CN113445829B - Intelligent locker lock with face recognition function and use method - Google Patents
Intelligent locker lock with face recognition function and use method Download PDFInfo
- Publication number
- CN113445829B CN113445829B CN202110837487.9A CN202110837487A CN113445829B CN 113445829 B CN113445829 B CN 113445829B CN 202110837487 A CN202110837487 A CN 202110837487A CN 113445829 B CN113445829 B CN 113445829B
- Authority
- CN
- China
- Prior art keywords
- information
- voice
- matching
- module
- action
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- E—FIXED CONSTRUCTIONS
- E05—LOCKS; KEYS; WINDOW OR DOOR FITTINGS; SAFES
- E05B—LOCKS; ACCESSORIES THEREFOR; HANDCUFFS
- E05B49/00—Electric permutation locks; Circuits therefor ; Mechanical aspects of electronic locks; Mechanical keys therefor
-
- E—FIXED CONSTRUCTIONS
- E05—LOCKS; KEYS; WINDOW OR DOOR FITTINGS; SAFES
- E05B—LOCKS; ACCESSORIES THEREFOR; HANDCUFFS
- E05B51/00—Operating or controlling locks or other fastening devices by other non-mechanical means
-
- E—FIXED CONSTRUCTIONS
- E05—LOCKS; KEYS; WINDOW OR DOOR FITTINGS; SAFES
- E05B—LOCKS; ACCESSORIES THEREFOR; HANDCUFFS
- E05B65/00—Locks or fastenings for special use
- E05B65/52—Other locks for chests, boxes, trunks, baskets, travelling bags, or the like
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Lock And Its Accessories (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention discloses a storage cabinet intelligent lock with a face recognition function, which comprises a storage module, a camera shooting acquisition module, an action acquisition module, a voice acquisition module, a matching module, an analysis module, a processor and a control module, wherein the camera shooting acquisition module is used for shooting the action of a user; the storage module is used for storing the face information and the sound information of the user which are acquired in advance; the camera shooting acquisition module is used for acquiring camera shooting information of a user requesting unlocking; the action acquisition module is used for acquiring mouth action information of a user requesting unlocking; the voice acquisition module is used for acquiring request voice information of a user requesting unlocking; the invention also discloses a use method of the intelligent locker lock with the face recognition function; the invention solves the technical problems that when the intelligent identification is carried out only by a single face identification technology in the prior art, the identification accuracy is low due to the fact that the intelligent identification is easily interfered by external environment light, and the unlocking effect is further influenced.
Description
Technical Field
The invention relates to the technical field of intelligent locks, in particular to an intelligent locker lock with a face recognition function and a using method thereof.
Background
The intelligent lock is an improved lock which is different from the traditional mechanical lock and is more intelligent and simpler in the aspects of user safety, identification and manageability. The intelligent lock can be intelligently unlocked based on the existing face recognition technology, intelligent voice technology or fingerprint recognition technology.
The intelligent lock of the storage cabinet with the face recognition function has certain defects when being used, and is easy to be interfered by external environment light to ensure that the recognition accuracy is low when intelligent recognition is carried out only by a single face recognition technology, so that the unlocking effect is influenced.
Disclosure of Invention
The invention aims to provide a locker intelligent lock with a face recognition function and a use method thereof, and mainly aims to solve the technical problems that when intelligent recognition is carried out only through a single face recognition technology in the prior art, the recognition accuracy is low due to the fact that the intelligent recognition is easily interfered by external ambient light, and the unlocking effect is further influenced.
The purpose of the invention can be realized by the following technical scheme:
a locker intelligent lock with a face recognition function comprises a storage module, a camera shooting acquisition module, an action acquisition module, a voice acquisition module, a matching module, an analysis module, a processor and a control module;
the storage module is used for storing the face information and the sound information of the user which are acquired in advance; the camera shooting acquisition module is used for acquiring camera shooting information of a user requesting unlocking; the action acquisition module is used for acquiring mouth action information of a user requesting unlocking; the voice acquisition module is used for acquiring request voice information of a user requesting unlocking;
the matching module is used for matching the acquired camera information and the acquired request voice information with face information and voice information of a pre-stored user to obtain first matching information and second matching information; the analysis module comprises a motion analysis unit and a feature recognition unit, and the motion analysis unit analyzes the mouth motion information and generates first analysis data; the characteristic identification unit is used for analyzing the first matching information and the second matching information to obtain second analysis data; and the control module controls the switch of the storage cabinet according to the first analysis data and the second analysis data and prompts the switch.
Further, the matching module is used for matching the collected camera shooting information and the request voice information with the face information and the voice information of the pre-stored user, and the specific steps are as follows:
receiving camera information, extracting a plurality of image features on the camera image, combining the image features to obtain an image feature set, acquiring a brightness value of the camera image, marking a first identification, matching the image feature set with a plurality of facial features in facial information stored in advance according to the first identification, and if the image features in the image feature set are the same as the facial features in the facial information, successfully matching and generating a first matching signal; if the image features in the image feature set are different from the face features in the face information, matching fails, a second matching signal is generated, and a plurality of first matching signals and the second matching signals are combined to obtain first matching information;
receiving request voice information, extracting voice loudness, voice frequency and voice amplitude, marking the voice loudness as a second identifier, respectively matching the voice frequency and the voice amplitude with a plurality of voice frequencies and voice amplitudes in pre-stored voice information according to the second identifier, and if the voice information has the voice frequency and the voice amplitude which are the same as the voice frequency and the voice amplitude, successfully matching and generating a first judgment signal; if at least one sound frequency or sound amplitude different from the voice frequency and the voice amplitude exists in the sound information, the matching is failed and a second judgment signal is generated; and combining the first judgment signal and the second judgment signal to obtain second matching information.
Further, the specific steps of the motion analysis unit analyzing the mouth motion information and generating the first analysis data are as follows:
setting a center in a person as a circle center and a preset distance to establish a coordinate system, marking the coordinate of the upper lip when the upper lip is static as a first coordinate, marking the coordinate of the lower lip when the lower lip is static as a second coordinate, respectively acquiring corresponding moving coordinates according to the upper lip action and the lower lip action in the mouth action information, and respectively combining and marking the corresponding moving coordinates as a first moving coordinate set and a second moving coordinate set; calculating the distance differences between a plurality of mobile coordinates in the first mobile coordinate set and the first coordinates, and sequentially combining the distance differences to obtain a first action set; calculating the distance differences between a plurality of mobile coordinates in the first mobile coordinate set and the second coordinates, and sequentially combining the distance differences to obtain a second action set;
and classifying and combining the first action set and the second action set to obtain first analysis data.
Further, the specific steps of the feature recognition unit for analyzing the first matching information and the second matching information are as follows:
receiving first matching information and second matching information, extracting a first identifier in the first matching information, matching the first identifier with a preset image threshold value, and judging that the camera image is qualified and generating a first analysis signal if the first identifier is not smaller than the image threshold value; matching the image feature set with a plurality of face features in the face information stored in advance according to the first analysis signal; if the first identification is smaller than the image threshold, judging that the shot image is unqualified and generating a second analysis signal, and controlling the image feature set not to be matched with a plurality of face features in the face information stored in advance according to the second analysis signal;
extracting a second identifier in the second matching information, matching the second identifier with a preset sound threshold, and if the second identifier is not smaller than the sound threshold, judging that the requested voice is qualified and generating a third analysis signal; controlling the voice frequency and the voice amplitude to be respectively matched with a plurality of voice frequencies and voice amplitudes in the pre-stored voice information according to the third analysis signal; if the second identifier is smaller than the sound threshold, judging that the requested voice is unqualified and generating a fourth analysis signal, and controlling the voice frequency and the voice amplitude not to be matched with a plurality of voice frequencies and voice amplitudes in the pre-stored voice information according to the fourth analysis signal;
if the first matching information comprises a first matching signal or the second matching information comprises a first judgment signal, judging that the data acquired by the unlocking request user is normal and generating a first control instruction; if the first matching information does not contain the first matching signal and the second matching information does not contain the first judgment signal, judging that the data acquired by the unlocking request user is abnormal and generating a second control instruction; and classifying and combining the first judgment signal and the second judgment signal to obtain second analysis data.
Further, the specific steps that the control module controls the switch of the storage cabinet according to the first analysis data and the second analysis and prompts comprise:
receiving second analysis data, and if the second analysis data contains a first judgment signal, processing the first analysis data according to the first judgment signal, wherein the method comprises the following steps: respectively carrying out value taking on a first action set and a second action set in first analysis data to obtain a plurality of first distance differences and second distance differences, accumulating the plurality of first distance differences to obtain a first distance sum, accumulating the plurality of first distance differences to obtain a second distance sum, respectively matching the first distance sum and the second distance sum with a preset distance range, and if the first distance sum and the second distance sum both belong to the preset distance range, judging that the unlocking request user identity corresponding to the first judgment signal is normal and controlling the locker to be opened;
if at least one of the first distance sum and the second distance sum does not belong to the preset distance range, judging that the unlocking request user corresponding to the first judgment signal is abnormal in identity to control the locker not to be opened, and prompting the unlocking request user to perform face recognition and voice input again by voice;
and if the second analysis data contains a second judgment signal, controlling the locker not to be opened according to the second judgment signal, and requesting the unlocking user to perform facial recognition and voice input again through voice prompt.
A use method of an intelligent lock based on a storage cabinet with a face recognition function comprises the following specific steps:
the method comprises the steps that camera shooting information of a user requesting unlocking is collected through a camera shooting collection module, mouth action information of the user requesting unlocking is collected through an action collection module, and request voice information of the user requesting unlocking is collected through a voice collection module;
matching the acquired camera information and the acquired request voice information with face information and voice information of a pre-stored user through a matching module to obtain first matching information and second matching information; analyzing the mouth action information through an action analysis unit in the analysis module and generating first analysis data; analyzing the first matching information and the second matching information through a feature recognition unit in the analysis module to obtain second analysis data;
and controlling the switch of the storage cabinet through the control module according to the first analysis data and the second analysis data and prompting.
The invention has the beneficial effects that:
according to the invention, through the cooperation of the storage module, the camera shooting acquisition module, the action acquisition module, the voice acquisition module, the matching module, the analysis module, the processor and the control module, the mode of combining face recognition verification and voice recognition verification can be realized to improve the accuracy of recognition; matching the acquired camera information and the acquired request voice information with face information and voice information of a pre-stored user through a matching module to obtain first matching information and second matching information; the analysis module comprises a motion analysis unit and a feature recognition unit, and analyzes the mouth motion information through the motion analysis unit to generate first analysis data; the characteristic identification unit is used for analyzing the first matching information and the second matching information to obtain second analysis data; the control module controls the switch of the storage cabinet according to the first analysis data and the second analysis data and prompts the switch, voice verification and recognition are carried out under the condition that the image recognition condition is poor or fails, and the problem that auxiliary verification is carried out when the face recognition condition is poor so as to improve the unlocking efficiency is solved; the voice loudness is used as an identifier to judge whether the acquired voice request is qualified or not, and the acquired mouth action information is verified under the condition that the analysis of the requested voice information is qualified, so that the accuracy of unlocking verification can be effectively improved, and the purposes of intelligent verification and protection can be achieved.
Drawings
The invention will be further described with reference to the accompanying drawings.
FIG. 1 is a schematic block diagram of an intelligent locker lock with facial recognition function according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, the present invention is a smart lock with facial recognition function for a storage cabinet, comprising a storage module, a camera module, an action acquisition module, a voice acquisition module, a matching module, an analysis module, a processor and a control module; the processor is used for calculating data among the modules;
the storage module is used for storing the face information and the sound information of the user which are acquired in advance; the face information and the sound information can be face images and face features of family members and request unlocking sound, the face features include but are not limited to length, width and area of features such as eyebrows, eyes, a nose, a mouth and a face, and the request unlocking sound can be 'unlocking'; the camera shooting acquisition module is used for acquiring camera shooting information of a user requesting unlocking, and the camera shooting information comprises a camera shooting image; the action acquisition module is used for acquiring mouth action information of a user requesting unlocking, such as mouth action when 'unlocking' voice is sent out; the voice acquisition module is used for acquiring request voice information of a user requesting unlocking, and the request voice information comprises voice loudness, voice frequency and voice amplitude;
the matching module is used for matching the acquired camera information and the acquired request voice information with face information and voice information of a pre-stored user to obtain first matching information and second matching information; the method comprises the following specific steps:
receiving camera information, extracting a plurality of image features on the camera image, combining the image features to obtain an image feature set, acquiring a brightness value of the camera image, marking a first identification, matching the image feature set with a plurality of facial features in facial information stored in advance according to the first identification, and if the image features in the image feature set are the same as the facial features in the facial information, successfully matching and generating a first matching signal; wherein, at least two items of data of the length, the width and the area of the plurality of facial features are the same to represent that the matching is successful; if the image features in the image feature set are different from the face features in the face information, matching fails, a second matching signal is generated, and a plurality of first matching signals and the second matching signals are combined to obtain first matching information;
in the embodiment of the invention, the extraction of a plurality of image features on the shot image is realized based on the existing LBP algorithm, and the LBP algorithm is a local binary pattern and is a nonparametric operator for describing the local spatial structure of the image. The basic idea is as follows: the gray value of the central pixel is used as a threshold value, and the binary code obtained by comparing the gray value with the neighborhood of the central pixel is used for expressing local texture characteristics, so that the method has the advantages of good robustness, high calculation speed and no need of pre-assuming the distribution of the gray value; the purpose of facial recognition is achieved by matching a plurality of collected image characteristics with pre-stored image characteristics to determine whether the identity of a requesting user is legal.
Receiving request voice information, extracting voice loudness, voice frequency and voice amplitude, marking the voice loudness as a second identifier, respectively matching the voice frequency and the voice amplitude with a plurality of voice frequencies and voice amplitudes in pre-stored voice information according to the second identifier, and if the voice information has the voice frequency and the voice amplitude which are the same as the voice frequency and the voice amplitude, successfully matching and generating a first judgment signal; if at least one sound frequency or sound amplitude different from the voice frequency and the voice amplitude exists in the sound information, the matching is failed and a second judgment signal is generated; and combining the first judgment signal and the second judgment signal to obtain second matching information.
In the embodiment of the invention, the request voice information is acquired and processed and matched for carrying out voice verification and identification under the condition of poor or failed image identification, so that the problem of carrying out auxiliary verification to improve the unlocking efficiency when the face identification is poor is solved; the voice loudness is used as an identifier to judge whether the acquired voice request is qualified, for example, if the acquired voice request loudness is lower than a preset standard loudness, the voice recognition prompt cannot be performed to perform voice acquisition again; through analyzing the acquired request voice data, the defect that the unlocking effect is poor due to the fact that the face recognition is influenced by the poor external environment can be overcome.
The analysis module comprises a motion analysis unit and a feature recognition unit, and the motion analysis unit analyzes the mouth motion information and generates first analysis data; the method comprises the following specific steps:
setting a center in a person as a circle center and a preset distance to establish a coordinate system, marking the coordinate of the upper lip when the upper lip is static as a first coordinate, marking the coordinate of the lower lip when the lower lip is static as a second coordinate, respectively acquiring corresponding moving coordinates according to the upper lip action and the lower lip action in the mouth action information, and respectively combining and marking the corresponding moving coordinates as a first moving coordinate set and a second moving coordinate set; using distance formulas
Calculating the distance between a plurality of mobile coordinates in the first mobile coordinate set and the first coordinateDispersion and combination are carried out in sequence to obtain a first action set; wherein x isiAbscissa, x, expressed as movement coordinate0Expressed as abscissa, y, in the first coordinateiExpressed as ordinate, y, of the movement coordinate0Expressed as the ordinate in the first coordinate, the value of i is 1,2,3.. n; calculating the distance differences between a plurality of mobile coordinates in the first mobile coordinate set and the second coordinates by using the distance formula, and sequentially combining the distance differences to obtain a second action set;
and classifying and combining the first action set and the second action set to obtain first analysis data.
In the embodiment of the invention, the voice authenticity is improved by acquiring the mouth action information to perform auxiliary verification on the request voice information, voice unlocking through recording is avoided, and the validity of voice recognition can be improved by performing comprehensive analysis on each item of data of the request voice information in combination with the corresponding mouth action.
The characteristic identification unit is used for analyzing the first matching information and the second matching information to obtain second analysis data; the method comprises the following specific steps:
receiving first matching information and second matching information, extracting a first identifier in the first matching information, matching the first identifier with a preset image threshold value, and judging that the camera image is qualified and generating a first analysis signal if the first identifier is not smaller than the image threshold value; matching the image feature set with a plurality of face features in face information stored in advance according to the first analysis signal; if the first identification is smaller than the image threshold, judging that the shot image is unqualified and generating a second analysis signal, and controlling the image feature set not to be matched with a plurality of facial features in the pre-stored facial information according to the second analysis signal;
extracting a second identifier in the second matching information, matching the second identifier with a preset sound threshold, and if the second identifier is not smaller than the sound threshold, judging that the requested voice is qualified and generating a third analysis signal; controlling the voice frequency and the voice amplitude to be respectively matched with a plurality of voice frequencies and voice amplitudes in the pre-stored voice information according to the third analysis signal; if the second identifier is smaller than the sound threshold, judging that the requested voice is unqualified and generating a fourth analysis signal, and controlling the voice frequency and the voice amplitude not to be matched with a plurality of voice frequencies and voice amplitudes in the pre-stored voice information according to the fourth analysis signal;
if the first matching information comprises a first matching signal or the second matching information comprises a first judgment signal, judging that the data acquired by the unlocking request user is normal and generating a first control instruction; if the first matching information does not contain the first matching signal and the second matching information does not contain the first judgment signal, judging that the data acquired by the unlocking request user is abnormal and generating a second control instruction; and classifying and combining the first judgment signal and the second judgment signal to obtain second analysis data.
The control module controls the switch of the storage cabinet according to the first analysis data and the second analysis data and prompts, and the specific steps comprise:
receiving second analysis data, and if the second analysis data comprises a first judgment signal, processing the first analysis data according to the first judgment signal, wherein the processing method comprises the following steps: respectively carrying out value taking on a first action set and a second action set in first analysis data to obtain a plurality of first distance differences and second distance differences, accumulating the plurality of first distance differences to obtain a first distance sum, accumulating the plurality of first distance differences to obtain a second distance sum, respectively matching the first distance sum and the second distance sum with a preset distance range, and if the first distance sum and the second distance sum both belong to the preset distance range, judging that the unlocking request user identity corresponding to the first judgment signal is normal and controlling the locker to be opened;
if at least one of the first distance sum and the second distance sum does not belong to the preset distance range, judging that the unlocking request user identity corresponding to the first judgment signal is abnormal, controlling the storage cabinet not to be opened, and prompting the unlocking request user to perform face recognition and voice input again by voice;
and if the second analysis data contains a second judgment signal, controlling the locker not to be opened according to the second judgment signal, and requesting the unlocking user to perform facial recognition and voice input again through voice prompt.
In the embodiment of the invention, the collected mouth action information is verified under the condition that the requested voice information is qualified in analysis, and the identity of the user requested to be unlocked is determined to be legal only if the mouth action information is verified, otherwise, the authentication is illegal, so that the authentication accuracy can be effectively improved, and the problem that the identification accuracy is poor due to the single authentication mode in the conventional scheme can be overcome.
A use method of an intelligent lock based on a storage cabinet with a face recognition function comprises the following specific steps:
the method comprises the steps that camera shooting information of a user requesting unlocking is collected through a camera shooting collection module, mouth action information of the user requesting unlocking is collected through an action collection module, and request voice information of the user requesting unlocking is collected through a voice collection module;
matching the acquired camera information and the acquired request voice information with face information and voice information of a pre-stored user through a matching module to obtain first matching information and second matching information; analyzing the mouth action information through an action analysis unit in the analysis module and generating first analysis data; analyzing the first matching information and the second matching information through a feature recognition unit in the analysis module to obtain second analysis data;
and controlling the switch of the storage cabinet through the control module according to the first analysis data and the second analysis data and prompting.
The formulas in the invention are all a formula which is obtained by removing dimensions and taking numerical value calculation, and software simulation is carried out by collecting a large amount of data to obtain the formula closest to the real condition, and the preset proportionality coefficient and the threshold value in the formula are set by the technical personnel in the field according to the actual condition or are obtained by simulating a large amount of data.
In the description of the present invention, it is to be understood that the terms "upper", "lower", "left", "right", and the like, indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, are only for convenience in describing the present invention and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation and a specific orientation configuration and operation, and thus, should not be construed as limiting the present invention. Furthermore, "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 one or more of that feature. In the description of the present invention, "a plurality" means two or more unless otherwise specified.
In the description of the present invention, it should be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and the like are to be construed broadly and may be, for example, fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be directly connected or indirectly connected through an intermediate member, or they may be connected through two or more elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
While one embodiment of the present invention has been described in detail, the description is only a preferred embodiment of the present invention and should not be taken as limiting the scope of the invention. All equivalent changes and modifications made within the scope of the present invention shall fall within the scope of the present invention.
Claims (7)
1. A locker intelligent lock with a face recognition function is characterized by comprising a storage module, a camera shooting acquisition module, an action acquisition module, a voice acquisition module, a matching module, an analysis module, a processor and a control module;
the storage module is used for storing the face information and the sound information of the user which are acquired in advance; the camera shooting acquisition module is used for acquiring camera shooting information of a user requesting unlocking; the action acquisition module is used for acquiring mouth action information of a user requesting unlocking; the voice acquisition module is used for acquiring request voice information of a user requesting unlocking;
the matching module is used for matching the acquired camera information and the acquired request voice information with face information and voice information of a pre-stored user to obtain first matching information and second matching information; the analysis module comprises a motion analysis unit and a feature recognition unit, and the motion analysis unit analyzes the mouth motion information and generates first analysis data; the characteristic identification unit is used for analyzing the first matching information and the second matching information to obtain second analysis data; the control module controls the switch of the storage cabinet according to the first analysis data and the second analysis data and prompts;
the matching module is used for matching the collected camera shooting information and the request voice information with the face information and the voice information of the pre-stored user, and comprises the following specific steps:
receiving camera information, extracting a plurality of image features on a camera image, and matching the image feature set with a plurality of facial features in pre-stored facial information to obtain first matching information;
and receiving the request voice information, extracting voice loudness, voice frequency and voice amplitude, and respectively matching the voice frequency and the voice amplitude with a plurality of voice frequencies and voice amplitudes in the pre-stored voice information to obtain second matching information.
2. The intelligent locker lock with face recognition function as claimed in claim 1, wherein the action analysis unit analyzes the mouth action information and generates the first analysis data by the following specific steps:
marking the coordinate of the upper lip when the upper lip is static as a first coordinate, marking the coordinate of the lower lip when the lower lip is static as a second coordinate, respectively acquiring corresponding moving coordinates according to the upper lip action and the lower lip action in the mouth action information, and respectively combining and marking the corresponding moving coordinates as a first moving coordinate set and a second moving coordinate set;
and performing calculation analysis according to the plurality of moving coordinates.
3. The intelligent locker lock with face recognition function as claimed in claim 2, wherein the specific steps of performing calculation and analysis according to the plurality of mobile coordinates are as follows:
calculating distance differences between a plurality of mobile coordinates in the first mobile coordinate set and the first coordinates, and sequentially combining the distance differences to obtain a first action set; calculating the distance differences between a plurality of mobile coordinates in the first mobile coordinate set and the second coordinates, and sequentially combining the distance differences to obtain a second action set; and classifying and combining the first action set and the second action set to obtain first analysis data.
4. The intelligent locker lock with the face recognition function as claimed in claim 3, wherein the specific steps of the feature recognition unit for analyzing the first matching information and the second matching information are as follows:
extracting a first identifier in the first matching information, matching the first identifier with a preset image threshold value, and controlling the image feature set and a plurality of facial features in the pre-stored facial information not to be verified; and performing matching analysis according to the second identifier in the second matching information.
5. The intelligent locker lock with the face recognition function as claimed in claim 4, wherein the specific steps of performing the matching analysis according to the second identifier in the second matching information are as follows:
extracting a second identifier in the second matching information, matching the second identifier with a preset sound threshold, and controlling the voice frequency and the voice amplitude not to be verified with a plurality of voice frequencies and voice amplitudes in the pre-stored sound information; generating a first control instruction according to the first matching information; generating a second control instruction according to the first matching information and the second matching information; and classifying and combining the first judgment signal and the second judgment signal to obtain second analysis data.
6. The intelligent locker lock with the face recognition function as claimed in claim 5, wherein the specific steps of the control module controlling the locker to be turned on and off and prompting according to the first analysis data and the second analysis data comprise:
receiving second analysis data, and if the second analysis data comprises a first judgment signal, processing the first analysis data and controlling whether the storage cabinet is opened or not; if at least one of the first distance sum and the second distance sum does not belong to the preset distance range, controlling the storage cabinet not to be opened, and requesting the unlocking user to perform facial recognition and voice input again through voice prompt; and if the second analysis data contains a second judgment signal, controlling the storage cabinet not to be opened and prompting by voice to request the unlocking user to perform facial recognition and voice input again.
7. A use method of an intelligent lock based on a storage cabinet with a face recognition function is characterized by comprising the following specific steps:
the method comprises the steps that camera shooting information of a user requesting unlocking is collected through a camera shooting collection module, mouth action information of the user requesting unlocking is collected through an action collection module, and request voice information of the user requesting unlocking is collected through a voice collection module;
matching the acquired camera information and the acquired request voice information with face information and voice information of a pre-stored user through a matching module to obtain first matching information and second matching information; analyzing the mouth action information through an action analysis unit in the analysis module and generating first analysis data; analyzing the first matching information and the second matching information through a feature recognition unit in the analysis module to obtain second analysis data;
and controlling the switch of the storage cabinet and prompting according to the first analysis data and the second analysis data through the control module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110837487.9A CN113445829B (en) | 2021-07-23 | 2021-07-23 | Intelligent locker lock with face recognition function and use method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110837487.9A CN113445829B (en) | 2021-07-23 | 2021-07-23 | Intelligent locker lock with face recognition function and use method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113445829A CN113445829A (en) | 2021-09-28 |
| CN113445829B true CN113445829B (en) | 2022-05-24 |
Family
ID=77817223
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110837487.9A Active CN113445829B (en) | 2021-07-23 | 2021-07-23 | Intelligent locker lock with face recognition function and use method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113445829B (en) |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104361276B (en) * | 2014-11-18 | 2017-07-18 | 新开普电子股份有限公司 | A kind of multi-modal biological characteristic identity identifying method and system |
| US10635893B2 (en) * | 2017-10-31 | 2020-04-28 | Baidu Usa Llc | Identity authentication method, terminal device, and computer-readable storage medium |
| CN108537980A (en) * | 2018-03-30 | 2018-09-14 | 百度在线网络技术（北京）有限公司 | Face recognition opens method, apparatus, storage medium and the terminal device of locker |
| CN108682064A (en) * | 2018-05-14 | 2018-10-19 | 广东汇泰龙科技有限公司 | A kind of method for unlocking and system based on speech recognition and recognition of face |
| CN109493494A (en) * | 2018-12-15 | 2019-03-19 | 深圳壹账通智能科技有限公司 | Method for unlocking, device, equipment and medium based on smart lock |
| CN110210196B (en) * | 2019-05-08 | 2023-01-06 | 北京地平线机器人技术研发有限公司 | Identity authentication method and device |
-
2021
- 2021-07-23 CN CN202110837487.9A patent/CN113445829B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN113445829A (en) | 2021-09-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107609383B (en) | 3D face identity authentication method and device | |
| CN109446981B (en) | Face living body detection and identity authentication method and device | |
| JP3469031B2 (en) | Face image registration apparatus and method | |
| US7158657B2 (en) | Face image recording system | |
| Sun et al. | Improving iris recognition accuracy via cascaded classifiers | |
| CN102646190B (en) | A kind of authentication method based on biological characteristic, apparatus and system | |
| CN102902959B (en) | Face recognition method and system for storing identification photo based on second-generation identity card | |
| EP2722792B1 (en) | Image processing device, image processing method, and storage medium storing image processing program | |
| US20040042645A1 (en) | Fingerprint recognition method, and fingerprint control method and system | |
| WO2019080579A1 (en) | 3d face identity authentication method and apparatus | |
| US10922399B2 (en) | Authentication verification using soft biometric traits | |
| CN112199530B (en) | Multi-dimensional face library picture automatic updating method, system, equipment and medium | |
| CN110688901A (en) | Face recognition method and device | |
| CN113515988A (en) | Palm print recognition method, feature extraction model training method, device and medium | |
| CN105374098A (en) | Method used for unlocking using human body double-characteristic identification module | |
| CN104036254A (en) | Face recognition method | |
| CN113221086B (en) | Offline face authentication method and device, electronic equipment and storage medium | |
| KR20020022295A (en) | Device And Method For Face Recognition Using 3 Dimensional Shape Information | |
| CN113421079B (en) | Borrowing and returning shared charger baby method based on shared charger baby rental cabinet | |
| CN115019364A (en) | Identity authentication method and device based on face recognition, electronic equipment and medium | |
| CN118172860B (en) | Intelligent campus access control system based on identity recognition | |
| CN110309814A (en) | A kind of iris identification method and device based on edge detection | |
| CN113445829B (en) | Intelligent locker lock with face recognition function and use method | |
| CN113673477B (en) | Palm vein non-contact three-dimensional modeling method, device and authentication method | |
| CN116266419A (en) | Living body detection method and device 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |