CN109147430A - A kind of teleeducation system based on cloud platform - Google Patents

A kind of teleeducation system based on cloud platform Download PDF

Info

Publication number
CN109147430A
CN109147430A CN201811224834.5A CN201811224834A CN109147430A CN 109147430 A CN109147430 A CN 109147430A CN 201811224834 A CN201811224834 A CN 201811224834A CN 109147430 A CN109147430 A CN 109147430A
Authority
CN
China
Prior art keywords
vertex
dimensional grid
teacher
face
student side
Prior art date
Application number
CN201811224834.5A
Other languages
Chinese (zh)
Inventor
罗琪
Original Assignee
渭南师范学院
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 渭南师范学院 filed Critical 渭南师范学院
Priority to CN201811224834.5A priority Critical patent/CN109147430A/en
Publication of CN109147430A publication Critical patent/CN109147430A/en

Links

Classifications

    • GPHYSICS
    • G09EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
    • G09BEDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
    • G09B5/00Electrically-operated educational appliances
    • G09B5/06Electrically-operated educational appliances with both visual and audible presentation of the material to be studied
    • G09B5/065Combinations of audio and video presentations, e.g. videotapes, videodiscs, television systems
    • GPHYSICS
    • G09EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
    • G09BEDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
    • G09B5/00Electrically-operated educational appliances
    • G09B5/08Electrically-operated educational appliances providing for individual presentation of information to a plurality of student stations
    • G09B5/14Electrically-operated educational appliances providing for individual presentation of information to a plurality of student stations with provision for individual teacher-student communication

Abstract

The present invention provides a kind of teleeducation systems based on cloud platform, including teacher side, student side and Cloud Server;The student side includes acquisition module, the first display module, input module;The teacher side includes that module, the second display module are recorded in teaching;The teaching records module and carries out the recording of instructional video for teacher, and the instructional video is sent to the Cloud Server;The Cloud Server responds the request of student side for storing the instructional video, and the instructional video is sent to the student side;First display module is for showing the instructional video.The content of courses of one teacher's end subscriber can be transferred to multiple student sides by the effect of Cloud Server by the present invention, meanwhile, teacher's end subscriber can judge the lecture level of oneself by information such as expressions when listening to the teacher of observation student's end subscriber.

Description

A kind of teleeducation system based on cloud platform

Technical field

The present invention relates to Cloud Server fields, and in particular to a kind of teleeducation system based on cloud platform.

Background technique

Currently, it is fairly common to be imparted knowledge to students using electronic classroom.The Normal practice of the teaching method is that teacher passes through The laptop that oneself is carried or the multimedia console that is mounted on the dais of classroom are by the courseware on Computer for teachers Content is transferred on projector by video line and is launched onto curtain, or is launched by video line to the student in classroom On computer terminal.But the classroom that Faculty and Students must all go to relevant device could complete teaching process, place of giving lessons It is limited.

In the prior art, can solve the above problem by the way of remote teaching using Cloud Server, still, existing skill Remote teaching is carried out due to using Cloud Server in art, Faculty and Students are not in the same classroom, therefore teacher cannot lead to The information such as expression when listening to the teacher of observation students are crossed to judge the lecture level of oneself, so as to adjust the explanation side of knowledge point Formula.

It would therefore be desirable to which a kind of teleeducation system based on cloud platform, solves the above problems.

Summary of the invention

In view of the above-mentioned problems, the present invention provides a kind of teleeducation systems based on cloud platform, for solving above-mentioned ask Topic.

The purpose of the present invention is realized using following technical scheme:

A kind of teleeducation system based on cloud platform, including teacher side, Cloud Server and student side;The student side packet Include acquisition module, the first display module;The teacher side includes that module, the second display module are recorded in teaching;

The teaching records module for recording instructional video, and the instructional video is sent to the Cloud Server;

The Cloud Server stores the instructional video, and responds the request of student side, and the instructional video is sent to The student side;

First display module is for showing the instructional video;

The acquisition module is used to acquire and listens to the teacher information and be sent to Cloud Server;The information of listening to the teacher includes at least and It causes trouble the face diagram of block of corresponding user;

The Cloud Server is also used to analyze to obtain corresponding expression information the face diagram of block;Cloud Server counts the expression information, and statistical result is sent to teacher side;

Second display module is for showing the statistical result.

In one embodiment, the Cloud Server includes database, and the database is for storing the teaching view Frequently.

In one embodiment, the quantity of the student side is multiple;The student side further includes corresponding for student side The input module of user's inputting word information.

The invention has the benefit that being taken the present invention provides a kind of teleeducation system based on cloud platform by cloud The effect of business device, can be transferred to multiple student sides for the content of courses of a teacher side, moreover, teaching compared to traditional electronics Room is not required spatially using teacher's end subscriber and student's end subscriber of this system, as long as student side is equal with teacher side It can be communicated with the same server.It is advantageous for the propagation of the instructional video of high quality in this way.The present invention also passes through Cloud Server counts the expression information of student's end subscriber, so that teacher's end subscriber is analyzed.Teacher's end subscriber foundation Analysis result makes suitable adjustment to the teaching strategy of oneself.

Detailed description of the invention

The present invention will be further described with reference to the accompanying drawings, but the embodiment in attached drawing is not constituted to any limit of the invention System, for those of ordinary skill in the art, without creative efforts, can also obtain according to the following drawings Other attached drawings.

Fig. 1 shows the frame construction drawing of an illustrative embodiment of the invention.

Appended drawing reference:

Teacher side 1, Cloud Server 2, student side 3.

Specific embodiment

The invention will be further described with the following Examples.

Referring to Fig. 1, the present invention provides a kind of teleeducation systems based on cloud platform, including teacher side 1, Cloud Server 2 and student side 3;The student side 3 includes acquisition module, the first display module;The teacher side 1 includes that module is recorded in teaching, Second display module;

The teaching records module for recording instructional video, and the instructional video is sent to the Cloud Server 2;

The Cloud Server 2 stores the instructional video, and responds the request of student side 3, and the instructional video is sent To the student side 3;

First display module is for showing the instructional video;

The acquisition module is used to acquire and listens to the teacher information and be sent to Cloud Server 2;It is described listen to the teacher information include at least with The face diagram of block of the corresponding user of student side 3;

The Cloud Server 2 is also used to analyze to obtain corresponding expression information the face diagram of block; Cloud Server 2 counts the expression information, and statistical result is sent to teacher side 1;

Second display module is for showing the statistical result.

Above-mentioned student side 3, teacher side 1 are two different user terminals, using the student side 3, teacher side 1 user not It is defined in student, teacher.

Acquisition module may include image acquisition device, sound collector.

In one embodiment, the Cloud Server 2 includes database, and the database is for storing the teaching view Frequently.The database can be distributed data base.

In one embodiment, the quantity of the student side 3 is multiple;The student side 3 further includes right for student side 3 Using the input module of family inputting word information.As a preferred solution, the preferred amount of the student side 3 is the cloud The 90% of the maximum number of connections that server 2 is set.Wherein, the text information includes answering for the exercise in the instructional video Case, the evaluation that 3 user of student side is aiming at the problem that instructional video proposes, 3 user of student side is to the instructional video, in turn It has the beneficial effect that, 1 user of teacher side can understand 3 user of student side to described according to the answer of the exercise in the instructional video The grasp situation of knowledge point in instructional video, and 1 user of teacher side can be asked for the instructional video proposition described Topic is replied, and completion 1 user of teacher side interacts with 3 user's of student side.

Input module may include mode, the input mode of speech-to-text of the mode of keyboard input, touch-control input.

The present invention passes through Cloud Server 2 embodiment described above provides a kind of teleeducation system based on cloud platform The content of courses of one teacher side 1, can be transferred to multiple student sides 3 by effect, moreover, compared to traditional electronic classroom, It is not required spatially using 1 user of teacher side and 3 user of student side of this system, as long as student side 3 and teacher side 1 are equal It can be communicated with the same server.It is advantageous for the propagation of the instructional video of high quality in this way.The present invention also passes through Cloud Server 2 counts the expression information of 3 user of student side, and for teacher side, 1 user is analyzed.1 user of teacher side Suitable adjustment is made to the teaching strategy of oneself according to analysis result.

In one embodiment, the data analysis module includes pretreatment unit, for face diagram of block It is pre-processed, obtains face three-dimensional grid;

Key point selecting unit, for determining the key on the face three-dimensional grid according to the face three-dimensional grid Point;

Descriptor generation unit, for obtaining the descriptor of the key point according to the key point;

Three-dimensional grid indicates unit, for obtaining the table for indicating the face three-dimensional grid according to the descriptor Show parameter;

Dictionary creation unit is obtained for the face diagram of block with same type expression by setting quantity Dictionary corresponding to the type;

Recognition unit is used for according to the dictionary, to the institute from the expression in the face diagram of block that student side 3 is sent back to Belong to classification to be judged.

It is in one embodiment, described that face diagram of block is pre-processed, comprising:

Grid dividing is carried out to face diagram of block;Divide obtained three-dimensional grid with a plurality of vertices with it is a plurality of Side, any one grid are made of three vertex and three sides;Three dimensional space coordinate corresponding to each vertex is recorded Come;The three-dimensional grid is denoted as M, all vertex in M are denoted as set a SP, SP={ P1, P2 ..., Pnum }, wherein Num is the sum on vertex in M.

In one embodiment, the key point selecting unit includes scale space building subelement, flexometer operator Unit, neighborhood determine that subelement, extreme point determine subelement and filtering subelement;

The scale space building subelement is used to construct the scale space of three-dimensional grid M;

The curvature estimation subelement is used to obtain average master of the vertex each of three-dimensional grid M in setting scale Curvature;

The neighborhood determines subelement for determining that each of three-dimensional grid M pushes up neighborhood of a point;

The extreme point determines subelement for whether determining each vertex according to the average principal curvatures and the neighborhood For the extreme point in three-dimensional grid M;

The filtering subelement is used for from the extreme point with filtering out key point.

In one embodiment, the scale space of the building three-dimensional grid M, is carried out by following functions:

Wherein,

In formula,For convolution algorithm, k is the quantity of scale, and s is scale, σ0For the standard deviation of setting, d1、d2、d3It indicates Dimensional parameter, M (x, y, z) indicate the coordinate on vertex.

In one embodiment, the average master for obtaining the vertex each of three-dimensional grid M in setting scale Curvature, comprising:

Set be dimensioned so as to s when, for the vertex p on three-dimensional grid Mm, its average principal curvatures is calculated using following functions

In formula, m ∈ [1, num], pmIndicate m-th of vertex on three-dimensional grid M, KS, max(pm) and KS, min(pm) it is vertex pmMaximum principal curvatures and minimum principal curvatures at scale s;α and β is the weight coefficient of setting, alpha+beta=1;

When needing to calculate the average principal curvatures on vertex under other scales, it is only necessary to which the scale for changing setting can be with.

In one embodiment, each of described determining three-dimensional grid M pushes up neighborhood of a point, comprising:

For a vertex p in three-dimensional grid Mm, top neighborhood of a point is determined by following functions:

N(pm)={ q | Dist (pm, q) and < R }

In formula, m ∈ [1, num], pmIndicate m-th of vertex on three-dimensional grid M, R is setting with vertex pmCentered on The radius of ball, Dist (pm, q) and indicate vertex pmTo the geodesic distance of vertex q.

In one embodiment, described according to the average principal curvatures and the neighborhood, determine each vertex whether be Extreme point in three-dimensional grid M, comprising:

When scale is s, vertex p is calculated using following formulamDifference coefficient difHs:

difHs(pm)=Hs+1(pm)-Hs(pm)

In formula, m ∈ [1, num], pmIndicate m-th of vertex on three-dimensional grid M;To calculate vertex p under other scalesm Difference coefficient, it is only necessary to according to actual needs modify scale.

If meeting qualifications, this vertex pmFor the extreme point of three-dimensional grid M, all extreme points are formed into a set SEP;The qualifications include first condition and second condition, vertex pmDifH when scale is ss(pmAs long as) meet institute Stating any one in first condition and second condition is to meet qualifications;

The first condition are as follows:

Vertex pmDifHs(pm) it is greater than difHs+1(pm) and difHs-1, and when scale is s, vertex pmDifHs (pm) it is greater than the difference coefficient on all vertex in its neighborhood, and when scale is s+1, vertex pmDifHs+1(pm) it is greater than its neighbour The difference coefficient on all vertex in domain, and when scale is s-1, vertex pmDifHs-1(pm) it is greater than all vertex in its neighborhood Difference coefficient;

The second condition are as follows:

Vertex pmDifHs(pm) it is less than difHs+1(pm) and difHs-1, and when scale is s, vertex pmDifHs (pm) it is less than the difference coefficient on all vertex in its neighborhood, and when scale is s+1, vertex pmDifHs+1(pm) it is less than its neighbour The difference coefficient on all vertex in domain, and when scale is s-1, vertex pmDifHs-1(pm) it is less than all vertex in its neighborhood Difference coefficient.

In one embodiment, it is described from the extreme point with filtering out key point, comprising:

Subelement is filtered according to filtering rule, set SEP is filtered, deletes the edge extreme point in set SEP, really Determine the set SKP of the key point on three-dimensional grid M;

The filtering rule specifically: in three-dimensional grid M, for any one extreme point in set SEP, if with institute The quantity for stating the side that extreme point is connected directly is less than or equal to 5, and the extreme point is then edge extreme point;By the extreme point from collection It closes and is deleted in SEP;

Subelement is filtered using element remaining in set SEP as the element in set SKP.

In the present embodiment, extreme point is filtered, improves the performance of recognition of face.Know in traditional face In other algorithm, to the extreme point in three-dimensional grid edge without excluding, in this way, symbol is described using the extreme point When generation, the inaccuracy of descriptor will lead to.By the effect of filtering subelement, the accuracy of descriptor is improved, The accuracy to 3 user's Expression Recognition of student side can be improved in turn, be conducive to 1 user of teacher side and 3 user of student side is watched The accurate assurance of the state of instructional video, while the operand of the generation descriptor of Cloud Server 2 is reduced, save calculating money Source.

In one embodiment, descriptor generation unit, for obtaining retouching for the key point according to the key point State symbol, comprising:

For a key point P in set SKPq, descriptor generation unit determines the key point according to following formula Each neighborhood shape index histogram:

In formula, PqIndicate q-th of key point in set SKP, q ∈ [1, Q], Q are the sum of key point in set SKP; NPtIndicate key point PqT-th of neighborhood when scale is s, t ∈ [1, T], T are key point PqNeighborhood when scale is s Sum;SIPq(NPt) indicate when scale is s, the shape index histogram of t-th of neighborhood of q-th of key point;KS, max(NPt) And KS, min(NPt) it is respectively maximum principal curvatures of t-th of the neighborhood at scale S and minimum principal curvatures;

Descriptor generation unit is by the key point PqEach neighborhood shape index histogram be normalized to unit to Amount, and the unit vector after normalization of connecting obtains the descriptor fP of the key pointq,

fPq=[SIPq(NP1), SIPq(NP2) ..., SIPq(NPt)]

In formula, t ∈ [1, T], T are key point PqNeighborhood sum.

In one embodiment, three-dimensional grid indicates unit, for according to the descriptor, obtaining for indicating described The expression parameter of face three-dimensional grid, comprising:

The expression parameter is denoted as F, F specifically: F=[fP1, fP2..., fPQ]。

Above embodiment of the present invention, solving traditional recognition of face can not lose to due to occurring data caused by blocking The case where face diagram of block of mistake is identified.Traditional face recognition algorithms encounter the situation and generally pass through estimation Restore the data lost, but in order to realize this purpose, traditional recognition of face generally requires to restore the number lost by hand According to which limits the application range of face recognition algorithms and service efficiencies.And the present invention passes through to the multiple crucial click-through of face Line descriptor indicates, in this manner it is possible to go to indicate a face three-dimension curved surface by multiple descriptors.Due to the face being blocked Only accounted for a part of face, the present invention can according to other parts key point to the table on the face diagram of block Feelings are identified, and then obtain the expression data of 3 user of student side of viewing instructional video, so that 1 user of teacher side is according to institute Expression data is stated to understand the teaching situation of oneself and be adjusted the teaching strategy of oneself.

In one embodiment, dictionary creation unit, for the people with same type expression by setting quantity Face diagram of block obtains dictionary corresponding to the type, comprising:

Be set with conducive to analysis 3 user of student side expression be three classes, respectively normally, happily and feel uncertain;

It include the three-dimensional song of each face of the face concentration of the face diagram of block of N number of normal class expression by one Face figure is all input to pretreatment unit, passes through pretreatment unit, key point selecting unit, descriptor generation unit, three-dimensional grid Indicate that unit obtains the normal class expression dictionary Dictnor, wherein

Dictnor=[F1, F2..., FN]

In formula, F1The expression parameter of the three-dimensional grid for the 1st face diagram of block that the face is concentrated is indicated, with this Analogize, FiIndicate the expression parameter of the three-dimensional grid for i-th of face diagram of block that the face is concentrated, i ∈ [1, N].

Similarly, happy class expression dictionary Dict can be obtainedhap, doubt class expression dictionary Dictconf

In one embodiment, recognition unit is used for according to the dictionary, three-dimensional to the face sent back to from student side 3 The generic of expression in surface chart is judged, comprising:

Obtain the face diagram of block of the corresponding user of the student side 3 sent back from student side 3;

The face diagram of block is input to pretreatment unit, by pretreatment unit, key point selecting unit, is retouched Symbol generation unit, three-dimensional grid expression unit are stated, the expression parameter F of the face diagram of block is obtainedstu=[fP1, fP2..., fPQ];

By expression parameter FstuUse Dictnor、Dicthap、DictconfRarefaction representation is carried out respectively, determines rarefaction representation knot Fruit;

Rarefaction representation result is solved, determines F respectivelystuReconstructed error in three kinds of dictionaries;

The reconstructed error and the classification thresholds error of setting are compared, determine the institute of the face diagram of block Belong to classification.

In one embodiment, described by expression parameter FstuUse Dictnor、Dicthap、DictconfIt carries out respectively sparse It indicates, determines rarefaction representation result, comprising:

Use DictnorTo expression parameter FstuRarefaction representation is carried out, specifically:

Using following functions to expression parameter FstuCarry out rarefaction representation:

In formula, X=(x1, x2..., xQ)∈R1×Q, X is the sparse matrix of setting, R1×tIndicate that this matrix is one 1 The matrix of row Q column;

Use DicthapTo expression parameter FstuRarefaction representation is carried out, specifically:

Using following functions to expression parameter FstuCarry out rarefaction representation:

In formula, X=(x1, x2..., xQ)∈R1×Q, X is the sparse matrix of setting, R1×tIndicate that this matrix is one 1 The matrix of row Q column;

Use DictconfTo expression parameter FstuRarefaction representation is carried out, specifically:

Using following functions to expression parameter FstuCarry out rarefaction representation:

In formula, X=(x1, x2..., xQ)∈R1×Q, X is the sparse matrix of setting, R1×tIndicate that this matrix is one 1 The matrix of row Q column;

In one embodiment, rarefaction representation result is solved, determines F respectivelystuReconstruct in three kinds of dictionaries Error, comprising:

Using lower surface function to DictnorTo expression parameter FstuThe rarefaction representation result for carrying out rarefaction representation is transported It calculates, finds out reconstructed error:

Wherein,

In formula, K is the sparse control parameter of setting;

Using lower surface function to DicthapTo expression parameter FstuThe rarefaction representation result for carrying out rarefaction representation is transported It calculates, finds out reconstructed error:

Wherein,

In formula, K is the sparse control parameter of setting;

Using lower surface function to DictconfTo expression parameter FstuThe rarefaction representation result for carrying out rarefaction representation is transported It calculates, finds out reconstructed error:

Wherein,

In formula, K is the sparse control parameter of setting;

In one embodiment, the reconstructed error and the classification thresholds error of setting are compared, described in determination The generic of face diagram of block, comprising:

Normal, happy, these three types of classification thresholds of feeling uncertain are respectively set as THnor、THhap、THconf

By Enor (Fstu) and THnorIt compares, if Enor (Fstu) < THnor, then the student side that is sent back from student side 3 Expression in the face diagram of block of 3 users belongs to normal class;

By Ehap (Fstu) and THnorIt compares, if Ehap (Fstu) < THhap, then sent back from student side 3 The expression caused trouble in the face diagram of block of 3 users belongs to happy class;

By Econf (Fstu) and THnorIt compares, if Econf (Fstu) < THconf, then described to be sent back from student side 3 3 user of student side face diagram of block in expression belong to doubt class;

If the expression in the face diagram of block of 3 user of student side sent back from student side 3 is unsatisfactory for above-mentioned The emotag is then unavailable classification by judgement.

Traditional face diagram of block recognizer needs to handle a large amount of key point, and operand is big, reduces algorithm Practicability, the use scope of the algorithm of limitation.But in the above-mentioned a series of embodiment of the present invention, in face three-dimensional Balance is achieved between the calculating cost and accuracy of identification of surface chart identification, the energy has been saved, has improved the efficiency of identification.Favorably In the present invention with lower energy consumption complete 3 user's human face expression data of student side acquisition, thus solution the invention solves Technical problem.

In one embodiment, the Cloud Server 2 further includes statistical module, for applying to 3 Duis of different student sides The classification results of the face diagram of block at family are counted, and obtain statistical result, and statistical result is sent to the teacher End 1;The effect that the statistical result is taught for the corresponding customer analysis oneself of teacher side 1, and make corresponding adjustment.

For example, the corresponding user of most student side 3 is when watching instructional video if the statistical result showed received There is the expression felt uncertain, the corresponding user of teacher side 1 is known that oneself may say to solve and is too deep, it is not easy to understand, therefore, The corresponding user of teacher side 1 can be adjusted lecture content, be easier to receive to say in this way, being conducive to the corresponding user of student side 3 The content of class.

Through the above description of the embodiments, those skilled in the art can be understood that it should be appreciated that can To realize the embodiments described herein with hardware, software, firmware, middleware, code or its any appropriate combination.For hardware It realizes, processor can be realized in one or more the following units: specific integrated circuit (ASIC), digital signal processor (DSP), digital signal processing appts (DSPD), programmable logic device (PLD), field programmable gate array (FPGA), processing Device, controller, microcontroller, microprocessor, other electronic units designed for realizing functions described herein or combinations thereof. For software implementations, some or all of embodiment process can instruct relevant hardware to complete by computer program. When realization, above procedure can be stored in computer-readable medium or as the one or more on computer-readable medium Instruction or code are transmitted.Computer-readable medium includes computer storage media and communication media, wherein communication media packet It includes convenient for from a place to any medium of another place transmission computer program.Storage medium can be computer can Any usable medium of access.Computer-readable medium can include but is not limited to RAM, ROM, EEPROM, CD-ROM or other Optical disc storage, magnetic disk storage medium or other magnetic storage apparatus or can be used in carry or store have instruction or data The desired program code of structure type simultaneously can be by any other medium of computer access.

Finally it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than the present invention is protected The limitation of range is protected, although explaining in detail referring to preferred embodiment to the present invention, those skilled in the art are answered Work as understanding, it can be with modification or equivalent replacement of the technical solution of the present invention are made, without departing from the reality of technical solution of the present invention Matter and range.

Claims (8)

1. a kind of teleeducation system based on cloud platform, which is characterized in that including teacher side, Cloud Server and student side;Institute Stating student side includes acquisition module, the first display module;The teacher side includes that module, the second display module are recorded in teaching;
The teaching records module for recording instructional video, and the instructional video is sent to the Cloud Server;
The Cloud Server stores the instructional video, and responds the request of student side, the instructional video is sent to described Student side;
First display module is for showing the instructional video;
The acquisition module is used to acquire and listens to the teacher information and be sent to Cloud Server;The information of listening to the teacher includes at least and student side The face diagram of block of corresponding user;
The Cloud Server is also used to analyze to obtain corresponding expression information the face diagram of block;Cloud service Device counts the expression information, and statistical result is sent to teacher side;
Second display module is for showing the statistical result.
2. a kind of teleeducation system based on cloud platform according to claim 1, which is characterized in that the Cloud Server Including database, the database is for storing the instructional video.
3. a kind of teleeducation system based on cloud platform according to claim 1, which is characterized in that the student side Quantity is multiple;The student side further includes the input module that user's inputting word information is corresponded to for student side.
4. a kind of teleeducation system based on cloud platform according to claim 1, which is characterized in that the data analysis Module includes pretreatment unit, for pre-processing to face diagram of block, obtains face three-dimensional grid;
Key point selecting unit, for determining the key point on the face three-dimensional grid according to the face three-dimensional grid;
Descriptor generation unit, for obtaining the descriptor of the key point according to the key point;
Three-dimensional grid indicates unit, for according to the descriptor, obtaining the expression ginseng for indicating the face three-dimensional grid Number;
Dictionary creation unit obtains described for the face diagram of block with same type expression by setting quantity Dictionary corresponding to type;
Recognition unit is used for according to the dictionary, to the affiliated class from the expression in the face diagram of block that student side is sent back to Do not judged.
5. a kind of teleeducation system based on cloud platform according to claim 4, which is characterized in that described to face three Dimension surface chart is pre-processed, comprising:
Grid dividing is carried out to face diagram of block using delaunay triangulation;Dividing obtained three-dimensional grid has Multiple vertex and multiple summits, any one grid are made of three vertex and three sides;The three-dimensional grid is denoted as M, in M All vertex be denoted as set a SP, SP={ P1, P2 ..., Pnum }, wherein num be M in vertex sum.
6. a kind of teleeducation system based on cloud platform according to claim 4, which is characterized in that the key clicks Select unit include scale space building subelement, curvature estimation subelement, neighborhood determine subelement, extreme point determine subelement and Filter subelement;
The scale space building subelement is used to construct the scale space of three-dimensional grid M;
The curvature estimation subelement is used to obtain average main song of the vertex each of three-dimensional grid M in setting scale Rate;
The neighborhood determines subelement for determining that each of three-dimensional grid M pushes up neighborhood of a point;
The extreme point determines subelement for determining whether each vertex is three according to the average principal curvatures and the neighborhood Tie up the extreme point in grid M;
The filtering subelement is used for from the extreme point with filtering out key point.
7. a kind of teleeducation system based on cloud platform according to claim 6, which is characterized in that the building is three-dimensional The scale space of grid M is carried out by following functions:
Wherein,
In formula,For convolution algorithm, k is the quantity of scale, and s is scale, σ0For the standard deviation of setting, d1、d2、d3Indicate dimension ginseng Number, M (x, y, z) indicate the coordinate on vertex.
8. a kind of teleeducation system based on cloud platform according to claim 7, which is characterized in that the acquisition is three-dimensional Average principal curvatures of the vertex each of grid M in setting scale, comprising:
Set be dimensioned so as to s when, for the vertex p on three-dimensional grid Mm, its average principal curvatures is calculated using following functions
In formula, m ∈ [1, num], pmIndicate m-th of vertex on three-dimensional grid M, KS, max(pm) and KS, min(pm) it is vertex pm? Maximum principal curvatures and minimum principal curvatures under scale s;α and β is the weight coefficient of setting, alpha+beta=1;
The scale for changing setting can obtain the average main song on the vertex each of three-dimensional grid M vertex under other scales Rate.
CN201811224834.5A 2018-10-19 2018-10-19 A kind of teleeducation system based on cloud platform CN109147430A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811224834.5A CN109147430A (en) 2018-10-19 2018-10-19 A kind of teleeducation system based on cloud platform

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811224834.5A CN109147430A (en) 2018-10-19 2018-10-19 A kind of teleeducation system based on cloud platform

Publications (1)

Publication Number Publication Date
CN109147430A true CN109147430A (en) 2019-01-04

Family

ID=64808701

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811224834.5A CN109147430A (en) 2018-10-19 2018-10-19 A kind of teleeducation system based on cloud platform

Country Status (1)

Country Link
CN (1) CN109147430A (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2004347786A (en) * 2003-05-21 2004-12-09 Casio Comput Co Ltd Speech display output controller, image display controller, and speech display output control processing program, image display control processing program
CN102542849A (en) * 2012-01-20 2012-07-04 东南大学 Formative evaluation system
CN102945624A (en) * 2012-11-14 2013-02-27 南京航空航天大学 Intelligent video teaching system based on cloud calculation model and expression information feedback
CN106096503A (en) * 2016-05-30 2016-11-09 东南大学 A kind of based on key point with the three-dimensional face identification method of local feature
CN106709997A (en) * 2016-04-29 2017-05-24 电子科技大学 Three-dimensional key point detection method based on deep neural network and sparse auto-encoder
CN107871416A (en) * 2017-11-06 2018-04-03 合肥亚慕信息科技有限公司 A kind of online course learning system caught based on face recognition expression

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2004347786A (en) * 2003-05-21 2004-12-09 Casio Comput Co Ltd Speech display output controller, image display controller, and speech display output control processing program, image display control processing program
CN102542849A (en) * 2012-01-20 2012-07-04 东南大学 Formative evaluation system
CN102945624A (en) * 2012-11-14 2013-02-27 南京航空航天大学 Intelligent video teaching system based on cloud calculation model and expression information feedback
CN106709997A (en) * 2016-04-29 2017-05-24 电子科技大学 Three-dimensional key point detection method based on deep neural network and sparse auto-encoder
CN106096503A (en) * 2016-05-30 2016-11-09 东南大学 A kind of based on key point with the three-dimensional face identification method of local feature
CN107871416A (en) * 2017-11-06 2018-04-03 合肥亚慕信息科技有限公司 A kind of online course learning system caught based on face recognition expression

Similar Documents

Publication Publication Date Title
Clifton Jr et al. Similarity relations among certain English sentence constructions.
Theall et al. Looking for bias in all the wrong places: a search for truth or a witch hunt in student ratings of instruction?
Massoud Computer attitudes and computer knowledge of adult students
Tobler Frame independent spatial analysis
Ferris et al. Academic oral communication needs of EAP learners: What subject‐matter instructors actually require
US8137112B2 (en) Scaffolding support for learning application programs in a computerized learning environment
Bain et al. Speech recognition in university classrooms: liberated learning project
Conference Board of the Mathematical Sciences The mathematical education of teachers
Kyongho et al. Reducing the vocabulary load and encouraging vocabulary learning through reading newspapers
Baer et al. The literacy of America's college students.
Hooghe et al. Compulsory voting in Belgium: An application of the Lijphart thesis
DeCoux Kolb's learning style inventory: A review of its applications in nursing research
Rushby An introduction to educational computing
Herrington et al. What happens when machines read our students' writing?
EP1872353A2 (en) Systems and methods for semantic knowledge assessment, instruction, and acquisition
Carroll et al. Statistics made simple for school leaders: data-driven decision making
Sampson Jr Computer-assisted testing and assessment: Current status and implications for the future
JPH11282826A (en) Electronic education system using internet
CN1437143A (en) Studying system
Mok et al. Effect of Catholic school culture on students’ achievement in the higher school certificate examination: A multilevel path analysis
Young THE EFFECTIVENESS OF SELF INSTRUCTION IN TEACHER EDUCATION USING MODELLING AND VIDEO TAPE FEEDBACK.
Hambleton et al. Computerized adaptive testing: Theory, applications, and standards
JP2004279808A (en) Telelearning system
Lamontagne et al. Textual reuse for email response
Reckase 18 Multidimensional Item Response Theory

Legal Events

Date Code Title Description
PB01 Publication
SE01 Entry into force of request for substantive examination