CN113689585B - Non-inductive attendance card punching method, system and related equipment - Google Patents
Non-inductive attendance card punching method, system and related equipment Download PDFInfo
- Publication number
- CN113689585B CN113689585B CN202111240622.8A CN202111240622A CN113689585B CN 113689585 B CN113689585 B CN 113689585B CN 202111240622 A CN202111240622 A CN 202111240622A CN 113689585 B CN113689585 B CN 113689585B
- Authority
- CN
- China
- Prior art keywords
- human body
- picture
- iris
- card
- recognition result
- 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
- 238000004080 punching Methods 0.000 title claims abstract description 102
- 238000000034 method Methods 0.000 title claims abstract description 68
- 238000001514 detection method Methods 0.000 claims abstract description 97
- 230000001939 inductive effect Effects 0.000 claims abstract description 13
- 238000000605 extraction Methods 0.000 claims description 20
- 238000004590 computer program Methods 0.000 claims description 13
- 238000007781 pre-processing Methods 0.000 claims description 5
- 238000013473 artificial intelligence Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 15
- 238000013527 convolutional neural network Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000005429 filling process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
Images
Classifications
-
- 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
- G07C1/00—Registering, indicating or recording the time of events or elapsed time, e.g. time-recorders for work people
- G07C1/10—Registering, indicating or recording the time of events or elapsed time, e.g. time-recorders for work people together with the recording, indicating or registering of other data, e.g. of signs of identity
Abstract
The invention is suitable for the field of artificial intelligence technology application, and provides a non-inductive attendance card punching method, a system and related equipment, wherein the method comprises the following steps: acquiring video stream data, and decoding the video stream data to obtain a picture to be identified; carrying out human body detection and human body identification on the picture to be identified to obtain a human body identification result; carrying out face detection and face recognition on the picture to be recognized to obtain a face recognition result; performing iris detection and iris recognition on the picture to be recognized to obtain an iris recognition result; and obtaining card punching feedback information according to the human body recognition result, the human face recognition result and the iris recognition result. The invention solves the problems of use scene limitation, high false detection rate and long time consumption of the existing non-inductive attendance.
Description
Technical Field
The invention belongs to the field of artificial intelligence technology application, and particularly relates to a non-inductive attendance card punching method, a system and related equipment.
Background
With the development of artificial intelligence technology, attendance checking is gradually developing from traditional interactive modes such as signature and card punching machine to a non-inductive card punching mode. The iris recognition and face recognition method can be effectively used as a technical means for the non-sensitive attendance card punching, but the iris recognition and face recognition have large limitation on the scene of the non-sensitive attendance card punching, relatively clear iris images or face images need to be captured, and in addition, personnel can not capture the iris images and the face images in the advancing process, so the attendance card punching method based on the iris recognition and the face recognition has the problems of high false detection rate and long time consumption because the shooting distance cannot be too far when the attendance card punching method is deployed and used, or the interaction card punching method needs to be manually matched, and the existing card punching method has the limitations of use environment and recognition content.
Disclosure of Invention
The embodiment of the invention provides a method, a system and related equipment for noninductive attendance checking, and aims to solve the problems of use scene limitation, high false detection rate and long time consumption of the conventional noninductive attendance checking.
In a first aspect, an embodiment of the present invention provides a method for punching a card on an attendance record without any sense, including the following steps:
acquiring video stream data, and decoding the video stream data to obtain a picture to be identified;
carrying out human body detection and human body identification on the picture to be identified to obtain a human body identification result;
carrying out face detection and face recognition on the picture to be recognized to obtain a face recognition result;
performing iris detection and iris recognition on the picture to be recognized to obtain an iris recognition result;
and obtaining card punching feedback information according to the human body recognition result, the human face recognition result and the iris recognition result.
Further, the step of obtaining video stream data and decoding the video stream data to obtain the picture to be identified includes the following sub-steps:
acquiring real-time video stream data from video acquisition equipment, and performing frame extraction according to a preset frame interval to obtain a frame extraction image;
and preprocessing the frame-extracted image to obtain the picture to be identified.
Further, the step of performing human body detection and human body recognition on the picture to be recognized to obtain a human body recognition result comprises the following substeps:
acquiring preset card punching personnel information, and creating a human body identification counter with an initial value of 0 and a maximum value of 3 for each card punching personnel;
and carrying out human body detection on the picture to be recognized, wherein:
if no human body image exists in the picture to be recognized, directly starting the processing of the picture to be recognized of the next frame;
if at least one human body image exists in the picture to be identified, starting to perform face detection, simultaneously sequentially performing feature extraction on the human body images by using a human body feature extractor, comparing the human body information of the card punch personnel in the preset card punch personnel information, and adding 1 to the numerical value of the human body identification counter corresponding to the card punch personnel which is successfully compared, wherein:
if the value of the human body identification counter corresponding to the card punch is smaller than 3, returning the value of the human body identification counter as the human body identification result, and carrying out target tracking on the human body image corresponding to the card punch;
and if the value of the human body identification counter corresponding to the card punch is equal to 3, returning a flag bit information of successful card punching as the human body identification result.
Further, the step of performing face detection and face recognition on the picture to be recognized to obtain a face recognition result includes the following substeps:
acquiring preset card punching personnel information, and creating a face recognition counter with an initial value of 0 and a maximum value of 2 for each card punching personnel;
carrying out face detection on the picture to be recognized, wherein:
if the picture to be recognized does not have the face image, directly carrying out target tracking on the human body image in the picture to be recognized;
if at least one face image exists in the picture to be recognized, iris detection is started, meanwhile, a face feature extractor is used for sequentially extracting features of the face images, the face information of the punch card personnel in the preset punch card personnel information is compared, and the numerical value of the face recognition counter corresponding to the punch card personnel, which is successfully compared, is added with 1, wherein:
if the numerical value of the face recognition counter corresponding to the card punch is smaller than 2, returning the numerical value of the face recognition counter as the face recognition result, and carrying out target tracking on the human body image corresponding to the card punch;
and if the numerical value of the face recognition counter corresponding to the card punch personnel is equal to 2, returning a flag bit information of successful card punching as the face recognition result.
Furthermore, the step of performing iris detection and iris recognition on the picture to be recognized to obtain an iris recognition result comprises the following substeps:
acquiring preset card punching personnel information, and creating an iris identification counter with an initial value of 0 and a maximum value of 1 for each card punching personnel;
carrying out iris detection on the picture to be identified, wherein:
if the picture to be recognized does not have the iris image, directly carrying out target tracking on the face image in the picture to be recognized;
if at least one iris image exists in the picture to be identified, an iris feature extractor is utilized to sequentially extract the features of the iris images, the iris information of the card punch personnel in the preset card punch personnel information is compared, and the numerical value of the iris identification counter corresponding to the card punch personnel, which is successfully compared, is added with 1, wherein:
if the numerical value of the iris recognition counter corresponding to the card punch is smaller than 1, returning the numerical value of the face recognition counter as the iris recognition result, and carrying out target tracking on the human body image corresponding to the card punch;
and if the numerical value of the iris identification counter corresponding to the card punch is equal to 1, directly returning a successful card punch information as the iris identification result.
Furthermore, after the step of performing iris detection and iris recognition on the picture to be recognized to obtain an iris recognition result, the method further comprises the following steps:
storing the human body image subjected to target tracking in a tracking queue by using a preset target tracking algorithm, carrying out human body detection and human body recognition, human face detection and human face recognition, iris detection and iris recognition on the human body image in the tracking queue in the picture to be recognized of the next frame, and deleting the human body image from the tracking queue if the human body recognition result of the card punch corresponding to the human body image, or the human face recognition result, or the iris recognition result contains information of successful card punching.
Further, the step of obtaining the card punching feedback information according to the human body recognition result, the human face recognition result and the iris recognition result specifically comprises:
if the human body recognition result is the zone bit information, or the human face recognition result is the zone bit information, or the iris recognition result is the successful card punching information, the card punching personnel corresponding to the human body recognition result, the human face recognition result and the iris recognition result are judged to be in a card punching state, and the numerical values of the human body recognition counter, the human face recognition counter and the iris recognition counter of the card punching personnel are reset.
In a second aspect, an embodiment of the present invention further provides a system for checking attendance without sensing, including:
the data acquisition module is used for acquiring video stream data and decoding the video stream data to obtain a picture to be identified;
the human body detection and identification module is used for carrying out human body detection and human body identification on the picture to be identified to obtain a human body identification result;
the face detection and recognition module is used for carrying out face detection and face recognition on the picture to be recognized to obtain a face recognition result;
the iris detection and identification module is used for carrying out iris detection and iris identification on the picture to be identified to obtain an iris identification result;
and the card punching information feedback module is used for obtaining card punching feedback information according to the human body recognition result, the face recognition result and the iris recognition result.
In a third aspect, an embodiment of the present invention further provides a computer device, including: the system comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the computer program to realize the steps of the non-inductive attendance card-punching method in any one of the above embodiments.
In a fourth aspect, the embodiment of the present invention further provides the computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when executed by a processor, the computer program implements the steps in the non-sensory attendance checking method according to any one of the above embodiments.
The invention has the advantages that the card punching scheme which combines a plurality of identification modes and identifies simultaneously is adopted, so that the card punching accuracy is improved in the face of a middle-distance and long-distance real scene, the false detection rate is reduced, and the time of the card punching detection process is shortened.
Drawings
Fig. 1 is a general logic diagram of a method for punching a card on an attendance record in an embodiment of the present invention;
fig. 2 is a block flow diagram of a method for punching a card on an attendance record without sensing according to an embodiment of the present invention;
fig. 3 is a block diagram of a sub-flow of step S101 in the method for checking attendance at a location without sensing the attendance provided by the embodiment of the present invention;
fig. 4 is a block diagram of a sub-flow of step S102 in the method for checking attendance without sensing according to the embodiment of the present invention;
fig. 5 is a block diagram of a sub-flow of step S103 in the method for checking attendance without sensing according to the embodiment of the present invention;
fig. 6 is a block diagram of a sub-flow of step S104 in the method for checking attendance at a location without sensing the attendance;
fig. 7 is a block diagram of a structure of a non-inductive attendance card punching system according to an embodiment of the present invention;
fig. 8 is a schematic structural diagram of a computer device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Referring to fig. 1 and fig. 2, fig. 1 is a general logic diagram of a non-inductive attendance checking method according to an embodiment of the present invention, and fig. 2 is a flow chart of the non-inductive attendance checking method according to the embodiment of the present invention. The non-inductive attendance card punching method provided by the embodiment of the invention specifically comprises the following steps:
s101, video stream data is obtained, and a picture to be identified is obtained by decoding the video stream data.
Referring to fig. 3, fig. 3 is a sub-flow block diagram of step S101 in the method for checking attendance and checking card according to the embodiment of the present invention, where step S101 in this embodiment specifically includes the following sub-steps:
s1011, acquiring real-time video stream data from the video acquisition equipment, and performing frame extraction according to a preset frame interval to obtain a frame extraction image.
In the embodiment of the invention, the video acquisition equipment is image acquisition equipment for realizing high-definition data acquisition, the video acquisition equipment acquires video stream data including a card punch in real time, and performs frame extraction of the video stream data according to a preset frame interval to obtain a frame extraction image, wherein the preset frame interval adopted in the embodiment of the invention is 10 frames, and the image with a time interval is used for analyzing the advancing process and the card punch behavior of the card punch, so that the accuracy of card punch detection can be improved, and the image extracted through the time interval is favorable for acquiring a plurality of images of the same target in different states, and multi-mode discrimination is facilitated.
And S1012, preprocessing the frame extraction image to obtain the picture to be identified.
In the embodiment of the present invention, the manner of preprocessing the frame-extracted image includes image scaling and image filling, specifically, in the embodiment of the present invention, the resolution of the frame-extracted image obtained by frame-extracting the video stream data is 1920 × 1080, after image scaling, the resolution of the frame-extracted image is reduced to 640 × 360, then, the frame-extracted image with the resolution of 640 × 360 is subjected to image filling of gray pixels, so that the frame-extracted image becomes a rectangular image with the resolution of 640 × 640, and the frame-extracted image after the image filling process is used as the picture to be identified.
S102, carrying out human body detection and human body identification on the picture to be identified to obtain a human body identification result.
Referring to fig. 4, fig. 4 is a sub-flowchart diagram of step S102 in the method for checking attendance and checking card according to the embodiment of the present invention, which specifically includes the following sub-steps:
s1021, obtaining preset card punching personnel information, and creating a human body recognition counter with an initial value of 0 and a maximum value of 3 for each card punching personnel.
In the embodiment of the present invention, the preset punch-card information is collected biological feature information of a target punch-card person, where the biological feature information collected by each punch-card person includes human body feature information, human face feature information, and iris feature information, and at this time, a human body identification counter with an initial value of 0 and a maximum value of 3 is respectively created for each punch-card person in the preset punch-card information, and a value of the human body identification counter indicates the number of times that the human body feature information of the punch-card person is accurately identified.
And S1022, carrying out human body detection on the picture to be recognized.
In the embodiment of the present invention, a tool for performing human body detection on the to-be-identified picture is an image detector, and the image detector is formed by a pre-trained convolutional neural network with an image identification function, wherein the image detector is used for performing human body detection on the to-be-identified picture, and according to whether there is a human body image in the detected to-be-identified picture, the method further includes:
1022a, if there is no human body image in the picture to be recognized, directly starting the processing of the picture to be recognized of the next frame.
If the image detector does not recognize any human body image from the picture to be recognized, there is no object that can be determined by checking the card in the picture to be recognized, and at this time, the processing stage of the step S101 is returned again, and the flow from the step S102 is performed again from the next extracted frame extraction image.
1022b, if at least one human body image exists in the picture to be identified, starting to perform human face detection, simultaneously sequentially performing feature extraction on the human body images by using a human body feature extractor, comparing the human body information of the card punch in the preset card punch information, and adding 1 to the value of the human body identification counter corresponding to the card punch which is successfully compared.
If the image detector identifies at least one human body image from the picture to be identified, step S103 is performed, and meanwhile, the human body feature extractor continues to be used for feature extraction of the human body image, in the embodiment of the present invention, the human body feature extractor is also composed of a convolutional neural network, but is dedicated to feature extraction of the whole human body image, the human body features extracted by the human body feature extractor are compared with the human body feature information corresponding to the card punch, and the value of the human body identification counter corresponding to the card punch that is successfully compared is added by 1, at this time, according to the value of the human body identification counter corresponding to the card punch, the method further includes:
1022b1, if the value of the human body identification counter corresponding to the card punch is less than 3, returning the value of the human body identification counter as the human body identification result, and performing target tracking on the human body image corresponding to the card punch.
1022b2, if the value of the human body identification counter corresponding to the card punch person is equal to 3, returning flag bit information of successful card punching as the human body identification result.
S103, carrying out face detection and face recognition on the picture to be recognized to obtain a face recognition result.
Referring to fig. 5, fig. 5 is a sub-flowchart diagram of step S103 in the method for checking attendance and checking card according to the embodiment of the present invention, which specifically includes the following sub-steps:
and S1031, obtaining preset card punch person information, and creating a face recognition counter with an initial value of 0 and a maximum value of 2 for each card punch person.
Respectively creating a face recognition counter with an initial value of 0 and a maximum value of 2 for each punch-card person in the preset punch-card person information, wherein the value of the face recognition counter represents the number of times that the human body feature information of the punch-card person is accurately recognized.
S1032, face detection is conducted on the picture to be recognized.
In the embodiment of the present invention, a tool for performing face detection on the picture to be recognized is still the image detector, wherein the image detector is used for performing face detection on the picture to be recognized, and according to whether a face image exists in the detected picture to be recognized, the method further includes:
1032a, if the picture to be recognized does not have the face image, directly carrying out target tracking on the human body image in the picture to be recognized.
If the image detector does not recognize any face image from the to-be-recognized image, but it is determined that the image has the human body image whose card punching is to be determined to be successful after the detection of the step S1022b, at this time, the corresponding human body image in the to-be-recognized image is additionally placed in a tracking queue, and target tracking is performed.
1032b, if at least one face image exists in the picture to be recognized, iris detection is started, meanwhile, a face feature extractor is used for sequentially extracting features of the face images, the face information of the punch card personnel in the preset punch card personnel information is compared, and the value of the face recognition counter corresponding to the punch card personnel, which is successfully compared, is added with 1.
If the image detector identifies at least one face image from the picture to be identified, step S104 is performed, and the human body feature extractor is continuously used to extract features of the face image, in the embodiment of the present invention, the face feature extractor is also composed of a convolutional neural network, but is dedicated to extracting features of the face image, the face features extracted by the face feature extractor are compared with the face feature information corresponding to the card punch, and the value of the face identification counter corresponding to the card punch who succeeds in comparison is added by 1, at this time, according to the value of the face identification counter corresponding to the card punch, the method further includes:
1032b1, if the numerical value of the face recognition counter corresponding to the card punch is smaller than 2, returning the numerical value of the face recognition counter as the face recognition result, and performing target tracking on the human body image corresponding to the card punch.
1032b2, if the value of the face recognition counter corresponding to the punch card personnel is equal to 2, returning a flag bit information of successful punch card as the face recognition result.
And S104, performing iris detection and iris recognition on the picture to be recognized to obtain an iris recognition result.
Referring to fig. 6, fig. 6 is a sub-flow block diagram of step S104 in the method for checking attendance and checking card according to the embodiment of the present invention, which specifically includes the following sub-steps:
s1041, obtaining preset card punch person information, and creating an iris identification counter with an initial value of 0 and a maximum value of 1 for each card punch person.
And respectively creating an iris identification counter with an initial value of 0 and a maximum value of 1 for each punch person in the preset punch person information, wherein the value of the iris identification counter represents the accurate identification times of the iris characteristic information of the punch person.
And S1042, carrying out iris detection on the picture to be recognized.
In the embodiment of the present invention, the means for performing iris detection on the picture to be recognized is still the image detector, wherein the image detector is used for performing iris detection on the picture to be recognized, and according to whether there is an iris image in the detected picture to be recognized, the method further includes:
1042a, if there is no iris image in the picture to be recognized, directly performing target tracking on the human body image in the picture to be recognized.
If the image detector does not recognize any iris image from the image to be recognized, but it is determined that the image has the human body image to be determined whether the card punching is successful after the detection of the step S1022b, and the human body image also passes the human face detection of the step S1023b, at this time, the human body image corresponding to the image to be recognized is taken as the whole tracking target, and is placed in a tracking queue for target tracking.
1042b, if there is at least one iris image in the picture to be identified, sequentially extracting features of the iris images by using an iris feature extractor, comparing the iris information of the punch card personnel in the preset punch card personnel information, and adding 1 to the numerical value of the iris identification counter corresponding to the punch card personnel which is successfully compared.
If the image detector identifies at least one iris image from the picture to be identified, the iris feature extractor is used for extracting the features of the iris image, the iris feature extractor is also composed of a convolutional neural network and is focused on the feature extraction of the iris image, the iris features extracted by the iris feature extractor are compared with the iris feature information corresponding to the person who checks the card, the numerical value of the iris identification counter corresponding to the person who checks the card successfully compared is added with 1, and at the moment, the method further comprises the following steps of:
1042b1, if the value of the iris recognition counter corresponding to the person who punches the card is less than 1, returning the value of the face recognition counter as the iris recognition result, and performing target tracking on the human body image corresponding to the person who punches the card.
1042b2, if the value of the iris recognition counter corresponding to the person who punches the card is equal to 1, directly returning a successful information of punching the card as the iris recognition result.
In the above steps S1032a, 1042a, performing target tracking on the to-be-identified pictures having the human body images, where the sequence of the target tracking is the sequence of the human body images being placed in the tracking queue, and for the to-be-identified pictures performing the target tracking, the human body images have a characteristic that the value of the corresponding human body identification counter is at least 1, but the corresponding human body identification result, the corresponding face identification result, and the corresponding iris identification result do not completely meet the judgment basis of successful card punching, the card punching personnel corresponding to the to-be-identified pictures in the tracking queue will continue to extract the human body feature information, the corresponding face feature information, and the corresponding iris feature information of the same card punching personnel when detecting the next frame of image, and the human body identification result, the to-be-identified picture having the human body images, are obtained according to the above steps, The face recognition result and the iris recognition result.
And S105, obtaining card punching feedback information according to the human body recognition result, the human face recognition result and the iris recognition result.
In the embodiment of the present invention, the human body recognition result, the human face recognition result, and the iris recognition result respectively correspond to values of the human body recognition counter, the human face recognition counter, and the iris recognition counter for different cardholders, and in the embodiment of the present invention, when a value of any one counter of the values of the counters reaches a preset maximum value, it is determined that the cardholder has successfully carded the card, and more specifically, in the whole process of detecting and recognizing the picture to be recognized, if the human body feature information of the cardholder is successfully recognized 3 times, or the human face feature information is successfully recognized 2 times, or the iris feature information is successfully recognized 1 time, it is determined that the cardholder has successfully cardholder the card, and meanwhile, in the embodiment of the present invention, the human body feature information of the cardholder is successfully recognized 1 time, And if the face feature information is successfully recognized for 1 time, the card punching is also determined to be successful.
And then, sending the information of successful card punching of the card punching personnel as the card punching feedback information to the card punching personnel for confirmation.
Preferably, the method further includes presetting a card punching time period, and the card punching personnel who do not successfully punch the card in the card punching time period will receive the card punching feedback information for reminding card replenishment at the end of the card punching time period.
The invention has the advantages that the card punching scheme which combines a plurality of identification modes and identifies simultaneously is adopted, so that the card punching accuracy is improved in the face of a middle-distance and long-distance real scene, the false detection rate is reduced, and the time of the card punching detection process is shortened.
Referring to fig. 7, fig. 7 is a block diagram of a structure of a non-inductive attendance card punching system according to an embodiment of the present invention, where the non-inductive attendance card punching system 200 includes a data acquisition module 201, a human body detection and identification module 202, a human face detection and identification module 203, an iris detection and identification module 204, a target tracking module 205, and a card punching information feedback module 206, where:
the data obtaining module 201 is configured to obtain video stream data, and decode the video stream data to obtain a picture to be identified;
the human body detection and identification module 202 is configured to perform human body detection and human body identification on the picture to be identified to obtain a human body identification result;
the face detection and recognition module 203 is configured to perform face detection and face recognition on the picture to be recognized to obtain a face recognition result;
the iris detection and recognition module 204 is configured to perform iris detection and iris recognition on the picture to be recognized to obtain an iris recognition result;
the punch card information feedback module 205 is configured to obtain punch card feedback information according to the human body recognition result, the face recognition result, and the iris recognition result.
The system 200 for checking attendance record can implement the steps in the method for checking attendance record in the above embodiment and achieve the same technical effects, and is not described herein again with reference to the description of the above embodiment.
Referring to fig. 8, fig. 8 is a schematic structural diagram of a computer device provided in an embodiment of the present invention, where the computer device 300 includes: a memory 302, a processor 301, and a computer program stored on the memory 302 and executable on the processor 301.
The processor 301 calls the computer program stored in the memory 302 to execute the steps of the method for checking attendance without sensing provided by the embodiment of the present invention, and with reference to fig. 1, the method specifically includes:
s101, video stream data is obtained, and a picture to be identified is obtained by decoding the video stream data.
Further, the step of obtaining video stream data and decoding the video stream data to obtain the picture to be identified includes the following sub-steps:
acquiring real-time video stream data from video acquisition equipment, and performing frame extraction according to a preset frame interval to obtain a frame extraction image;
and preprocessing the frame-extracted image to obtain the picture to be identified.
S102, carrying out human body detection and human body identification on the picture to be identified to obtain a human body identification result.
Further, the step of performing human body detection and human body recognition on the picture to be recognized to obtain a human body recognition result comprises the following substeps:
acquiring preset card punching personnel information, and creating a human body identification counter with an initial value of 0 and a maximum value of 3 for each card punching personnel;
and carrying out human body detection on the picture to be recognized, wherein:
if no human body image exists in the picture to be recognized, directly starting the processing of the picture to be recognized of the next frame;
if at least one human body image exists in the picture to be identified, starting to perform face detection, simultaneously sequentially performing feature extraction on the human body images by using a human body feature extractor, comparing the human body information of the card punch personnel in the preset card punch personnel information, and adding 1 to the numerical value of the human body identification counter corresponding to the card punch personnel which is successfully compared, wherein:
if the value of the human body identification counter corresponding to the card punch is smaller than 3, returning the value of the human body identification counter as the human body identification result, and carrying out target tracking on the human body image corresponding to the card punch;
and if the value of the human body identification counter corresponding to the card punch is equal to 3, returning a flag bit information of successful card punching as the human body identification result.
S103, carrying out face detection and face recognition on the picture to be recognized to obtain a face recognition result.
Further, the step of performing face detection and face recognition on the picture to be recognized to obtain a face recognition result includes the following substeps:
acquiring preset card punching personnel information, and creating a face recognition counter with an initial value of 0 and a maximum value of 2 for each card punching personnel;
carrying out face detection on the picture to be recognized, wherein:
if the picture to be recognized does not have the face image, directly carrying out target tracking on the human body image in the picture to be recognized;
if at least one face image exists in the picture to be recognized, iris detection is started, meanwhile, a face feature extractor is used for sequentially extracting features of the face images, the face information of the punch card personnel in the preset punch card personnel information is compared, and the numerical value of the face recognition counter corresponding to the punch card personnel, which is successfully compared, is added with 1, wherein:
if the numerical value of the face recognition counter corresponding to the card punch is smaller than 2, returning the numerical value of the face recognition counter as the face recognition result, and carrying out target tracking on the human body image corresponding to the card punch;
and if the numerical value of the face recognition counter corresponding to the card punch personnel is equal to 2, returning a flag bit information of successful card punching as the face recognition result.
And S104, performing iris detection and iris recognition on the picture to be recognized to obtain an iris recognition result.
Furthermore, the step of performing iris detection and iris recognition on the picture to be recognized to obtain an iris recognition result comprises the following substeps:
acquiring preset card punching personnel information, and creating an iris identification counter with an initial value of 0 and a maximum value of 1 for each card punching personnel;
carrying out iris detection on the picture to be identified, wherein:
if the picture to be recognized does not have the iris image, directly carrying out target tracking on the face image in the picture to be recognized;
if at least one iris image exists in the picture to be identified, an iris feature extractor is utilized to sequentially extract the features of the iris images, the iris information of the card punch personnel in the preset card punch personnel information is compared, and the numerical value of the iris identification counter corresponding to the card punch personnel, which is successfully compared, is added with 1, wherein:
if the numerical value of the iris recognition counter corresponding to the card punch is smaller than 1, returning the numerical value of the face recognition counter as the iris recognition result, and carrying out target tracking on the human body image corresponding to the card punch;
and if the numerical value of the iris identification counter corresponding to the card punch is equal to 1, directly returning a successful card punch information as the iris identification result.
Furthermore, after the step of performing iris detection and iris recognition on the picture to be recognized to obtain an iris recognition result, the method further comprises the following steps:
storing the human body image subjected to target tracking in a tracking queue by using a preset target tracking algorithm, carrying out human body detection and human body recognition, human face detection and human face recognition, iris detection and iris recognition on the human body image in the tracking queue in the picture to be recognized of the next frame, and deleting the human body image from the tracking queue if the human body recognition result of the card punch corresponding to the human body image, or the human face recognition result, or the iris recognition result contains information of successful card punching.
And S105, obtaining card punching feedback information according to the human body recognition result, the human face recognition result and the iris recognition result.
Further, the step of obtaining the card punching feedback information according to the human body recognition result, the human face recognition result and the iris recognition result specifically comprises:
if the human body recognition result is the zone bit information, or the human face recognition result is the zone bit information, or the iris recognition result is the successful card punching information, the card punching personnel corresponding to the human body recognition result, the human face recognition result and the iris recognition result are judged to be in a card punching state, and the numerical values of the human body recognition counter, the human face recognition counter and the iris recognition counter of the card punching personnel are reset.
The computer device 300 provided in the embodiment of the present invention can implement the steps in the non-sensitive attendance checking method in the above embodiments, and can implement the same technical effects, and reference is made to the description in the above embodiments, and details are not repeated here.
The embodiment of the invention also provides a computer-readable storage medium, wherein a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program realizes each process and step in the non-inductive attendance card-reading method provided by the embodiment of the invention, and can realize the same technical effect, and in order to avoid repetition, the detailed description is omitted here.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal (such as a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present invention.
While the present invention has been described with reference to the preferred embodiments, it is to be understood that the invention is not limited to the disclosed embodiments, which are illustrative, but not restrictive, and that various changes may be made therein by those skilled in the art without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (9)
1. A non-inductive attendance card punching method is characterized by comprising the following steps:
acquiring video stream data, and decoding the video stream data to obtain a picture to be identified;
carrying out human body detection and human body identification on the picture to be identified to obtain a human body identification result;
carrying out face detection and face recognition on the picture to be recognized to obtain a face recognition result;
performing iris detection and iris recognition on the picture to be recognized to obtain an iris recognition result;
obtaining card punching feedback information according to the human body recognition result, the face recognition result and the iris recognition result;
the step of carrying out human body detection and human body identification on the picture to be identified to obtain a human body identification result comprises the following substeps:
acquiring preset card punching personnel information, and creating a human body identification counter with an initial value of 0 and a maximum value of 3 for each card punching personnel;
and carrying out human body detection on the picture to be recognized, wherein:
if no human body image exists in the picture to be recognized, directly starting the processing of the picture to be recognized of the next frame;
if at least one human body image exists in the picture to be identified, starting to perform face detection, simultaneously sequentially performing feature extraction on the human body images by using a human body feature extractor, comparing the human body information of the card punch personnel in the preset card punch personnel information, and adding 1 to the numerical value of the human body identification counter corresponding to the card punch personnel which is successfully compared, wherein:
if the value of the human body identification counter corresponding to the card punch is smaller than 3, returning the value of the human body identification counter as the human body identification result, and carrying out target tracking on the human body image corresponding to the card punch;
and if the value of the human body identification counter corresponding to the card punch is equal to 3, returning a flag bit information of successful card punching as the human body identification result.
2. The method for checking attendance and checking card according to claim 1, wherein the steps of obtaining video stream data and decoding the video stream data to obtain the picture to be identified comprise the following substeps:
acquiring real-time video stream data from video acquisition equipment, and performing frame extraction according to a preset frame interval to obtain a frame extraction image;
and preprocessing the frame-extracted image to obtain the picture to be identified.
3. The method for checking attendance and checking card according to claim 1, wherein the step of performing face detection and face recognition on the picture to be recognized to obtain a face recognition result comprises the following substeps:
acquiring preset card punching personnel information, and creating a face recognition counter with an initial value of 0 and a maximum value of 2 for each card punching personnel;
carrying out face detection on the picture to be recognized, wherein:
if the picture to be recognized does not have the face image, directly carrying out target tracking on the human body image in the picture to be recognized;
if at least one face image exists in the picture to be recognized, iris detection is started, meanwhile, a face feature extractor is used for sequentially extracting features of the face images, the face information of the punch card personnel in the preset punch card personnel information is compared, and the numerical value of the face recognition counter corresponding to the punch card personnel, which is successfully compared, is added with 1, wherein:
if the numerical value of the face recognition counter corresponding to the card punch is smaller than 2, returning the numerical value of the face recognition counter as the face recognition result, and carrying out target tracking on the human body image corresponding to the card punch;
and if the numerical value of the face recognition counter corresponding to the card punch personnel is equal to 2, returning a flag bit information of successful card punching as the face recognition result.
4. The method for checking attendance and checking card according to claim 3, wherein the step of performing iris detection and iris recognition on the picture to be recognized to obtain an iris recognition result comprises the following substeps:
acquiring preset card punching personnel information, and creating an iris identification counter with an initial value of 0 and a maximum value of 1 for each card punching personnel;
carrying out iris detection on the picture to be identified, wherein:
if the picture to be recognized does not have the iris image, directly carrying out target tracking on the human body image in the picture to be recognized;
if at least one iris image exists in the picture to be identified, an iris feature extractor is utilized to sequentially extract the features of the iris images, the iris information of the card punch personnel in the preset card punch personnel information is compared, and the numerical value of the iris identification counter corresponding to the card punch personnel, which is successfully compared, is added with 1, wherein:
if the numerical value of the iris recognition counter corresponding to the card punch is smaller than 1, returning the numerical value of the face recognition counter as the iris recognition result, and carrying out target tracking on the human body image corresponding to the card punch;
and if the numerical value of the iris identification counter corresponding to the card punch is equal to 1, directly returning a successful card punch information as the iris identification result.
5. The method for checking attendance and checking card according to claim 4, wherein after the steps of performing iris detection and iris recognition on the picture to be recognized and obtaining the iris recognition result, the method further comprises:
storing the human body image subjected to target tracking in a tracking queue by using a preset target tracking algorithm, carrying out human body detection and human body recognition, human face detection and human face recognition, iris detection and iris recognition on the human body image in the tracking queue in the picture to be recognized of the next frame, and deleting the human body image from the tracking queue if the human body recognition result of the card punch corresponding to the human body image, or the human face recognition result, or the iris recognition result contains information of successful card punching.
6. The method for checking attendance according to claim 5, wherein the step of obtaining the checking-card feedback information according to the human body recognition result, the human face recognition result and the iris recognition result comprises:
if the human body recognition result is the zone bit information, or the human face recognition result is the zone bit information, or the iris recognition result is the successful card punching information, the card punching personnel corresponding to the human body recognition result, the human face recognition result and the iris recognition result are judged to be in a card punching state, and the numerical values of the human body recognition counter, the human face recognition counter and the iris recognition counter of the card punching personnel are reset.
7. A noninductive attendance card punching system is characterized by comprising:
the data acquisition module is used for acquiring video stream data and decoding the video stream data to obtain a picture to be identified;
the human body detection and identification module is used for carrying out human body detection and human body identification on the picture to be identified to obtain a human body identification result;
the face detection and recognition module is used for carrying out face detection and face recognition on the picture to be recognized to obtain a face recognition result;
the iris detection and identification module is used for carrying out iris detection and iris identification on the picture to be identified to obtain an iris identification result;
the card punching information feedback module is used for obtaining card punching feedback information according to the human body recognition result, the face recognition result and the iris recognition result;
the step of carrying out human body detection and human body identification on the picture to be identified to obtain a human body identification result comprises the following substeps:
acquiring preset card punching personnel information, and creating a human body identification counter with an initial value of 0 and a maximum value of 3 for each card punching personnel;
and carrying out human body detection on the picture to be recognized, wherein:
if no human body image exists in the picture to be recognized, directly starting the processing of the picture to be recognized of the next frame;
if at least one human body image exists in the picture to be identified, starting to perform face detection, simultaneously sequentially performing feature extraction on the human body images by using a human body feature extractor, comparing the human body information of the card punch personnel in the preset card punch personnel information, and adding 1 to the numerical value of the human body identification counter corresponding to the card punch personnel which is successfully compared, wherein:
if the value of the human body identification counter corresponding to the card punch is smaller than 3, returning the value of the human body identification counter as the human body identification result, and carrying out target tracking on the human body image corresponding to the card punch;
and if the value of the human body identification counter corresponding to the card punch is equal to 3, returning a flag bit information of successful card punching as the human body identification result.
8. A computer device, comprising: memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps in the sensorless attendance card punching method according to any one of claims 1 to 6 when executing the computer program.
9. A computer-readable storage medium, having stored thereon a computer program which, when executed by a processor, implements the steps in the method of noninductive attendance checking according to any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111240622.8A CN113689585B (en) | 2021-10-25 | 2021-10-25 | Non-inductive attendance card punching method, system and related equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111240622.8A CN113689585B (en) | 2021-10-25 | 2021-10-25 | Non-inductive attendance card punching method, system and related equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113689585A CN113689585A (en) | 2021-11-23 |
| CN113689585B true CN113689585B (en) | 2022-01-04 |
Family
ID=78587800
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111240622.8A Active CN113689585B (en) | 2021-10-25 | 2021-10-25 | Non-inductive attendance card punching method, system and related equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113689585B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114253614A (en) * | 2021-11-25 | 2022-03-29 | 上海齐感电子信息科技有限公司 | Control method and control system |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2013029954A (en) * | 2011-07-28 | 2013-02-07 | Ricoh Co Ltd | Attendance state improvement support system, device, method, program, and recording medium |
| CN104851140A (en) * | 2014-12-12 | 2015-08-19 | 重庆凯泽科技有限公司 | Face recognition-based attendance access control system |
| CN107766234A (en) * | 2017-08-31 | 2018-03-06 | 广州数沃信息科技有限公司 | A kind of assessment method, the apparatus and system of the webpage health degree based on mobile device |
| CN107833306A (en) * | 2017-12-15 | 2018-03-23 | 南京工业职业技术学院 | The intelligent check class attendance system of face and iris feature fusion recognition |
| CN109102582A (en) * | 2018-08-03 | 2018-12-28 | 四川民工加网络科技有限公司 | Attendance recognition methods and device |
| CN109360132B (en) * | 2018-11-30 | 2021-02-12 | 惠州市耀昇科技有限公司 | Campus management method based on face recognition |
-
2021
- 2021-10-25 CN CN202111240622.8A patent/CN113689585B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN113689585A (en) | 2021-11-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109858371B (en) | Face recognition method and device | |
| CN109508694B (en) | Face recognition method and recognition device | |
| US10210415B2 (en) | Method and system for recognizing information on a card | |
| CN107944427B (en) | Dynamic face recognition method and computer readable storage medium | |
| CN111339806B (en) | Training method of lip language recognition model, living body recognition method and device | |
| CN107111755B (en) | Video counterfeit detection method and system based on liveness evaluation | |
| CN111263955A (en) | Method and device for determining movement track of target object | |
| CN110738103A (en) | Living body detection method, living body detection device, computer equipment and storage medium | |
| CN110599129A (en) | Campus attendance checking method, device, identification terminal and system based on image tracking | |
| CN111079687A (en) | Certificate camouflage identification method, device, equipment and storage medium | |
| CN113689585B (en) | Non-inductive attendance card punching method, system and related equipment | |
| CN114677607A (en) | Real-time pedestrian counting method and device based on face recognition | |
| CN110705469A (en) | Face matching method and device and server | |
| CN112016437B (en) | Living body detection method based on face video key frame | |
| CN113869110A (en) | Article detection method, device, terminal and computer readable storage medium | |
| CN112183167B (en) | Attendance checking method, authentication method, living body detection method, device and equipment | |
| CN114266267B (en) | Automatic identification method, device and storage medium for integrating two-dimension codes, documents, certificates and faces | |
| CN110956093A (en) | Big data-based model identification method, device, equipment and medium | |
| CN110795980A (en) | Network video-based evasion identification method, equipment, storage medium and device | |
| US20220405527A1 (en) | Target Detection Methods, Apparatuses, Electronic Devices and Computer-Readable Storage Media | |
| CN116152908A (en) | Method and device for identifying actions, detecting living bodies and training models, and electronic equipment | |
| CN111242189B (en) | Feature extraction method and device and terminal equipment | |
| CN112307916A (en) | Alarm monitoring method based on visible light camera | |
| CN114463820A (en) | Face positioning method, device, equipment and medium | |
| CN117542124A (en) | Face video depth forging detection method and device |
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 | ||
| PP01 | Preservation of patent right |
Effective date of registration: 20240109 Granted publication date: 20220104 |