CN109822578A - A kind of intelligent cooking machine people system and control method - Google Patents
A kind of intelligent cooking machine people system and control method Download PDFInfo
- Publication number
- CN109822578A CN109822578A CN201910271988.8A CN201910271988A CN109822578A CN 109822578 A CN109822578 A CN 109822578A CN 201910271988 A CN201910271988 A CN 201910271988A CN 109822578 A CN109822578 A CN 109822578A
- Authority
- CN
- China
- Prior art keywords
- module
- cooking machine
- machine people
- central processing
- intelligent cooking
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Abstract
The invention belongs to intelligent robot technology fields, disclose a kind of intelligent cooking machine people system and control method, intelligent cooking machine people's system includes: power module, control module, display module, acquisition module, central processing module, operation module, conveyor module, and central processing module carries out the processing of data using support vector machines (SVM) and mixed signal control processor.SVM provided by the invention joined regularization term in solving system to optimize structure risk, it is the classifier with sparsity and robustness, it is had a wide range of applications in Identification of Images, text classification, the processing that signal is carried out using mixed signal control processor, allows intelligent cooking machine people to be completed at the same time multiple instruction.
Description
Technical field
The invention belongs to intelligent robot technology field more particularly to a kind of intelligent cooking machine people systems and controlling party
Method.
Background technique
Currently, culinary art refers to the art of diet, it is a kind of complicated and regular motion of matter form.It is to make to food
Working process keeps food more palatable, more good-looking, more smelling good.One good cooking, color, smell and taste meaning shape is supported all good, not only people is allowed to exist
Feel to meet when edible, and the nutrition of food can be allowed to be easier to be absorbed by the body.
The occasion, such as school, army and factory etc. of the existing culinary art for needing to carry out on a large scale, since meal time is non-
It often concentrates, so needing to provide diet to a large amount of crowds simultaneously, it is therefore desirable to which many cooks cook in advance, not only increase
The amount of labour of cook, and higher cost.
In conclusion problem of the existing technology is:
Existing technology, which originally cannot lead to, carries out taste, the intelligent adjusting of quantity progress according to different crowd quantity, can not
Meet the needs of large-scale crowd.
In intelligent cooking machine people's Image Information Processing of the prior art, processing capacity is poor, affects the reality of robot
Copy operation ability.
Summary of the invention
In view of the problems of the existing technology, the present invention provides a kind of intelligent cooking machine people system and control methods.
The invention is realized in this way a kind of control method of intelligent cooking machine people's system, the intelligent cooking machine
The control method of people's system includes: by control module and display module intelligent cooking machine people starting and the dish for selecting needs
Meat and fish dishes, cooking robot are acquired the movement of cooking operation person by acquisition module, are transferred to central processing module, central processing module
Movement is analyzed, is stored；
Central processing module sends instructions to operation module, and the order that operation module executes transmission carries out the production of dish,
After completing, conveyor module transfers out dish；
Cooking robot is acquired the movement of cooking operation person by controlling the angle of camera, after the completion of acquisition,
It is transferred to central processing module, the support vector machines of central processing module carries out action recognition by expansion algorithm and decomposes, and
It is stored；
Central processing module carries out in the processing of data, is carried out using motion images signal of the regularization to cooking operation person
Feature extraction obtains sampling feature vectors Y；
It is iterated optimizing using kernel functional parameter of the particle swarm algorithm to support vector machines, population utilizes solution mutual trust
The joint histogram method of breath redefines the speed and displacement more new formula of the h (e, g) and particle in joint histogram, grain
The speed and displacement more new formula of son are as follows:
Wherein, v indicates particle speed
Degree, t indicate the time, and i indicates that i-th of particle, j indicate j-th of path, and w is inertia weight, c1、c2Indicate Studying factors, pi,jTable
Show the desired positions that i-th of particle lives through, pg,jIndicate the desired positions that all particles of group live through, wherein e, g are respectively
Path to be matched and template path, h (e, g) is indicated on the position that optimal path e occurs, in the corresponding position g of historical path
The number of appearance；The speed and displacement that particle is updated by the speed and displacement more new formula of particle, find excellent solution, excellent solution formula
Are as follows:xi,jIndicate the displacement updated required for i-th of particle, j-th of path, xi,j(1)Indicate be
xi,jIt is next, changing every time, next time just be xi,j(2)；
SVM classifier is trained using the optimized parameter after optimization, image is carried out using trained classifier
Classification prediction.
Further, during the displacement of particle updates, according to xi,j=vi,j+wvi,jTo xi,jIt is modified；
With probability c1H (e, g) modifies (pi,j-xi,j) switching sequence, obtain xi,j(1)For xi,jWith
c1h(e,g)(pi,j-xi,j) sum, pi,j-xi,j(t) switching sequence of each particle and personal best particle is indicated；
With probability c2H (e, g) modifies (pg,j-xi,j) switching sequence, obtain xi,j(2)For xi,j(1)With's
With, pg,j-xi,j(t) switching sequence for indicating group's optimal location and body position updates displacement and finishes.
Further, it after carrying out classification prediction to image using trained classifier, also needs to carry out: eliminating the surprise in figure
Change part；The mathematical model for establishing two figures establishes eigenmatrix corresponding with figure, meter by the complete Vector Groups of description figure
Calculate the angle on adjacent both sides；Calculate the minimum distance between two figures；Enhancement processing to calculated result.
Further, the side length of the mathematical model polygon of the foundation and adjacent angle are by one vector S of construction counterclockwise1Table
Show polygon:
S1=(l1,α1,l2, α2…lN-1,αN-1,lN,αN)；
S1There are mapping relations one by one with the polygon, indicates unrelated with corner initial order.
Further, the complete Vector Groups have 2N vector S counterclockwise1、S2……S2N-1、S2NAnd polygon
There are mapping relations one by one, constitute a complete Vector Groups of the polygon, be expressed as follows:
S1=(l1,α1,l2, α2…lN-1,αN-1,lN,αN)；
S2=(α1,l2, α2…lN-1,αN-1,lN,αN,l1)；
……
S2N-1=(lN,αN,l1,α1,l2, α2…lN-1,αN-1)；
S2N=(αN,l1,α1,l2, α2…lN-1,αN-1,lN)；
With matrix SEIt indicates complete vector, and defines SEFor the eigenmatrix of the polygon, SEIt is expressed as follows:
Further, source figure and targeted graphical work pretreatment include: in the figure
Appropriate thresholding is set according to figure minimum containment rectangle length-width ratio, is filtered；
Thresholding is set according to side length each in the figure of source and the minimum value of perimeter ratio, removes the surpriseization part in targeted graphical；
Abbreviation processing is made to targeted graphical number of edges, makes that there is identical number of edges with source figure.
Further, the Euclidean distance of most like vector and maximum phase in source figure and targeted graphical eigenmatrix are obtained and is
Number specifically includes:
Firstly, establishing the eigenmatrix P of source figure P and targeted graphical Q respectively counterclockwiseEAnd QE:
PE=[P1 T P2 T … P2N-1 T P2N T]；
QE=[Q1 T Q2 T … Q2N-1 T Q2N T]；
Euclidean distance formula d (x, y) and included angle cosine formula sim (x, y) are as follows:
With d (x, y) and it is the basis sim (x, y), redefines two matrix Ds and S, make:
Find out the minimum value in D and S；
Eu is enabled respectivelye=min { Dij, 1≤i≤j=2N；Sime=max { Sij, 1≤i≤j=2N；
Then the eigenmatrix of needle directional structure vectorical structure figure P and Q, the above-mentioned calculation method of repetition find out two features in order again
Minimum value Eu in matrix between most complete vectorcAnd Simc；
Finally enable Eu=min { Eue, Euc}；
Sim=min { Sime, Simc}；
Eu and Sim be two figure of P, Q correspond to most like vector Euclidean distance and it is maximum mutually and coefficient.
Further, the enhancement of calculated result, which is handled, includes:
Initial vector is carried out once to repeatedly deformation, on the basis of with adjacent corner sequence structure initial vector, then
The geometrical characteristic for adding figure, using the adjacent corner of order of addition than as new initial vector；Initial vector is carried out
Multiple nonlinear processing is once arrived, carries out evolution processing using by initial vector；
Multiple similarity calculation is carried out to deformed initial vector, finally by weighted average value, with Euclidean distance Eu
It is as follows with the evaluation formula mutually with coefficient S im:
N is the number of vector deformation, k in above formulaiFor weight coefficient, EuiAnd SimiVector is European after deforming for i-th
Distance, Eu (P, Q) are the evaluation of Euclidean distance, n=4, kiTake 0.25.
Another object of the present invention is to provide a kind of intelligent cooking machine people's system, intelligent cooking machine people's system
Include:
Power module is attached with central processing module, connects domestic power supply by electric wire, is entire intelligent robot
It is energized；
Control module is attached with central processing module, and operator can be as desired by control module to culinary art
Intelligent robot is controlled；
Display module is attached with central processing module, and display panel module is display screen, and operator can pass through display
The information of module reaction further controls intelligent cooking machine people；
Acquisition module is attached with central processing module, and acquisition module is camera, and intelligent cooking machine people can pass through
Acquisition module acquires movement of the operator in culinary art and handles, stores；
Central processing module, with power module, control module, display module, acquisition module, operation module, conveyor module
It is attached, central processing module carries out the processing of data using SVM and mixed signal control processor, will treated data
Information publication instruction；
Operation module is attached with central processing module, and control cooks intelligent robot according to the operating process of input
Or the operating process of acquisition carries out the culinary art of dish；
Conveyor module is attached with central processing module, and control intelligent cooking machine people carries out the dish of completion defeated
It send.
Further, the acquisition situation of acquisition module is as follows, and intelligent cooking machine people is by the angle of control camera to behaviour
The movement of author is acquired, and after the completion of acquisition, is transferred to central processing module, the support vector machines of central processing module passes through
Expansion algorithm carries out action recognition and decomposes, and is stored.
Advantages of the present invention and good effect are as follows:
The present invention is provided with acquisition module, the movement of cook can be acquired by acquisition module, therefore can be dynamic by cook
To carry out the adjusting of taste, central processing module of the invention uses support vector machines (SVM) and mixed signal for the transformation of work
Control processor carries out the processing of data, and SVM joined regularization term in solving system to optimize structure risk, and energy is effective
The Classification and Identification rate for improving signal is the classifier with sparsity and robustness.Guarantor is provided for the demand information of crowd
Card.
Cooking robot of the present invention is acquired the movement of cooking operation person by controlling the angle of camera, has acquired
Cheng Hou, is transferred to central processing module, and the support vector machines of central processing module is carried out action recognition and divided by expansion algorithm
Solution, and stored；
Central processing module carries out in the processing of data, is carried out using motion images signal of the regularization to cooking operation person
Feature extraction obtains sampling feature vectors Y；
The present invention is iterated optimizing using kernel functional parameter of the particle swarm algorithm to support vector machines, and population is utilized and asked
The joint histogram method for solving mutual information, the speed and displacement for redefining the h (e, g) and particle in joint histogram update public
Formula, the speed and displacement more new formula of particle are as follows:
Wherein, v indicates particle speed
Degree, t indicate the time, and i indicates that i-th of particle, j indicate j-th of path, and w is inertia weight, c1、c2Indicate Studying factors, pi,jTable
Show the desired positions that i-th of particle lives through, pg,jIndicate the desired positions that all particles of group live through, wherein e, g are respectively
Path to be matched and template path, h (e, g) is indicated on the position that optimal path e occurs, in the corresponding position g of historical path
The number of appearance；The speed and displacement that particle is updated by the speed and displacement more new formula of particle, find excellent solution, excellent solution formula
Are as follows:xi,jIndicate the displacement updated required for i-th of particle, j-th of path, xi,j(1)Indicate be
xi,jIt is next, changing every time, next time just be xi,j(2)；Improve the operational capacity of robot.
The present invention improves machine to the visual discrimination effect of shape similarity, especially to manually being not easy to differentiate high similarity
The difficult point of figure has very great help；Test pattern effect has stronger stability and reliability；Detection time is short, and operation is efficient,
Implementation result is at low cost.The present invention only inquires the side of figure, reduces data processing amount.The present invention passes through constructing graphic
Eigenmatrix, suitable decision criteria is chosen, and multiple enhancement nonlinear transformation is carried out to eigenmatrix element, with majority
Value, multi-standard weighted average establish Measurement of Similarity, reached algorithm efficiently and have stronger stability
Detailed description of the invention
Fig. 1 is the structure chart of intelligent cooking machine people's system provided in an embodiment of the present invention.
In figure: 1, power module；2, control module；3, display module；4, acquisition module；5, central processing module；6, it grasps
Make module；7, conveyor module.
Fig. 2 is the processing method flow chart that SVM provided in an embodiment of the present invention carries out data.
Specific embodiment
In order to further understand the content, features and effects of the present invention, the following examples are hereby given, and cooperate attached drawing
Detailed description are as follows.
Structure of the invention is explained in detail with reference to the accompanying drawing.
As shown in Figure 1, intelligent cooking machine people's system provided in an embodiment of the present invention is provided with power module 1, control mould
Block 2, display module 3, acquisition module 4, central processing module 5, operation module 6, conveyor module 7.
Power module 1 is attached with central processing module 5, connects domestic power supply by electric wire, is entire intelligence machine
People energizes.
Control module 2 is attached with central processing module 5, and operator can be as desired by control module to cooking
Intelligent robot of preparing food is controlled.
Display module 3 is attached with central processing module 5, and display panel module is display screen, and operator can be by aobvious
Show that the information of module reaction further controls intelligent cooking machine people.
Acquisition module 4 is attached with central processing module 5, and acquisition module is camera, intelligent cooking machine people Ke Tong
It crosses movement of the acquisition module acquisition operator in culinary art and handles, stores.
Central processing module 5, with power module 1, control module 2, display module 3, acquisition module 4, operation module 6, defeated
Module 7 is sent to be attached, central processing module 5 carries out the processing of data, Neng Gouwen using SVM and mixed signal control processor
Fixed processing data information and publication instructs.
Operation module 6 is attached with central processing module 5, can control culinary art intelligent robot according to the operation of input
Process or the operating process of acquisition carry out the culinary art of dish.
Conveyor module 7 is attached with central processing module 5, can control intelligent cooking machine people to the dish of completion into
Row conveying.
Further, the acquisition situation of acquisition module 4 is as follows, and intelligent cooking machine people is by the angle of control camera to behaviour
The movement of author is acquired, and after the completion of acquisition, is transmitted to central processing module 5, the supporting vector of central processing module 5
Machine carries out action recognition by expansion algorithm and decomposes, and is stored.
Central processing module 5 is specifically included using the processing that SVM carries out data:
S101: feature extraction is carried out to signal using regularization, obtains sampling feature vectors Y；
S102: optimizing is iterated using kernel functional parameter of the particle swarm algorithm to support vector machines；
S103: being trained SVM classifier using the optimized parameter after optimization, using trained classifier to sample
Carry out classification prediction.
Further, required for input signal goes the mixed signal control processor to generate wherein from mixed signal
The output signal separated.
As the preferred embodiment of the present invention, a preprocessor can be provided in mixed signal control processor, so as to
The intrinsic directionality of input signal is improved by establishing relative time lag between input signal.In addition, being mixed being added to
Preprocessor makes improved input signal receive decorrelative transformation before closing signal control processor.It goes at mixed signal control
Output after managing the selection of device can be used as input or by another processor for further processing to enhance signal.
The working principle of the invention: intelligent cooking machine people can control to start and select by control module 2 and display module 3
The dish of needs is selected, cooking robot is acquired the movement of cook by acquisition module 4, is transferred to central processing module 5, centre
Reason 5 pairs of movements of module are analyzed, are stored, and after completing above-mentioned steps, central processing module 5 sends instructions to operation module 6, behaviour
Make the production that module 6 executes the order progress dish of transmission, after completing, conveyor module 7 transfers out dish.
In embodiments of the present invention, the control method of intelligent cooking machine people system includes: by control module and display
The dish that module intelligent cooking machine people starting and selection need, cooking robot acquire cooking operation person by acquisition module
Movement, be transferred to central processing module, central processing module is analyzed movement, stored；
Central processing module sends instructions to operation module, and the order that operation module executes transmission carries out the production of dish,
After completing, conveyor module transfers out dish；
Cooking robot is acquired the movement of cooking operation person by controlling the angle of camera, after the completion of acquisition,
It is transferred to central processing module, the support vector machines of central processing module carries out action recognition by expansion algorithm and decomposes, and
It is stored；
Central processing module carries out in the processing of data, is carried out using motion images signal of the regularization to cooking operation person
Feature extraction obtains sampling feature vectors Y；
It is iterated optimizing using kernel functional parameter of the particle swarm algorithm to support vector machines, population utilizes solution mutual trust
The joint histogram method of breath redefines the speed and displacement more new formula of the h (e, g) and particle in joint histogram, grain
The speed and displacement more new formula of son are as follows:
Wherein, v indicates particle speed
Degree, t indicate the time, and i indicates that i-th of particle, j indicate j-th of path, and w is inertia weight, c1、c2Indicate Studying factors, pi,jTable
Show the desired positions that i-th of particle lives through, pg,jIndicate the desired positions that all particles of group live through, wherein e, g are respectively
Path to be matched and template path, h (e, g) is indicated on the position that optimal path e occurs, in the corresponding position g of historical path
The number of appearance；The speed and displacement that particle is updated by the speed and displacement more new formula of particle, find excellent solution, excellent solution formula
Are as follows:xi,jIndicate the displacement updated required for i-th of particle, j-th of path, xi,j(1)Indicate be
xi,jIt is next, changing every time, next time just be xi,j(2)；
SVM classifier is trained using the optimized parameter after optimization, image is carried out using trained classifier
Classification prediction.
During the displacement of particle updates, according to xi,j=vi,j+wvi,jTo xi,jIt is modified；
With probability c1H (e, g) modifies (pi,j-xi,j) switching sequence, obtain xi,j(1)For xi,jWith
c1h(e,g)(pi,j-xi,j) sum, pi,j-xi,j(t) switching sequence of each particle and personal best particle is indicated；
With probability c2H (e, g) modifies (pg,j-xi,j) switching sequence, obtain xi,j(2)For xi,j(1)With's
With, pg,j-xi,j(t) switching sequence for indicating group's optimal location and body position updates displacement and finishes.
It after carrying out classification prediction to image using trained classifier, also needs to carry out: eliminating the surpriseization part in figure；
The mathematical model for establishing two figures establishes eigenmatrix corresponding with figure by the complete Vector Groups of description figure, calculates phase
The angle on adjacent both sides；Calculate the minimum distance between two figures；Enhancement processing to calculated result.
Further, the side length of the mathematical model polygon of the foundation and adjacent angle are by one vector S of construction counterclockwise1Table
Show polygon:
S1=(l1,α1,l2, α2…lN-1,αN-1,lN,αN)；
S1There are mapping relations one by one with the polygon, indicates unrelated with corner initial order.
The complete Vector Groups have 2N vector S counterclockwise1、S2……S2N-1、S2NHave one with polygon
One mapping relations constitute a complete Vector Groups of the polygon, are expressed as follows:
S1=(l1,α1,l2, α2…lN-1,αN-1,lN,αN)；
S2=(α1,l2, α2…lN-1,αN-1,lN,αN,l1)；
……
S2N-1=(lN,αN,l1,α1,l2, α2…lN-1,αN-1)；
S2N=(αN,l1,α1,l2, α2…lN-1,αN-1,lN)；
With matrix SEIt indicates complete vector, and defines SEFor the eigenmatrix of the polygon, SEIt is expressed as follows:
Source figure and targeted graphical, which are made to pre-process, in the figure includes:
Appropriate thresholding is set according to figure minimum containment rectangle length-width ratio, is filtered；
Thresholding is set according to side length each in the figure of source and the minimum value of perimeter ratio, removes the surpriseization part in targeted graphical；
Abbreviation processing is made to targeted graphical number of edges, makes that there is identical number of edges with source figure.
The Euclidean distance of most like vector and maximum phase and coefficient are specific in acquisition source figure and targeted graphical eigenmatrix
Include:
Firstly, establishing the eigenmatrix P of source figure P and targeted graphical Q respectively counterclockwiseEAnd QE:
PE=[P1 T P2 T … P2N-1 T P2N T]；
QE=[Q1 T Q2 T … Q2N-1 T Q2N T]；
Euclidean distance formula d (x, y) and included angle cosine formula sim (x, y) are as follows:
With d (x, y) and it is the basis sim (x, y), redefines two matrix Ds and S, make:
Find out the minimum value in D and S；
Eu is enabled respectivelye=min { Dij, 1≤i≤j=2N；Sime=max { Sij, 1≤i≤j=2N；
Then the eigenmatrix of needle directional structure vectorical structure figure P and Q, the above-mentioned calculation method of repetition find out two features in order again
Minimum value Eu in matrix between most complete vectorcAnd Simc；
Finally enable Eu=min { Eue, Euc}；
Sim=min { Sime, Simc}；
Eu and Sim be two figure of P, Q correspond to most like vector Euclidean distance and it is maximum mutually and coefficient.
The enhancement of calculated result is handled
Initial vector is carried out once to repeatedly deformation, on the basis of with adjacent corner sequence structure initial vector, then
The geometrical characteristic for adding figure, using the adjacent corner of order of addition than as new initial vector；Initial vector is carried out
Multiple nonlinear processing is once arrived, carries out evolution processing using by initial vector；
Multiple similarity calculation is carried out to deformed initial vector, finally by weighted average value, with Euclidean distance Eu
It is as follows with the evaluation formula mutually with coefficient S im:
N is the number of vector deformation, k in above formulaiFor weight coefficient, EuiAnd SimiVector is European after deforming for i-th
Distance, Eu (P, Q) are the evaluation of Euclidean distance, n=4, kiTake 0.25.
The above is only the preferred embodiments of the present invention, and is not intended to limit the present invention in any form,
Any simple modification made to the above embodiment according to the technical essence of the invention, equivalent variations and modification, belong to
In the range of technical solution of the present invention.
Claims (10)
1. a kind of control method of intelligent cooking machine people's system, which is characterized in that the control of intelligent cooking machine people's system
Method processed includes: by control module and display module intelligent cooking machine people starting and the dish for selecting needs, cooking machine
Device people acquires the movement of cooking operation person by acquisition module, is transferred to central processing module, central processing module to act into
Row analysis, storage；
Central processing module sends instructions to operation module, and the order that operation module executes transmission carries out the production of dish, production
After the completion, conveyor module transfers out dish；
Cooking robot is acquired the movement of cooking operation person by controlling the angle of camera, after the completion of acquisition, transmission
Support vector machines to central processing module, central processing module carries out action recognition by expansion algorithm and decomposes, and carries out
Storage；
Central processing module carries out in the processing of data, carries out feature using motion images signal of the regularization to cooking operation person
It extracts, obtains sampling feature vectors Y；
It is iterated optimizing using kernel functional parameter of the particle swarm algorithm to support vector machines, population utilizes solution mutual information
Joint histogram method redefines the speed and displacement more new formula of the h (e, g) and particle in joint histogram, particle
Speed and displacement more new formula are as follows:
Wherein, v indicates particle rapidity, t table
Show the time, i indicates that i-th of particle, j indicate j-th of path, and w is inertia weight, c1、c2Indicate Studying factors, pi,jIndicate i-th
The desired positions that a particle lives through, pg,jIndicate the desired positions that live through of all particles of group, wherein e, g be respectively to
With path and template path, h (e, g) is indicated on the position that optimal path e occurs, and is occurred in the corresponding position g of historical path
Number；The speed and displacement that particle is updated by the speed and displacement more new formula of particle, find excellent solution, excellent solution
Formula are as follows:xi,jIndicate the displacement updated required for i-th of particle, j-th of path, xi,j(1)Table
That show is xi,jIt is next, changing every time, next time just be xi,j(2)；
SVM classifier is trained using the optimized parameter after optimization, is classified using trained classifier to image
Prediction.
2. the control method of intelligent cooking machine people's system as described in claim 1, which is characterized in that the displacement of particle updates
In, according to xi,j=vi,j+wvi,jTo xi,jIt is modified；
With probability c1H (e, g) modifies (pi,j-xi,j) switching sequence, obtain xi,j(1)For xi,jWith c1h(e,g)(pi,j-xi,j) sum,
pi,j-xi,j(t) switching sequence of each particle and personal best particle is indicated；
With probability c2H (e, g) modifies (pg,j-xi,j) switching sequence, obtain xi,j(2)For xi,j(1)With c2h(e,g)(pg,j-xi,j)
With pg,j-xi,j(t) switching sequence for indicating group's optimal location and body position updates displacement and finishes.
3. the control method of intelligent cooking machine people's system as described in claim 1, which is characterized in that
It after carrying out classification prediction to image using trained classifier, also needs to carry out: eliminating the surpriseization part in figure；It establishes
The mathematical model of two figures establishes eigenmatrix corresponding with figure by the complete Vector Groups of description figure, calculates adjacent two
The angle on side；Calculate the minimum distance between two figures；Enhancement processing to calculated result.
4. the control method of intelligent cooking machine people's system as claimed in claim 3, which is characterized in that the mathematics of the foundation
The side length of model polygon and adjacent angle are by one vector S of construction counterclockwise1Indicate polygon:
S1=(l1,α1,l2, α2…lN-1,αN-1,lN,αN)；
S1There are mapping relations one by one with the polygon, indicates unrelated with corner initial order.
5. the control method of intelligent cooking machine people's system as claimed in claim 3, which is characterized in that the complete vector
Group has 2N vector S counterclockwise1、S2……S2N-1、S2NThere are mapping relations one by one with polygon, it is more to constitute this
One complete Vector Groups of side shape, are expressed as follows:
S1=(l1,α1,l2, α2…lN-1,αN-1,lN,αN)；
S2=(α1,l2, α2…lN-1,αN-1,lN,αN,l1)；
……
S2N-1=(lN,αN,l1,α1,l2, α2…lN-1,αN-1)；
S2N=(αN,l1,α1,l2, α2…lN-1,αN-1,lN)；
With matrix SEIt indicates complete vector, and defines SEFor the eigenmatrix of the polygon, SEIt is expressed as follows:
6. the control method of intelligent cooking machine people's system as claimed in claim 3, which is characterized in that source figure in the figure
Shape and targeted graphical make pretreatment
Appropriate thresholding is set according to figure minimum containment rectangle length-width ratio, is filtered；
Thresholding is set according to side length each in the figure of source and the minimum value of perimeter ratio, removes the surpriseization part in targeted graphical；
Abbreviation processing is made to targeted graphical number of edges, makes that there is identical number of edges with source figure.
7. the control method of intelligent cooking machine people's system as claimed in claim 3, which is characterized in that obtain source figure and mesh
The Euclidean distance of most like vector and maximum phase and coefficient specifically include in shape of marking on a map eigenmatrix:
Firstly, establishing the eigenmatrix P of source figure P and targeted graphical Q respectively counterclockwiseEAnd QE:
PE=[P1 T P2 T…P2N-1 T P2N T]；
QE=[Q1 T Q2 T…Q2N-1 T Q2N T]；
Euclidean distance formula d (x, y) and included angle cosine formula sim (x, y) are as follows:
With d (x, y) and it is the basis sim (x, y), redefines two matrix Ds and S, make:
Find out the minimum value in D and S；
Eu is enabled respectivelye=min { Dij, 1≤i≤j=2N；Sime=max { Sij, 1≤i≤j=2N；
Then the eigenmatrix of needle directional structure vectorical structure figure P and Q, the above-mentioned calculation method of repetition find out two eigenmatrixes in order again
In minimum value Eu between most complete vectorcAnd Simc；
Finally enable Eu=min { Eue, Euc}；
Sim=min { Sime, Simc}；
Eu and Sim be two figure of P, Q correspond to most like vector Euclidean distance and it is maximum mutually and coefficient.
8. the control method of intelligent cooking machine people's system as claimed in claim 3, which is characterized in that the enhancing of calculated result
Property processing include:
Initial vector once on the basis of with adjacent corner sequence structure initial vector, then add to repeatedly deformation
The geometrical characteristic of figure, using the adjacent corner of order of addition than as new initial vector；Initial vector is carried out primary
To multiple nonlinear processing, evolution processing is carried out using by initial vector；
Multiple similarity calculation is carried out to deformed initial vector, finally by weighted average value, with Euclidean distance Eu and phase
It is as follows with the evaluation formula of coefficient S im:
N is the number of vector deformation, k in above formulaiFor weight coefficient, EuiAnd SimiThe Euclidean distance of vector after being deformed for i-th,
Eu (P, Q) is the evaluation of Euclidean distance, n=4, kiTake 0.25.
9. a kind of intelligent cooking machine people's system, which is characterized in that intelligent cooking machine people's system includes:
Power module is attached with central processing module, is connected domestic power supply by electric wire, is carried out for entire intelligent robot
Energy supply；
Control module is attached with central processing module, and operator can be as desired by control module to culinary art intelligence
Robot is controlled；
Display module is attached with central processing module, and display panel module is display screen, and operator can pass through display module
The information of reaction further controls intelligent cooking machine people；
Acquisition module is attached with central processing module, and acquisition module is camera, and intelligent cooking machine people can pass through acquisition
Module acquires movement of the operator in culinary art and handles, stores；
Central processing module is carried out with power module, control module, display module, acquisition module, operation module, conveyor module
Connection, central processing module carry out the processing of data using SVM and mixed signal control processor, will treated data information
Publication instruction；
Operation module is attached with central processing module, control culinary art intelligent robot according to the operating process of input or
The operating process of acquisition carries out the culinary art of dish；
Conveyor module is attached with central processing module, and control intelligent cooking machine people conveys the dish of completion.
10. intelligent cooking machine people's system as claimed in claim 9, which is characterized in that the acquisition situation of acquisition module is as follows,
Intelligent cooking machine people is acquired the movement of operator by controlling the angle of camera, after the completion of acquisition, is transferred to
Processing module is entreated, the support vector machines of central processing module carries out action recognition by expansion algorithm and decomposes, and is stored.
Further, central processing module is specifically included using the processing that SVM carries out data:
Step 1, feature extraction is carried out to EEG signals using regularization, obtains sampling feature vectors Y；
Step 2, optimizing is iterated using kernel functional parameter of the particle swarm algorithm to support vector machines；
Step 3, SVM classifier is trained using the optimized parameter after optimization, using trained classifier to sample into
Row classification prediction.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910271988.8A CN109822578A (en) | 2019-04-04 | 2019-04-04 | A kind of intelligent cooking machine people system and control method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910271988.8A CN109822578A (en) | 2019-04-04 | 2019-04-04 | A kind of intelligent cooking machine people system and control method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109822578A true CN109822578A (en) | 2019-05-31 |
Family
ID=66874857
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910271988.8A Pending CN109822578A (en) | 2019-04-04 | 2019-04-04 | A kind of intelligent cooking machine people system and control method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109822578A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110919650A (en) * | 2019-11-20 | 2020-03-27 | 江苏大学 | Low-delay grabbing teleoperation system based on SVM (support vector machine) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7174830B1 (en) * | 2003-06-05 | 2007-02-13 | Dawei Dong | Robotic cooking system |
| CN103777595A (en) * | 2013-12-30 | 2014-05-07 | 深圳市德宝威科技有限公司 | Robot system, robot office affair handling system, robot teaching system, robot designing system, robot engineering system and robot household system |
| CN105354866A (en) * | 2015-10-21 | 2016-02-24 | 郑州航空工业管理学院 | Polygon contour similarity detection method |
| CN105459127A (en) * | 2015-12-31 | 2016-04-06 | 葛武 | Cooking robot |
| CN105740887A (en) * | 2016-01-26 | 2016-07-06 | 杭州电子科技大学 | Electroencephalogram feature classification method based on PSO-SVM (Particle Swarm Optimization-Support Vector Machine) |
| CN106250979A (en) * | 2016-08-16 | 2016-12-21 | 安阳师范学院 | A kind of particle group optimizing method based on mutual information similarity Strategy |
| CN106272446A (en) * | 2016-08-01 | 2017-01-04 | 纳恩博（北京）科技有限公司 | The method and apparatus of robot motion simulation |
-
2019
- 2019-04-04 CN CN201910271988.8A patent/CN109822578A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7174830B1 (en) * | 2003-06-05 | 2007-02-13 | Dawei Dong | Robotic cooking system |
| CN103777595A (en) * | 2013-12-30 | 2014-05-07 | 深圳市德宝威科技有限公司 | Robot system, robot office affair handling system, robot teaching system, robot designing system, robot engineering system and robot household system |
| CN105354866A (en) * | 2015-10-21 | 2016-02-24 | 郑州航空工业管理学院 | Polygon contour similarity detection method |
| CN105459127A (en) * | 2015-12-31 | 2016-04-06 | 葛武 | Cooking robot |
| CN105740887A (en) * | 2016-01-26 | 2016-07-06 | 杭州电子科技大学 | Electroencephalogram feature classification method based on PSO-SVM (Particle Swarm Optimization-Support Vector Machine) |
| CN106272446A (en) * | 2016-08-01 | 2017-01-04 | 纳恩博（北京）科技有限公司 | The method and apparatus of robot motion simulation |
| CN106250979A (en) * | 2016-08-16 | 2016-12-21 | 安阳师范学院 | A kind of particle group optimizing method based on mutual information similarity Strategy |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110919650A (en) * | 2019-11-20 | 2020-03-27 | 江苏大学 | Low-delay grabbing teleoperation system based on SVM (support vector machine) |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106446930B (en) | Robot operative scenario recognition methods based on deep layer convolutional neural networks | |
| CN110287863B (en) | Gesture recognition method based on WiFi signal | |
| CN105095902B (en) | Picture feature extracting method and device | |
| CN105938564A (en) | Rice disease recognition method based on principal component analysis and neural network and rice disease recognition system thereof | |
| Herdiyeni et al. | Combination of morphological, local binary pattern variance and color moments features for indonesian medicinal plants identification | |
| CN108596102A (en) | Indoor scene object segmentation grader building method based on RGB-D | |
| CN105262991B (en) | A kind of substation equipment object identifying method based on Quick Response Code | |
| CN109117897A (en) | Image processing method, device and readable storage medium storing program for executing based on convolutional neural networks | |
| CN109409994A (en) | The methods, devices and systems of analog subscriber garments worn ornaments | |
| CN103514459A (en) | Method and system for identifying crop diseases and pests based on Android mobile phone platform | |
| CN104063686A (en) | System and method for performing interactive diagnosis on crop leaf segment disease images | |
| CN105701467A (en) | Many-people abnormal behavior identification method based on human body shape characteristic | |
| CN109446889A (en) | Object tracking method and device based on twin matching network | |
| CN109376625A (en) | A kind of human facial expression recognition method based on convolutional neural networks | |
| CN109190559A (en) | A kind of gesture identification method, gesture identifying device and electronic equipment | |
| CN108537168A (en) | Human facial expression recognition method based on transfer learning technology | |
| CN106022467A (en) | Crop disease detection system based on neural network | |
| Zhu et al. | A modified deep neural network enables identification of foliage under complex background | |
| CN106296709A (en) | A kind of based on population and the cell image segmentation method of fuzzy means clustering | |
| WO2024060978A1 (en) | Key point detection model training method and apparatus and virtual character driving method and apparatus | |
| CN115343704A (en) | Gesture recognition method of FMCW millimeter wave radar based on multi-task learning | |
| CN112528811A (en) | Behavior recognition method and device | |
| CN109822578A (en) | A kind of intelligent cooking machine people system and control method | |
| CN111507325A (en) | Industrial visual OCR recognition system and method based on deep learning | |
| Yang et al. | Visual saliency detection with center shift |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190531 |
|
| RJ01 | Rejection of invention patent application after publication |