CN113313856A - Door lock system with 3D face recognition function and using method - Google Patents
Door lock system with 3D face recognition function and using method Download PDFInfo
- Publication number
- CN113313856A CN113313856A CN202010084602.5A CN202010084602A CN113313856A CN 113313856 A CN113313856 A CN 113313856A CN 202010084602 A CN202010084602 A CN 202010084602A CN 113313856 A CN113313856 A CN 113313856A
- Authority
- CN
- China
- Prior art keywords
- face
- face image
- living body
- door lock
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 19
- 238000001514 detection method Methods 0.000 claims description 44
- 238000012549 training Methods 0.000 claims description 22
- 238000006073 displacement reaction Methods 0.000 claims description 3
- 230000002194 synthesizing effect Effects 0.000 claims description 3
- 238000012986 modification Methods 0.000 description 6
- 230000004048 modification Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000002366 time-of-flight method Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 4
- 238000013135 deep learning Methods 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 230000001960 triggered effect Effects 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000008921 facial expression Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—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
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C9/00—Individual registration on entry or exit
- G07C9/00174—Electronically operated locks; Circuits therefor; Nonmechanical keys therefor, e.g. passive or active electrical keys or other data carriers without mechanical keys
- G07C9/00309—Electronically operated locks; Circuits therefor; Nonmechanical keys therefor, e.g. passive or active electrical keys or other data carriers without mechanical keys operated with bidirectional data transmission between data carrier and locks
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C9/00—Individual registration on entry or exit
- G07C9/00174—Electronically operated locks; Circuits therefor; Nonmechanical keys therefor, e.g. passive or active electrical keys or other data carriers without mechanical keys
- G07C9/00563—Electronically operated locks; Circuits therefor; Nonmechanical keys therefor, e.g. passive or active electrical keys or other data carriers without mechanical keys using personal physical data of the operator, e.g. finger prints, retinal images, voicepatterns
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Computer Networks & Wireless Communication (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention provides a door lock system with 3D face recognition and a use method thereof, wherein the door lock system comprises a 3D face recognition module and a door lock main control module; the 3D face recognition module is used for acquiring a face image of a target face, performing living body recognition and face recognition on the face image, and generating an unlocking signal when the face image is a living body face and the face image is a preset white list face, otherwise generating an error prompt; the face image comprises an RGB face image, an infrared face image and a depth face image; and the door lock main control module is used for receiving the unlocking signal or the error prompt so as to control the door lock to unlock according to the unlocking signal or send the error prompt. In the invention, the human face image is subjected to living body recognition and human face recognition to judge whether the acquired target human face is a living body image or not and whether the acquired target human face is a preset white list human face allowing unlocking or not, so that the door lock main control module controls the door lock to unlock or prompts error information, and the intelligent control of the door lock can be realized.
Description
Technical Field
The invention relates to a face recognition system, in particular to a door lock system with 3D face recognition and a using method.
Background
In 2014, deep learning is firstly applied to the field of face recognition, strong feature learning capability is shown, and the LFW (laboratory Faces in the wild) recognition accuracy is improved from 94% to 97%, so that the method greatly surpasses the classic face recognition method. With the development of the related deep learning theory and the driving of large-scale face data, the accuracy rate of face recognition continues to rise, and the 99.8% of major relations are quickly broken through, which indicates that the face recognition algorithm tends to be mature and the rapid commercial application falls to the ground. At present, the face recognition technology is widely applied to the fields of security protection, self-service customs clearance, medical treatment, education, household administration, payment and the like.
In the face recognition system based on deep learning, the input is 2D RGB or IR images, and a good face recognition effect can be achieved in a controllable scene. But the face recognition accuracy rate is rapidly reduced under the conditions of darkness, backlight and the like under the influence of illumination, face posture, face expression change and the like; in addition, the face recognition system based on the 2D image has great risk in the aspect of false body (false face) attack resistance, and the application and popularization of the face recognition in the scenes such as door lock, financial payment and the like are influenced.
The 3D camera module widens the dimensionality of front-end perception, can well solve the problems of false body attack resistance and low identification accuracy under extreme conditions encountered by 2D face identification, and has the advantages of market acceptance and strong demand.
Known companies that can currently complete 3D face recognition solutions in the market include payroll, wechat, cloud, and the like, with very high technical and resource thresholds. These companies make terminal solutions according to their own needs, but do not provide public edition module, can't satisfy scene such as lock, entrance guard and Unionpay and to 3D face identification's strong demand far away. Therefore, a solution for getting through 3D face recognition needs to be provided, which can be applied to 3D face recognition related products and gradually be popularized to the fields of door lock, door control, payment, etc.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to provide a door lock system with 3D face recognition and a using method thereof.
The door lock system with the 3D face recognition function comprises a 3D face recognition module and a door lock main control module;
the 3D face recognition module is used for collecting a face image of a target face, carrying out living body recognition and face recognition on the face image, and generating an unlocking signal when the face image is a living body face and the face image is a preset white list face, or else generating an error prompt; the face image comprises any one or more of an RGB face image, an infrared face image and a depth face image;
and the door lock main control module is used for receiving the unlocking signal or the error prompt, controlling the door lock to unlock according to the unlocking signal or sending the error prompt.
Preferably, the 3D face recognition module includes a first computing unit, a laser speckle projector, and an infrared detector; the laser speckle projector and the infrared detector are electrically connected with the first computing unit;
the laser speckle projector is used for projecting speckle-shaped infrared beams to a target face;
the infrared detector is used for collecting light spot patterns formed by infrared beams reflected by the target face;
the first calculating unit is used for acquiring the light spot image and further calculating and generating a depth face image of the target face according to the deformation or displacement of the light spot pattern.
Preferably, the 3D face recognition module includes a second calculation unit, a light projector, and a TOF sensor; the light projector, the RGB camera module and the infrared camera module are electrically connected with the second computing unit;
the light projector is used for projecting infrared floodlight to the target face;
the TOF sensor is used for receiving infrared floodlight reflected by a target face and generating a plurality of infrared face images;
and the second calculating unit is used for calculating and generating the depth image of the surface of the target face according to the phase difference of a plurality of infrared face images in a preset acquisition period.
Preferably, a first proximity sensor is further included; the first proximity sensor is electrically connected with the door lock main control module;
the first proximity sensor is used for detecting the distance of the target person;
and the 3D face recognition module is used for acquiring the face image of the target face when the distance is smaller than a preset distance threshold.
Preferably, the 3D face recognition module further comprises an RGB camera module;
the RGB camera module is used for collecting RGB face images of the target face;
the first calculating unit or the second calculating unit is used for identifying whether the RGB face image is a preset white list face.
Preferably, the LED floodlight source is also included;
the LED floodlight source is used for projecting a floodlight beam to the target face;
the infrared detector is used for collecting an infrared face image formed by floodlight beams reflected by a target face;
the first calculating unit is used for identifying whether the infrared face image is a preset white list face.
Preferably, the 3D face recognition module and the door lock main control module transmit RGB face images through a USB on the one hand, and transmit control instructions and recognition results through a serial port on the other hand.
Preferably, the living body face recognition is performed through a preset living body detection model, and the training of the living body detection model comprises the following steps:
step M1: collecting a plurality of face images, and performing key point detection on each face image to determine a plurality of face key points;
step M2: normalizing the face image to a preset size to generate a preprocessed face image, and acquiring the position of each face key point in the preprocessed face image;
step M3: selecting a plurality of face key points in each preprocessed face image, and taking the selected face key points as centers to intercept the face key points into a plurality of ROI (region of interest), wherein the ROI comprises any area of a left eye area, a right eye area, a nose tip area and a mouth area in the face image;
step M4: and synthesizing the ROI corresponding to each preprocessed face image into training data, and training and generating the living body detection model according to the training data.
Preferably, the living body detection model comprises a first living body detection model generated based on RGB face image training, a second living body detection model generated based on infrared face image training and a third living body detection model generated based on depth face image training;
when the living body face recognition is carried out, the living body face recognition is carried out through any one model or any multiple models of the first living body detection model, the second living body detection model and the third living body detection model;
when the living body is identified by the plurality of living body detection models, the face image is determined to be a living body face only when all of the plurality of living body detection models are determined to be the living body face.
The invention provides a use method of a door lock system with 3D face recognition, which comprises the following steps:
step S1: detecting the distance of the target face, and triggering the step S2 when the distance is smaller than a preset distance threshold;
step S2: collecting a face image of the target face, wherein the face image comprises any one or more of an RGB face image, an infrared face image and a depth face image;
step S3: and performing living body recognition and face recognition on the face image, controlling a door lock to unlock when the face image is judged to be a living body face and the face image is a preset white list face, and otherwise, performing error prompt.
Compared with the prior art, the invention has the following beneficial effects:
according to the invention, the face image is collected through the 3D face, and whether the collected target face is a living body image or not and whether the collected target face is a preset white list face allowing unlocking or not is judged through living body identification and face identification on the face image, so that the door lock main control module controls the door lock to unlock or prompts error information, and the intelligent control of the door lock can be realized.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts. Other features, objects and advantages of the invention will become more apparent upon reading of the detailed description of non-limiting embodiments with reference to the following drawings:
FIG. 1 is a schematic view of a door lock system with 3D face recognition according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a 3D face recognition module according to an embodiment of the present invention;
fig. 3 is a schematic diagram of a 3D face recognition module according to a variation of the present invention;
FIG. 4 is a flowchart illustrating steps performed during face recognition of a living subject according to an embodiment of the present invention;
FIG. 5 is a flowchart illustrating steps of a method for using a door lock system with 3D face recognition according to an embodiment of the present invention;
fig. 6 is a flowchart illustrating a specific use of the door lock system with 3D face recognition according to an embodiment of the present invention.
Detailed Description
The present invention will be described in detail with reference to specific examples. The following examples will assist those skilled in the art in further understanding the invention, but are not intended to limit the invention in any way. It should be noted that variations and modifications can be made by persons skilled in the art without departing from the spirit of the invention. All falling within the scope of the present invention.
The terms "first," "second," "third," "fourth," and the like in the description and in the claims, as well as in the drawings, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are, for example, capable of operation in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
The technical solution of the present invention will be described in detail below with specific examples. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments.
The invention provides a door lock system with 3D face recognition, and aims to solve the problems in the prior art.
The following describes the technical solutions of the present invention and how to solve the above technical problems with specific embodiments. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments. Embodiments of the present invention will be described below with reference to the accompanying drawings.
Fig. 1 is a schematic diagram of a door lock system with 3D face recognition in an embodiment of the present invention, and as shown in fig. 1, the door lock system with 3D face recognition provided in the present invention includes a 3D face recognition module, a door lock main control module, and a first proximity sensor;
the 3D face recognition module is used for collecting a face image of a target face, carrying out living body recognition and face recognition on the face image, and generating an unlocking signal when the face image is a living body face and the face image is a preset white list face, or else generating an error prompt; the face image comprises any one or more of an RGB face image, an infrared face image and a depth face image;
and the door lock main control module is used for receiving the unlocking signal or the error prompt, controlling the door lock to unlock according to the unlocking signal or sending the error prompt.
The first proximity sensor is electrically connected with the door lock main control module;
the first proximity sensor is used for detecting the distance of the target person;
and the 3D face recognition module is used for acquiring the face image of the target face when the distance is smaller than a preset distance threshold.
The 3D face recognition module and the door lock main control module transmit RGB face images through a USB on one hand, and transmit control instructions and recognition results through a serial port on the other hand.
In the embodiment of the present invention, the preset distance threshold may be any value between 0.5 m and 2 m, and is preferably 1 m in the embodiment of the present invention. The door lock main control module can be a separately arranged control module or a controller of an installed electronic lock.
In the embodiment of the invention, the face image is collected through the 3D face, and whether the collected target face is the living body image or not and whether the collected target face is the preset white list face allowing unlocking or not is judged through living body identification and face identification on the face image, so that the door lock main control module controls the door lock to unlock or prompts error information, and the intelligent control of the door lock can be realized.
Fig. 2 is a schematic diagram of a 3D face recognition module according to an embodiment of the present invention, and as shown in fig. 2, the 3D face recognition module includes a first computing unit, a laser speckle projector, and an infrared detector; the laser speckle projector and the infrared detector are electrically connected with the first computing unit;
the laser speckle projector is used for projecting speckle-shaped infrared beams to a target face;
the infrared detector is used for collecting light spot patterns formed by infrared beams reflected by the target face;
the first calculating unit is used for acquiring the light spot image and further calculating and generating a depth face image of the target face according to the deformation or displacement of the light spot pattern.
In the embodiment of the invention, the 3D face recognition module acquires the depth face image by adopting a structured light method, and the first computing unit is arranged in front, so that the first computing unit can quickly acquire the light spot pattern, the quick computation of the depth image is realized, and the 3D face recognition module is also convenient for the quick matching connection with other electronic equipment.
In the embodiment of the present invention, a second proximity sensor may be further disposed in the 3D face recognition module, and when the second proximity sensor detects that the face is too close to the 3D face recognition module, for example, the face is less than 15 cm, the laser speckle projector is controlled to be turned off.
In the embodiment or the modification of the invention, the 3D face recognition module further comprises an RGB camera module and an LED floodlight source;
the RGB camera module is used for collecting RGB face images of the target face;
the LED floodlight source is used for projecting a floodlight beam to the target face;
and the infrared detector is used for collecting an infrared face image formed by the floodlight beams reflected by the target face.
The first computing unit is configured to identify whether the infrared face image or the RGB face image is a preset white list face. Specifically, the recognition can be performed by a pre-trained face recognition model. The white list face is a preset permitted face. The first computing unit may further synthesize a 3D face image from the RGB face image and the depth image.
In the embodiment of the invention, the quality of the infrared image is improved by projecting the floodlight beam to the target face and then acquiring the infrared image through the infrared detector. The 3D face recognition module can also be with RGB face preview image that the RGB module of making a video recording gathered sends to lock master control model to lock master control module carries out the try on preview of target people's face.
Fig. 3 is a schematic diagram of a 3D face recognition module according to a variation of the present invention, and as shown in fig. 3, the 3D face recognition module includes a second calculation unit, a light projector, and a TOF sensor; the light projector, the RGB camera module and the infrared camera module are electrically connected with the second computing unit;
the light projector is used for projecting infrared floodlight to the target face;
the TOF sensor is used for receiving infrared floodlight reflected by a target face and generating a plurality of infrared face images;
and the second calculating unit is used for calculating and generating the depth image of the surface of the target face according to the phase difference of a plurality of infrared face images in a preset acquisition period.
In the modification of the invention, the 3D face recognition module calculates the depth image of the target face surface by using a time-of-flight method so as to be suitable for the acquisition of the depth image at a longer distance.
In an embodiment of the present invention, the first computing unit and the second computing unit employ an i.mx8m mini processor.
Fig. 4 is a flowchart of steps in performing living body face recognition according to an embodiment of the present invention, and as shown in fig. 4, the living body face recognition is performed through a preset living body detection model, and the training of the living body detection model includes the following steps:
step M1: collecting a plurality of face images, and performing key point detection on each face image to determine a plurality of face key points;
step M2: normalizing the face image to a preset size to generate a preprocessed face image, and acquiring the position of each face key point in the preprocessed face image;
in the embodiment of the invention, during normalization processing, a conversion matrix of the key points of the human face is calculated according to preset standard key point distribution, and the key point positions in the normalized human face image are determined according to the conversion matrix.
Step M3: selecting a plurality of face key points in each face image, and taking the selected face key points as centers to intercept the face key points to a plurality of ROI (region of interest), wherein the ROI comprises any area of a left eye area, a right eye area, a nose tip area and a mouth area in the face image;
step M4: and synthesizing the ROI corresponding to each face image into training data, and training according to the training data to generate the living body detection model.
In the embodiment of the present invention, the ROI includes a left eye region, a right eye region, a nose tip region, and a mouth region in the face image, that is, four ROI regions are synthesized into training data of a four-channel. Each of the ROI regions has a size of 48 × 48 in units of pixels. The number of the face key points is 106. The preset size is 180 × 220, and the unit is a pixel.
In the embodiment of the invention, the living body detection model comprises a first living body detection model generated based on RGB (red, green and blue) face image training, a second living body detection model generated based on infrared face image training and a third living body detection model generated based on depth face image training;
when the living body face recognition is carried out, the living body face recognition is carried out through any one model or any multiple models of the first living body detection model, the second living body detection model and the third living body detection model;
when the living body recognition is performed by the three living body detection models, the face image is determined as the living body face only when all of the three living body detection models are determined as the living body face.
In the embodiment of the invention, the living body face recognition is performed sequentially through the first living body detection model, the second living body detection model and the third living body detection model, and when a face image is determined by each model, the face image is determined to be a living body face. In the modification of the present invention, the living body recognition may be performed by either one of the living body models or both of the living body models.
Fig. 5 is a flowchart illustrating steps of a method for using a door lock system with 3D face recognition according to an embodiment of the present invention, and as shown in fig. 5, the method for using a door lock system with 3D face recognition according to the present invention includes the following steps:
step S1: detecting the distance of the target face, and triggering the step S2 when the distance is smaller than a preset distance threshold;
step S2: collecting a face image of the target face, wherein the face image comprises any one or more of an RGB face image, an infrared face image and a depth face image;
step S3: and performing living body recognition and face recognition on the face image, controlling a door lock to unlock when the face image is judged to be a living body face and the face image is a preset white list face, and otherwise, performing error prompt.
Figure 6 is a flow chart of the specific use of the door lock system with 3D face recognition in the embodiment of the present invention, as shown in fig. 6, the proximity sensor on the door lock main control module always detects a human face, when the approach of the human face is detected, for example, the distance between the human face and the approach sensor is only 50 cm, the 3D human face recognition model is triggered, at the moment, the 3D human face module is started, opening the RGB camera module and the infrared camera module, collecting RGB face image and infrared face image of the target face, performing face detection and key point detection on the RGB face image and the infrared face image, determining face regions and key points on the RGB face image and the infrared face image, and calculating to generate a depth face image according to the infrared image or the light spot pattern, and outputting a recognition result after living bodies of the RGB face image, the depth face image and the infrared face image are sequentially carried out. And when the recognition result is a living body, performing face recognition on the RGB face image and the infrared face image to determine whether the face is a pre-stored white list face allowing unlocking. And outputting the identification result passing the verification only when the target face passes the living body identification and the face identification, otherwise, outputting the identification result with the wrong identification. When the identification result passing the verification is output, the 3D face recognition model is triggered to send an unlocking instruction to the door lock main control module, and the door lock main control module controls the door lock to be unlocked. The time from starting to outputting the identification result is only two seconds.
In the embodiment of the invention, the face image is collected through the 3D face, and whether the collected target face is the living body image or not and whether the collected target face is the preset white list face allowing unlocking or not is judged through living body identification and face identification on the face image, so that the door lock main control module controls the door lock to unlock or prompts error information, and the intelligent control of the door lock can be realized.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
The foregoing description of specific embodiments of the present invention has been presented. It is to be understood that the present invention is not limited to the specific embodiments described above, and that various changes and modifications may be made by one skilled in the art within the scope of the appended claims without departing from the spirit of the invention.
Claims (10)
1. A door lock system with 3D face recognition is characterized by comprising a 3D face recognition module and a door lock main control module;
the 3D face recognition module is used for collecting a face image of a target face, carrying out living body recognition and face recognition on the face image, and generating an unlocking signal when the face image is a living body face and the face image is a preset white list face, or else generating an error prompt; the face image comprises any one or more of an RGB face image, an infrared face image and a depth face image;
and the door lock main control module is used for receiving the unlocking signal or the error prompt, controlling the door lock to unlock according to the unlocking signal or sending the error prompt.
2. The door lock system with 3D face recognition according to claim 1, wherein the 3D face recognition module comprises a first computing unit, a laser speckle projector, and an infrared detector; the laser speckle projector and the infrared detector are electrically connected with the first computing unit;
the laser speckle projector is used for projecting speckle-shaped infrared beams to a target face;
the infrared detector is used for collecting light spot patterns formed by infrared beams reflected by the target face;
the first calculating unit is used for acquiring the light spot image and further calculating and generating a depth face image of the target face according to the deformation or displacement of the light spot pattern.
3. The door lock system with 3D face recognition according to claim 1, wherein the 3D face recognition module comprises a second computing unit, a light projector and a TOF sensor; the light projector, the RGB camera module and the infrared camera module are electrically connected with the second computing unit;
the light projector is used for projecting infrared floodlight to the target face;
the TOF sensor is used for receiving infrared floodlight reflected by a target face and generating a plurality of infrared face images;
and the second calculating unit is used for calculating and generating the depth image of the surface of the target face according to the phase difference of a plurality of infrared face images in a preset acquisition period.
4. The door lock system with 3D face recognition as claimed in claim 1, further comprising a first proximity sensor; the first proximity sensor is electrically connected with the door lock main control module;
the first proximity sensor is used for detecting the distance of the target person;
and the 3D face recognition module is used for acquiring the face image of the target face when the distance is smaller than a preset distance threshold.
5. The door lock system with 3D face recognition according to claim 2 or 3, wherein the 3D face recognition module further comprises an RGB camera module;
the RGB camera module is used for collecting RGB face images of the target face;
the first calculating unit or the second calculating unit is used for identifying whether the RGB face image is a preset white list face.
6. The door lock system with 3D face recognition according to claim 2, further comprising an LED floodlight source;
the LED floodlight source is used for projecting a floodlight beam to the target face;
the infrared detector is used for collecting an infrared face image formed by floodlight beams reflected by a target face;
the first calculating unit is used for identifying whether the infrared face image is a preset white list face.
7. The door lock system with 3D face recognition according to claim 1, wherein the 3D face recognition module and the door lock main control module transmit RGB face images through a USB on one hand, and transmit control instructions and recognition results through a serial port on the other hand.
8. The door lock system with 3D face recognition according to claim 1, wherein the live body face recognition is performed through a preset live body detection model, and the training of the live body detection model comprises the following steps:
step M1: collecting a plurality of face images, and performing key point detection on each face image to determine a plurality of face key points;
step M2: normalizing the face image to a preset size to generate a preprocessed face image, and acquiring the position of each face key point in the preprocessed face image;
step M3: selecting a plurality of face key points in each preprocessed face image, and taking the selected face key points as centers to intercept the face key points into a plurality of ROI (region of interest), wherein the ROI comprises any area of a left eye area, a right eye area, a nose tip area and a mouth area in the face image;
step M4: and synthesizing the ROI corresponding to each preprocessed face image into training data, and training and generating the living body detection model according to the training data.
9. The door lock system with 3D face recognition according to claim 7, wherein the living body detection models comprise a first living body detection model generated based on RGB face image training, a second living body detection model generated based on infrared face image training, and a third living body detection model generated based on depth face image training;
when the living body face recognition is carried out, the living body face recognition is carried out through any one model or any multiple models of the first living body detection model, the second living body detection model and the third living body detection model;
when the living body is identified by the plurality of living body detection models, the face image is determined to be a living body face only when all of the plurality of living body detection models are determined to be the living body face.
10. The use method of the door lock system with the 3D face recognition function is characterized by comprising the following steps:
step S1: detecting the distance of the target face, and triggering the step S2 when the distance is smaller than a preset distance threshold;
step S2: collecting a face image of the target face, wherein the face image comprises any one or more of an RGB face image, an infrared face image and a depth face image;
step S3: and performing living body recognition and face recognition on the face image, controlling a door lock to unlock when the face image is judged to be a living body face and the face image is a preset white list face, and otherwise, performing error prompt.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010084602.5A CN113313856A (en) | 2020-02-10 | 2020-02-10 | Door lock system with 3D face recognition function and using method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010084602.5A CN113313856A (en) | 2020-02-10 | 2020-02-10 | Door lock system with 3D face recognition function and using method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113313856A true CN113313856A (en) | 2021-08-27 |
Family
ID=77369813
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010084602.5A Pending CN113313856A (en) | 2020-02-10 | 2020-02-10 | Door lock system with 3D face recognition function and using method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113313856A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114565993A (en) * | 2022-02-24 | 2022-05-31 | 深圳福鸽科技有限公司 | Intelligent lock system based on face recognition and cat eye |
| CN115273288A (en) * | 2022-08-03 | 2022-11-01 | 深圳市杉川机器人有限公司 | Unlocking method based on face recognition, intelligent door lock and readable storage medium |
| CN115294676A (en) * | 2022-07-08 | 2022-11-04 | 重庆甲智甲创科技有限公司 | Face recognition unlocking method and face recognition unlocking device |
| CN115664878A (en) * | 2022-09-14 | 2023-01-31 | 重庆甲智甲创科技有限公司 | Image acquisition module processing control method and system in double power supply mode |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN206249454U (en) * | 2016-09-30 | 2017-06-13 | 王力安防科技股份有限公司 | A kind of Intelligent door lock capable of recognizing face system and safety door |
| CN107066942A (en) * | 2017-03-03 | 2017-08-18 | 上海斐讯数据通信技术有限公司 | A kind of living body faces recognition methods and system |
| CN107291221A (en) * | 2017-05-04 | 2017-10-24 | 浙江大学 | Across screen self-adaption accuracy method of adjustment and device based on natural gesture |
| CN108022355A (en) * | 2018-02-07 | 2018-05-11 | 谢超鹏 | A kind of control method of recognition of face lockset, system and a kind of recognition of face lockset |
| CN109448189A (en) * | 2018-10-29 | 2019-03-08 | 极鱼（北京）科技有限公司 | Self-service bank's management method, self-service bank and self-service bank's system |
| CN110287900A (en) * | 2019-06-27 | 2019-09-27 | 深圳市商汤科技有限公司 | Verification method and verifying device |
| CN110290376A (en) * | 2019-05-24 | 2019-09-27 | 深圳市光鉴科技有限公司 | Display device and electronic equipment with 3D camera module |
| CN110718008A (en) * | 2019-11-15 | 2020-01-21 | 杭州艾芯智能科技有限公司 | 3D face identification module, lock and door |
-
2020
- 2020-02-10 CN CN202010084602.5A patent/CN113313856A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN206249454U (en) * | 2016-09-30 | 2017-06-13 | 王力安防科技股份有限公司 | A kind of Intelligent door lock capable of recognizing face system and safety door |
| CN107066942A (en) * | 2017-03-03 | 2017-08-18 | 上海斐讯数据通信技术有限公司 | A kind of living body faces recognition methods and system |
| CN107291221A (en) * | 2017-05-04 | 2017-10-24 | 浙江大学 | Across screen self-adaption accuracy method of adjustment and device based on natural gesture |
| CN108022355A (en) * | 2018-02-07 | 2018-05-11 | 谢超鹏 | A kind of control method of recognition of face lockset, system and a kind of recognition of face lockset |
| CN109448189A (en) * | 2018-10-29 | 2019-03-08 | 极鱼（北京）科技有限公司 | Self-service bank's management method, self-service bank and self-service bank's system |
| CN110290376A (en) * | 2019-05-24 | 2019-09-27 | 深圳市光鉴科技有限公司 | Display device and electronic equipment with 3D camera module |
| CN110287900A (en) * | 2019-06-27 | 2019-09-27 | 深圳市商汤科技有限公司 | Verification method and verifying device |
| CN110718008A (en) * | 2019-11-15 | 2020-01-21 | 杭州艾芯智能科技有限公司 | 3D face identification module, lock and door |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114565993A (en) * | 2022-02-24 | 2022-05-31 | 深圳福鸽科技有限公司 | Intelligent lock system based on face recognition and cat eye |
| CN114565993B (en) * | 2022-02-24 | 2023-11-17 | 深圳福鸽科技有限公司 | Intelligent lock system based on face recognition and cat eye |
| CN115294676A (en) * | 2022-07-08 | 2022-11-04 | 重庆甲智甲创科技有限公司 | Face recognition unlocking method and face recognition unlocking device |
| CN115294676B (en) * | 2022-07-08 | 2024-03-19 | 重庆甲智甲创科技有限公司 | Face recognition unlocking method and face recognition unlocking device |
| CN115273288A (en) * | 2022-08-03 | 2022-11-01 | 深圳市杉川机器人有限公司 | Unlocking method based on face recognition, intelligent door lock and readable storage medium |
| CN115664878A (en) * | 2022-09-14 | 2023-01-31 | 重庆甲智甲创科技有限公司 | Image acquisition module processing control method and system in double power supply mode |
| CN115664878B (en) * | 2022-09-14 | 2023-08-25 | 重庆甲智甲创科技有限公司 | Image acquisition module processing control method and system in double power supply mode |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113313856A (en) | Door lock system with 3D face recognition function and using method | |
| CN103383723B (en) | Method and system for spoof detection for biometric authentication | |
| US20210287026A1 (en) | Method and apparatus with liveness verification | |
| JP4679121B2 (en) | Human identification device and method using infrared rays | |
| JP5955133B2 (en) | Face image authentication device | |
| RU2431190C2 (en) | Facial prominence recognition method and device | |
| CN109643366A (en) | For monitoring the method and system of the situation of vehicle driver | |
| CN107341481A (en) | It is identified using structure light image | |
| US20040037450A1 (en) | Method, apparatus and system for using computer vision to identify facial characteristics | |
| CN102521578A (en) | Method for detecting and identifying intrusion | |
| CN111274928A (en) | Living body detection method and device, electronic equipment and storage medium | |
| CN112364842B (en) | Double-shot face recognition method and device | |
| CN111916219A (en) | Intelligent safety early warning method, device and electronic system for inspection and quarantine | |
| JP5955031B2 (en) | Face image authentication device | |
| US20210256244A1 (en) | Method for authentication or identification of an individual | |
| KR101919090B1 (en) | Apparatus and method of face recognition verifying liveness based on 3d depth information and ir information | |
| KR20180134280A (en) | Apparatus and method of face recognition verifying liveness based on 3d depth information and ir information | |
| CN111666835A (en) | Face living body detection method and device | |
| CN108052813A (en) | Unlocking method, device and the mobile terminal of terminal device | |
| CN113255401A (en) | 3D face camera device | |
| CN113256298A (en) | Payment system with 3D face recognition and using method | |
| JP5726595B2 (en) | Image monitoring device | |
| CN113255400A (en) | Training and recognition method, system, equipment and medium of living body face recognition model | |
| CN111985442A (en) | In-vivo detection and identification method based on multi-modal data fusion | |
| US20230290185A1 (en) | Anti-Spoofing System |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210827 |