vector set recorded in the face recognition neural network model to obtain a face feature vector corresponding to the third face feature vector in the recorded face feature vector set;
and determining an ID (identity) based on a face feature vector corresponding to a third face feature vector in the input face feature vector set, and determining whether a driver in a cab of the vehicle A has the driving permission of the vehicle A based on the driver represented by the ID.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and operable on the processor, wherein the processor when executing the program implements the method for qualification of face recognition of a driver based on liveness detection according to any one of claims 1 to 4.
10. A non-transitory computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the method for qualifying driver face identification based on liveness detection according to any of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110624048.XA CN113298008A (en) | 2021-06-04 | 2021-06-04 | Living body detection-based driver face identification qualification authentication method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110624048.XA CN113298008A (en) | 2021-06-04 | 2021-06-04 | Living body detection-based driver face identification qualification authentication method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113298008A true CN113298008A (en) | 2021-08-24 |
Family
ID=77327401
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110624048.XA Pending CN113298008A (en) | 2021-06-04 | 2021-06-04 | Living body detection-based driver face identification qualification authentication method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113298008A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150341370A1 (en) * | 2014-02-25 | 2015-11-26 | Sal Khan | Systems and methods relating to the authenticity and verification of photographic identity documents |
| CN105844227A (en) * | 2016-03-21 | 2016-08-10 | 湖南君士德赛科技发展有限公司 | Driver identity authentication method for school bus safety |
| CN109657609A (en) * | 2018-12-19 | 2019-04-19 | 新大陆数字技术股份有限公司 | Face identification method and system |
| CN109977771A (en) * | 2019-02-22 | 2019-07-05 | 杭州飞步科技有限公司 | Verification method, device, equipment and the computer readable storage medium of driver identification |
| CN112183449A (en) * | 2020-10-15 | 2021-01-05 | 上海汽车集团股份有限公司 | Driver identity verification method and device, electronic equipment and storage medium |
| CN112232204A (en) * | 2020-10-16 | 2021-01-15 | 中科智云科技有限公司 | Living body detection method based on infrared image |
-
2021
- 2021-06-04 CN CN202110624048.XA patent/CN113298008A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150341370A1 (en) * | 2014-02-25 | 2015-11-26 | Sal Khan | Systems and methods relating to the authenticity and verification of photographic identity documents |
| CN105844227A (en) * | 2016-03-21 | 2016-08-10 | 湖南君士德赛科技发展有限公司 | Driver identity authentication method for school bus safety |
| CN109657609A (en) * | 2018-12-19 | 2019-04-19 | 新大陆数字技术股份有限公司 | Face identification method and system |
| CN109977771A (en) * | 2019-02-22 | 2019-07-05 | 杭州飞步科技有限公司 | Verification method, device, equipment and the computer readable storage medium of driver identification |
| CN112183449A (en) * | 2020-10-15 | 2021-01-05 | 上海汽车集团股份有限公司 | Driver identity verification method and device, electronic equipment and storage medium |
| CN112232204A (en) * | 2020-10-16 | 2021-01-15 | 中科智云科技有限公司 | Living body detection method based on infrared image |
Non-Patent Citations (3)
| Title |
|---|
| 任梓涵等: "基于视觉跟踪的实时视频人脸识别", 《厦门大学学报(自然科学版)》 * |
| 张汶汶等: "基于多样本扩充的卷积神经网络人脸识别算法", 《计算机与数字工程》 * |
| 王轶萍等: "一种网约车智能服务终端的设计与实现", 《公路交通科技(应用技术版)》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111709409B (en) | Face living body detection method, device, equipment and medium | |
| CN109711243B (en) | Static three-dimensional face in-vivo detection method based on deep learning | |
| EP3916627A1 (en) | Living body detection method based on facial recognition, and electronic device and storage medium | |
| CN109858375B (en) | Living body face detection method, terminal and computer readable storage medium | |
| CN107590430A (en) | Biopsy method, device, equipment and storage medium | |
| CN101551852B (en) | Training system, training method and detection method | |
| CN111126366B (en) | Method, device, equipment and storage medium for distinguishing living human face | |
| CN109766755A (en) | Face identification method and Related product | |
| CN111091075A (en) | Face recognition method and device, electronic equipment and storage medium | |
| CN112507889A (en) | Method and system for verifying certificate and certificate holder | |
| US11475707B2 (en) | Method for extracting image of face detection and device thereof | |
| CN112507772A (en) | Face recognition security system and suspicious person detection and early warning method | |
| US20100008546A1 (en) | Pattern identification method, registration device, verification device and program | |
| CN113642507A (en) | Examination monitoring method, system, equipment and medium based on multi-camera one-person detection | |
| CN112329516A (en) | Method, device and medium for detecting wearing of mask of driver based on key point positioning and image classification | |
| CN113298008A (en) | Living body detection-based driver face identification qualification authentication method and device | |
| CN112149517A (en) | Face attendance checking method and system, computer equipment and storage medium | |
| CN113989886A (en) | Crew identity verification method based on face recognition | |
| CN112598576B (en) | Safety verification method and system based on face recognition | |
| CN115019364A (en) | Identity authentication method and device based on face recognition, electronic equipment and medium | |
| CN115222621A (en) | Image correction method, electronic device, storage medium, and computer program product | |
| CN107742112A (en) | A kind of face method for anti-counterfeit and device based on image | |
| CN114332981A (en) | Face living body detection method and device, electronic equipment and storage medium | |
| CN114038030A (en) | Image tampering identification method, device and computer storage medium | |
| CN113553928A (en) | Human face living body detection method and system and computer equipment |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210824 |
|
| RJ01 | Rejection of invention patent application after publication |