CN112800866A - Face recognition device, application system, method, computer equipment and storage medium - Google Patents
Face recognition device, application system, method, computer equipment and storage medium Download PDFInfo
- Publication number
- CN112800866A CN112800866A CN202110039916.8A CN202110039916A CN112800866A CN 112800866 A CN112800866 A CN 112800866A CN 202110039916 A CN202110039916 A CN 202110039916A CN 112800866 A CN112800866 A CN 112800866A
- Authority
- CN
- China
- Prior art keywords
- face
- information
- image
- target object
- face 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.)
- Granted
Links
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
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/51—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
Abstract
The application relates to the field of artificial intelligence, especially, relate to a face recognition device, it includes: the face recognition module comprises a main board processing unit, wherein the main board processing unit is used for acquiring face image information and/or at least one image characteristic value information of an acquisition object, and the at least one image characteristic value information is at least one characteristic value extracted from the face image information; the local database module is used for storing and updating the face image data of the target object and sending the face image data of the target object to the face recognition module; the face recognition module is further used for comparing the face image information and/or the at least one characteristic value information of the collected object with the face image data of the target object to obtain a comparison result, and determining whether the collected object is the target object or not based on the comparison result.
Description
Technical Field
The present application relates to the field of artificial intelligence, and in particular, to a face recognition apparatus, an application system, a method, a computer device, and a storage medium.
Background
At present, the face recognition technology gradually becomes a bottom-layer application tool technology along with the maturity of method conditions such as a camera, an algorithm, data volume and the like, and is continuously popularized.
Although the face brushing of the related art also realizes the identity authentication through the face recognition, the face brushing requires that the object maintain a specific posture at a specific position, and such an application scene is not perfect enough for a high-flow and disturbance-free application scene, however, in a non-intervention situation, interference of various factors such as glasses, a mask, a side face, a head-lowering state, a hat and the like may occur to a naturally flowing crowd, and the recognition efficiency is reduced.
With respect to the related art in the above, the inventors consider that there is a defect that face recognition efficiency is low.
Disclosure of Invention
In order to improve the efficiency of face recognition, the application provides a face recognition device, an application system, a method, computer equipment and a storage medium.
In a first aspect, the present application provides a face recognition apparatus, which adopts the following technical scheme:
a face recognition apparatus comprising:
the face recognition module comprises a main board processing unit, wherein the main board processing unit is used for acquiring face image information and/or at least one image characteristic value information of an acquisition object, and the at least one image characteristic value information is at least one characteristic value extracted from the face image information;
the local database module is used for storing and updating the face image data of the target object and sending the face image data of the target object to the face recognition module;
the face recognition module is further configured to compare the face image information and/or the at least one feature value information of the acquired object with the face image data of the target object to obtain a comparison result, and determine whether the acquired object is the target object based on the comparison result.
By adopting the technical scheme, the face image information and/or at least one image characteristic value information of the collected object is obtained through the face recognition module, the face image data of the target object is stored in the local database module, and the face image data of the target object is sent to the face recognition module, further, the face recognition module compares the face image information and/or at least one characteristic value information with the face image data of the target object, and obtains a comparison result, whether the collected object is the target object is determined according to the comparison result, the at least one characteristic value information is compared with the face image data of the target object, compared with the comparison by adopting the whole picture, the interference of various factors can be avoided, and therefore, the face recognition efficiency can be improved.
Optionally, the face recognition module further includes an interface construction unit and an offline board storage unit; wherein the content of the first and second substances,
the interface construction unit is used for constructing at least one expansion interface based on the main board processing unit;
the off-line board storage unit is used for storing off-line data, the off-line data comprises face image data of a target object, and the face image data of the target object is sent to the main board processing unit through at least one expansion interface.
Through the technical scheme, the interface construction unit and the off-line board storage unit are arranged, then at least one expansion interface can be constructed through the interface construction unit, the off-line face image data of the target object can be stored through the off-line board storage unit, the off-line face image data of the target object can be transmitted to the main board processing unit through the at least one expansion interface, the main board processing unit can compare and recognize the data, therefore, under the off-line condition of the local database module, face recognition can be achieved, and the face recognition efficiency is further improved.
Optionally, the face recognition module includes:
the image acquisition subunit is used for acquiring the face video information of the acquisition object and preprocessing the face video information to acquire preprocessed face video information;
the video stream intercepting subunit is used for intercepting the video stream of the preprocessed face video information to obtain video stream data, and the video stream data comprises the video stream information of each frame of image;
the image screening subunit is used for screening the video stream information of each frame of image to obtain qualified face image information;
the image analysis subunit is used for analyzing the face image information meeting the conditions to obtain an analysis result, wherein the analysis result comprises at least one piece of image characteristic value information;
the image identification subunit is used for comparing at least one image characteristic value information with the face image data of the target object to obtain a comparison result;
and the result analysis subunit is used for determining whether the acquisition object is the target object or not based on the comparison result.
By adopting the technical scheme, the face video information of the acquisition object is acquired through the image acquisition subunit, the face video information is preprocessed, the face video is intercepted through the video stream intercepting subunit to obtain the video stream information of each frame image, the video stream information of each frame image is screened through the image screening subunit to obtain the face image information meeting the conditions, the face image information meeting the conditions is analyzed through the image analysis subunit, at least one image characteristic value information is extracted from the face image information, the at least one image characteristic value information is compared with the face image data of the target object through the image identification subunit to obtain a comparison result, finally, the analysis result is analyzed through the result analysis subunit, if the comparison result shows that the comparison result is consistent, the acquisition object is determined to be the target object, if the comparison result shows that the comparison result is not matched, the non-target object of the acquisition object is determined, and the face recognition efficiency can be improved by adopting a face characteristic value information comparison recognition mode.
Optionally, the system further comprises a cloud server, wherein the cloud server is used for receiving the uploaded face image information of the target object and storing the uploaded face image information of the target object in the local database module at regular time.
By adopting the technical scheme, the face image information of the target object is uploaded to the cloud server through the uploading platform, then the cloud server stores the face image information of the uploaded target object in the local database module at regular time, and then the face image data of the target object stored in the local database module can be updated so as to aim at different collected objects.
Optionally, the local database module includes:
the basic database unit is used for storing the face image data of the target object and deleting failure information, wherein the failure information comprises the face image data of the cancelled target object;
and the increment database unit is used for acquiring the face image information of the updated target object in the cloud server and combining the face image information of the updated target object into the basic database unit.
By adopting the technical scheme, the basic database unit stores the face image data of the target object, has the function of deleting the stored invalid face data, and can increase the available capacity of the basic database unit, so that the data transmission efficiency of the basic database unit can be improved, the incremental database unit acquires the face image information of the updated target object in the cloud server, updates and combines the updated face image information of the target object into the basic database unit, and further updates the face data of the target object in the basic database unit.
In a second aspect, the present application provides a face recognition application system, which adopts the following technical solution:
a face recognition application system applies the device of the first aspect to a bus taking charging system.
Through adopting above-mentioned technical scheme, be applied to bus charge system by bus with face identification device, because face identification device has higher face identification efficiency, compare in the charge of punching the card of correlation technique, can promote the efficiency that bus was charged by bus.
In a third aspect, the present application provides a face recognition method, which adopts the following technical scheme:
a face recognition method, applying the apparatus of the first aspect, comprising:
acquiring face video information of an acquisition object based on a video acquisition program, and preprocessing the face video information to obtain preprocessed face video information;
intercepting a video stream of the preprocessed face video information based on a video stream intercepting program to obtain video stream data, wherein the video stream data comprises video stream information of each frame of image;
based on an image screening program, screening the video stream information of each frame of image to obtain qualified face image information;
analyzing qualified face image information based on an image analysis program to obtain an analysis result, wherein the analysis result comprises at least one image characteristic value information;
comparing and identifying at least one image characteristic value information with the face image data of the target object based on an image identification program to obtain a comparison identification result;
analyzing and comparing the recognition result based on the result analysis program to determine whether the acquisition object is a target object;
the method comprises the steps of constructing at least one expansion interface based on face image data of a target object, and transmitting the face image data of the target object based on the at least one expansion interface under an offline condition.
By adopting the technical scheme, the method comprises the steps of acquiring face video information of an acquisition object through a video acquisition program, preprocessing the face video information, performing video stream interception on the face video information through a video stream interception program to obtain video stream information of each frame of image, screening the video stream information of each frame of image through an image screening program to obtain face image information meeting conditions, performing data analysis on the face image information meeting the conditions through an image analysis program to extract at least one image characteristic value information from the face image information, comparing the at least one image characteristic value information with the face image data of a target object through an image recognition program to obtain a comparison recognition result, analyzing the recognition result through a result analysis program to finally determine whether the acquisition object is the target object, the method and the device have the advantages that at least one image characteristic value information is adopted for comparison and identification, and compared with the photo identification of the related technology, the efficiency of face identification can be improved, at least one expansion interface can be constructed according to the stored face image data of the target object, furthermore, under the condition of off-line storage, the face image data of the target object can be transmitted according to the at least one expansion interface, so that the face identification can be realized under the off-line condition, and the face identification efficiency is further improved.
In a fourth aspect, the present application provides a computer device, which adopts the following technical solution:
a computer device comprising a memory, a processor and a computer program stored on the memory and capable of running on the processor, the processor when loading and executing the computer program employing the method of the second aspect.
By adopting the technical scheme, the computer program is generated based on the face recognition method of the third aspect and is stored in the memory so as to be loaded and executed by the processor, and therefore, the computer equipment is manufactured according to the memory and the processor, and the use by a user is facilitated.
In a fifth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solutions:
a computer-readable storage medium having stored thereon a computer program which, when loaded and executed by a processor, carries out the method of the second aspect.
By adopting the technical scheme, the computer program is generated based on the face recognition method of the third aspect and is stored in the computer readable storage medium to be loaded and executed by the processor, and the computer program can be conveniently read and stored through the computer readable storage medium, so that a user can conveniently call and use the computer program.
Drawings
Fig. 1 is a schematic block diagram of a face recognition apparatus according to the present application.
Fig. 2 is a module framework diagram of the face recognition module of the present application.
Fig. 3 is a flowchart of a method of the face recognition method of the present application.
Description of reference numerals: 1. a face recognition module; 11. a main board processing unit; 111. an image acquisition subunit; 112. a video stream intercepting subunit; 113. an image screening subunit; 114. an image analysis subunit; 115. an image identification subunit; 116. a result analysis subunit; 12. an interface construction unit; 13. an offline board storage unit; 2. a local database module; 21. a base database unit; 22. an incremental database unit; 3. and a cloud server.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is further described in detail below with reference to fig. 1-3 and the embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
At present, a public transport payment system comprises three forms of manual ticket selling, automatic coin inserting, intelligent card swiping payment and the like.
For intelligent card swiping payment, different preferential policies are adopted by various regions to discount different groups, in order to further improve urban image and respect to the old, the old who is over a certain age in the region takes a free bus, however, the free bus needs to handle identity identification, most of cities in China adopt that the old needs to handle an old IC card by a bus company, and when getting on the bus, the old IC card is swiped on a bus card swiping machine to be effective; in a few rural areas, the old people need to go to a public transport company to handle the old cards pasted with personal photos, and when getting on a bus, a ticket seller on the bus checks the old cards to take the bus free.
Society has gradually stepped into the cashless era, people have habitually used WeChat or Payment treasures to pay, and people often carry cash. However, for the elderly, the use of electronic payment requires a large amount of operation, and has a high learning cost, and in the process of getting on the vehicle quickly, the elderly who use electronic payment slowly will slow down the speed of getting on the vehicle, and in addition, electronic payment cannot make the elderly enjoy a discount.
In order to enjoy the benefits, the old people need to carry the old IC card or the related certificate, but the old IC card or the related certificate has many defects of losing, forgetting or inconvenient taking and the like, and does not discuss the problem of difficult replenishment.
Therefore, for the old people to enjoy the preferential policy by taking the bus, the old people can not enjoy the preferential policy by depending on the old IC card or the related certificate of the related technology, and the old people can not enjoy the preferential policy by losing or forgetting to carry the IC card or the related certificate sometimes.
The embodiment of the application discloses a face recognition device. Referring to fig. 1, the face recognition device includes a face recognition module 1 and a local database module 2, and the face recognition module 1 communicates with the local database module 2, in this embodiment, the face recognition module 1 communicates with the local database module 2 through a wireless communication module, wherein the communication mode of the wireless communication module includes any one of 5G, WIFI, Zigbee and the like, and certainly, according to actual use requirements, the face recognition module 1 and the local database module 2 can also be set to be in wired communication.
Wherein, the face recognition module 1 includes a main board processing unit 11, an interface construction unit 12 and an off-board storage unit 13, in this embodiment, the main board processing unit 11 includes an AI main board with computing power function, the off-board storage unit 13 includes an off-board with storage function, and the AI main board is used to obtain face image information and/or at least one image feature value information of the collected object, in this embodiment, the at least one image feature value information is at least one feature value extracted from the face image information, the interface construction module is used to construct at least one expansion interface according to the AI main board, in this embodiment, the interface construction module is used to construct eight expansion interfaces as an example, the off-board is used to store off-line data, in this embodiment, the off-line data includes face image data of the target object, and the off-board is connected with the AI main board through the constructed expansion interface, furthermore, under the offline condition of the local database module, the facial image data of the target object stored on the offline board is sent to the AI main board through the expansion interface, the acquired facial image information and the received facial image data are compared and identified through the AI main board, in the embodiment, the number of the offline boards is eight, so that the offline board is arranged, the comparison and identification of the human face can be realized under the offline condition of the local database module, and the facial recognition efficiency is improved.
Specifically, the AI motherboard can provide a basic fifty thousand offline face recognition algorithm on the basis of processing a conventional AI basic algorithm by itself, for example, calculating a human head, optimizing a circuit, and the like, when the amount of face image data in the local database module 2 exceeds fifty thousand, the face image data of the target object can be transmitted to the AI motherboard through eight offline boards, the storage amount of each offline board is 2T, and a Linux system is provided in the AI motherboard, and a calling program is provided in the Linux system, and then the offline board is called based on the calling program.
Referring to fig. 2, the AI main board processing unit 11 includes an image acquisition subunit 111, a video stream capturing subunit 112, an image filtering subunit 113, an image analysis subunit 114, an image identification subunit 115, and a result analysis subunit 116, where the video stream capturing subunit 112 communicates with the image acquisition subunit 111 and the image filtering subunit 113, the image analysis subunit 114 communicates with the image filtering subunit 113 and the image identification subunit 115, respectively, and the result analysis subunit 116 communicates with the image identification subunit 115.
Specifically, the image obtaining subunit 111 obtains the face video information of the collection object, and preprocesses the face video information to obtain preprocessed face video information, and sends the preprocessed face video information to the video stream intercepting subunit 112, in this embodiment, the collection object is an elderly person, the video stream intercepting subunit 112 intercepts the video stream of the preprocessed face video information to obtain video stream data, wherein the video stream data includes the video stream information of each frame of image, and sends the obtained video stream information of each frame of image to the image screening subunit 113, the image screening subunit 113 screens the video stream information of each frame of image to obtain qualified face image information, in this embodiment, the screening indexes of the image screening subunit 113 mainly include the integrity of the face image, the sharpness of the face image, and the like, and sends the face image information meeting the conditions to the image analysis subunit 114, that is, sends the face image meeting the requirements for completeness and definition to the image analysis subunit 114, the image analysis subunit 114 performs data analysis on the face image information meeting the conditions to obtain an analysis result, and the analysis result includes at least one image characteristic value information, that is, at least one image characteristic value information is extracted from the face image information, and sends at least one image characteristic value information to the image identification subunit 115, and the image characteristic value information includes at least one image characteristic value, in this embodiment, the image characteristic value mainly includes a stable contour of a main organ such as a face, a mouth, and eyes, but according to the actual use requirement, the unstable information such as a contour of an ear, wrinkles of a forehead, and the like can also be collected, the image identification subunit 115 compares the at least one image characteristic value information with the face image data of the target object to obtain a comparison result, and sends the comparison result to the result analysis subunit 116, where the face image data of the target object is a photo image pre-stored and uploaded by the elderly, and the result analysis subunit 116 determines whether the acquired object is the target object according to the comparison result, where the comparison result includes whether the at least one image characteristic value information matches or does not match the face image data of the target object in this embodiment.
The image acquisition subunit 111 acquires face video information of an acquisition object by using a 3D structured light imaging technology, that is, light with certain structural characteristics is projected onto the face of the acquisition object by using a near-infrared laser, and then is acquired by using a special infrared camera, different image phase information is acquired due to different depth regions of the face of the acquisition object by using the light with certain structure, and then the change of the structure is converted into depth information by using an operation unit, so that a three-dimensional structure is obtained, and further, the face characteristics of the acquisition object can be accurately identified; regarding the 3D structured light imaging technology, it should be understood by those skilled in the art that the description is omitted here, so as to ensure that the face video information of the captured object is the face video information of the elderly, rather than the video or photo that has been taken in advance.
The method for comparing the at least one image characteristic value information with the face image data by checking the digital signature is adopted, namely, a data snapshot mode is adopted, and then the effect of high-speed retrieval and comparison can be achieved.
Referring to fig. 1, in this embodiment, the cloud server 3 is further included, that is, when the face information of the target object is obtained, usually, the target object autonomously uploads the face image information of the target object to the cloud server 3 through the platform, and the cloud server 3 generates an update package of the face image according to a certain time interval, generally speaking, the certain time interval is 1 to 5 minutes, and downloads the update package of the face image, so as to periodically send the generated update package of the face image to the local database module 2.
Referring to fig. 1, in this embodiment, the local database module 2 has a larger memory amount, that is, can contain more data, generally speaking, the contained data amount is more than twenty thousand, while the memory amount of the more common database in the market is smaller, generally about five thousand, and further, by using the local database module 2 of the present application, the face image data of more target objects can be contained.
Specifically, the local database module 2 includes a basic database unit 21 and an incremental database unit 22, the basic database unit 21 stores therein face image data of a target object, and the basic database unit 21 can also execute a deletion operation on the face image data of a failed target object stored therein, the face image data of the failed target object being the face image data of the cancelled target object, and further, can expand the available capacity of the basic database unit 21, the incremental database unit 22 is configured to acquire face image information of the target object updated in the cloud server 3 and merge the face image information of the updated target object into the basic database unit 21, that is, the incremental database unit 22 receives and decompresses an update package of a downloaded face image, and then, decompresses and merges the decompressed face image information of the target object into the basic database unit 21, updating of the underlying database unit 21 is facilitated.
Since the amount of the face image data of the target object stored in the local database module 2 is large, the retrieval and identification speed is slow according to a normal retrieval mode, and thus the boarding rate is affected, the retrieval mode of the face image data of the target object in the basic database unit 21 is optimized, that is, the retrieval and screening are performed group by group step by step, for example, the face image data of one thousand target objects are used as a group.
Preferably, in this embodiment, when performing face recognition, the AI motherboard preferably compares with the face image data in the local database module 2, and if there is no face image data in the local database module 2, the AI motherboard preferably compares with the face image information of the target object stored in the cloud server 3, that is, the eigenvalue obtained by the AI motherboard is uploaded to the cloud server 3, and the cloud server 3 automatically searches the face image information of the target object in the big database to obtain a search result, and returns the search result to the AI motherboard, and further, the AI motherboard compares and recognizes.
In the process of face recognition, the acquired at least one image characteristic value information is preferentially compared with the face image data of the target object stored in the local database module 2, if the comparison result is not matched, the local database module 2 may be not updated in time, and therefore, if the comparison result is not matched, the acquired at least one image characteristic value information is compared with the face image information of the target object uploaded in the cloud server 3, and then whether the acquired object is the target object is determined, so that the comprehensiveness of face recognition can be improved.
In the embodiment, different basic face template libraries are made according to the characteristics of the public transportation system, such as the particularity and the regionality of the distribution of line personnel, that is, the basic face template library is correspondingly made according to the actual use requirement.
The face recognition device is installed on the bus, namely, the face recognition device is applied to a bus taking charge system to achieve the purpose of identifying the old people and taking the bus free of charge, so that the face recognition device installed on the bus needs to be subjected to an anti-seismic test to prevent the shaking of the bus in the driving process from affecting the stability of the face recognition device.
Wherein, the face identification device to installing at the bus carries out antidetonation test including hardware is fixed and the software shake, specifically, the hardware is fixed to include and consolidates face identification device on the bus, for example, the glue dripping of hookup location department is consolidated, the customization spring reinforcement of key position department etc., and then, in order to increase the redundant design of junction, the software shake can dismantle the parameter with expanded subassembly including the monitoring, utilize the face identification device of shake system shake setting at the bus, in order to judge whether to launch reserve protector, and then, face identification device's stability can further be promoted.
Wherein, still be provided with the card reader that is used for discerning the bus card on the bus, and then, in order to read the bus card through the card reader to old person's face image data do not upload to high in the clouds server 3 or do not save in local database module 2, lead to the condition that the old person can not take a bus to appear.
Wherein, because people in any age group on the bus can be present, and further, in order to reduce the calculation amount of the face recognition device installed on the bus, the face recognition device can be started for face recognition only by old people, that is, the face recognition device is provided with a switch button, when the old people get on the bus, the switch button needs to be pressed, and the face recognition device can be started for face recognition, of course, according to the actual use condition, a bus driver can also manually trigger the face recognition device, and a vital sign judgment device can be arranged near the face recognition device to judge the vital signs of the people getting on the bus, and further, the age range of the people getting on the bus can be judged, the vital sign judgment device is communicated with the face recognition device, and further, when the vital sign judgment device judges that the people getting on the bus is the old people, the signal is sent to the face recognition device, and the face recognition device is automatically started based on, therefore, the matching times of the face recognition device can be reduced, and the calculation amount of the face recognition device can be saved.
The implementation principle of the face recognition device in the embodiment of the application is as follows: the face video information of the elderly people getting on the bus is obtained through the image obtaining subunit 111, the obtained face video information is preprocessed to obtain preprocessed face video information, the preprocessed face video information is subjected to video stream interception through the video stream intercepting subunit 112 to obtain video stream information of each frame of image, then the video stream information of each frame of image is screened through the image screening subunit 113 to obtain a face image with better face integrity and definition, the obtained face image is subjected to data analysis through the image analysis subunit 114 to extract at least one image characteristic value information from the face image, at least one image characteristic value information for identifying the elderly people getting on the bus is compared with the face image data of the elderly people stored in the basic database subunit 21 through the image identifying subunit 115 to obtain a comparison identification result, the result analysis subunit 116 determines whether the image information of the elderly getting on the bus matches the image data of the elderly stored in the basic database unit 21 according to the comparison and identification result, and if the image information matches the image data of the elderly, the elderly getting on the bus is determined as a free riding object, and if the image information does not match the image data, the elderly getting on the bus is determined as not meeting the free riding condition.
The embodiment of the application discloses a face recognition method, and with reference to fig. 3, the method specifically comprises the following steps:
and acquiring the face video information of the acquired object based on a video acquisition program, and preprocessing the face video information to acquire preprocessed face video information.
In this embodiment, the collection object is set as the elderly people who get on the bus, that is, the camera device is turned on, the camera device is used to obtain the face video of the elderly people who get on the bus, and the face video of the elderly people who get on the bus is preprocessed, so that the preprocessed face video of the elderly people is obtained, and the preprocessing here mainly includes screening out the obtained face video to screen out fuzzy parts in the face video.
And intercepting the video stream of the preprocessed human face video information based on a video stream intercepting program to obtain video stream data, wherein the video stream data comprises video stream information of each frame of image.
The method comprises the steps of capturing an acquired video of the old people getting on the bus based on a common video stream capturing program, analyzing the captured face video by using canvas to generate video stream data, wherein the generated video stream data comprises video stream information of each frame of image, and capturing a face image in the video stream information of each frame of image.
And screening the video stream information of each frame of image based on an image screening program to obtain qualified face image information.
In this embodiment, the screening indexes include the integrity of the face image and the definition of the image in the image, and then, according to the indexes, the intercepted face image is screened to screen out the face image with higher integrity and definition.
And analyzing the qualified face image information based on an image analysis program to obtain an analysis result, wherein the analysis result comprises at least one piece of image characteristic value information.
In this embodiment, the at least one image feature value information includes at least one image feature value, and the at least one image feature value includes a contour of a main organ of the human face, for example, a contour of a nose, a contour of a mouth, a contour of an eye, and the like.
And comparing and identifying at least one piece of image characteristic value information with the face image data of the target object based on the image identification program to obtain a comparison and identification result.
In this embodiment, the face image data of the target object is stored face image data of the elderly, and then at least one image feature value of the elderly who gets on the vehicle is compared and identified with the stored face image data of the elderly, and a comparison identification result is obtained, wherein the comparison identification result includes matching and non-matching.
And analyzing and comparing the identification result based on the result analysis program to determine whether the acquisition object is the target object.
Wherein, according to comparing the recognition result, and compare and carry out the analysis to the recognition result, confirm whether the old person's of getting on the bus face image information agrees with the old person's of storage face image data, finally, confirm whether the old person of getting on the bus accords with the condition of taking the bus for free, if compare the recognition result and show to coincide, then the old person of affirming getting on the bus accords with the condition of taking the bus for free, otherwise, if compare the recognition result and show to not coincide, then the old person of affirming getting on the bus does not accord with the condition of taking the bus for free.
The method comprises the steps of constructing at least one expansion interface based on face image data of a target object, and transmitting the face image data of the target object based on the at least one expansion interface under an offline condition.
Specifically, according to the facial image data of the target object, at least one extension interface is constructed, that is, the extension interface is constructed on the AI main board, and further, the offline board is connected through the extension interface of the component, in this embodiment, the offline board is a storage board with a storage function, the facial image data of the target object is stored on the offline board, preferably, eight offline boards are also set by taking the construction of eight extension interfaces as an example, accordingly, under the condition that the local database is offline, the facial image data of the target object is transmitted through the offline board and the constructed extension interface to be compared with the facial image information of the collected object, and the facial recognition efficiency can be improved.
In this embodiment, the amount of memory in the basic database is relatively large, so that more face image data can be accommodated, and based on the image deletion program, face image information of an old person who fails in the basic database can be deleted, where the failure is a logout, so as to clear the logout face image data, thereby expanding the available capacity of the basic database.
The basic database can also call the updated face image information of the old people in the incremental database at regular time based on an image updating program, namely, the incremental database is used for updating the face image information of the old people who can take a bus at regular time and merging the updated face image information into the basic database, preferably, the old people who can take the bus at regular time upload the face image information to the cloud server by means of an uploading platform, the cloud server generates updating packages at certain time intervals, generally speaking, the cloud server updates the face image information at regular time intervals of 1-5 minutes, the incremental database acquires the updating packages in the cloud server and analyzes the updating packages to acquire and store the updated face image information of the old people.
The implementation principle of the face recognition method in the embodiment of the application is as follows: the method comprises the steps of acquiring a face video of an old person getting on a bus by adopting a camera device, preprocessing the face video, intercepting the face video to obtain video stream information of each frame of image, screening the video stream information of each frame of image to obtain a face image with better integrity and definition, analyzing the face image to extract at least one image characteristic value information from the face image, such as at least one of a nose outline, a mouth outline, an eye outline and the like, comparing the extracted at least one image characteristic value information with face image data of the old person which is stored locally and accords with free bus taking, and obtaining a comparison result, so that whether the old person getting on the bus accords with the free bus taking condition or not is determined according to the comparison result.
The embodiment of the application discloses computer equipment, which comprises a memory, a processor and a computer program which is stored in the memory and can run on the processor, wherein when the processor loads the computer program, the face recognition method is executed.
The computer device may be a desktop computer, a notebook computer, or a cloud server, and the computer device includes but is not limited to a processor and a memory, for example, the computer device may further include an input/output device, a network access device, a bus, and the like.
The processor may be a Central Processing Unit (CPU), and of course, according to an actual use situation, other general processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, and the like may also be used, and the general processor may be a microprocessor or any conventional processor, and the present application does not limit the present invention.
The memory may be an internal storage unit of the computer device, for example, a hard disk or a memory of the computer device, or an external storage device of the computer device, for example, a plug-in hard disk, a Smart Memory Card (SMC), a secure digital card (SD) or a flash memory card (FC) equipped on the computer device, or a combination of the internal storage unit of the computer device and the external storage device, and the memory is used for storing a computer program and other programs and data required by the computer device, and may also be used for temporarily storing data that has been output or will be output, which is not limited in this application.
The face recognition method of the embodiment is stored in a memory of the computer device through the computer device, and is loaded and executed on a processor of the computer device, so that the user can use the face recognition method conveniently.
The embodiment of the application discloses a computer-readable storage medium, and a computer program is stored in the computer-readable storage medium, wherein when the computer program is loaded by a processor, the face recognition method is executed.
The computer program may be stored in a computer readable medium, the computer program includes computer program code, the computer program code may be in a source code form, an object code form, an executable file or some intermediate form, and the like, the computer readable medium includes any entity or device capable of carrying the computer program code, a recording medium, a usb disk, a removable hard disk, a magnetic disk, an optical disk, a computer memory, a Read Only Memory (ROM), a Random Access Memory (RAM), an electrical carrier signal, a telecommunication signal, a software distribution medium, and the like, and the computer readable medium includes but is not limited to the above components.
The face recognition method of the above embodiment is stored in the computer-readable storage medium through the computer-readable storage medium, and is loaded and executed on the processor, so as to facilitate storage and application of the face recognition method.
The foregoing is a preferred embodiment of the present application and is not intended to limit the scope of the application in any way, and any features disclosed in this specification (including the abstract and drawings) may be replaced by alternative features serving equivalent or similar purposes, unless expressly stated otherwise. That is, unless expressly stated otherwise, each feature is only an example of a generic series of equivalent or similar features.
Claims (9)
1. A face recognition apparatus, comprising:
the face recognition module (1) comprises a main board processing unit (11), wherein the main board processing unit (11) is used for acquiring face image information and/or at least one image characteristic value information of an acquisition object, and the at least one image characteristic value information is at least one characteristic value extracted from the face image information;
the local database module (2) is used for storing and updating the face image data of the target object and sending the face image data of the target object to the face recognition module (1);
the face recognition module (1) is further configured to compare the face image information and/or the at least one feature value information of the acquired object with the face image data of the target object to obtain a comparison result, and determine whether the acquired object is the target object based on the comparison result.
2. The face recognition apparatus according to claim 1, wherein the face recognition module (1) further comprises an interface construction unit (12) and an offline board storage unit (13); wherein the content of the first and second substances,
the interface construction unit (12) is used for constructing at least one expansion interface based on the main board processing unit (11);
the offline board storage unit (13) is used for storing offline data, the offline data comprises face image data of a target object, and the face image data of the target object is sent to the main board processing unit (11) through at least one expansion interface.
3. The face recognition apparatus according to claim 2, wherein the main board processing unit (11) comprises:
the image acquisition subunit (111) is used for acquiring the face video information of the acquisition object and preprocessing the face video information to acquire preprocessed face video information;
a video stream intercepting subunit (112) for performing video stream interception on the preprocessed face video information to obtain video stream data, wherein the video stream data comprises video stream information of each frame of image;
the image screening subunit (113) is used for screening the video stream information of each frame of image to obtain qualified face image information;
an image analysis subunit (114) for analyzing the qualified face image information to obtain an analysis result, wherein the analysis result comprises at least one image characteristic value information;
the image identification subunit (115) is used for comparing at least one piece of image characteristic value information with the face image data of the target object to obtain a comparison result;
and a result analysis subunit (116) for determining whether the acquisition object is the target object based on the comparison result.
4. The face recognition device according to claim 1, further comprising a cloud server (3), wherein the cloud server (3) is configured to receive the uploaded face image information of the target object and store the uploaded face image information of the target object in the local database module (2) at regular time.
5. The face recognition device according to claim 4, characterized in that the local database module (2) comprises:
a basic database unit (21) for storing face image data of a target object and deleting invalidation information including face image data of a revoked target object;
and the increment database unit (22) is used for acquiring the face image information of the updated target object in the cloud server (3) and merging the face image information of the updated target object into the basic database unit (21).
6. A face recognition application system, characterized in that the device of any one of claims 1-5 is applied to a bus fare collection system.
7. A face recognition method, characterized in that the system of any one of claims 1-5 is applied, which comprises:
acquiring face video information of an acquisition object based on a video acquisition program, and preprocessing the face video information to obtain preprocessed face video information;
intercepting a video stream of the preprocessed face video information based on a video stream intercepting program to obtain video stream data, wherein the video stream data comprises video stream information of each frame of image;
based on an image screening program, screening the video stream information of each frame of image to obtain qualified face image information;
analyzing qualified face image information based on an image analysis program to obtain an analysis result, wherein the analysis result comprises at least one image characteristic value information;
comparing and identifying at least one image characteristic value information with the acquired face image data of the target object based on an image identification program to obtain a comparison identification result;
analyzing and comparing the recognition result based on the result analysis program to determine whether the acquisition object is a target object;
the method comprises the steps of constructing at least one expansion interface based on face image data of a target object, and transmitting the face image data of the target object based on the at least one expansion interface under an offline condition.
8. A computer device comprising a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor, when loaded with the computer program, performs the method of claim 7.
9. A computer-readable storage medium, in which a computer program is stored which, when loaded by a processor, carries out the method of claim 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110039916.8A CN112800866B (en) | 2021-01-13 | 2021-01-13 | Face recognition device, application system, method, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110039916.8A CN112800866B (en) | 2021-01-13 | 2021-01-13 | Face recognition device, application system, method, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112800866A true CN112800866A (en) | 2021-05-14 |
| CN112800866B CN112800866B (en) | 2022-05-06 |
Family
ID=75810267
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110039916.8A Active CN112800866B (en) | 2021-01-13 | 2021-01-13 | Face recognition device, application system, method, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112800866B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114512016A (en) * | 2022-02-17 | 2022-05-17 | 华录智达科技股份有限公司 | Bus stop passenger source gathering method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106650589A (en) * | 2016-09-30 | 2017-05-10 | 北京旷视科技有限公司 | Real-time face recognition system and method |
| CN106682607A (en) * | 2016-12-23 | 2017-05-17 | 山东师范大学 | Offline face recognition system and offline face recognition method based on low-power-consumption embedded and infrared triggering |
| CN110245561A (en) * | 2019-05-09 | 2019-09-17 | 深圳市锐明技术股份有限公司 | A kind of face identification method and device |
| CN110378696A (en) * | 2019-06-26 | 2019-10-25 | 深圳市万通顺达科技股份有限公司 | A kind of brush face method of payment, device, readable storage medium storing program for executing and terminal device |
| CN110866443A (en) * | 2019-10-11 | 2020-03-06 | 厦门身份宝网络科技有限公司 | Portrait storage method, face recognition equipment and storage medium |
-
2021
- 2021-01-13 CN CN202110039916.8A patent/CN112800866B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106650589A (en) * | 2016-09-30 | 2017-05-10 | 北京旷视科技有限公司 | Real-time face recognition system and method |
| CN106682607A (en) * | 2016-12-23 | 2017-05-17 | 山东师范大学 | Offline face recognition system and offline face recognition method based on low-power-consumption embedded and infrared triggering |
| CN110245561A (en) * | 2019-05-09 | 2019-09-17 | 深圳市锐明技术股份有限公司 | A kind of face identification method and device |
| CN110378696A (en) * | 2019-06-26 | 2019-10-25 | 深圳市万通顺达科技股份有限公司 | A kind of brush face method of payment, device, readable storage medium storing program for executing and terminal device |
| CN110866443A (en) * | 2019-10-11 | 2020-03-06 | 厦门身份宝网络科技有限公司 | Portrait storage method, face recognition equipment and storage medium |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114512016A (en) * | 2022-02-17 | 2022-05-17 | 华录智达科技股份有限公司 | Bus stop passenger source gathering method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112800866B (en) | 2022-05-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10657370B2 (en) | Determining images having unidentifiable license plates | |
| US10789786B2 (en) | Picture-based vehicle loss assessment | |
| EP3528156B1 (en) | Virtual reality environment-based identity authentication method and apparatus | |
| US20220172518A1 (en) | Image recognition method and apparatus, computer-readable storage medium, and electronic device | |
| JP5509753B2 (en) | System and method for generating recognition results | |
| CN107103218B (en) | Service implementation method and device | |
| CN108875478B (en) | People-authentication-integrated verification method, device and system and storage medium | |
| US20200265645A1 (en) | Utilizing machine learning to generate augmented reality vehicle information for a scale model of a vehicle | |
| CN110324350B (en) | Identity authentication method and server based on mobile terminal non-sensitive sensor data | |
| CN109978552B (en) | Payment processing method, device and equipment based on identity card information | |
| WO2018235055A1 (en) | Facial biometrics card emulation for in-store payment authorization | |
| JP2023520964A (en) | Efficient management of face recognition systems and face recognition methods in multiple domains | |
| US11922749B2 (en) | Providing virtual and physical access to secure storage container | |
| CN112800866B (en) | Face recognition device, application system, method, computer equipment and storage medium | |
| KR20220076398A (en) | Object recognition processing apparatus and method for ar device | |
| CN113409056B (en) | Payment method and device, local identification equipment, face payment system and equipment | |
| JP6903044B2 (en) | Cash handling system and cash transaction method | |
| CN114463015A (en) | Payment supervision system, method, electronic device and storage medium | |
| CN212766112U (en) | Novel remote face recognition vehicle starting device | |
| KR102027786B1 (en) | Method and system for recognizing face of user based on multiple images | |
| CN113269064A (en) | Riding method and device | |
| Ahmed | GPark: Vehicle parking management system using smart glass | |
| CN112750260B (en) | Quick safety response communication system of intelligent vehicle-mounted terminal | |
| CN110728522A (en) | Face brushing public traffic system | |
| CN116205726B (en) | Loan risk prediction method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| PP01 | Preservation of patent right |
Effective date of registration: 20230616 Granted publication date: 20220506 |
|
| PP01 | Preservation of patent right |