CN109919035A - Improve method, apparatus, computer equipment and storage medium that attendance is identified by - Google Patents
Improve method, apparatus, computer equipment and storage medium that attendance is identified by Download PDFInfo
- Publication number
- CN109919035A CN109919035A CN201910100428.6A CN201910100428A CN109919035A CN 109919035 A CN109919035 A CN 109919035A CN 201910100428 A CN201910100428 A CN 201910100428A CN 109919035 A CN109919035 A CN 109919035A
- Authority
- CN
- China
- Prior art keywords
- identification
- face
- attendance
- photo
- personnel
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Abstract
This application involves technical field of face recognition, in particular to a kind of method, apparatus, computer equipment and storage medium for improving attendance and being identified by.The described method includes: obtaining real-time face when recognition result of the attendance identifying system to the face attendance identification of personnel is to be identified by and identifying photo;Whether the quality for detecting real-time face identification photo is qualified;If detecting the quality of real-time face identification as qualification, by real-time face identification photo, the corresponding base map in base map library is compared with personnel, obtains similarity;Similarity is compared with preset threshold;It, will be in real-time face identification photo deposit identification library if similarity is greater than preset threshold;When attendance identifying system carries out face attendance identification to personnel again, the human face photo of personnel is identified with base map library, identification library simultaneously.The problem of aiming to solve the problem that in existing face attendance checking system, needing periodically artificial acquisition photo, lead to waste of manpower resource.
Description
Technical field
This application involves technical field of face recognition, in particular to a kind of to improve method, apparatus, the meter that attendance is identified by
Calculate machine equipment and storage medium.
Background technique
Recognition of face is a kind of biological identification technology for carrying out identification based on facial feature information of people.With camera shooting
Machine or camera acquire image or video flowing containing face, and automatic detection and tracking face in the picture, and then to detection
The face that arrives carries out a series of the relevant technologies of face recognition, usually also referred to as Identification of Images, face recognition.Current most of public affairs
The system that department uses face attendance, recognition of face require to regularly update percent of pass of employee's photo to guarantee recognition of face.It is right
It is also a no small workload that personnel's photo is collected for the company of a relatively large-scale, because regularly artificial acquisition is shone
Piece, the problem of leading to waste of manpower resource.
Apply for content
In view of the shortcomings of the prior art, the application proposes a kind of method, apparatus, computer equipment that raising attendance is identified by
And storage medium, it is intended to solve in existing face attendance checking system, need periodically artificial acquisition photo, waste of manpower is caused to provide
The problem of source.
The technical solution that the application proposes is:
A method of it improving attendance and is identified by, which comprises
When recognition result of the attendance identifying system to the face attendance identification of personnel is to be identified by, real-time face is obtained
Identify photo;
Whether the quality for detecting the real-time face identification photo is qualified;
If detecting, the quality of the real-time face identification is qualification, by real-time face identification photo and the people
Member's corresponding base map in base map library is compared, and obtains similarity;
The similarity is compared with preset threshold;
It, will be in real-time face identification photo deposit identification library if the similarity is greater than the preset threshold;
When the attendance identifying system carries out face attendance identification to the personnel again, the face of the personnel is shone
Piece is identified with the base map library, the identification library simultaneously;
If the photo successful match in the human face photo of the personnel and the base map library or the identification library, determines
The attendance identifying system is to be identified by the recognition result of the face attendance identification of the personnel.
Further, in the quality of detection real-time face identification photo whether in He Ge step, comprising:
Photo is identified according to the real-time face, obtains human face posture;
Judge the pitch angle of the human face posture whether in the range of pitch angle threshold value;
If the pitch angle of the human face posture not in the range of the pitch angle threshold value, determines that the real-time face is known
The quality of other photo is unqualified;
If the pitch angle of the human face posture is to judge the human face posture in the range of pitch angle threshold value
Whether yaw angle is in the range of yaw angle threshold value;
If the yaw angle of the human face posture is to determine that the real-time face is known in the range of the yaw angle threshold value
The quality of other photo is qualification;
If the yaw angle of the human face posture not in the range of the yaw angle threshold value, determines that the real-time face is known
The quality of other photo is unqualified.
It further, is to be identified by recognition result of the attendance identifying system to the face attendance identification of personnel described
When, obtain real-time face identification photo the step of before, comprising:
Detect the recognition result of face attendance identification of the attendance identifying system to personnel;
If the recognition result is that identification does not pass through, judge whether the order for receiving the typing for the first time of user's input;
If receiving the order, real-time face identification photo is obtained.
It further, is to be identified by recognition result of the attendance identifying system to the face attendance identification of personnel described
When, it obtains in the step of real-time face identifies photo, comprising:
When recognition result of the attendance identifying system to the face attendance identification of personnel is to be identified by, the personnel are detected
With the presence or absence of recognition failures before the recognition result of face attendance identification is to be identified by;
If detect the personnel before the recognition result that face attendance identifies is to be identified by there are recognition failures,
It obtains real-time face and identifies photo.
It further, is to be identified by recognition result of the attendance identifying system to the face attendance identification of personnel described
When, it obtains in the step of real-time face identifies photo, comprising:
When recognition result of the attendance identifying system to the face attendance identification of personnel is to be identified by, then the people is obtained
Member's time required when carrying out face attendance identification, obtain recognition time;
The recognition time is compared with time threshold;
If the recognition time is greater than the time threshold, real-time face identification photo is obtained.
Further, if being greater than the preset threshold in the similarity, the real-time face is identified into photo
In step in deposit identification library, comprising:
If the similarity is greater than the preset threshold, number of pictures of the personnel in the identification library is identified,
Obtain the number of pictures of typing;
The number of pictures of the typing is compared with amount threshold;
If the number of pictures of the typing is less than the amount threshold, real-time face identification photo deposit is known
In other library;
If the number of pictures of the typing is less than or equal to the amount threshold, from the number of pictures of the typing
An earliest photo of entry time is identified in amount, obtains photo to be replaced;
Real-time face identification photo is replaced into the photo to be replaced, deposit identifies in library.
Further, if in the human face photo of the personnel and the base map library or the photo identified in library
Successful match then determines that the recognition result of face attendance identification of the attendance identifying system to the personnel is identified by
After step, comprising:
Record the multiple attendance identification record of the personnel;
According to the multiple attendance identification record, human face photo and the base map Kucheng function for obtaining the personnel are matched
Number, obtains first number, and obtains the human face photo and the matched number of identification Kucheng's function of the personnel, acquisition the
Two numbers;
First number is compared with second number;
If second number is greater than first number, by the personnel, corresponding photo is replaced in the identification library
Change the personnel corresponding base map in the base map library.
The application also provides a kind of device that raising attendance is identified by, and described device includes:
Module is obtained, for being to be identified by recognition result of the attendance identifying system to the face attendance identification of personnel
When, it obtains real-time face and identifies photo;
Whether detection module, the quality for detecting the real-time face identification photo are qualified;
First comparison module, if for detecting that the quality of the real-time face identification is qualification, by the real-time people
Face identifies that the corresponding base map in base map library is compared photo with the personnel, obtains similarity;
Second comparison module, for the similarity to be compared with preset threshold;
Memory module deposits real-time face identification photo if being greater than the preset threshold for the similarity
Enter to identify in library;
Identification module is used for when the attendance identifying system carries out face attendance identification to the personnel again, by institute
It states the human face photo of personnel while being identified with the base map library, the identification library;
Determination module, if for the personnel human face photo and the base map library or it is described identification library in photo at
Function matching then determines that the recognition result of face attendance identification of the attendance identifying system to the personnel is to be identified by.
The application also provides a kind of computer equipment, including memory and processor, and the memory is stored with computer
The step of program, the processor realizes method described in any of the above embodiments when executing the computer program.
The application also provides a kind of computer readable storage medium, is stored thereon with computer program, the computer journey
The step of method described in any of the above embodiments is realized when sequence is executed by processor.
According to above-mentioned technical solution, the application is the utility model has the advantages that identify the face attendance of personnel in attendance identifying system
Recognition result be to obtain real-time face and identify photo, then examined to the quality of real-time face identification photo when being identified by
It surveys, when it is qualified for detecting its quality, then the similarity of real-time face identification photo and corresponding base map is obtained, in similarity
When greater than threshold value, by real-time face identification photo deposit identification library, then when the next progress face attendance identification to personnel, by personnel
Human face photo identified simultaneously with base map library, identification library, improve the time being identified by and be identified by rate, solve because
The problem of more new photo does not cause recognition time long or recognition failures for a long time, and solve in existing face attendance checking system
In, the problem of needing periodically artificial acquisition photo, lead to waste of manpower resource.
Detailed description of the invention
Fig. 1 is the flow chart for the method being identified by using raising attendance provided by the embodiments of the present application;
Fig. 2 is the functional block diagram for the device being identified by using raising attendance provided by the embodiments of the present application;
Fig. 3 is the structural schematic block diagram using computer equipment provided by the embodiments of the present application.
Specific embodiment
It is with reference to the accompanying drawings and embodiments, right in order to which the objects, technical solutions and advantages of the application are more clearly understood
The application is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the application, and
It is not used in restriction the application.
As shown in Figure 1, the embodiment of the present application proposes a kind of method that raising attendance is identified by, the method includes following
Step:
Step S101, it when recognition result of the attendance identifying system to the face attendance identification of personnel is to be identified by, obtains
Real-time face is taken to identify photo.
When recognition result of the attendance identifying system to the face attendance identification of personnel is to be identified by, the reality of personnel is obtained
When recognition of face photo, in the present embodiment, pass through camera shoot acquisition personnel real-time face identify photo.
In the present embodiment, before step S101, comprising:
Establish identification library.
Identification library is established, identification library is closed for storing real-time face identification photo, identification library and face attendance identifying system
Connection, when recognition result of the attendance identifying system to the face attendance identification of personnel is to be identified by, identification library is used for and personnel
Real-time face identification photo identified.
In some embodiments, before step S101, comprising:
Detect the recognition result of face attendance identification of the attendance identifying system to personnel;
If the recognition result is that identification does not pass through, judge whether the order for receiving the typing for the first time of user's input;
If receiving the order, real-time face identification photo is obtained.
It is obstructed out-of-date identifying, it may be possible to which that New Hire Onboarding needs by the photo typing of new employee, in such case
Under, need user to input the order of typing for the first time, thus available real-time face identifies photo, without carrying out hand
The photo of work typing new employee.
In the present embodiment, in step s101, comprising:
When attendance identifying system carries out face attendance identification to personnel, the knowledge of the face attendance identification of the personnel is identified
Other result;
If the recognition result that the face attendance of the personnel identifies is to be identified by, real-time face identification photo is obtained.
When attendance identifying system carries out face attendance identification to personnel, carried out to whether personnel pass through face attendance identification
Identification, if recognizing personnel can be identified by face attendance, illustrates that personnel are examined in face attendance identifying system
Diligent personnel, the real-time face identification photo for obtaining personnel illustrate people if recognizing personnel cannot be identified by face attendance
Member is not the personnel for needing to carry out attendance in face attendance identifying system, does not obtain the real-time face identification photo of personnel.
In some embodiments, in step s101, comprising:
When recognition result of the attendance identifying system to the face attendance identification of personnel is to be identified by, the personnel are detected
With the presence or absence of recognition failures before the recognition result of face attendance identification is to be identified by;
If detect the personnel before the recognition result that face attendance identifies is to be identified by there are recognition failures,
It obtains real-time face and identifies photo.
In face attendance identification process of the attendance identifying system to personnel, may there are the case where repeatedly identification, example
Such as, personnel A identifies 4 times in total in face attendance identification, is 3 times recognition failures, and the 4th, which is only, to be identified by,
When recognition result of the attendance identifying system to the face attendance identification of personnel is to be identified by, if identifying, personnel pass through face
Attendance identification, then testing staff whether there is recognition failures before identifying by face attendance, if detecting personnel logical
It crosses before face attendance identification there are recognition failures, illustrates that personnel's recognition success rate in face attendance identifying system is low, obtain
Real-time face identifies photo, if detecting personnel, there is no recognition failures before being identified by face attendance, illustrates personnel
Recognition success rate is high in face attendance identifying system, does not obtain real-time face identification photo.
In some embodiments, in step s101, comprising:
When recognition result of the attendance identifying system to the face attendance identification of personnel is to be identified by,
The personnel time required when carrying out face attendance identification is then obtained, recognition time is obtained;
The recognition time is compared with time threshold;
If the recognition time is greater than the time threshold, real-time face identification photo is obtained.
When recognition result of the attendance identifying system to the face attendance of personnel identification is to be identified by, obtain personnel into
Pedestrian's face attendance recognition time required when identifying judges the efficiency of face attendance identification, will know according to the length of recognition time
The other time is compared with time threshold, if recognition time is greater than time threshold, illustrates personnel in face attendance identifying system
Middle recognition efficiency is low, then obtains real-time face identification photo if recognition time is less than or equal to time threshold and illustrate personnel
Recognition efficiency is high in face attendance identifying system, then does not obtain real-time face identification photo.
Step S102, whether the quality for detecting the real-time face identification photo is qualified.
After obtaining real-time face identification photo, the quality of detection real-time face identification photo, according to the matter detected
Amount, judges whether qualification.
In the present embodiment, in step s 102, comprising:
Photo is identified according to the real-time face, obtains human face posture;
Judge the pitch angle of the human face posture whether in the range of pitch angle threshold value;
If the pitch angle of the human face posture not in the range of the pitch angle threshold value, determines that the real-time face is known
The quality of other photo is unqualified;
If the pitch angle of the human face posture is to judge the human face posture in the range of pitch angle threshold value
Whether yaw angle is in the range of yaw angle threshold value;
If the yaw angle of the human face posture is to determine that the real-time face is known in the range of the yaw angle threshold value
The quality of other photo is qualification;
If the yaw angle of the human face posture not in the range of the yaw angle threshold value, determines that the real-time face is known
The quality of other photo is unqualified.
After obtaining real-time face identification photo, photo is identified according to real-time face, human face posture is obtained, according to face
Posture obtains the pitch angle and yaw angle of human face posture, according to the pitch angle and yaw angle of human face posture, judges that real-time face is known
Whether the quality of other photo is qualified.
In the present embodiment, pitch angle threshold value is (- 20 ° ,+20 °), and yaw angle threshold value is (- 35 ° ,+35 °).
If the quality for step S103, detecting the real-time face identification is qualification, the real-time face is identified and is shone
The corresponding base map in base map library is compared piece with the personnel, obtains similarity.
It is corresponding in base map library from personnel are obtained in base map library when it is qualified for detecting the quality of real-time face identification
Real-time face after corresponding base map, is identified photo and personnel in base map library by base map in the personnel that get in base map library
Corresponding base map is compared, and obtains similarity.
In the present embodiment, the characteristic point for extracting real-time face photo, by the characteristic point of real-time face photo and real-time people
The corresponding base map of face photo is matched, and according to the quantity for the characteristic point being matched to, corresponding similarity is calculated, to obtain phase
Like degree.
Step S104, the similarity is compared with preset threshold.
After obtaining similarity, similarity is compared with preset threshold, according to comparison result, is judged whether reality
When recognition of face photo deposit identification library in.
If step S105, the described similarity is greater than the preset threshold, real-time face identification photo deposit is known
In other library.
If similarity is greater than preset threshold, illustrate that real-time face identification photo meets identification library storage condition, it will be real-time
In recognition of face photo deposit identification library, the photo as identification library.
In the present embodiment, same personnel are limited in the real-time face identification number of pictures of identification library storage,
In step S105, comprising:
If the similarity is greater than the preset threshold, number of pictures of the personnel in the identification library is identified,
Obtain the number of pictures of typing;
The number of pictures of the typing is compared with amount threshold;
If the number of pictures of the typing is less than the amount threshold, real-time face identification photo deposit is known
In other library;
If the number of pictures of the typing is less than or equal to the amount threshold, from the number of pictures of the typing
An earliest photo of entry time is identified in amount, obtains photo to be replaced;
Real-time face identification photo is replaced into the photo to be replaced, deposit identifies in library.
If similarity is greater than preset threshold, number of pictures of the identification personnel in identification library, according to identifying number of pictures
Amount obtains the number of pictures of typing, after the number of pictures for obtaining typing, by the number of pictures of typing and quantity threshold
Value is compared, and according to comparison result, the mode in deposit identification library is determined, if the number of pictures of typing is less than quantity threshold
Value, by real-time face identification photo deposit identification library in, as identification library photo, if the number of pictures of typing be less than or
Equal to amount threshold, then an earliest photo of entry time is identified from the number of pictures of typing, obtains photograph to be replaced
Real-time face identification photo is replaced photo to be replaced, deposit identifies in library, as knowledge after obtaining photo to be replaced by piece
The photo in other library.
Step S106, when the attendance identifying system carries out face attendance identification to the personnel again, by the people
The human face photo of member is identified with the base map library, the identification library simultaneously.
After real-time face identification photo deposit identification library, when the attendance identifying system carries out face to personnel again
When attendance identifies, the human face photo of personnel and base map library are identified, meanwhile, the human face photo of personnel and identification library are carried out
Identification increases the identification in identification library and the human face photo of personnel, improves attendance identification, and does not need manually to acquire photo progress
Replacement.
If the photo success in the human face photo of step S107, the described personnel and the base map library or the identification library
Match, then determines that the recognition result of face attendance identification of the attendance identifying system to the personnel is to be identified by.
Base map library and identification library all can serve as picture required for the identification of attendance identifying system, in human face photo and bottom
The photo successful match of picture library, identification library in any one, all thinks to be identified by, and improves attendance and is identified by.
In the present embodiment, after step S107, comprising:
Record the multiple attendance identification record of the personnel;
According to the multiple attendance identification record, human face photo and the base map Kucheng function for obtaining the personnel are matched
Number, obtains first number, and obtains the human face photo and the matched number of identification Kucheng's function of the personnel, acquisition the
Two numbers;
First number is compared with second number;
Second number is greater than first number, then the corresponding photo replacement in the identification library by the personnel
The personnel corresponding base map in the base map library.
The multiple attendance identification record of record personnel, attendance identification record include that the human face photo of personnel is and base map Kucheng
Function matching, or human face photo and the base map Kucheng of personnel are obtained according to multiple attendance identification record with identification library successful match
The matched number of function obtains first number, and according to multiple attendance identification record, obtains human face photo and the identification library of personnel
The number of successful match obtains second number, after obtaining first number and second number, by first several and second number
It is compared, according to comparing, judges whether to need replacing personnel's corresponding base map in base map library, if second number is greater than first
Number, then by personnel, corresponding photo replaces personnel's corresponding base map in base map library in identification library, if second number is less than
Or be equal to first number, then by personnel, corresponding photo replaces personnel's corresponding base map in base map library in identification library.
In conclusion being obtained when recognition result of the attendance identifying system to the face attendance identification of personnel is to be identified by
It takes real-time face to identify photo, then the quality of real-time face identification photo is detected, when it is qualified for detecting its quality,
The similarity for obtaining real-time face identification photo and corresponding base map again identifies real-time face when similarity is greater than threshold value
Photo deposit identification library, then next time to personnel carry out face attendance identification when, by the human face photo of personnel simultaneously with base map library, know
Other library is identified, is improved the time being identified by and is identified by rate, is solved because more new photo does not cause to identify for a long time
The problem of time length or recognition failures, and solve in existing face attendance checking system, periodically artificial acquisition photo is needed,
The problem of leading to waste of manpower resource.
As shown in Fig. 2, the embodiment of the present application proposes that a kind of device 1 that raising attendance is identified by, device 1 include obtaining mould
Block 11, detection module 12, the first comparison module 13, the second comparison module 14, memory module 15, identification module 16 and determination module
17。
Module 11 is obtained, for being to be identified by recognition result of the attendance identifying system to the face attendance identification of personnel
When, it obtains real-time face and identifies photo.
When recognition result of the attendance identifying system to the face attendance identification of personnel is to be identified by, the reality of personnel is obtained
When recognition of face photo, in the present embodiment, pass through camera shoot acquisition personnel real-time face identify photo.
In the present embodiment, device 1 includes:
Module is established, for establishing identification library.
Identification library is established, identification library is closed for storing real-time face identification photo, identification library and face attendance identifying system
Connection, when recognition result of the attendance identifying system to the face attendance identification of personnel is to be identified by, identification library is used for and personnel
Real-time face identification photo identified.
In some embodiments, device 1 includes:
First detection module, for detecting the recognition result of face attendance identification of the attendance identifying system to personnel;
First judgment module judges whether to receive user's input if being that identification does not pass through for the recognition result
Typing for the first time order;
First obtains module, if obtaining real-time face identification photo for receiving the order.
It is obstructed out-of-date identifying, it may be possible to which that New Hire Onboarding needs by the photo typing of new employee, in such case
Under, need user to input the order of typing for the first time, thus available real-time face identifies photo, without carrying out hand
The photo of work typing new employee.
In the present embodiment, obtaining module 11 includes:
First sub- identification module, for being identification in recognition result of the attendance identifying system to the face attendance identification of personnel
By when, identify the personnel face attendance identification recognition result;
First sub-acquisition module obtains if the recognition result that the face attendance for the personnel identifies is to be identified by
Real-time face is taken to identify photo.
When recognition result of the attendance identifying system to the face attendance identification of personnel is to be identified by, whether personnel are led to
It crosses face attendance to be identified, if recognizing personnel can be identified by face attendance, illustrates that personnel are that face attendance is known
The personnel for needing to carry out attendance in other system obtain the real-time face identification photo of personnel, if recognizing personnel cannot pass through
Face attendance identification, illustrating personnel not is the personnel for needing to carry out attendance in face attendance identifying system, does not obtain the reality of personnel
When recognition of face photo.
In some embodiments, obtaining module 11 includes:
First sub- detection module, for being identification in recognition result of the attendance identifying system to the face attendance identification of personnel
By when, detect the personnel before the recognition result that face attendance identifies is to be identified by with the presence or absence of recognition failures;
Second sub-acquisition module, if being to be identified by for detecting the personnel in the recognition result that face attendance identifies
There are recognition failures before, then obtains real-time face identification photo.
In face attendance identification process of the attendance identifying system to personnel, may there are the case where repeatedly identification, example
Such as, personnel A identifies 4 times in total in face attendance identification, is 3 times recognition failures, and the 4th, which is only, to be identified by,
When recognition result of the attendance identifying system to the face attendance identification of personnel is to be identified by, if identifying, personnel pass through face
Attendance identification, then testing staff whether there is recognition failures before identifying by face attendance, if detecting personnel logical
It crosses before face attendance identification there are recognition failures, illustrates that personnel's recognition success rate in face attendance identifying system is low, obtain
Real-time face identifies photo, if detecting personnel, there is no recognition failures before being identified by face attendance, illustrates personnel
Recognition success rate is high in face attendance identifying system, does not obtain real-time face identification photo.
In some embodiments, obtaining module 11 includes:
Second sub- identification module, for being identification in recognition result of the attendance identifying system to the face attendance identification of personnel
By when,
The personnel time required when carrying out face attendance identification is then obtained, recognition time is obtained;
First sub- comparison module, for the recognition time to be compared with time threshold;
Third sub-acquisition module obtains real-time face identification if being greater than the time threshold for the recognition time
Photo.
When recognition result of the attendance identifying system to the face attendance of personnel identification is to be identified by, obtain personnel into
Pedestrian's face attendance time required when identifying, recognition time is obtained, according to the length of recognition time, judges face attendance identification
Recognition time is compared by efficiency with time threshold, if recognition time is greater than time threshold, illustrates personnel in face attendance
Recognition efficiency is low in identifying system, then obtains real-time face identification photo, if recognition time is less than or equal to time threshold,
Illustrate that personnel's recognition efficiency in face attendance identifying system is high, does not then obtain real-time face identification photo.
Whether detection module 12, the quality for detecting the real-time face identification photo are qualified.
After obtaining real-time face identification photo, the quality of detection real-time face identification photo, according to the matter detected
Amount, judges whether qualification.
In the present embodiment, detection module 12 includes:
4th sub-acquisition module obtains human face posture for identifying photo according to the real-time face;
First sub- judgment module, for judging the pitch angle of the human face posture whether in the range of pitch angle threshold value;
First sub- determination module, if the pitch angle for the human face posture not in the range of the pitch angle threshold value,
Then determine that the quality of the real-time face identification photo is unqualified;
Second sub- judgment module, if the pitch angle for the human face posture be in the range of the pitch angle threshold value,
Then judge the yaw angle of the human face posture whether in the range of yaw angle threshold value;
Second sub- determination module, if the yaw angle for the human face posture be in the range of the yaw angle threshold value,
The quality for then determining the real-time face identification photo is qualification;
The sub- determination module of third, if the yaw angle for the human face posture not in the range of the yaw angle threshold value,
Then determine that the quality of the real-time face identification photo is unqualified.
After obtaining real-time face identification photo, photo is identified according to real-time face, human face posture is obtained, according to face
Posture obtains the pitch angle and yaw angle of human face posture, according to the pitch angle and yaw angle of human face posture, judges that real-time face is known
Whether the quality of other photo is qualified.
In the present embodiment, pitch angle threshold value is (- 20 ° ,+20 °), and yaw angle threshold value is (- 35 ° ,+35 °).
First comparison module 13 will be described real-time if the quality for detecting the real-time face identification is qualification
The corresponding base map in base map library is compared recognition of face photo with the personnel, obtains similarity.
It is corresponding in base map library from personnel are obtained in base map library when it is qualified for detecting the quality of real-time face identification
Real-time face after corresponding base map, is identified photo and personnel in base map library by base map in the personnel that get in base map library
Corresponding base map is compared, and obtains similarity.
In the present embodiment, the characteristic point for extracting real-time face photo, by the characteristic point of real-time face photo and real-time people
The corresponding base map of face photo is matched, and according to the quantity for the characteristic point being matched to, corresponding similarity is calculated, to obtain phase
Like degree.
Second comparison module 14, for the similarity to be compared with preset threshold.
After obtaining similarity, similarity is compared with preset threshold, according to comparison result, is judged whether reality
When recognition of face photo deposit identification library in.
The real-time face is identified photo if being greater than the preset threshold for the similarity by memory module 15
In deposit identification library.
If similarity is greater than preset threshold, illustrate that real-time face identification photo meets identification library storage condition, it will be real-time
In recognition of face photo deposit identification library, the photo as identification library.
In the present embodiment, same personnel are limited in the real-time face identification number of pictures of identification library storage, is deposited
Storing up module 15 includes:
4th sub- identification module identifies the personnel described if being greater than the preset threshold for the similarity
It identifies the number of pictures in library, obtains the number of pictures of typing;
Second sub- comparison module, for the number of pictures of the typing to be compared with amount threshold;
First sub- memory module, if the number of pictures for the typing is less than the amount threshold, by the reality
When recognition of face photo deposit identification library in;
5th sub- identification module, if the number of pictures for the typing is less than or equal to the amount threshold,
An earliest photo of entry time is identified from the number of pictures of the typing, obtains photo to be replaced;
Second sub- memory module, for real-time face identification photo to be replaced the photo to be replaced, deposit identification
In library.
If similarity is greater than preset threshold, number of pictures of the identification personnel in identification library, according to identifying number of pictures
Amount obtains the number of pictures of typing, after the number of pictures for obtaining typing, by the number of pictures of typing and quantity threshold
Value is compared, and according to comparison result, the mode in deposit identification library is determined, if the number of pictures of typing is less than quantity threshold
Value, by real-time face identification photo deposit identification library in, as identification library photo, if the number of pictures of typing be less than or
Equal to amount threshold, then an earliest photo of entry time is identified from the number of pictures of typing, obtains photograph to be replaced
Real-time face identification photo is replaced photo to be replaced, deposit identifies in library, as knowledge after obtaining photo to be replaced by piece
The photo in other library.
Identification module 16 is used for when the attendance identifying system carries out face attendance identification to the personnel again, will
The human face photo of the personnel is identified with the base map library, the identification library simultaneously.
After real-time face identification photo deposit identification library, when the attendance identifying system carries out face to personnel again
When attendance identifies, the human face photo of personnel and base map library are identified, meanwhile, the human face photo of personnel and identification library are carried out
Identification increases the identification in identification library and the human face photo of personnel, improves attendance identification, and does not need manually to acquire photo progress
Replacement.
Determination module 17, if for the photo in the human face photo of the personnel and the base map library or the identification library
Successful match then determines that the recognition result of face attendance identification of the attendance identifying system to the personnel is to be identified by.
Base map library and identification library all can serve as picture required for the identification of attendance identifying system, in human face photo and bottom
The photo successful match of picture library, identification library in any one, all thinks to be identified by, and improves attendance and is identified by.
In the present embodiment, device 1 includes:
First logging modle, for recording the multiple attendance identification record of the personnel;
Second obtains module, for obtaining human face photo and the institute of the personnel according to the multiple attendance identification record
The matched number of base map Kucheng's function is stated, first number, and human face photo and the identification Kucheng of the acquisition personnel are obtained
The matched number of function obtains second number;
Third comparison module, for first number to be compared with second number;
First replacement module is greater than first number for second number, then by the personnel in the identification
Corresponding photo replaces personnel's corresponding base map in the base map library in library.
The multiple attendance identification record of record personnel, attendance identification record include that the human face photo of personnel is and base map Kucheng
Function matching, or human face photo and the base map Kucheng of personnel are obtained according to multiple attendance identification record with identification library successful match
The matched number of function obtains first number, and according to multiple attendance identification record, obtains human face photo and the identification library of personnel
The number of successful match obtains second number, after obtaining first number and second number, by first several and second number
It is compared, according to comparing, judges whether to need replacing personnel's corresponding base map in base map library, if second number is greater than first
Number, then by personnel, corresponding photo replaces personnel's corresponding base map in base map library in identification library, if second number is less than
Or be equal to first number, then by personnel, corresponding photo replaces personnel's corresponding base map in base map library in identification library.
In conclusion being obtained when recognition result of the attendance identifying system to the face attendance identification of personnel is to be identified by
It takes real-time face to identify photo, then the quality of real-time face identification photo is detected, when it is qualified for detecting its quality,
The similarity for obtaining real-time face identification photo and corresponding base map again identifies real-time face when similarity is greater than threshold value
Photo deposit identification library, then next time to personnel carry out face attendance identification when, by the human face photo of personnel simultaneously with base map library, know
Other library is identified, is improved the time being identified by and is identified by rate, is solved because more new photo does not cause to identify for a long time
The problem of time length or recognition failures, and solve in existing face attendance checking system, periodically artificial acquisition photo is needed,
The problem of leading to waste of manpower resource.
As shown in figure 3, also providing a kind of computer equipment in the embodiment of the present application, which can be service
Device, internal structure can be as shown in Figure 3.The computer equipment includes processor, the memory, net connected by system bus
Network interface and database.Wherein, the processor of the Computer Design is for providing calculating and control ability.The computer equipment
Memory includes non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system, computer journey
Sequence and database.The internal memory provides environment for the operation of operating system and computer program in non-volatile memory medium.
The database of the computer equipment is used to store the data such as the model of method for improving that attendance is identified by.The computer equipment
Network interface is used to communicate with external terminal by network connection.To realize one kind when the computer program is executed by processor
Improve the method that attendance is identified by.
Above-mentioned processor executes the step of method that above-mentioned raising attendance is identified by: in attendance identifying system to personnel's
The recognition result of face attendance identification is to obtain real-time face when being identified by and identify photo;Detect the real-time face identification
Whether the quality of photo is qualified;If the quality for detecting the real-time face identification is qualification, the real-time face is identified
The corresponding base map in base map library is compared photo with the personnel, obtains similarity;By the similarity and preset threshold
It is compared;It, will be in real-time face identification photo deposit identification library if the similarity is greater than the preset threshold;?
The attendance identifying system again to the personnel carry out face attendance identification when, by the human face photo of the personnel simultaneously with institute
Base map library, the identification library is stated to be identified;If in the human face photo of the personnel and the base map library or the identification library
Photo successful match, then determine that the attendance identifying system is identification to the recognition result of the face attendance of personnel identification
Pass through.
In one embodiment, whether the quality of above-mentioned detection real-time face identification photo wraps in He Ge step
It includes:
Photo is identified according to the real-time face, obtains human face posture;
Judge the pitch angle of the human face posture whether in the range of pitch angle threshold value;
If the pitch angle of the human face posture not in the range of the pitch angle threshold value, determines that the real-time face is known
The quality of other photo is unqualified;
If the pitch angle of the human face posture is to judge the human face posture in the range of pitch angle threshold value
Whether yaw angle is in the range of yaw angle threshold value;
If the yaw angle of the human face posture is to determine that the real-time face is known in the range of the yaw angle threshold value
The quality of other photo is qualification;
If the yaw angle of the human face posture not in the range of the yaw angle threshold value, determines that the real-time face is known
The quality of other photo is unqualified.
In one embodiment, above-mentioned that the recognition result of the face attendance identification of personnel is identified in attendance identifying system
By when, obtain real-time face identification photo the step of before, comprising:
Detect the recognition result of face attendance identification of the attendance identifying system to personnel;
If the recognition result is that identification does not pass through, judge whether the order for receiving the typing for the first time of user's input;
If receiving the order, real-time face identification photo is obtained.
In one embodiment, above-mentioned that the recognition result of the face attendance identification of personnel is identified in attendance identifying system
By when, obtain real-time face identification photo the step of in, comprising:
When recognition result of the attendance identifying system to the face attendance identification of personnel is to be identified by, the personnel are detected
With the presence or absence of recognition failures before the recognition result of face attendance identification is to be identified by;
If detect the personnel before the recognition result that face attendance identifies is to be identified by there are recognition failures,
It obtains real-time face and identifies photo.
In one embodiment, above-mentioned that the recognition result of the face attendance identification of personnel is identified in attendance identifying system
By when, obtain real-time face identification photo the step of in, comprising:
When recognition result of the attendance identifying system to the face attendance identification of personnel is to be identified by, then the people is obtained
Member's time required when carrying out face attendance identification, obtain recognition time;
The recognition time is compared with time threshold;
If the recognition time is greater than the time threshold, real-time face identification photo is obtained.
In one embodiment, if the above-mentioned similarity is greater than the preset threshold, the real-time face is identified
In step in photo deposit identification library, comprising:
If the similarity is greater than the preset threshold, number of pictures of the personnel in the identification library is identified,
Obtain the number of pictures of typing;
The number of pictures of the typing is compared with amount threshold;
If the number of pictures of the typing is less than the amount threshold, real-time face identification photo deposit is known
In other library;
If the number of pictures of the typing is less than or equal to the amount threshold, from the number of pictures of the typing
An earliest photo of entry time is identified in amount, obtains photo to be replaced;
Real-time face identification photo is replaced into the photo to be replaced, deposit identifies in library.
In one embodiment, if in the human face photo of the above-mentioned personnel and the base map library or the identification library
Photo successful match then determines that the recognition result of face attendance identification of the attendance identifying system to the personnel is logical to identify
After the step of crossing, comprising:
Record the multiple attendance identification record of the personnel;
According to the multiple attendance identification record, human face photo and the base map Kucheng function for obtaining the personnel are matched
Number, obtains first number, and obtains the human face photo and the matched number of identification Kucheng's function of the personnel, acquisition the
Two numbers;
First number is compared with second number;
If second number is greater than first number, by the personnel, corresponding photo is replaced in the identification library
Change the personnel corresponding base map in the base map library.
It will be understood by those skilled in the art that structure shown in Fig. 3, only part relevant to application scheme is tied
The block diagram of structure does not constitute the restriction for the computer equipment being applied thereon to application scheme.
The computer equipment of the embodiment of the present application, in attendance identifying system to the recognition result of the face attendance identification of personnel
When to be identified by, obtaining real-time face and identifying photo, then the quality of real-time face identification photo is detected, when detecting
When its quality is qualified, then the similarity of real-time face identification photo and corresponding base map is obtained, when similarity is greater than threshold value,
By real-time face identification photo deposit identification library, then when the next progress face attendance identification to personnel, by the human face photo of personnel
It is identified simultaneously with base map library, identification library, improves the time being identified by and be identified by rate, solved because for a long time not more
The problem of new photo causes recognition time long or recognition failures, and solve in existing face attendance checking system, it is fixed to need
The problem of phase manually acquires photo, leads to waste of manpower resource.
One embodiment of the application also provides a kind of computer readable storage medium, is stored thereon with computer program, calculates
Machine program realizes a kind of method that raising attendance is identified by when being executed by processor, specifically: in attendance identifying system to people
The recognition result of the face attendance identification of member is to obtain real-time face when being identified by and identify photo;Detect the real-time face
Identify whether the quality of photo is qualified;If the quality for detecting the real-time face identification is qualification, by the real-time face
It identifies that the corresponding base map in base map library is compared photo with the personnel, obtains similarity;By the similarity and preset
Threshold value is compared;If the similarity is greater than the preset threshold, by real-time face identification photo deposit identification library
In;It is when the attendance identifying system carries out face attendance identification to the personnel again, the human face photo of the personnel is same
When identified with the base map library, the identification library;If the human face photo of the personnel and the base map library or the knowledge
Photo successful match in other library then determines the recognition result of face attendance identification of the attendance identifying system to the personnel
To be identified by.
In one embodiment, whether the quality of above-mentioned detection real-time face identification photo wraps in He Ge step
It includes:
Photo is identified according to the real-time face, obtains human face posture;
Judge the pitch angle of the human face posture whether in the range of pitch angle threshold value;
If the pitch angle of the human face posture not in the range of the pitch angle threshold value, determines that the real-time face is known
The quality of other photo is unqualified;
If the pitch angle of the human face posture is to judge the human face posture in the range of pitch angle threshold value
Whether yaw angle is in the range of yaw angle threshold value;
If the yaw angle of the human face posture is to determine that the real-time face is known in the range of the yaw angle threshold value
The quality of other photo is qualification;
If the yaw angle of the human face posture not in the range of the yaw angle threshold value, determines that the real-time face is known
The quality of other photo is unqualified.
In one embodiment, above-mentioned that the recognition result of the face attendance identification of personnel is identified in attendance identifying system
By when, obtain real-time face identification photo the step of before, comprising:
Detect the recognition result of face attendance identification of the attendance identifying system to personnel;
If the recognition result is that identification does not pass through, judge whether the order for receiving the typing for the first time of user's input;
If receiving the order, real-time face identification photo is obtained.
In one embodiment, above-mentioned that the recognition result of the face attendance identification of personnel is identified in attendance identifying system
By when, obtain real-time face identification photo the step of in, comprising:
When recognition result of the attendance identifying system to the face attendance identification of personnel is to be identified by, the personnel are detected
With the presence or absence of recognition failures before the recognition result of face attendance identification is to be identified by;
If detect the personnel before the recognition result that face attendance identifies is to be identified by there are recognition failures,
It obtains real-time face and identifies photo.
In one embodiment, above-mentioned that the recognition result of the face attendance identification of personnel is identified in attendance identifying system
By when, obtain real-time face identification photo the step of in, comprising:
When recognition result of the attendance identifying system to the face attendance identification of personnel is to be identified by, then the people is obtained
Member's time required when carrying out face attendance identification, obtain recognition time;
The recognition time is compared with time threshold;
If the recognition time is greater than the time threshold, real-time face identification photo is obtained.
In one embodiment, if the above-mentioned similarity is greater than the preset threshold, the real-time face is identified
In step in photo deposit identification library, comprising:
If the similarity is greater than the preset threshold, number of pictures of the personnel in the identification library is identified,
Obtain the number of pictures of typing;
The number of pictures of the typing is compared with amount threshold;
If the number of pictures of the typing is less than the amount threshold, real-time face identification photo deposit is known
In other library;
If the number of pictures of the typing is less than or equal to the amount threshold, from the number of pictures of the typing
An earliest photo of entry time is identified in amount, obtains photo to be replaced;
Real-time face identification photo is replaced into the photo to be replaced, deposit identifies in library.
In one embodiment, if in the human face photo of the above-mentioned personnel and the base map library or the identification library
Photo successful match then determines that the recognition result of face attendance identification of the attendance identifying system to the personnel is logical to identify
After the step of crossing, comprising:
Record the multiple attendance identification record of the personnel;
According to the multiple attendance identification record, human face photo and the base map Kucheng function for obtaining the personnel are matched
Number, obtains first number, and obtains the human face photo and the matched number of identification Kucheng's function of the personnel, acquisition the
Two numbers;
First number is compared with second number;
If second number is greater than first number, by the personnel, corresponding photo is replaced in the identification library
Change the personnel corresponding base map in the base map library.
The storage medium of the embodiment of the present application is in recognition result of the attendance identifying system to the face attendance of personnel identification
When being identified by, obtains real-time face and identify photo, then the quality of real-time face identification photo is detected, when detecting it
When quality is qualified, then the similarity of real-time face identification photo and corresponding base map is obtained, it, will when similarity is greater than threshold value
Real-time face identifies photo deposit identification library, then when the next progress face attendance identification to personnel, and the human face photo of personnel is same
When identified with base map library, identification library, improve the time being identified by and be identified by rate, solve because not updating for a long time
The problem of photo causes recognition time long or recognition failures, and solve in existing face attendance checking system, it needs periodically
The problem of manually acquiring photo, leading to waste of manpower resource.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the computer program can be stored in a non-volatile computer
In read/write memory medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein,
Any reference used in provided herein and embodiment to memory, storage, database or other media,
Including non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double speed are according to rate SDRAM (SSRSDRAM), enhancing
Type SDRAM (ESDRAM), synchronization link (Synchl ink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
The foregoing is merely the preferred embodiments of the application, not to limit the application, all essences in the application
Made any modifications, equivalent replacements, and improvements etc. within mind and principle should all include within the scope of protection of this application.
Claims (10)
1. a kind of method for improving attendance and being identified by, which is characterized in that the described method includes:
When recognition result of the attendance identifying system to the face attendance identification of personnel is to be identified by, real-time face identification is obtained
Photo;
Whether the quality for detecting the real-time face identification photo is qualified;
If detecting, the quality of the real-time face identification is qualification, and real-time face identification photo and the personnel are existed
Corresponding base map is compared in base map library, obtains similarity;
The similarity is compared with preset threshold;
It, will be in real-time face identification photo deposit identification library if the similarity is greater than the preset threshold;
It is when the attendance identifying system carries out face attendance identification to the personnel again, the human face photo of the personnel is same
When identified with the base map library, the identification library;
If the photo successful match in the human face photo of the personnel and the base map library or the identification library, described in judgement
Attendance identifying system is to be identified by the recognition result of the face attendance identification of the personnel.
2. the method according to claim 1 for improving attendance and being identified by, which is characterized in that described in real time in the detection
Whether the quality of recognition of face photo is in He Ge step, comprising:
Photo is identified according to the real-time face, obtains human face posture;
Judge the pitch angle of the human face posture whether in the range of pitch angle threshold value;
If the pitch angle of the human face posture not in the range of the pitch angle threshold value, determines that the real-time face identification is shone
The quality of piece is unqualified;
If the pitch angle of the human face posture is to judge the yaw of the human face posture in the range of pitch angle threshold value
Whether angle is in the range of yaw angle threshold value;
If the yaw angle of the human face posture is to determine that the real-time face identification is shone in the range of the yaw angle threshold value
The quality of piece is qualification;
If the yaw angle of the human face posture not in the range of the yaw angle threshold value, determines that the real-time face identification is shone
The quality of piece is unqualified.
3. the method according to claim 1 for improving attendance and being identified by, which is characterized in that be in described identified in attendance
Before the recognition result that the face attendance to personnel of uniting identifies is the step of acquisition real-time face identifies photo when being identified by,
Include:
Detect the recognition result of face attendance identification of the attendance identifying system to personnel;
If the recognition result is that identification does not pass through, judge whether the order for receiving the typing for the first time of user's input;
If receiving the order, real-time face identification photo is obtained.
4. the method according to claim 1 for improving attendance and being identified by, which is characterized in that be in described identified in attendance
The recognition result that the face attendance to personnel of uniting identifies is when being identified by, to obtain in the step of real-time face identifies photo, packet
It includes:
When recognition result of the attendance identifying system to the face attendance identification of personnel is to be identified by, the personnel are detected in people
The recognition result of face attendance identification is before being identified by with the presence or absence of recognition failures;
If detecting the personnel, there are recognition failures before the recognition result that face attendance identifies is to be identified by, obtain
Real-time face identifies photo.
5. the method according to claim 1 for improving attendance and being identified by, which is characterized in that be in described identified in attendance
The recognition result that the face attendance to personnel of uniting identifies is when being identified by, to obtain in the step of real-time face identifies photo, packet
It includes:
When recognition result of the attendance identifying system to the face attendance identification of personnel is to be identified by,
The personnel time required when carrying out face attendance identification is then obtained, recognition time is obtained;
The recognition time is compared with time threshold;
If the recognition time is greater than the time threshold, real-time face identification photo is obtained.
6. the method according to claim 1 for improving attendance and being identified by, which is characterized in that if in the similarity
It, then will be in the step in real-time face identification photo deposit identification library greater than the preset threshold, comprising:
If the similarity is greater than the preset threshold, identifies number of pictures of the personnel in the identification library, obtain
The number of pictures of typing;
The number of pictures of the typing is compared with amount threshold;
If the number of pictures of the typing is less than the amount threshold, by real-time face identification photo deposit identification library
In;
If the number of pictures of the typing is less than or equal to the amount threshold, from the number of pictures of the typing
It identifies an earliest photo of entry time, obtains photo to be replaced;
Real-time face identification photo is replaced into the photo to be replaced, deposit identifies in library.
7. the method according to claim 1 for improving attendance and being identified by, which is characterized in that if the personnel's
Photo successful match in human face photo and the base map library or the identification library, then determine the attendance identifying system to institute
State the face attendance identification of personnel recognition result be the step of being identified by after, comprising:
Record the multiple attendance identification record of the personnel;
According to the multiple attendance identification record, human face photo and the base map Kucheng function for obtaining the personnel are matched secondary
Number obtains first number, and obtains the human face photo and the matched number of identification Kucheng's function of the personnel, obtains second
Number;
First number is compared with second number;
If second number is greater than first number, by the personnel, corresponding photo replaces institute in the identification library
State personnel's corresponding base map in the base map library.
8. a kind of improve the device that is identified by of attendance, which is characterized in that described device includes:
Module is obtained, for obtaining when recognition result of the attendance identifying system to the face attendance identification of personnel is to be identified by
Real-time face is taken to identify photo;
Whether detection module, the quality for detecting the real-time face identification photo are qualified;
First comparison module, if knowing the real-time face for detecting that the quality of the real-time face identification is qualification
The corresponding base map in base map library is compared other photo with the personnel, obtains similarity;
Second comparison module, for the similarity to be compared with preset threshold;
Memory module knows real-time face identification photo deposit if being greater than the preset threshold for the similarity
In other library;
Identification module is used for when the attendance identifying system carries out face attendance identification to the personnel again, by the people
The human face photo of member is identified with the base map library, the identification library simultaneously;
Determination module, if for the photo success in the human face photo of the personnel and the base map library or the identification library
Match, then determines that the recognition result of face attendance identification of the attendance identifying system to the personnel is to be identified by.
9. a kind of computer equipment, including memory and processor, the memory are stored with computer program, feature exists
In the processor realizes method described in any one of claims 1 to 7 when executing computer program the step of.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of method described in any one of claims 1 to 7 is realized when being executed by processor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910100428.6A CN109919035A (en) | 2019-01-31 | 2019-01-31 | Improve method, apparatus, computer equipment and storage medium that attendance is identified by |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910100428.6A CN109919035A (en) | 2019-01-31 | 2019-01-31 | Improve method, apparatus, computer equipment and storage medium that attendance is identified by |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109919035A true CN109919035A (en) | 2019-06-21 |
Family
ID=66961255
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910100428.6A Pending CN109919035A (en) | 2019-01-31 | 2019-01-31 | Improve method, apparatus, computer equipment and storage medium that attendance is identified by |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109919035A (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110334688A (en) * | 2019-07-16 | 2019-10-15 | 重庆紫光华山智安科技有限公司 | Image-recognizing method, device and computer readable storage medium based on human face photo library |
CN111680616A (en) * | 2020-06-04 | 2020-09-18 | 中国建设银行股份有限公司 | Qualification authentication method, device, equipment and medium for subsidy retriever |
CN111680175A (en) * | 2020-05-15 | 2020-09-18 | 浙江大华技术股份有限公司 | Face database building method, computer equipment and computer readable storage medium |
CN112818784A (en) * | 2021-01-22 | 2021-05-18 | 浙江大华技术股份有限公司 | Control method and device of access control equipment and storage medium |
CN112926353A (en) * | 2019-12-05 | 2021-06-08 | 王体 | Distributed cloud processing method for field data |
CN113095110A (en) * | 2019-12-23 | 2021-07-09 | 浙江宇视科技有限公司 | Method, device, medium and electronic equipment for dynamically warehousing face data |
CN115798023A (en) * | 2023-02-13 | 2023-03-14 | 成都睿瞳科技有限责任公司 | Face identification authentication method and device, storage medium and processor |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20020175211A1 (en) * | 2001-03-19 | 2002-11-28 | Francisco Dominquez | Time and attendance system with verification of employee identity and geographical location |
CN105426869A (en) * | 2015-12-15 | 2016-03-23 | 重庆凯泽科技有限公司 | Face recognition system and recognition method based on railway security check |
CN105938552A (en) * | 2016-06-29 | 2016-09-14 | 北京旷视科技有限公司 | Face recognition method capable of realizing base image automatic update and face recognition device |
CN108875485A (en) * | 2017-09-22 | 2018-11-23 | 北京旷视科技有限公司 | A kind of base map input method, apparatus and system |
WO2018222136A1 (en) * | 2017-05-30 | 2018-12-06 | 正凯人工智能私人有限公司 | Image processing method and system |
-
2019
- 2019-01-31 CN CN201910100428.6A patent/CN109919035A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20020175211A1 (en) * | 2001-03-19 | 2002-11-28 | Francisco Dominquez | Time and attendance system with verification of employee identity and geographical location |
CN105426869A (en) * | 2015-12-15 | 2016-03-23 | 重庆凯泽科技有限公司 | Face recognition system and recognition method based on railway security check |
CN105938552A (en) * | 2016-06-29 | 2016-09-14 | 北京旷视科技有限公司 | Face recognition method capable of realizing base image automatic update and face recognition device |
WO2018222136A1 (en) * | 2017-05-30 | 2018-12-06 | 正凯人工智能私人有限公司 | Image processing method and system |
CN108875485A (en) * | 2017-09-22 | 2018-11-23 | 北京旷视科技有限公司 | A kind of base map input method, apparatus and system |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110334688A (en) * | 2019-07-16 | 2019-10-15 | 重庆紫光华山智安科技有限公司 | Image-recognizing method, device and computer readable storage medium based on human face photo library |
CN110334688B (en) * | 2019-07-16 | 2021-09-07 | 重庆紫光华山智安科技有限公司 | Image recognition method and device based on face photo library and computer readable storage medium |
CN112926353A (en) * | 2019-12-05 | 2021-06-08 | 王体 | Distributed cloud processing method for field data |
CN112926353B (en) * | 2019-12-05 | 2024-03-19 | 上海岽利信息科技有限公司 | Site data distributed cloud processing method |
CN113095110A (en) * | 2019-12-23 | 2021-07-09 | 浙江宇视科技有限公司 | Method, device, medium and electronic equipment for dynamically warehousing face data |
CN113095110B (en) * | 2019-12-23 | 2024-03-08 | 浙江宇视科技有限公司 | Method, device, medium and electronic equipment for dynamically warehousing face data |
CN111680175A (en) * | 2020-05-15 | 2020-09-18 | 浙江大华技术股份有限公司 | Face database building method, computer equipment and computer readable storage medium |
CN111680175B (en) * | 2020-05-15 | 2023-04-25 | 浙江大华技术股份有限公司 | Face database construction method, computer equipment and computer readable storage medium |
CN111680616A (en) * | 2020-06-04 | 2020-09-18 | 中国建设银行股份有限公司 | Qualification authentication method, device, equipment and medium for subsidy retriever |
CN112818784A (en) * | 2021-01-22 | 2021-05-18 | 浙江大华技术股份有限公司 | Control method and device of access control equipment and storage medium |
CN112818784B (en) * | 2021-01-22 | 2024-02-06 | 浙江大华技术股份有限公司 | Control method and device of access control equipment and storage medium |
CN115798023A (en) * | 2023-02-13 | 2023-03-14 | 成都睿瞳科技有限责任公司 | Face identification authentication method and device, storage medium and processor |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109919035A (en) | Improve method, apparatus, computer equipment and storage medium that attendance is identified by | |
CN104537389B (en) | Face identification method and device | |
CN111626201B (en) | Commodity detection method, commodity detection device and readable storage medium | |
CN108921026A (en) | Recognition methods, device, computer equipment and the storage medium of animal identification | |
CN111382623B (en) | Live broadcast auditing method, device, server and storage medium | |
KR20200068771A (en) | An attendance check system using deep learning based face recognition | |
CN110659397A (en) | Behavior detection method and device, electronic equipment and storage medium | |
CN109756760A (en) | Generation method, device and the server of video tab | |
CN110969045B (en) | Behavior detection method and device, electronic equipment and storage medium | |
CN110473426A (en) | Parking management method, device, computer equipment and storage medium | |
CN112347856A (en) | Non-perception attendance system and method based on classroom scene | |
CN111652145B (en) | Formula detection method and device, electronic equipment and storage medium | |
CN109919017B (en) | Face recognition optimization method, device, computer equipment and storage medium | |
CN109359689B (en) | Data identification method and device | |
CN109857878B (en) | Article labeling method and device, electronic equipment and storage medium | |
US20210279372A1 (en) | Fabric detecting and recording method and apparatus | |
CN110163084A (en) | Operator action measure of supervision, device and electronic equipment | |
CN109359609A (en) | A kind of recognition of face training sample acquisition methods and device | |
CN112580467A (en) | Video regression testing method and device, computer equipment and storage medium | |
CN108345902B (en) | Self-learning white list model base construction and white list detection method based on transaction characteristics | |
CN110689028A (en) | Site map evaluation method, site survey record evaluation method and site survey record evaluation device | |
CN113869364A (en) | Image processing method, image processing apparatus, electronic device, and medium | |
CN106547818B (en) | Checking-in result verification method and device | |
CN113837169B (en) | Text data processing method, device, computer equipment and storage medium | |
CN117095466B (en) | Image recognition-based job submitting method, device, medium and computing equipment |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |