CN110738165A - Dormitory clustering management method and system under Gaussian mixture models - Google Patents
Dormitory clustering management method and system under Gaussian mixture models Download PDFInfo
- Publication number
- CN110738165A CN110738165A CN201910971234.3A CN201910971234A CN110738165A CN 110738165 A CN110738165 A CN 110738165A CN 201910971234 A CN201910971234 A CN 201910971234A CN 110738165 A CN110738165 A CN 110738165A
- Authority
- CN
- China
- Prior art keywords
- dormitory
- person
- enter
- campus
- clustering
- 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.)
- Withdrawn
Links
- 238000007726 management method Methods 0.000 title claims abstract description 49
- 239000000203 mixture Substances 0.000 title claims abstract description 39
- 238000000034 method Methods 0.000 claims abstract description 17
- 230000001815 facial effect Effects 0.000 claims description 38
- 238000012795 verification Methods 0.000 claims description 25
- 238000000605 extraction Methods 0.000 claims description 11
- 238000013507 mapping Methods 0.000 claims description 8
- 238000012544 monitoring process Methods 0.000 claims description 8
- 230000004308 accommodation Effects 0.000 claims description 5
- 230000002776 aggregation Effects 0.000 claims description 4
- 238000004220 aggregation Methods 0.000 claims description 4
- 238000003780 insertion Methods 0.000 claims description 4
- 230000037431 insertion Effects 0.000 claims description 4
- 230000011218 segmentation Effects 0.000 claims description 4
- 238000007619 statistical method Methods 0.000 claims description 4
- 235000012571 Ficus glomerata Nutrition 0.000 abstract 2
- 244000153665 Ficus glomerata Species 0.000 abstract 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003252 repetitive effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
- G06F18/24155—Bayesian classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Tourism & Hospitality (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Educational Technology (AREA)
- Primary Health Care (AREA)
- Educational Administration (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Probability & Statistics with Applications (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Image Analysis (AREA)
Abstract
dormitory cluster management method and system under Gaussian mixture model, by using the computer network equipped in each dormitory building, the daily calling-in and calling-out information of students in dormitory is inputted into the computer management system in time, the Gaussian mixture model cluster method is adopted, every new lodging data is inserted into the existing Gaussian mixture model tree, then the cluster tree is updated according to the inserted result, whether the lodging data inserted into the cluster tree needs to be deleted or not is checked, if so, the lodging data is deleted, after all lodging data are read, the cluster result is determined.
Description
Technical Field
The invention belongs to the field of data clustering and analysis, and particularly relates to a dormitory clustering management method and system under Gaussian mixture models.
Background
At present, colleges and universities are still in a continuous extension and opening stage in China, the campus security problem of the colleges and universities is increasingly highlighted, campus security systems are actively paved in the colleges and universities to ensure the security of teachers and students in the campus, dormitory security is taken as an important ring in the campus security problem, and general attention is paid to the dormitory security.
At present, the university is larger and larger in scale, more and more students are used, the related information is correspondingly more and more, the energy of apartment managers is limited, and a lot of work is repetitive labor, so that the time and the energy of managers are occupied, and people know that the repetitive labor can be completely replaced by using information technology, so that the managers can put more energy into the aspect of improving the service quality, and therefore, a very necessary and very important point is to establish perfect management systems for the management of dormitories.
However, most colleges and universities in China still adopt an old mode of management depending on manpower, the main mode of dormitory management is to manually process entity records, such as paper data like note texts, the entry and daily statistics of students' attendance every year consume a large amount of manpower and material resources, the checking and counting work of the paper data is difficult to be effectively carried out, related materials are difficult to store, various changes in daily operation of dormitories and daily inquiry are difficult to be developed.
Therefore, dormitory clustering management methods and systems under Gaussian mixture models are provided, people who have entered a dormitory are orderly managed by means of the Gaussian mixture models, meanwhile, an image recognition algorithm is adopted to learn images of authorized users and analyze behavior data generated by the users, dormitory intelligent management is better achieved, and following the development trend of science and computer technology, intelligent type safe campuses are built in an assisted mode.
Disclosure of Invention
Therefore, in order to solve the problems that the current dormitory management is disordered, the data of students who have entered the dormitory is lack of electronic statistical cluster management, and the management of the entering and exiting of foreign personnel in the dormitory is soft, the dormitory cluster management method and the dormitory cluster management system under the Gaussian mixture models are disclosed, the students who have entered the dormitory are effectively clustered and managed through the Gaussian mixture models, meanwhile, the foreign personnel are reasonably recorded and analyzed, and the dormitory order safety is protected to the maximum extent.
The invention firstly requests to protect a dormitory clustering management method under Gaussian mixture models, and is characterized by comprising the following steps:
clustering and managing student information and campus manager information which have participated in a dormitory, wherein the student information comprises facial recognition features of students, and the campus manager information comprises facial recognition information of campus managers;
acquiring information of personnel to enter the dormitory, wherein the information of students entering the dormitory comprises facial recognition features of the personnel to enter the dormitory;
judging whether the personnel to enter the dormitory are students or campus managers who have checked in the dormitory;
if the person to enter the dormitory is a student who has already entered the dormitory or a campus manager, the person is allowed to enter the dormitory;
if the person to enter the dormitory is not the student who has already checked in the dormitory or the campus manager, the entrance condition is verified, and when the entrance condition is met, the person is allowed to enter without limit, otherwise, the restricted entrance mode is adopted.
The invention also claims a dormitory clustering management system under the Gaussian mixture models, which comprises:
the data clustering storage module: clustering and managing student information and campus manager information which have participated in a dormitory, wherein the student information comprises facial recognition features of students, and the campus manager information comprises facial recognition information of campus managers;
an image recognition module: acquiring information of personnel to enter the dormitory, wherein the information of students entering the dormitory comprises facial recognition features of the personnel to enter the dormitory;
an image matching module: judging whether the personnel to enter the dormitory are students or campus managers who have checked in the dormitory;
if the person to enter the dormitory is a student who has already entered the dormitory or a campus manager, the person is allowed to enter the dormitory;
a condition verification module: if the person to enter the dormitory is not the student who has already checked in the dormitory or the campus manager, the entrance condition is verified, and when the entrance condition is met, the person is allowed to enter without limit, otherwise, the restricted entrance mode is adopted.
According to the invention, effective clustering management is performed on addition and deletion improvement of dormitory internal accommodation personnel and campus management personnel by adopting a Gaussian mixture model algorithm, the current dormitory state is analyzed in time, and dormitory resources are reasonably distributed; meanwhile, the image recognition and random extraction algorithm is adopted to effectively supervise the entrance of the outside people in the dormitory into the dormitory, the people meeting the conditions are opened and pass, the dormitory personnel provide guarantees, the limitation mode is also adopted for the people not meeting the conditions, and the internal order of the dormitory is effectively managed electronically.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.
FIG. 1 is a flow chart of the dormitory clustering management method under the Gaussian mixture models according to the present invention;
FIG. 2 is a flowchart illustrating an embodiment of a dormitory clustering management method under Gaussian mixture models according to the present invention;
fig. 3 is a system block diagram of the dormitory clustering management system under the gaussian mixture models according to the present invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
Referring to fig. 1, the present invention relates to a work flow chart of a dormitory clustering management method under gaussian mixture models;
the dormitory clustering management method under the Gaussian mixture models is characterized by comprising the following steps:
clustering and managing student information and campus manager information which have participated in a dormitory, wherein the student information comprises facial recognition features of students, and the campus manager information comprises facial recognition information of campus managers;
acquiring information of personnel to enter the dormitory, wherein the information of students entering the dormitory comprises facial recognition features of the personnel to enter the dormitory;
judging whether the personnel to enter the dormitory are students or campus managers who have checked in the dormitory;
if the person to enter the dormitory is a student who has already entered the dormitory or a campus manager, the person is allowed to enter the dormitory;
if the person to enter the dormitory is not the student who has already checked in the dormitory or the campus manager, the entrance condition is verified, and when the entrance condition is met, the person is allowed to enter without limit, otherwise, the restricted entrance mode is adopted.
, clustering and managing the student information and campus manager information that have checked in the dormitory, wherein the student information includes facial recognition features of students, and the campus manager information includes facial recognition information of campus managers, specifically including:
adopting a Gaussian mixture model clustering method, for every new lodging data, inserting the new lodging data into the existing Gaussian mixture model tree, updating the clustering tree according to the insertion result, checking whether the lodging data inserted into the clustering tree needs to be deleted, and if so, deleting the lodging data;
selecting a clustering center, randomly extracting m sample values as m clustering centers of mixed data, inputting images, mapping the images to a gray space, extracting the gray value of the gray space, estimating the number of result clusters by adopting Bayesian statistical analysis, and automatically determining the number of classification categories and the complexity of model description by searching all classification possibilities of a model space;
the method comprises the steps of initially dividing a data set of living student information and campus manager information by using an aggregation level clustering method, estimating model parameters by using an EM (effective man) algorithm to optimize a clustering result, clustering an image gray level set by using the EM algorithm or a BYY backward structure dynamic canonical learning algorithm, converting the clustering result into an image space, obtaining a final segmentation result, and determining the clustering result after reading all accommodation data.
, judging whether the person to be entered into the dormitory is a student or a campus manager who has entered the dormitory, and if the person to be entered into the dormitory is a student or a campus manager who has entered the dormitory, allowing the person to enter the dormitory specifically includes:
the face image of a person to enter the dormitory is identified, the identified face image is compared with face image information stored in the cluster management information, whether the person is a student who has already checked in the school is judged firstly, if yes, the person is allowed to enter the dormitory, if not, the person is matched to judge whether the person is a campus manager of the school, if the person is successfully matched, the person is allowed to enter the dormitory, and the entering history of the person is recorded according to the identity authority of the student dormitory person or the campus manager.
Referring to fig. 2, a flowchart of an embodiment of a dormitory clustering management method under gaussian mixture models according to the present invention is shown;
if the person to enter the dormitory is not a student or a campus manager who has already entered the dormitory, the entry condition is verified, and the person is allowed to enter the dormitory without limitation when the entry condition is met, which specifically comprises the following steps:
if the person to enter the dormitory is not the student or the campus manager who has already entered the dormitory, providing verification options for the person to enter the dormitory, wherein the verification options include two options of a dormitory accompanying person and no dormitory accompanying person;
if the person to enter the dormitory selects the dormitory accompanying person, the dormitory accompanying person verifies the facial information, if the verification is successful, the person to enter the dormitory is allowed to enter the dormitory, otherwise, the dormitory accompanying person enters an option mode automatically;
if the person to enter the dormitory selects no accompanying person in the dormitory, providing two verification options of the condition two, including dormitory number input and dormitory person name input, for the person to enter the dormitory;
if the person to enter the dormitory selects the dormitory number input option, randomly extracting 3 times of dormitory personnel number of image photos from the dormitory by adopting a random extraction algorithm, wherein the image photos comprise all the personnel photos in the dormitory, and displaying the images to the person to enter the dormitory;
if the person to enter the dormitory selects at least photos of the person in the dormitory, allowing the person to enter the dormitory, otherwise, adopting a restricted entry mode;
if the person to enter the dormitory selects the name input option of the dormitory person, inputting the name content, randomly extracting all image photos of the dormitory person with the name content from the dormitory by adopting a random extraction algorithm, adding (the number of the dormitory person is 2 times to the number of the image photos of the dormitory person with the name content) photos, and displaying the photos to the person to enter the dormitory;
if the person to enter the dormitory has selected at least photographs of the person with the name, then the person is allowed to enter the dormitory, otherwise the restricted entry mode is used.
Specifically, the random extraction algorithm needs to initialize volume group parameters, including selecting a dormitory range, inputting dormitory data parameters, setting extracted probability values of dormitories of all floors, and the like;
judging and adjusting, including calculating the total number of dormitories, the floor distribution average degree, the number of full people in the dormitories and the like, and judging whether the extraction expectation is met or not, otherwise, returning to the step for adjusting parameters;
For the subject of selection, i.e. byFromObtaining the image subset of the dormitory personnel by the middle lottery dormitory personnel;
ComputingThe occurrence frequency of each dormitory and the hit frequency of dormitories in which personnel appear for many times are included in the above description;
replacement adjustment ofThe dormitory personnel images with the middle knowledge points appearing for multiple times are sequentially arranged in the dormitory according to the priority from high to low of the hit timesSearch in andcarrying out lottery replacement on the people in different dormitories according to the priorities of the hit times from low to high; if atCannot be searchedSelecting the test questions of different dormitory personnelReplacing dormitory personnel with smaller hit times;
generating a dormitory personnel image set, namely obtaining the dormitory personnel image set from the adjusted dormitory personnel image subset;
, if the person to enter the dormitory is not the student or campus manager who has checked in the dormitory, verifying the entry condition, allowing the person to enter without limit when the entry condition is satisfied, otherwise, adopting a limited entry mode, specifically including:
the entrance limiting mode is that when the current people waiting to enter the dormitory are not in accordance with the entrance conditions, the facial images of the people waiting to enter the dormitory are recorded, the people are marked as dormitory monitoring people, the maximum detention time of the people in the dormitory is set, the monitoring mark is removed through facial feature recognition when the dormitory leaves, and if the maximum detention time in the dormitory is exceeded, a warning notice is sent to dormitory management people.
Specifically, if the person to enter the dormitory selects the dormitory accompanying person and the dormitory accompanying person successfully verifies the dormitory accompanying person, establishing a mapping association relationship between the person to enter the dormitory and the dormitory accompanying person, and storing the mapping association relationship for subsequent data analysis; if the person to enter the dormitory selects no person accompanied by the dormitory and is verified successfully, namely selects a person with a certain dormitory number or a member of the dormitory, establishing a mapping association relationship between the person to enter the dormitory and the dormitory number or the dormitory person, and storing the mapping association relationship for subsequent data analysis.
Referring to fig. 3, a system block diagram of a dormitory clustering management system under gaussian mixture models according to the present invention is shown;
the dormitory clustering management system under the Gaussian mixture models comprises:
the data clustering storage module: clustering and managing student information and campus manager information which have participated in a dormitory, wherein the student information comprises facial recognition features of students, and the campus manager information comprises facial recognition information of campus managers;
an image recognition module: acquiring information of personnel to enter the dormitory, wherein the information of students entering the dormitory comprises facial recognition features of the personnel to enter the dormitory;
an image matching module: judging whether the personnel to enter the dormitory are students or campus managers who have checked in the dormitory;
if the person to enter the dormitory is a student who has already entered the dormitory or a campus manager, the person is allowed to enter the dormitory;
a condition verification module: if the person to enter the dormitory is not the student who has already checked in the dormitory or the campus manager, the entrance condition is verified, and when the entrance condition is met, the person is allowed to enter without limit, otherwise, the restricted entrance mode is adopted.
, the data cluster storage module performs cluster management on the student information and campus manager information which have checked in the dormitory, wherein the student information includes facial recognition features of students, and the campus manager information includes facial recognition information of campus managers, and specifically includes:
adopting a Gaussian mixture model clustering method, for every new lodging data, inserting the new lodging data into the existing Gaussian mixture model tree, updating the clustering tree according to the insertion result, checking whether the lodging data inserted into the clustering tree needs to be deleted, and if so, deleting the lodging data;
selecting a clustering center, randomly extracting m sample values as m clustering centers of mixed data, inputting images, mapping the images to a gray space, extracting the gray value of the gray space, estimating the number of result clusters by adopting Bayesian statistical analysis, and automatically determining the number of classification categories and the complexity of model description by searching all classification possibilities of a model space;
the method comprises the steps of initially dividing a data set of living student information and campus manager information by using an aggregation level clustering method, estimating model parameters by using an EM (effective man) algorithm to optimize a clustering result, clustering an image gray level set by using the EM algorithm or a BYY backward structure dynamic canonical learning algorithm, converting the clustering result into an image space, obtaining a final segmentation result, and determining the clustering result after reading all accommodation data.
, the image matching module judges whether the person to enter the dormitory is a student or a campus manager who has entered the dormitory, and if the person to enter the dormitory is a student or a campus manager who has entered the dormitory, the image matching module allows the person to enter the dormitory, and specifically comprises:
the face image of a person to enter the dormitory is identified, the identified face image is compared with face image information stored in the cluster management information, whether the person is a student who has already checked in the school is judged firstly, if yes, the person is allowed to enter the dormitory, if not, the person is matched to judge whether the person is a campus manager of the school, if the person is successfully matched, the person is allowed to enter the dormitory, and the entering history of the person is recorded according to the identity authority of the student dormitory person or the campus manager.
, if the person to enter the dormitory is not the student or campus manager who has already entered the dormitory, the condition verification module verifies the entry condition, and allows the person to enter without limit when the entry condition is satisfied, otherwise, the condition verification module adopts the limited entry mode, which specifically includes:
if the person to enter the dormitory is not the student or the campus manager who has already entered the dormitory, providing verification options for the person to enter the dormitory, wherein the verification options include two options of a dormitory accompanying person and no dormitory accompanying person;
if the person to enter the dormitory selects the dormitory accompanying person, the dormitory accompanying person verifies the facial information, if the verification is successful, the person to enter the dormitory is allowed to enter the dormitory, otherwise, the dormitory accompanying person enters an option mode automatically;
if the person to enter the dormitory selects no accompanying person in the dormitory, providing two verification options of the condition two, including dormitory number input and dormitory person name input, for the person to enter the dormitory;
if the person to enter the dormitory selects the dormitory number input option, randomly extracting 3 times of dormitory personnel number of image photos from the dormitory by adopting a random extraction algorithm, wherein the image photos comprise all the personnel photos in the dormitory, and displaying the images to the person to enter the dormitory;
if the person to enter the dormitory selects at least photos of the person in the dormitory, allowing the person to enter the dormitory, otherwise, adopting a restricted entry mode;
if the person to enter the dormitory selects the name input option of the dormitory person, inputting the name content, randomly extracting all image photos of the dormitory person with the name content from the dormitory by adopting a random extraction algorithm, adding (the number of the dormitory person is 2 times to the number of the image photos of the dormitory person with the name content) photos, and displaying the photos to the person to enter the dormitory;
if the person to enter the dormitory has selected at least photographs of the person with the name, then the person is allowed to enter the dormitory, otherwise the restricted entry mode is used.
, if the person to enter the dormitory is not the student or campus manager who has already entered the dormitory, the condition verification module verifies the entry condition, and allows the person to enter without limit when the entry condition is satisfied, otherwise, the condition verification module adopts the limited entry mode, which specifically includes:
the entrance limiting mode is that when the current people waiting to enter the dormitory are not in accordance with the entrance conditions, the facial images of the people waiting to enter the dormitory are recorded, the people are marked as dormitory monitoring people, the maximum detention time of the people in the dormitory is set, the monitoring mark is removed through facial feature recognition when the dormitory leaves, and if the maximum detention time in the dormitory is exceeded, a warning notice is sent to dormitory management people.
The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (10)
1, a dormitory clustering management method under Gaussian mixture models, which is characterized by comprising the following steps:
clustering and managing student information and campus manager information which have participated in a dormitory, wherein the student information comprises facial recognition features of students, and the campus manager information comprises facial recognition information of campus managers;
acquiring information of personnel to enter the dormitory, wherein the information of students entering the dormitory comprises facial recognition features of the personnel to enter the dormitory;
judging whether the personnel to enter the dormitory are students or campus managers who have checked in the dormitory;
if the person to enter the dormitory is a student who has already entered the dormitory or a campus manager, the person is allowed to enter the dormitory;
if the person to enter the dormitory is not the student who has already checked in the dormitory or the campus manager, the entrance condition is verified, and when the entrance condition is met, the person is allowed to enter without limit, otherwise, the restricted entrance mode is adopted.
2. The dormitory clustering management method under Gaussian mixture models according to claim 1, comprising:
carry out cluster management to the student information and the campus managers information that have lived in the dormitory inside, student information includes student's facial recognition feature, and campus managers information includes campus managers' facial recognition information, specifically includes:
adopting a Gaussian mixture model clustering method, for every new lodging data, inserting the new lodging data into the existing Gaussian mixture model tree, updating the clustering tree according to the insertion result, checking whether the lodging data inserted into the clustering tree needs to be deleted, and if so, deleting the lodging data;
selecting a clustering center, randomly extracting m sample values as m clustering centers of mixed data, inputting images, mapping the images to a gray space, extracting the gray value of the gray space, estimating the number of result clusters by adopting Bayesian statistical analysis, and automatically determining the number of classification categories and the complexity of model description by searching all classification possibilities of a model space;
the method comprises the steps of initially dividing a data set of living student information and campus manager information by using an aggregation level clustering method, estimating model parameters by using an EM (effective man) algorithm to optimize a clustering result, clustering an image gray level set by using the EM algorithm or a BYY backward structure dynamic canonical learning algorithm, converting the clustering result into an image space, obtaining a final segmentation result, and determining the clustering result after reading all accommodation data.
3. The dormitory clustering management method under Gaussian mixture models according to claim 1, comprising:
judge whether the personnel that wait to get into dormitory inside are student or campus managers that this dormitory has checked in, if the personnel that wait to get into dormitory inside are student or campus managers that this dormitory has checked in, then allow it to get into this dormitory, specifically include:
the face image of a person to enter the dormitory is identified, the identified face image is compared with face image information stored in the cluster management information, whether the person is a student who has already checked in the school is judged firstly, if yes, the person is allowed to enter the dormitory, if not, the person is matched to judge whether the person is a campus manager of the school, if the person is successfully matched, the person is allowed to enter the dormitory, and the entering history of the person is recorded according to the identity authority of the student dormitory person or the campus manager.
4. The dormitory clustering management method under Gaussian mixture models according to claim 1, comprising:
if the person to enter the dormitory is not a student or a campus manager who has already entered the dormitory, the entry condition is verified, and the person is allowed to enter the dormitory without limitation when the entry condition is met, which specifically comprises the following steps:
if the person to enter the dormitory is not the student or the campus manager who has already entered the dormitory, providing verification options for the person to enter the dormitory, wherein the verification options include two options of a dormitory accompanying person and no dormitory accompanying person;
if the person to enter the dormitory selects the dormitory accompanying person, the dormitory accompanying person verifies the facial information, if the verification is successful, the person to enter the dormitory is allowed to enter the dormitory, otherwise, the dormitory accompanying person enters an option mode automatically;
if the person to enter the dormitory selects no accompanying person in the dormitory, providing two verification options of the condition two, including dormitory number input and dormitory person name input, for the person to enter the dormitory;
if the person to enter the dormitory selects the dormitory number input option, randomly extracting 3 times of dormitory personnel number of image photos from the dormitory by adopting a random extraction algorithm, wherein the image photos comprise all the personnel photos in the dormitory, and displaying the images to the person to enter the dormitory;
if the person to enter the dormitory selects at least photos of the person in the dormitory, allowing the person to enter the dormitory, otherwise, adopting a restricted entry mode;
if the person to enter the dormitory selects the name input option of the dormitory person, inputting the name content, randomly extracting all image photos of the dormitory person with the name content from the dormitory by adopting a random extraction algorithm, adding (the number of the dormitory person is 2 times to the number of the image photos of the dormitory person with the name content) photos, and displaying the photos to the person to enter the dormitory;
if the person to enter the dormitory has selected at least photographs of the person with the name, then the person is allowed to enter the dormitory, otherwise the restricted entry mode is used.
5. The dormitory clustering management method under Gaussian mixture models according to claim 1, comprising:
if the person to enter the dormitory is not the student who has already checked in the dormitory or the campus manager, the entrance condition is verified, and the person is allowed to enter the dormitory without limitation when the entrance condition is met, otherwise, a limited entrance mode is adopted, which specifically comprises the following steps:
the entrance limiting mode is that when the current people waiting to enter the dormitory are not in accordance with the entrance conditions, the facial images of the people waiting to enter the dormitory are recorded, the people are marked as dormitory monitoring people, the maximum detention time of the people in the dormitory is set, the monitoring mark is removed through facial feature recognition when the dormitory leaves, and if the maximum detention time in the dormitory is exceeded, a warning notice is sent to dormitory management people.
6, dormitory cluster management system under gaussian mixture model, the system comprising:
the data clustering storage module: clustering and managing student information and campus manager information which have participated in a dormitory, wherein the student information comprises facial recognition features of students, and the campus manager information comprises facial recognition information of campus managers;
an image recognition module: acquiring information of personnel to enter the dormitory, wherein the information of students entering the dormitory comprises facial recognition features of the personnel to enter the dormitory;
an image matching module: judging whether the personnel to enter the dormitory are students or campus managers who have checked in the dormitory;
if the person to enter the dormitory is a student who has already entered the dormitory or a campus manager, the person is allowed to enter the dormitory;
a condition verification module: if the person to enter the dormitory is not the student who has already checked in the dormitory or the campus manager, the entrance condition is verified, and when the entrance condition is met, the person is allowed to enter without limit, otherwise, the restricted entrance mode is adopted.
7. The dormitory cluster management system under Gaussian mixture models of claim 6, wherein:
the data cluster storage module: carry out cluster management to the student information and the campus managers information that have lived in the dormitory inside, student information includes student's facial recognition feature, and campus managers information includes campus managers' facial recognition information, specifically includes:
adopting a Gaussian mixture model clustering method, for every new lodging data, inserting the new lodging data into the existing Gaussian mixture model tree, updating the clustering tree according to the insertion result, checking whether the lodging data inserted into the clustering tree needs to be deleted, and if so, deleting the lodging data;
selecting a clustering center, randomly extracting m sample values as m clustering centers of mixed data, inputting images, mapping the images to a gray space, extracting the gray value of the gray space, estimating the number of result clusters by adopting Bayesian statistical analysis, and automatically determining the number of classification categories and the complexity of model description by searching all classification possibilities of a model space;
the method comprises the steps of initially dividing a data set of living student information and campus manager information by using an aggregation level clustering method, estimating model parameters by using an EM (effective man) algorithm to optimize a clustering result, clustering an image gray level set by using the EM algorithm or a BYY backward structure dynamic canonical learning algorithm, converting the clustering result into an image space, obtaining a final segmentation result, and determining the clustering result after reading all accommodation data.
8. The dormitory cluster management system under Gaussian mixture models of claim 6, wherein:
the image matching module: judge whether the personnel that wait to get into dormitory inside are student or campus manager that this dormitory has checked in, if the personnel that wait to get into dormitory inside are student or campus manager that this dormitory has checked in, then allow it to get into this dormitory, specifically include:
the method comprises the steps of identifying faces of persons to enter the dormitory, comparing the identified faces with face image information stored in cluster management information, judging whether the persons are students who have already checked in the school or not, if so, allowing the persons to enter the dormitory, otherwise, matching to judge whether the persons are campus managers of the school or not, if matching is successful, allowing the persons to enter the dormitory, and recording the entrance history of the persons according to the identity authority of the students' dormitory or the campus managers.
9. The dormitory cluster management system under Gaussian mixture models of claim 6, wherein:
the condition verification module: if the person waiting to enter the dormitory is not the student who has already checked in the dormitory or the campus manager, the entrance condition is verified, and the person is allowed to enter without limit when the entrance condition is met, otherwise, a limited entrance mode is adopted, and the method specifically comprises the following steps:
if the person to enter the dormitory is not the student or the campus manager who has already entered the dormitory, providing verification options for the person to enter the dormitory, wherein the verification options include two options of a dormitory accompanying person and no dormitory accompanying person;
if the person to enter the dormitory selects the dormitory accompanying person, the dormitory accompanying person verifies the facial information, if the verification is successful, the person to enter the dormitory is allowed to enter the dormitory, otherwise, the dormitory accompanying person enters an option mode automatically;
if the person to enter the dormitory selects no accompanying person in the dormitory, providing two verification options of the condition two, including dormitory number input and dormitory person name input, for the person to enter the dormitory;
if the person to enter the dormitory selects the dormitory number input option, randomly extracting 3 times of dormitory personnel number of image photos from the dormitory by adopting a random extraction algorithm, wherein the image photos comprise all the personnel photos in the dormitory, and displaying the images to the person to enter the dormitory;
if the person to enter the dormitory selects at least photos of the person in the dormitory, allowing the person to enter the dormitory, otherwise, adopting a restricted entry mode;
if the person to enter the dormitory selects the name input option of the dormitory person, inputting the name content, randomly extracting all image photos of the dormitory person with the name content from the dormitory by adopting a random extraction algorithm, adding (the number of the dormitory person is 2 times to the number of the image photos of the dormitory person with the name content) photos, and displaying the photos to the person to enter the dormitory;
if the person to enter the dormitory has selected at least photographs of the person with the name, then the person is allowed to enter the dormitory, otherwise the restricted entry mode is used.
10. The dormitory cluster management system under Gaussian mixture models of claim 6, wherein:
the condition verification module: if the person waiting to enter the dormitory is not the student who has already checked in the dormitory or the campus manager, the entrance condition is verified, and the person is allowed to enter without limit when the entrance condition is met, otherwise, a limited entrance mode is adopted, and the method specifically comprises the following steps:
the entrance limiting mode is that when the current people waiting to enter the dormitory are not in accordance with the entrance conditions, the facial images of the people waiting to enter the dormitory are recorded, the people are marked as dormitory monitoring people, the maximum detention time of the people in the dormitory is set, the monitoring mark is removed through facial feature recognition when the dormitory leaves, and if the maximum detention time in the dormitory is exceeded, a warning notice is sent to dormitory management people.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910971234.3A CN110738165A (en) | 2019-10-14 | 2019-10-14 | Dormitory clustering management method and system under Gaussian mixture models |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910971234.3A CN110738165A (en) | 2019-10-14 | 2019-10-14 | Dormitory clustering management method and system under Gaussian mixture models |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110738165A true CN110738165A (en) | 2020-01-31 |
Family
ID=69269971
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910971234.3A Withdrawn CN110738165A (en) | 2019-10-14 | 2019-10-14 | Dormitory clustering management method and system under Gaussian mixture models |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110738165A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112200957A (en) * | 2020-09-07 | 2021-01-08 | 东南大学 | Intelligent power control method based on face recognition |
-
2019
- 2019-10-14 CN CN201910971234.3A patent/CN110738165A/en not_active Withdrawn
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112200957A (en) * | 2020-09-07 | 2021-01-08 | 东南大学 | Intelligent power control method based on face recognition |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108304427B (en) | User passenger group classification method and device | |
US20150033362A1 (en) | Notification and Privacy Management of Online Photos and Videos | |
CN111818198B (en) | Domain name detection method, domain name detection device, equipment and medium | |
US8341012B2 (en) | Working skill estimating program | |
CN111444952A (en) | Method and device for generating sample identification model, computer equipment and storage medium | |
US20180061254A1 (en) | Academic-Integrity-Preserving Continuous Assessment Technologies | |
CN109190588A (en) | A kind of method and device of population classification | |
CN109360305B (en) | Library management method and system based on face recognition | |
KR20180038169A (en) | Safety classification method of the city image using deep learning-based data feature | |
CN111178136A (en) | Big data-based smart campus identity recognition method and system | |
CN112581081A (en) | Seat management method, device and equipment based on computer examination informatization computer room | |
CN108268886A (en) | For identifying the method and system of plug-in operation | |
WO2021027569A1 (en) | Law enforcement analysis method and apparatus, electronic device, and storage medium | |
CN113946657A (en) | Knowledge reasoning-based automatic identification method for power service intention | |
CN111667171A (en) | Big data-based group reading behavior analysis method, device, equipment and medium | |
CN113158771B (en) | Community personnel information acquisition method, system and application | |
CN110738165A (en) | Dormitory clustering management method and system under Gaussian mixture models | |
CN113986660A (en) | Matching method, device, equipment and storage medium of system adjustment strategy | |
CN113268870A (en) | Monte Carlo-based image recognition reliability evaluation method under outdoor environment condition | |
CN111898548A (en) | Visitor identity authentication method and device based on machine learning and computer equipment | |
CN115511670A (en) | Online education method and online education platform | |
CN106530199B (en) | Multimedia integration steganalysis method based on window type hypothesis testing | |
CN115510248A (en) | Method for constructing and analyzing person behavior characteristic knowledge graph based on deep learning | |
CN115062725A (en) | Hotel income abnormity analysis method and system | |
CN113128452A (en) | Greening satisfaction acquisition method and system based on image recognition |
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 | ||
TA01 | Transfer of patent application right | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20200807 Address after: 250200 No. 888, Wenhua Road, Zhangqiu University City, Shandong, Ji'nan Applicant after: SHANDONG College OF ELECTRONIC TECHNOLOGY Applicant after: Wang Ruifeng Address before: Lixia District, Shandong city of Ji'nan Province Cultural Road 250000 No. 88 Applicant before: Wang Ruifeng |
|
WW01 | Invention patent application withdrawn after publication | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20200131 |