CN107742181A - A kind of tableware recognition methods for intelligent scoring of being set a table for Chinese meal dinner party table top - Google Patents
A kind of tableware recognition methods for intelligent scoring of being set a table for Chinese meal dinner party table top Download PDFInfo
- Publication number
- CN107742181A CN107742181A CN201710897544.6A CN201710897544A CN107742181A CN 107742181 A CN107742181 A CN 107742181A CN 201710897544 A CN201710897544 A CN 201710897544A CN 107742181 A CN107742181 A CN 107742181A
- Authority
- CN
- China
- Prior art keywords
- tableware
- circle
- center
- recognition methods
- table top
- 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.)
- Granted
Links
Classifications
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/12—Hotels or restaurants
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
- G06Q50/2057—Career enhancement or continuing education service
Abstract
Set a table the tableware recognition methods of intelligent scoring for Chinese meal dinner party table top the present invention relates to a kind of, the tableware recognition methods includes circular tableware recognition methods, tableware packet merger and sorting technique, table top center identification and method of selecting, and special-shaped tableware recognition methods.Tableware recognition methods of the present invention solve centering dinner can table top effect of setting a table carry out one of existing main bugbear during intelligent appraisement --- problem of image recognition, obstacle has been cleared away for smooth application of the new technologies such as artificial intelligence in the field.Tableware recognition methods of the present invention is realized according to Digital Image Processing algorithm completely, both without doing any transformation in itself to tableware, without setting up other any hardware facilities, hardware input is zero, innate advantage thus with low cost, be advantageous to it in the related pre-internship time course of Tourism & hotel industry and Skill Competition popularization and application.
Description
Technical field
The invention belongs to Tourism & hotel industry field, and in particular to one kind is managed using machine vision and artificial intelligence
By the tableware recognition methods for effect progress intelligent scoring of being set a table with method centering dinner meeting table top.
Background technology
Tourism and hotel management, it is one of global ten big hot topic industries.Disappear along with Chinese Economy Development and people's lives
Take process of the center of gravity from " food " to " You Yangle " transition with upgrading, the domestic demand to the Tourism & hotel industry talent
Also increasingly increasing.In, western-style food dinner party table top is set a table is that Tourism & hotel industry student is necessary in personnel training
The basic training of grasp, most domestic Vocationl Technical College have the dinner party table top opened up for the Major to set a table theme
Pre-internship time course and Skill Competition etc..
However, the outstanding problem that presently, there are is:The set a table judge of effect of student is all by real training teacher or big
What match judging panel was measured by estimating with instrument.Following disadvantage be present in this complete artificial, mode of manual measurement:1. it is laborious,
Workload is big, in particular for once evaluate dozens of student set a table effect when, the measurement amount of labour right and wrong of teacher or judging panel
Chang Fanchong's;2. time-consuming, measurement and marking evaluation expend time length, it is impossible to are instantly available the appraisal result for effect of setting a table, neither
Adapt to all kinds of Skill Competition scenes should field provide the needs of result of the match, can not also meet to require classroom in modern teaching mode
On the result of setting a table of student is commented on and fed back the requirement of raising;3. precision is low, due to right in effect score by rules of setting a table
Required distance is accurate to grade, and manual measurement is extremely difficult to such required precision;4. stability is poor, and by the subjectivity of people
Property influences serious, and the result of setting a table of same student, different teachers or judging panel may provide different scorings.
A kind of feasible solution is that image processing and artificial intelligence technology is introduced into Tourism & hotel industry
Table top is set a table in effect judge, is thoroughly changed and was fully relied on the present situation manually judged originally, also overcomes original judge mode to exist
Many disadvantages.In realizing, western-style food dinner party table top set a table the intelligent scoring of effect, standing in the breach, to be solved is exactly that tableware is known
Other problem.A kind of base is provided in disclosed patent (publication number " CN204856749U ", title " tableware identification computing system ")
In the tableware identifying schemes of REID, the built-in installation storage chip inside tableware is mainly characterized by, in addition also one
The RFID chip read write line to match with tableware RFID chip, for reading tableware chip information.Patent (publication number
" CN204557573U ", title " automatic set meal marketing system ") in then reached by way of identifying and being encoded on tableware tableware knowledge
Other purpose, possible coding form include the recognizable volume that bar code, Quick Response Code, RFID radio frequency chips or alphanumeric are formed
Code.Above two method is required for transforming tableware, if it is more complicated to install radio frequency chip additional inside tableware;Also need to set up
A whole set of is used for the hardware devices such as the scanner of coded scanning/reading or chip read-write and server;In addition, both approaches are only
The classification of tableware can be identified, and cannot get the information such as positioning and the relative distance of tableware.Thus, the above method is not suitable for travelling
The occasion judged with effect of being set a table in hotel management specialty to table top, need to look for another way, and invent new tableware recognition methods.
The content of the invention
Set a table the tableware recognition methods of intelligent scoring for Chinese meal dinner party table top it is an object of the invention to provide a kind of, gram
One of existing main difficulty, realizes Chinese meal dinner party when machine vision and artificial intelligence theory and method are applied to the subject under discussion by clothes
Table top set a table effect scoring automate, be rapid, objectifying and it is intelligent, thoroughly change in the subdivision field and fully rely on people
The present situation that work is judged.
In order to achieve the above object, the technical solution adopted in the present invention is:
A kind of tableware recognition methods for intelligent scoring of being set a table for Chinese meal dinner party table top, it is characterised in that the tableware is known
Other method includes circular tableware recognition methods, tableware packet merger and sorting technique, table top center identification and method of selecting, and
Special-shaped tableware recognition methods;
The circular tableware recognition methods is used for meal dish, soup bowl, taste dish, cup, wineglass and white spirit cup totally 6 kinds of tablewares
Identification, recognition result be circular tableware central coordinate of circle and radius information, by calculating the gradient vector at doubtful circumferential point,
Then using obtained gradient, the doubtful circumferential point of distance specifies search for respectively looking at radius on the gradient direction and its opposite direction
A bit, and the number of choosing of the point is recorded, the home position of doubtful circle is finally determined according to voting results;
The tableware packet merger and sorting technique include packet merging method and sorting technique, wherein, it is grouped merger side
Method uses k-means clustering methods, and clusters number is arranged to Chinese meal dinner party guest's number and adds 1, i.e., dining table center vase and guest
Tableware is put on an equal footing, and is also identified using circular tableware recognition methods;Radius difference and position of the sorting technique by different tablewares
The tableware group after relation pair merger is put to be classified, classification results be specify meal dish in tableware group, soup bowl, taste dish,
The class label and central coordinate of circle information of cup, wineglass and white spirit cup totally 6 kinds of tablewares;
The table top center identification and method of selecting are used for the determination of Chinese meal dinner party table top central point, comprising recognition methods and
Method of selecting, wherein, recognition methods obtains its central coordinate of circle using the circular tableware recognition methods identification dining table center vase
And radius information;There is the situation in multiple centers of circle in the dining table center vase group that method of selecting is used for after merger;
The special-shaped tableware recognition methods is used for the identification of chopsticks rack, chopsticks sheath, soup ladle, toothpick wrapper and menu totally 5 kinds of tablewares, knows
Center and four vertex point coordinate informations of the other result for special-shaped tableware edge contour boundary rectangle, can table top pendulum by centering dinner
Platform image obtains the edge contour of special-shaped tableware after carrying out binary conversion treatment, then draws the minimum area-encasing rectangle of the edge contour
As its boundary rectangle.
Further, the specific steps of the tableware recognition methods progress tableware identification include:
Step 1:Chinese meal dinner party table top is received to set a table image set;
Step 2:Circular tableware recognition methods identification is called to specify table top to set a table all circular tablewares in image, and meal
Table center vase;
Step 3:Call tableware packet merging method to look for round result to cluster circular tableware recognition methods, obtain total
Number is more than Chinese meal dinner party guest's number 1 tableware group;
Step 4:The sequence number for tableware group of the image determination with positive vertical view visual angle of being set a table according to table top;
Step 5:Tableware specification method is called, is obtained with the meal dish in the positive tableware group for overlooking visual angle, soup bowl, taste
The class label and central coordinate of circle information of dish, cup, wineglass and white spirit cup totally 6 kinds of tablewares;
Step 6:Table top center method of selecting is called, determines table top centre coordinate;
Step 7:Special-shaped tableware recognition methods is called, obtains chopsticks rack, chopsticks sheath, soup ladle, toothpick wrapper and menu totally 5 kinds of tablewares
The center of edge contour boundary rectangle and four vertex point coordinate informations;
Step 8:Judge whether to perform circulate operation to all images in image set, be then to continue in next step, otherwise to select
In lower piece image and go to step 2;
Step 9:Export all tableware identification informations.
Further, the table top center method of selecting specific steps include:
Step 601:Calculate all centers of circle and Chinese meal dinner party table top in the vase group of dining table center set a table picture centre away from
From, and be stored in pre-defined distance vector;
Step 602:Being arranged apart from element by numerical values recited ascending order in distance vector;
Step 603:For specified in distance vector one apart from element, corresponding central coordinate of circle is found;
Step 604:The current center of circle is calculated respectively with two groups with the meal dish center in the positive tableware group for overlooking visual angle
Distance;
Step 605:Whether the deviation of two distances (distance at the current center of circle and two meal dish centers) in judgment step 604
Within 5%, if it is, the sequence number in the current center of circle is stored in pre-defined center of circle sequence number vector;
Step 606:Judge whether to adjust the distance in vector it is each perform completion apart from element circular, be continue it is next
Step, otherwise by subscript from increasing 1, and 604 are gone to step, perform next operation apart from element in vector of adjusting the distance;
Step 607:Judge whether the element number in the sequence number vector of the center of circle is more than 1, be then to continue in next step, otherwise to continue
Judge element number whether be equal to 1, be then using the center of circle corresponding to the only element in the sequence number vector of the center of circle as table top center, and
611 are gone to step, if the element number in the sequence number vector of the center of circle is 0, needs to relax apart from deviation threshold in step 605, and turns step
Rapid 604 re-execute circulation;
Step 608:Now whether the element number in center of circle sequence number vector is more than 1, takes the first two element, finds respectively pair
The center of circle answered and radius, calculate the distance between two centers of circle;
Step 609:Judge whether the distance between two centers of circle are less than larger radius of circle, be then to continue in next step, it is no
Then correspond to dining table center vase bottleneck and bottle tripe only finds a circle, but mistake have found circle, and the circle elsewhere on table top
The center of circle and the range deviation satisfaction requirement for choosing meal dish, at this moment take the less center of circle of range deviation as table top center, and turn step
Rapid 611;
Step 610:Corresponding dining table center vase bottleneck and bottle tripe find round situation simultaneously, take the circle conduct that radius is larger
Table top center;
Step 611:Export the table top central information determined.
Further, the circular tableware recognition methods also needs to set the maximum and minimum value for looking for radius of circle, is respectively
Twice of maximum circular tableware radius and the 1/3 of smallest circular tableware radius.
Further, the threshold value of the binary conversion treatment of the special-shaped tableware recognition methods is arranged to gray value 124.
Compared with prior art, the beneficial effects of the invention are as follows:Tableware recognition methods of the present invention solves centering
Dinner can table top effect of setting a table carry out one of existing main bugbear during intelligent appraisement --- problem of image recognition, be artificial intelligence
Obstacle has been cleared away etc. smooth application of the new technology in the field, and then has realized that Chinese meal dinner party table top is set a table the automatic of effect scoring
Change, be rapid, objectifying and be intelligent, thoroughly changing in the subdivision field and fully rely on the present situation manually judged.In addition, with showing
There is method to compare, tableware recognition methods of the present invention is realized according to Digital Image Processing algorithm completely, both without to tableware
Any transformation itself is done, without other any hardware facilities are set up, hardware input is zero, thus with the congenital excellent of low cost
Gesture, be advantageous to it in the related pre-internship time course of Tourism & hotel industry and Skill Competition popularization and application.
Brief description of the drawings
Fig. 1 is the structural representation of the tableware recognition methods of the present invention.
Fig. 2 be the present invention centering dinner can table top set a table image set carry out tableware identification idiographic flow block diagram.
Fig. 3 is the idiographic flow block diagram of the table top center method of selecting in the tableware recognition methods of the present invention.
Fig. 4 is that the randomly selected Chinese meal dinner party table top in embodiment provided by the invention is set a table image.
Fig. 5 is circular tableware recognition methods and tableware packet merging method pair in the tableware recognition methods of the application present invention
The result images of operation are identified in Fig. 4.
Fig. 6 is result of the tableware specification method in the tableware recognition methods of the application present invention to Fig. 4 progress tableware specifications
Image.
Fig. 7 is to the specified tableware group in Fig. 4 using the special-shaped tableware recognition methods in tableware recognition methods of the invention
The result images that other chopsticks rack is identified.
Embodiment
For the ease of those of ordinary skill in the art understand and implement the present invention, the present invention is made with reference to embodiment into
The detailed description of one step, it will be appreciated that implementation example described herein is merely to illustrate and explain the present invention, and is not used to limit
The fixed present invention.
Referring to Fig. 1, for the structural representation of tableware recognition methods of the present invention.Described tableware recognition methods includes
Circular tableware recognition methods, tableware packet merger and sorting technique, table top center identification and method of selecting, and special-shaped tableware are known
Other method.
The circular tableware recognition methods is used for meal dish, soup bowl, taste dish, cup, wineglass and white spirit cup totally 6 kinds of tablewares
Identification, recognition result be circular tableware central coordinate of circle and radius information, by calculating the gradient vector at doubtful circumferential point,
Then using obtained gradient, the doubtful circumferential point of distance specifies search for respectively looking at radius on the gradient direction and its opposite direction
A bit, and the number of choosing of the point is recorded, the home position of doubtful circle is finally determined according to voting results.The circular tableware is known
Other method also needs to set the maximum and minimum value for looking for radius of circle, is respectively twice and smallest circular of maximum circular tableware radius
The 1/3 of tableware radius.
The tableware packet merger and sorting technique include packet merging method and sorting technique, wherein, it is grouped merger side
Method uses k-means clustering methods, and clusters number is arranged to Chinese meal dinner party guest's number and adds 1, i.e., dining table center vase and guest
Tableware is put on an equal footing, and is also identified using circular tableware recognition methods;Radius difference and position of the sorting technique by different tablewares
The tableware group after relation pair merger is put to be classified, classification results be specify meal dish in tableware group, soup bowl, taste dish,
The class label and central coordinate of circle information of cup, wineglass and white spirit cup totally 6 kinds of tablewares.
The table top center identification and method of selecting are used for the determination of Chinese meal dinner party table top central point, comprising recognition methods and
Method of selecting, wherein, recognition methods obtains its central coordinate of circle using the circular tableware recognition methods identification dining table center vase
And radius information;There is the situation in multiple centers of circle in the dining table center vase group that method of selecting is used for after merger.
The special-shaped tableware recognition methods is used for the identification of chopsticks rack, chopsticks sheath, soup ladle, toothpick wrapper and menu totally 5 kinds of tablewares, knows
Center and four vertex point coordinate informations of the other result for special-shaped tableware edge contour boundary rectangle, can table top pendulum by centering dinner
Platform image obtains the edge contour of special-shaped tableware after carrying out binary conversion treatment, then draws the minimum area-encasing rectangle of the edge contour
As its boundary rectangle.The threshold value of binary conversion treatment is arranged to gray value 124.
Referring to Fig. 2, the idiographic flow for image set progress tableware identification of being set a table for centering dinner of the present invention meeting table top
Block diagram.Idiographic flow is as follows:
Step 1:Chinese meal dinner party table top is received to set a table image set;
Step 2:Circular tableware recognition methods identification is called to specify table top to set a table all circular tablewares in image, and meal
Table center vase;
Step 3:Call tableware packet merging method to look for round result to cluster circular tableware recognition methods, obtain total
Number is more than Chinese meal dinner party guest's number 1 tableware group;
Step 4:The sequence number for tableware group of the image determination with positive vertical view visual angle of being set a table according to table top;
Step 5:Tableware specification method is called, is obtained with the meal dish in the positive tableware group for overlooking visual angle, soup bowl, taste
The class label and central coordinate of circle information of dish, cup, wineglass and white spirit cup totally 6 kinds of tablewares;
Step 6:Table top center method of selecting is called, determines table top centre coordinate;
Step 7:Special-shaped tableware recognition methods is called, obtains chopsticks rack, chopsticks sheath, soup ladle, toothpick wrapper and menu totally 5 kinds of tablewares
The center of edge contour boundary rectangle and four vertex point coordinate informations;
Step 8:Judge whether to perform circulate operation to all images in image set, be then to continue in next step, otherwise to select
In lower piece image and go to step 2;
Step 9:Export all tableware identification informations.
Referring to Fig. 3, for the idiographic flow block diagram of the table top center method of selecting in tableware recognition methods of the present invention.
Idiographic flow is as follows:
Step 601:Calculate all centers of circle and Chinese meal dinner party table top in the vase group of dining table center set a table picture centre away from
From, and be stored in pre-defined distance vector;
Step 602:Being arranged apart from element by numerical values recited ascending order in distance vector;
Step 603:For specified in distance vector one apart from element, corresponding central coordinate of circle is found;
Step 604:The current center of circle is calculated respectively with two groups with the meal dish center in the positive tableware group for overlooking visual angle
Distance;
Step 605:Whether the deviation of two distances (distance at the current center of circle and two meal dish centers) in judgment step 604
Within 5%, if it is, the sequence number in the current center of circle is stored in pre-defined center of circle sequence number vector;
Step 606:Judge whether to adjust the distance in vector it is each perform completion apart from element circular, be continue it is next
Step, otherwise by subscript from increasing 1, and 604 are gone to step, perform next operation apart from element in vector of adjusting the distance;
Step 607:Judge whether the element number in the sequence number vector of the center of circle is more than 1, be then to continue in next step, otherwise to continue
Judge element number whether be equal to 1, be then using the center of circle corresponding to the only element in the sequence number vector of the center of circle as table top center, and
611 are gone to step, if the element number in the sequence number vector of the center of circle is 0, needs to relax apart from deviation threshold in step 605, and turns step
Rapid 604 re-execute circulation;
Step 608:Now whether the element number in center of circle sequence number vector is more than 1, takes the first two element, finds respectively pair
The center of circle answered and radius, calculate the distance between two centers of circle;
Step 609:Judge whether the distance between two centers of circle are less than larger radius of circle, be then to continue in next step, it is no
Then correspond to dining table center vase bottleneck and bottle tripe only finds a circle, but mistake have found circle, and the circle elsewhere on table top
The center of circle and the range deviation satisfaction requirement for choosing meal dish, at this moment take the less center of circle of range deviation as table top center, and turn step
Rapid 611;
Step 610:Corresponding dining table center vase bottleneck and bottle tripe find round situation simultaneously, take the circle conduct that radius is larger
Table top center;
Step 611:Export the table top central information determined.
Referring to Fig. 4, the piece image in image set of being set a table for randomly selected Chinese meal dinner party table top.Substep is applied below
The tableware group wherein specified is identified for the tableware recognition methods of the present invention.
Referring to Fig. 5, merger is grouped for the circular tableware recognition methods in the tableware recognition methods of the application present invention and tableware
Method Fig. 4 is identified the result images of operation.In Figure 5, the circular tableware found, and circle have been gone out with the circle of light color
In serial number tableware packet merger after group sequence number.Need to identify in Fig. 5 is proximate to meal center-right below image
Has group, the group serial number 1 in figure.In addition to the tableware group that this group needs identifies, knowledge also have also been made to other tablewares
Not, the situation of erroneous judgement is there may be when identifying other tablewares.As seen from Figure 5, in other tableware groups such as meal dish
There is deviation with cup etc., but due to these wrong recognition results are in our target tableware group, thus not shadow
Ring final result.
Referring to Fig. 6, tableware specification is carried out to Fig. 4 for the tableware specification method in the tableware recognition methods of the application present invention
Result images, classification results are to specify totally 6 kinds of meal dish, soup bowl, taste dish, cup, wineglass and white spirit cup in tableware group 1
The class label and central coordinate of circle information of tableware, these information are clearly demonstrated in Fig. 6, as the central coordinate of circle of meal dish is
(3174.75,2967.75), radius 201.953, unit are pixel.In addition, also to wrong merger in this tableware group
Circle information rejected, the circle information being removed is:Central coordinate of circle (3283,2188), radius 59.Other tableware classifications
If the recognition result of soup bowl, taste dish, cup, wineglass and white spirit cup is as shown in fig. 6, repeat no more.
After circular tableware identification is completed, then table top center will be determined.It is to call table top center identification first
Method, same method is identified with circular tableware because table top center uses, is completed simultaneously with the identification of circular tableware, packet is returned
And result display that in Figure 5.As shown in Figure 5, the group serial number 2 of dining table center vase.It is pointed out that except meal
Outside the vase of table center, circle is also mistakenly have found on the scaling board of table top, and merger is in group 2.At this moment need to call
Table top center method of selecting.The distance vector and relevant information obtained using the method for selecting is as shown in the table.
The dining table center all centers of circle of vase group of table 1 and table top are set a table the distance and relevant information of picture centre
As can be seen from Table 1, the deviation of the pixel distance at all centers of circle of dining table center vase group and specified meal dish center
In data, only the center of circle of serial number 8 meets the requirement less than 5%, so this 8 is added in the sequence number vector of the center of circle.
After having performed the step 606 in the method for selecting of table top center, the element number in the sequence number vector of the center of circle is only
For 1, so at this moment directly using the center of circle corresponding to this only element as table top center.
It is to the specified meal in Fig. 4 using the special-shaped tableware recognition methods in tableware recognition methods of the invention referring to Fig. 7
Have the result images that the chopsticks rack of group is identified, identify the chopsticks rack for the specified tableware group that identification obtains in Fig. 7 with numeral 1
Edge contour boundary rectangle.
It should be appreciated that the part that this specification does not elaborate belongs to prior art.
It should be appreciated that the above-mentioned description for preferred embodiment is more detailed, therefore can not be considered to this
The limitation of invention patent protection scope, one of ordinary skill in the art are not departing from power of the present invention under the enlightenment of the present invention
Profit is required under protected ambit, can also be made replacement or deformation, be each fallen within protection scope of the present invention, this hair
It is bright scope is claimed to be determined by the appended claims.
Claims (5)
- A kind of 1. tableware recognition methods for intelligent scoring of being set a table for Chinese meal dinner party table top, it is characterised in that the tableware identification Method includes circular tableware recognition methods, tableware packet merger and sorting technique, table top center identification and method of selecting, Yi Jiyi Shape tableware recognition methods;The circular tableware recognition methods is used for the knowledge of meal dish, soup bowl, taste dish, cup, wineglass and white spirit cup totally 6 kinds of tablewares Not, recognition result is the central coordinate of circle and radius information of circular tableware, by calculating the gradient vector at doubtful circumferential point, then Using obtained gradient, the doubtful circumferential point of distance specifies search for respectively looking for one at radius on the gradient direction and its opposite direction Point, and the number of choosing of the point is recorded, the home position of doubtful circle is finally determined according to voting results;The tableware packet merger and sorting technique include packet merging method and sorting technique, wherein, packet merging method is adopted With k-means clustering methods, clusters number is arranged to Chinese meal dinner party guest's number and adds 1, i.e., dining table center vase and guest's tableware Put on an equal footing, be also identified using circular tableware recognition methods;Sorting technique is closed by the radius difference of different tablewares and position System is classified to the tableware group after merger, classification results be specify meal dish in tableware group, soup bowl, taste dish, cup, The class label and central coordinate of circle information of wineglass and white spirit cup totally 6 kinds of tablewares;The table top center identification and method of selecting are used for the determination of Chinese meal dinner party table top central point, comprising recognition methods and select Method, wherein, recognition methods obtains its central coordinate of circle and half using the circular tableware recognition methods identification dining table center vase Footpath information;There is the situation in multiple centers of circle in the dining table center vase group that method of selecting is used for after merger;The special-shaped tableware recognition methods is used for the identification of chopsticks rack, chopsticks sheath, soup ladle, toothpick wrapper and menu totally 5 kinds of tablewares, identification knot Center and four vertex point coordinate informations of the fruit for special-shaped tableware edge contour boundary rectangle, by centering dinner can table top set a table figure As obtaining the edge contour of special-shaped tableware after carrying out binary conversion treatment, the minimum area-encasing rectangle conduct of the edge contour is then drawn Its boundary rectangle.
- 2. the tableware recognition methods for intelligent scoring of being set a table as claimed in claim 1 for Chinese meal dinner party table top, it is characterised in that The specific steps that the tableware recognition methods carries out tableware identification include:Step 1:Chinese meal dinner party table top is received to set a table image set;Step 2:Circular tableware recognition methods identification is called to specify table top to set a table all circular tablewares in image, and in dining table Disc flower bottle;Step 3:Tableware packet merging method is called to look for round result to cluster circular tableware recognition methods, obtaining sum is The 1 tableware group more than Chinese meal dinner party guest's number;Step 4:The sequence number for tableware group of the image determination with positive vertical view visual angle of being set a table according to table top;Step 5:Tableware specification method is called, is obtained with the meal dish in the positive tableware group for overlooking visual angle, soup bowl, taste dish, water The class label and central coordinate of circle information of cup, wineglass and white spirit cup totally 6 kinds of tablewares;Step 6:Table top center method of selecting is called, determines table top centre coordinate;Step 7:Special-shaped tableware recognition methods is called, obtains the edge of chopsticks rack, chopsticks sheath, soup ladle, toothpick wrapper and menu totally 5 kinds of tablewares The center of profile boundary rectangle and four vertex point coordinate informations;Step 8:Judge whether to perform circulate operation to all images in image set, be then to continue in next step, otherwise to choose down Piece image simultaneously goes to step 2;Step 9:Export all tableware identification informations.
- 3. the tableware recognition methods for intelligent scoring of being set a table as claimed in claim 1 or 2 for Chinese meal dinner party table top, its feature exist In the table top center method of selecting specific steps include:Step 601:All centers of circle and Chinese meal dinner party table top in the vase group of dining table center are calculated to set a table the distance of picture centre, and It is stored in pre-defined distance vector;Step 602:Being arranged apart from element by numerical values recited ascending order in distance vector;Step 603:For specified in distance vector one apart from element, corresponding central coordinate of circle is found;Step 604:Calculate the current center of circle has the distance at the meal dish center in the positive tableware group for overlooking visual angle with two groups respectively;Step 605:In judgment step 604 deviation of two distances (distance at the current center of circle and two meal dish centers) whether Within 5%, if it is, the sequence number in the current center of circle is stored in pre-defined center of circle sequence number vector;Step 606:Judge whether to adjust the distance in vector it is each perform completion apart from element circular, be then to continue in next step, it is no Then by subscript from increasing 1, and 604 are gone to step, perform next operation apart from element in vector of adjusting the distance;Step 607:Judge whether the element number in the sequence number vector of the center of circle is more than 1, be then to continue in next step, otherwise to continue to judge Element number whether be equal to 1, be then using the center of circle corresponding to the only element in the sequence number vector of the center of circle as table top center, and turn walk Rapid 611, if the element number in the sequence number vector of the center of circle is 0, need to relax apart from deviation threshold in step 605, and go to step 604 Re-execute circulation;Step 608:Now whether the element number in center of circle sequence number vector is more than 1, takes the first two element, finds respectively corresponding The center of circle and radius, calculate the distance between two centers of circle;Step 609:Judge whether the distance between two centers of circle are less than larger radius of circle, be then to continue in next step, it is otherwise right Dining table center vase bottleneck and bottle tripe is answered only to find a circle, but mistake have found circle, and center of the circle elsewhere on table top With choosing the range deviation of meal dish to meet requirement, the less center of circle of range deviation is at this moment taken as table top center, and go to step 611;Step 610:Corresponding dining table center vase bottleneck and bottle tripe find round situation simultaneously, take the larger circle of radius as table top Center;Step 611:Export the table top central information determined.
- 4. the tableware recognition methods for intelligent scoring of being set a table as claimed in claim 1 or 2 for Chinese meal dinner party table top, its feature exist In the circular tableware recognition methods also needs to set the maximum and minimum value for looking for radius of circle, is respectively maximum circular tableware half Twice of footpath and the 1/3 of smallest circular tableware radius.
- 5. the tableware recognition methods for intelligent scoring of being set a table as claimed in claim 1 or 2 for Chinese meal dinner party table top, its feature exist In the threshold value of the binary conversion treatment of the special-shaped tableware recognition methods is arranged to gray value 124.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710897544.6A CN107742181B (en) | 2017-09-28 | 2017-09-28 | Tableware identification method for intelligent scoring of table arrangement of Chinese food banquet table |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710897544.6A CN107742181B (en) | 2017-09-28 | 2017-09-28 | Tableware identification method for intelligent scoring of table arrangement of Chinese food banquet table |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107742181A true CN107742181A (en) | 2018-02-27 |
CN107742181B CN107742181B (en) | 2021-06-08 |
Family
ID=61236229
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710897544.6A Expired - Fee Related CN107742181B (en) | 2017-09-28 | 2017-09-28 | Tableware identification method for intelligent scoring of table arrangement of Chinese food banquet table |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107742181B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110633370A (en) * | 2019-09-19 | 2019-12-31 | 携程计算机技术(上海)有限公司 | Generation method, system, electronic device and medium of OTA hotel label |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH10105774A (en) * | 1996-09-26 | 1998-04-24 | Tec Corp | Tableware recognition device |
JPH10255169A (en) * | 1997-03-06 | 1998-09-25 | Hitachi Keiyo Eng Co Ltd | Automatic adjusting device for beverage price |
CN203812418U (en) * | 2014-05-12 | 2014-09-03 | 成都职业技术学院 | Practical training and teaching system for Chinese and western food feasts |
CN204007383U (en) * | 2014-06-13 | 2014-12-10 | 江苏省吴江中等专业学校 | A kind of Novel Chinese food dinner party measurer of setting a table |
CN106096932A (en) * | 2016-06-06 | 2016-11-09 | 杭州汇萃智能科技有限公司 | The pricing method of vegetable automatic recognition system based on tableware shape |
CN107038425A (en) * | 2017-04-25 | 2017-08-11 | 上海理工大学 | The settlement system of intelligent restaurant based on machine vision |
-
2017
- 2017-09-28 CN CN201710897544.6A patent/CN107742181B/en not_active Expired - Fee Related
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH10105774A (en) * | 1996-09-26 | 1998-04-24 | Tec Corp | Tableware recognition device |
JPH10255169A (en) * | 1997-03-06 | 1998-09-25 | Hitachi Keiyo Eng Co Ltd | Automatic adjusting device for beverage price |
CN203812418U (en) * | 2014-05-12 | 2014-09-03 | 成都职业技术学院 | Practical training and teaching system for Chinese and western food feasts |
CN204007383U (en) * | 2014-06-13 | 2014-12-10 | 江苏省吴江中等专业学校 | A kind of Novel Chinese food dinner party measurer of setting a table |
CN106096932A (en) * | 2016-06-06 | 2016-11-09 | 杭州汇萃智能科技有限公司 | The pricing method of vegetable automatic recognition system based on tableware shape |
CN107038425A (en) * | 2017-04-25 | 2017-08-11 | 上海理工大学 | The settlement system of intelligent restaurant based on machine vision |
Non-Patent Citations (2)
Title |
---|
BO FU 等: "Motion-blurred SITF invariants based on sampling in image deformation space and univariate search", 《THE INSTITUTION OF ENGINEERING》 * |
杨皋: "基于机器视觉的餐盘缺陷检测技术研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110633370A (en) * | 2019-09-19 | 2019-12-31 | 携程计算机技术(上海)有限公司 | Generation method, system, electronic device and medium of OTA hotel label |
CN110633370B (en) * | 2019-09-19 | 2023-07-04 | 携程计算机技术(上海)有限公司 | OTA hotel label generation method, system, electronic device and medium |
Also Published As
Publication number | Publication date |
---|---|
CN107742181B (en) | 2021-06-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108763606B (en) | Method and system for automatically extracting house type graphic primitive based on machine vision | |
CN102521558B (en) | Bar code identifying method and device | |
CN109508664B (en) | Dish identification pricing method based on deep learning | |
CN100456314C (en) | QR two-dimensional bar code recognition method based on pickup head for chatting | |
EP3032461A1 (en) | Detecting unkown identical products in an image | |
CN104239909B (en) | A kind of recognition methods of image and device | |
CN105574063A (en) | Image retrieval method based on visual saliency | |
CN110705424B (en) | Method and device for positioning commodity display position and storage medium | |
CN106096932A (en) | The pricing method of vegetable automatic recognition system based on tableware shape | |
CN104866849A (en) | Food nutrition label identification method based on mobile terminal | |
CN108345912A (en) | Commodity rapid settlement system based on RGBD information and deep learning | |
CN109255344A (en) | A kind of digital display instrument positioning and Recognition of Reading method based on machine vision | |
CN104281572B (en) | A kind of target matching method and its system based on mutual information | |
CN110377727A (en) | A kind of multi-tag file classification method and device based on multi-task learning | |
CN109409377A (en) | The detection method and device of text in image | |
CN115272652A (en) | Dense object image detection method based on multiple regression and adaptive focus loss | |
US20220415012A1 (en) | Image processing based methods and apparatus for planogram compliance | |
CN109086772A (en) | A kind of recognition methods and system distorting adhesion character picture validation code | |
CN112508132A (en) | Training method and device for identifying SKU | |
CN105868269A (en) | Precise image searching method based on region convolutional neural network | |
Karaoglu et al. | Con-text: text detection using background connectivity for fine-grained object classification | |
CN108733749A (en) | A kind of image search method based on sketch | |
CN107742181A (en) | A kind of tableware recognition methods for intelligent scoring of being set a table for Chinese meal dinner party table top | |
CN104410867A (en) | Improved video shot detection method | |
CN109086781A (en) | A kind of cabinet lamp state identification method based on deep learning |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20210608 Termination date: 20210928 |