CN109992693A - House type matching process and device - Google Patents
House type matching process and device Download PDFInfo
- Publication number
- CN109992693A CN109992693A CN201910311235.5A CN201910311235A CN109992693A CN 109992693 A CN109992693 A CN 109992693A CN 201910311235 A CN201910311235 A CN 201910311235A CN 109992693 A CN109992693 A CN 109992693A
- Authority
- CN
- China
- Prior art keywords
- house type
- image
- feature
- matched
- geometrical characteristic
- 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 present invention provides a kind of house type matching process and devices, wherein this method comprises: obtaining house type image to be matched;Extract the geometrical characteristic of house type image to be matched;Geometrical characteristic includes contour feature, area features and position feature;House type sample image in geometrical characteristic and the database pre-established is subjected to similarity mode, obtains the similarity between the house type sample image in geometrical characteristic and database;According to similarity, screening obtains the house type sample image to match with house type image to be matched from database.Similarity mode is carried out to the house type sample image in database by the geometrical characteristic of house type, the most similar floor plan can be quickly obtained from database, improves the house type matching efficiency in house ornamentation design process.
Description
Technical field
The present invention relates to house ornamentation design fields, more particularly, to a kind of house type matching process and device.
Background technique
As real estate industry quickly grows, there is miscellaneous house type, and the demand that people design house ornamentation
Also higher and higher.Designer is when carrying out Size Dwelling Design to house, it is necessary first to use for reference the similar house type of integral layout, in this way
Design cost can be substantially reduced by way of reference, and is also easier to so that user receives.
During using for reference layout similar house type, need to carry out traversal screening in the house type database pre-established.
Often data volume is very big for these house type databases, and the layout of house type is varied, takes so that the process of artificial screening is time-consuming
Power is unfavorable for designer and is quickly filtered out suitable house type as reference, causes whole house ornamentation design efficiency low.
Summary of the invention
In view of this, being designed the purpose of the present invention is to provide a kind of house type matching process and device with improving house ornamentation
House type matching efficiency in journey.
In a first aspect, the embodiment of the invention provides a kind of house type matching process, wherein this method comprises: obtain to
The house type image matched;Extract the geometrical characteristic of house type image to be matched;Geometrical characteristic includes contour feature, area features and position
Set feature;House type sample image in geometrical characteristic and the database pre-established is subjected to similarity mode, obtains geometry spy
The similarity between house type sample image in sign and database;According to similarity, from database screening obtain with it is to be matched
The house type sample image that matches of house type image.
With reference to first aspect, the embodiment of the invention provides the first possible embodiments of first aspect, wherein mentions
The step of taking the geometrical characteristic of house type image to be matched, comprising: extracted from the corresponding XML data of house type image to be matched
Geometrical characteristic;Alternatively, extracting house type image geometrical characteristic to be matched by the way of deep learning.
With reference to first aspect, the embodiment of the invention provides second of possible embodiments of first aspect, wherein will
The step of house type sample image in geometrical characteristic and the database pre-established carries out similarity mode, comprising: obtain preparatory
The geometrical characteristic of each house type sample image in the database of foundation;By the geometrical characteristic of house type image to be matched respectively with number
Similarity mode is carried out according to the geometrical characteristic of each house type sample image in library, obtains the corresponding phase of each house type sample image
Like degree.
The possible embodiment of second with reference to first aspect, the embodiment of the invention provides the third of first aspect
Possible embodiment, wherein by the geometrical characteristic of house type image to be matched respectively with each house type sample in database
The geometrical characteristic of image carries out the step of similarity mode, comprising: from the geometrical characteristic and house type sample of house type image to be matched
Extract fisrt feature combination in the geometrical characteristic of this image, fisrt feature combination include: the contour feature in full room, area features,
Full room length-width ratio;Feature in the fisrt feature combination of house type image and house type sample image more to be matched, obtains full room
House type overall similarity.
The third possible embodiment with reference to first aspect, the embodiment of the invention provides the 4th kind of first aspect
Possible embodiment, wherein the feature in the fisrt feature combination of house type image and house type sample image more to be matched
The step of, comprising:
When the contour feature in the full room in combining to fisrt feature is compared, to including in the contour feature in full room
Outline polygon carries out geometric transformation, special to the profile in the full room of transformed house type image and house type sample image to be matched
Sign is compared;Geometric transformation, including one of translation, rotation, scaling, mirror image operation or a variety of;Alternatively, using profile ratio
Contour feature compared with the full room that function treats matched house type image and house type sample image is compared.
The possible embodiment of second with reference to first aspect, the embodiment of the invention provides the 5th kind of first aspect
Possible embodiment, wherein the geometrical characteristic of house type image to be matched respectively with each house type sample graph in database
The geometrical characteristic of picture carries out the step of similarity mode, comprising: from the geometrical characteristic and house type sample of house type image to be matched
Second feature combination is extracted in the geometrical characteristic of image, second feature combination includes: the position feature in full room and the position in single room
Set feature;Feature in the second feature combination of house type image and house type sample image more to be matched, obtains between single room
Space layout similarity.
The 5th kind of possible embodiment with reference to first aspect, the embodiment of the invention provides the 6th kind of first aspect
Possible embodiment, wherein the feature in the second feature combination of house type image and house type sample image more to be matched
The step of, comprising: it is combined using the second feature of deep learning algorithm comparison house type image to be matched and house type sample image
In feature;Alternatively, being arranged first on house type image to be matched according to the combination of the second feature of house type image to be matched
Standard point;According to the combination of the second feature of house type sample image, the second normal place point is set on house type sample image;Compare
First normal place point and the second normal place point.
The possible embodiment of second with reference to first aspect, the embodiment of the invention provides the 7th kind of first aspect
Possible embodiment, wherein by the geometrical characteristic of house type image to be matched respectively with each house type sample in database
The geometrical characteristic of image carries out the step of similarity mode, comprising: from the geometrical characteristic and house type sample of house type image to be matched
Third feature combination is extracted in the geometrical characteristic of this image, third feature combination includes: the area in the contour feature in single room, single room
The length-width ratio of feature and single room;Feature in the third feature combination of house type image and house type sample image more to be matched,
Obtain the overall similarity in single room.
The 7th kind of possible embodiment with reference to first aspect, the embodiment of the invention provides the 8th kind of first aspect
Possible embodiment, wherein the feature in the third feature combination of house type image and house type sample image more to be matched
The step of, comprising: when the contour feature in each room in combining to third feature is compared, to the profile in each room
The outline polygon for including in feature carries out geometric transformation, to transformed house type image and house type sample image to be matched
The contour feature in each room is compared;Geometric transformation, including one of translation, rotation, scaling, mirror image operation or more
Kind;Alternatively, treating the contour feature in each room of matched house type image and house type sample image using profile comparison function
It is compared.
Second aspect, the embodiment of the present invention provide a kind of house type coalignment, which includes: input module, for obtaining
Take house type image to be matched;Characteristic extracting module, for extracting the geometrical characteristic of house type image to be matched;Geometrical characteristic packet
Include contour feature, area features and position feature;Characteristic matching module, for will geometrical characteristic in the database that pre-establishes
House type sample image carry out similarity mode, obtain similar between geometrical characteristic and the house type sample image in database
Degree;Feature determination module obtains the house type sample image to match with house type image to be matched for screening from database.
The embodiment of the present invention bring it is following the utility model has the advantages that
The present invention provides a kind of house type matching process and device, this method obtains house type image to be matched first;So
The geometrical characteristic of house type image to be matched, including contour feature, area features and position feature are extracted afterwards;Again by geometrical characteristic
Similarity mode is carried out with the house type sample image in the database that pre-establishes, obtains the house type in geometrical characteristic and database
Similarity between sample image;Finally according to similarity, screens and obtain and house type image phase to be matched from database
The house type sample image matched.Similarity mode is carried out to the house type sample image in database by the geometrical characteristic of house type, it can
The most similar floor plan is quickly obtained from database, improves the house type matching efficiency in house ornamentation design process.
Other features and advantages of the present invention will illustrate in the following description, also, partly become from specification
It obtains it is clear that understand through the implementation of the invention.The objectives and other advantages of the invention are in specification, claims
And specifically noted structure is achieved and obtained in attached drawing.
To enable the above objects, features and advantages of the present invention to be clearer and more comprehensible, preferred embodiment is cited below particularly, and cooperate
Appended attached drawing, is described in detail below.
Detailed description of the invention
It, below will be to specific in order to illustrate more clearly of the specific embodiment of the invention or technical solution in the prior art
Embodiment or attached drawing needed to be used in the description of the prior art be briefly described, it should be apparent that, it is described below
Attached drawing is some embodiments of the present invention, for those of ordinary skill in the art, before not making the creative labor
It puts, is also possible to obtain other drawings based on these drawings.
Fig. 1 is a kind of flow chart of house type matching process provided in an embodiment of the present invention;
Fig. 2 is in another house type matching process provided in an embodiment of the present invention, by geometrical characteristic and the number pre-established
The specific flow chart of similarity mode is carried out according to the house type sample image in library;
Fig. 3 is in another house type matching process provided in an embodiment of the present invention, by the first by floor plan to be matched
The geometrical characteristic of picture carries out the flow chart of similarity mode with the geometrical characteristic of each house type sample image in database respectively;
Fig. 4 is in another house type matching process provided in an embodiment of the present invention, by second by floor plan to be matched
The geometrical characteristic of picture carries out the flow chart of similarity mode with the geometrical characteristic of each house type sample image in database respectively;
Fig. 5 is in another house type matching process provided in an embodiment of the present invention, by the third by floor plan to be matched
The geometrical characteristic of picture carries out the flow chart of similarity mode with the geometrical characteristic of each house type sample image in database respectively;
Fig. 6 is the flow chart of another house type matching process provided in an embodiment of the present invention;
Fig. 7 is a kind of structural schematic diagram of house type coalignment provided in an embodiment of the present invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with attached drawing to the present invention
Technical solution be clearly and completely described, it is clear that described embodiments are some of the embodiments of the present invention, rather than
Whole embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art are not making creative work premise
Under every other embodiment obtained, shall fall within the protection scope of the present invention.
In view of there is the problem of inefficiency, it is an object of the invention to mention when house type matching in the design of current house ornamentation
For a kind of house type matching process and device, which can be applied to the terminals such as mobile phone, tablet computer, computer, special-purpose terminal
In equipment, it can be used in the scenes such as APP (Application, application program) page, Webpage, the operating system page.
For convenient for understanding the present embodiment, first to a kind of house type matching process disclosed in the embodiment of the present invention into
Row is discussed in detail.A kind of flow chart of house type matching process shown in Figure 1, comprising the following steps:
Step S110 obtains house type image to be matched;
House type image can also pass through in-site measurement and draw out floor plan by directly acquiring in building unit
Picture.House type image is usually two-dimensional digital picture, is the top view in house.
Step S120 extracts the geometrical characteristic of house type image to be matched;
Geometrical characteristic therein is extracted from house type image obtained in step S110, these geometrical characteristics include to be matched
House type image contour feature, area features and position feature.Current common house house type is not single square
Or rectangle, but the irregular shape being composed of multiple square or rectangulars, there is the profile of some special house types also
Have circular arc.Although the profile of house type image is varied, these profiles are all the figures that can be divided into multiple rules, therefore
These profiles are that have respective feature, such as shape, the curvature of profile of profile, the length etc. of profile all can serve as to characterize
The parameter of contour feature.
Area features can be characterized by the area and house type entire area in room each in house type, and the plane in room is simultaneously
It is not necessarily the shape of rule, but the group of multiple regular geometric figures can be divided by the method that geometry divides
It closes, therefore the calculating of area can be obtained by the cumulative of these geometric areas.
Position feature includes relative position, balcony position and the other special objects of position between each room, door and window
Data characteristics is formed by between the position (such as caliduct, sewer pipe, gas piping) of product.These position features are to sit
Mark form is presented, and position feature data are obtained by way of geometric operation.
House type sample image in geometrical characteristic and the database pre-established is carried out similarity mode by step S130,
Obtain the similarity between the house type sample image in geometrical characteristic and database;
The above-mentioned house type sample image database pre-established is realized by collecting various house types, these house type samples
This image can be provided by various units in charge of construction;Different house type sample images can also be automatically added to after the completion of every secondary design
Database;Database can be enriched with designed, designed some typical house types.House type sample image number in these databases
Bigger according to measuring, matched effect is better.
The geometrical characteristic obtained in S120 carries out similarity respectively at all house type sample images in database
Match, successively obtains its similarity data.Both this data indicates with numerical value, and numerical value more greatly shows similarity is higher, can
The degree of reference is higher.
Step S140, according to similarity, screening obtains the house type to match with house type image to be matched from database
Sample image.
House type image and number to be matched is obtained after the traversal of all house type sample images in completion database in S130
According to the matching result of house type images all in library, the family to match with house type image to be matched then can be obtained by screening
Type sample image.The obtained house type sample image quantity to match is simultaneously not fixed, settable one, may also set up it is multiple,
Quantity is set by designer.
House type matching process provided in an embodiment of the present invention, by the geometrical characteristic of house type to the house type sample in database
Image carries out similarity mode, can realize automatically and quickly and obtain the most similar floor plan from database, improve
House type matching efficiency in house ornamentation design process.
The embodiment of the present invention also provides another house type matching process, and how the description of this method emphasis extracts family to be matched
The realization of the geometrical characteristic of type image, this method has following manner:
Mode one: geometrical characteristic is extracted from the corresponding XML data of house type image to be matched;
The corresponding XML of house type image (Extensible Markup Language, extensible markup language) to be matched
It include house type image attribute tag in data, these attribute tags can be used to describe the characteristic of house type, and can therefrom extract geometry
Feature.It, can after the completion of modeling if floor plan to be matched seems to be obtained by related house type indoor design software modeling
Automatically derive the corresponding XML data of house type image;If floor plan to be matched seems to be obtained by other approach, can pass through
Related house type indoor design software imports image, obtains corresponding XML data by data conversion.
Mode two: house type image geometrical characteristic to be matched is extracted by the way of deep learning.
By carrying out deep learning to geometrical characteristic in the house type sample image database that pre-establishes.Deep learning
Process needs to establish model of geometrical features and is trained, and geometrical characteristic includes contour feature, area features and position feature.It will
House type image to be matched, which is input to, has trained in the model of geometrical features finished, and the several of house type image to be matched can be completed
What feature extraction.
It should be noted that the geometrical characteristic for extracting house type image to be matched can be used it is any in above two mode
It is a kind of.Since the geometrical characteristic of house type is very intuitive, and can rapidly extracting family to be matched by one of above two mode
The geometrical characteristic of type image, to promote the matched speed of house type.
The embodiment of the present invention also provides another house type matching process, and how the description of this method emphasis is by geometrical characteristic and pre-
House type sample image in the database first established carries out similarity mode, as shown in Fig. 2, this method comprises the following steps:
Step S210 obtains the geometrical characteristic of each house type sample image in the database pre-established.
The database pre-established is traversed to obtain each house type sample image, then to each house type sample image
Carry out the extraction of geometrical characteristic.House type image geometrical characteristic to be matched includes: contour feature, area features and position feature.
Step S220, by the geometrical characteristic of house type image to be matched respectively with each house type sample image in database
Geometrical characteristic carry out similarity mode, obtain the corresponding similarity of each house type sample image.The step is by to be matched
The geometrical characteristic of house type image and the geometrical characteristic of house type sample image in extract different feature combinations, similarity can be improved
Matched accuracy.
The embodiment of the present invention also provides another house type matching process, and this method emphasis describes the first for family to be matched
The geometrical characteristic of type image carries out the side of similarity mode with the geometrical characteristic of each house type sample image in database respectively
Method, as shown in figure 3, this method comprises the following steps:
Step S310: is extracted from the geometrical characteristic of house type image to be matched and the geometrical characteristic of house type sample image
The combination of one feature, fisrt feature combination include: the contour feature, area features, full room length-width ratio in full room;
Step S320: the feature in the fisrt feature combination of house type image and house type sample image more to be matched obtains
To the house type overall similarity in full room.
When the contour feature in the full room in combining to fisrt feature is compared, to including in the contour feature in full room
Outline polygon carries out geometric transformation, special to the profile in the full room of transformed house type image and house type sample image to be matched
Sign is compared;Geometric transformation includes one of the translation of full room profile, rotation, scaling, mirror image operation or a variety of.
When the contour feature in the full room in combining to fisrt feature is compared, profile comparison function can also be used and treat
The contour feature in the full room of matched house type image and house type sample image is compared.Above-mentioned profile comparison function can be used and open
Profile function in source computer vision library (OpenCV), such as can be direct using CvMatchShape function built-in in OpenCV
Match graph outline.
The integrally-built parameter in full room of fisrt feature combination characterization house type in aforesaid way, is combined using these features
When carrying out similarity mode, matching speed can be improved without the details in the excessive single room of consideration.
The embodiment of the present invention also provides another house type matching process, and this method emphasis describes second for family to be matched
The geometrical characteristic of type image carries out the side of similarity mode with the geometrical characteristic of each house type sample image in database respectively
Method, as shown in figure 4, this method comprises the following steps:
Step S410: is extracted from the geometrical characteristic of house type image to be matched and the geometrical characteristic of house type sample image
The combination of two features, second feature combination include: the position feature in full room and the position feature in single room.
Step S420: the feature in the second feature combination of house type image and house type sample image more to be matched obtains
To the space layout similarity between single room.
When contour feature in combining to second feature is compared, it is to be matched that deep learning algorithm comparison can be used
Feature in the combination of the second feature of house type image and house type sample image.Deep learning algorithm needs in advance to a large amount of floor plans
Position carries out model training between full room position and single room as in, and model, can be by house type to be matched after training obtains
Image is input in model, and the matching result about second feature combination can be obtained, the space between single room then can be obtained
It is laid out similarity.
It, can also be according to the second of house type image to be matched when contour feature in combining to second feature is compared
The first standard point is arranged on house type image to be matched in feature combination;It is combined according to the second feature of house type sample image at family
Second normal place point is set on type sample image;Compare relative position between the first normal place point and the second normal place point
Direction and distance, the matching result of second feature combination can be obtained, and then obtain the space layout similarity between single room.
By single room position in second feature combination and full room positional relationship, to obtain space layout similar in aforesaid way
Degree, compared to the matching for the integrally-built similarity in full room, more considered between the full structure in portion within doors, precision is higher.
The embodiment of the present invention also provides another house type matching process, and this method emphasis describes the third for family to be matched
The geometrical characteristic of type image carries out the side of similarity mode with the geometrical characteristic of each house type sample image in database respectively
Method, as shown in figure 5, this method comprises the following steps:
Step S510: is extracted from the geometrical characteristic of house type image to be matched and the geometrical characteristic of house type sample image
The combination of three features, third feature combination include: the length-width ratio of the contour feature in single room, the area features in single room and single room.
Step S520: the feature in the third feature combination of house type image and house type sample image more to be matched obtains
To the overall similarity in single room.
When contour feature in combining to third feature is compared, to the wheel for including in the contour feature in each room
Wide polygon carries out geometric transformation, to the profile in each room of transformed house type image and house type sample image to be matched
Feature is compared;Geometric transformation, including one of translation, rotation, scaling, mirror image operation or a variety of.
When contour feature in combining to third feature is compared, open source computer vision library (OpenCV) can be used
The contour feature that middle profile comparison function treats each room of matched house type image and house type sample image is compared.It is right
It during the similarity-rough set in single room, can be matched by the relationship of the position of door and window, such as each room can be passed through
Door and window where the relative positional relationship in space carry out similarity mode, or the method for deep learning window position on the door can be used
It is compared.
Third feature combination in aforesaid way, characterizes the characteristic in each room, is the highest characteristic matching of accuracy
Method.
The embodiment of the present invention provides another house type matching process, as shown in fig. 6, method includes the following steps:
Step S602 inputs house type image.
House type image can also pass through in-site measurement and draw out floor plan by directly acquiring in building unit
Picture.Floor plan seems two-dimensional digital picture, is the top view in house.
Step S604 obtains house type image to be matched.
The above-mentioned house type sample image database pre-established is realized by collecting various house types, these house type samples
This image can be provided by various units in charge of construction;Different house type sample images can also be automatically added to after the completion of every secondary design
Database;Database can be enriched with designed, designed some typical house types.House type sample image number in these databases
Bigger according to measuring, matched effect is better.
Step S606 extracts geometrical characteristic from house type image.
House type image includes the house type image to be matched in input house type image and step S604 in step S602.House type
The geometrical characteristic of image includes: contour feature, area features and position feature.The extraction of geometrical characteristic can use following two side
Formula:
Mode one: geometrical characteristic is extracted from the corresponding XML data of house type image;
It include house type image attribute tag in the corresponding XML data of house type image, these attribute tags can be used to describe family
The characteristic of type, and can therefrom extract geometrical characteristic.If floor plan seems to be obtained by related house type indoor design software modeling
, then the corresponding XML data of house type image can be automatically derived after the completion of modeling;If floor plan seems to be obtained by other approach
, image can be imported by related house type indoor design software, obtain corresponding XML data by data conversion.
Mode two: the geometrical characteristic of house type image is extracted by the way of deep learning.
By carrying out deep learning to geometrical characteristic in the house type sample image database that pre-establishes.Deep learning
Process needs to establish model of geometrical features and is trained, and geometrical characteristic includes contour feature, area features and position feature.It will
House type image, which is input to, has trained in the model of geometrical features finished, and the Extraction of Geometrical Features of house type image can be completed.
Step S608, full room overall similarity compare.
Fisrt feature combination can be used to be characterized for full room overall similarity, and fisrt feature combination includes: the profile in full room
Feature, area features, full room length-width ratio.When the contour feature in the full room in combining to fisrt feature is compared, to full room
Contour feature in include outline polygon carry out geometric transformation, to transformed house type image and house type sample to be matched
The contour feature in the full room of image is compared;Geometric transformation include the translation of full room profile, rotation, scaling, in mirror image operation
It is one or more.
When the contour feature in the full room in combining to fisrt feature is compared, profile comparison function can also be used and treat
The contour feature in the full room of matched house type image and house type sample image is compared.Above-mentioned profile comparison function can be used and open
Profile function in source computer vision library (OpenCV), such as can be direct using CvMatchShape function built-in in OpenCV
Match graph outline.
Step S610, space layout similarity-rough set.
Second feature combination can be used to be characterized for space layout similarity, and second feature combination includes: the position in full room
The position feature of feature and single room.When contour feature in combining to second feature is compared, deep learning can be used
Feature in the combination of the second feature of algorithm comparison house type image to be matched and house type sample image.Deep learning algorithm needs
Model training is carried out to position between room position complete in a large amount of house type images and single room in advance, model after trained obtain,
House type image to be matched can be input in model, the matching result about second feature combination can be obtained, then can obtain
To the space layout similarity between single room.
It, can also be according to the second of house type image to be matched when contour feature in combining to second feature is compared
The first standard point is arranged on house type image to be matched in feature combination;It is combined according to the second feature of house type sample image at family
Second normal place point is set on type sample image;Compare relative position between the first normal place point and the second normal place point
Direction and distance, the matching result of second feature combination can be obtained, and then obtain the space layout similarity between single room.
Step S612, single space similarity compare.
Relatively third feature combination can be used to be characterized for single space similarity, and third feature combination includes: the wheel in single room
The length-width ratio of wide feature, the area features in single room and single room.It is right when contour feature in combining to third feature is compared
The outline polygon that includes in the contour feature in each room carries out geometric transformation, to transformed house type image to be matched and
The contour feature in each room of house type sample image is compared;Geometric transformation, including translation, rotation, scaling, mirror image operation
One of or it is a variety of.When contour feature in combining to third feature is compared, open source computer vision library can be used
(OpenCV) in profile comparison function treat the contour feature in each room of matched house type image and house type sample image into
Row compares.During the similarity-rough set in single room, it can be matched by the relationship of the position of door and window, such as can pass through
The relative positional relationship in space carries out similarity mode where the door and window in each room, or the method pair of deep learning can be used
Door and window position is compared.
Step S614 judges whether house type traverses and finishes.If traversal finishes, S618 is thened follow the steps;If not time
It goes through and finishes, then follow the steps S616.
All floor plans to be matched seem no traversal in the house type image and step S604 inputted in judgment step S602
It finishes, step S608, step S610, step S612 is successively executed in ergodic process.Above-mentioned steps S608, step S610, step
The sequence of S612 does not limit, and can adjust mutual sequence according to the actual situation.
Step S616 updates house type library.
From newly updating house type library and obtaining house type image to be matched if traversal does not finish, house type is then re-started
Matching step.
Step S618, sequencing of similarity.
House type obtains the similarity mode of all house types as a result, then carrying out sequencing of similarity after traversing, and interim
It saves.
Step S620, obtains matching result.
According to actual needs, closest one or several house types are chosen from the sequencing of similarity result temporarily saved
Figure.
From aforesaid way, similarity is carried out to the house type sample image in database by the geometrical characteristic of house type
Match, can realize automatically and quickly and obtain the most similar floor plan from database, solves and deposited in current house ornamentation design
In house type matching the problem of inefficiency.
Corresponding to above method embodiment, referring to a kind of house type coalignment described in Fig. 7, which is set to terminal and sets
Standby, which includes:
Input module 710, for obtaining house type image to be matched;
Characteristic extracting module 720, for extracting the geometrical characteristic of house type image to be matched;Geometrical characteristic includes profile spy
Sign, area features and position feature;
Characteristic matching module 730, for carrying out the house type sample image in geometrical characteristic and the database pre-established
Similarity mode obtains the similarity between the house type sample image in geometrical characteristic and database;
Feature determination module 740 obtains the house type to match with house type image to be matched for screening from database
Sample image.
The technical effect and preceding method of house type matching system provided by the embodiment of the present invention, realization principle and generation
Embodiment is identical, and to briefly describe, embodiment part does not refer to place, can refer to corresponding contents in preceding method embodiment.
In the description of the present invention, it should be noted that term " center ", "upper", "lower", "left", "right", "vertical",
The orientation or positional relationship of the instructions such as "horizontal", "inner", "outside" be based on the orientation or positional relationship shown in the drawings, merely to
Convenient for description the present invention and simplify description, rather than the device or element of indication or suggestion meaning must have a particular orientation,
It is constructed and operated in a specific orientation, therefore is not considered as limiting the invention.In addition, term " first ", " second ",
" third " is used for descriptive purposes only and cannot be understood as indicating or suggesting relative importance.
In addition, in the description of the embodiment of the present invention unless specifically defined or limited otherwise, term " installation ", " phase
Even ", " connection " shall be understood in a broad sense, for example, it may be being fixedly connected, may be a detachable connection, or be integrally connected;It can
To be mechanical connection, it is also possible to be electrically connected;It can be directly connected, can also can be indirectly connected through an intermediary
Connection inside two elements.For the ordinary skill in the art, above-mentioned term can be understood at this with concrete condition
Concrete meaning in invention.
In several embodiments provided herein, it should be understood that disclosed systems, devices and methods, it can be with
It realizes by another way.The apparatus embodiments described above are merely exemplary, for example, the division of the unit,
Only a kind of logical function partition, there may be another division manner in actual implementation, in another example, multiple units or components can
To combine or be desirably integrated into another system, or some features can be ignored or not executed.Another point, it is shown or beg for
The mutual coupling, direct-coupling or communication connection of opinion can be through some communication interfaces, device or unit it is indirect
Coupling or communication connection can be electrical property, mechanical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.
It, can be with if the function is realized in the form of SFU software functional unit and when sold or used as an independent product
It is stored in the executable non-volatile computer-readable storage medium of a processor.Based on this understanding, of the invention
Technical solution substantially the part of the part that contributes to existing technology or the technical solution can be with software in other words
The form of product embodies, which is stored in a storage medium, including some instructions use so that
One computer equipment (can be personal computer, server or the network equipment etc.) executes each embodiment institute of the present invention
State all or part of the steps of method.And storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory (ROM, Read-
Only Memory), random access memory (RAM, Random Access Memory), magnetic or disk etc. are various can be with
Store the medium of program code.
Finally, it should be noted that embodiment described above, only a specific embodiment of the invention, to illustrate the present invention
Technical solution, rather than its limitations, scope of protection of the present invention is not limited thereto, although with reference to the foregoing embodiments to this hair
It is bright to be described in detail, those skilled in the art should understand that: anyone skilled in the art
In the technical scope disclosed by the present invention, it can still modify to technical solution documented by previous embodiment or can be light
It is readily conceivable that variation or equivalent replacement of some of the technical features;And these modifications, variation or replacement, do not make
The essence of corresponding technical solution is detached from the spirit and scope of technical solution of the embodiment of the present invention, should all cover in protection of the invention
Within the scope of.Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. a kind of house type matching process, which is characterized in that the described method includes:
Obtain house type image to be matched;
Extract the geometrical characteristic of the house type image to be matched;The geometrical characteristic includes contour feature, area features and position
Set feature;
House type sample image in the geometrical characteristic and the database pre-established is subjected to similarity mode, is obtained described several
The similarity between house type sample image in what feature and the database;
According to the similarity, screening obtains the house type sample to match with the house type image to be matched from the database
This image.
2. the method according to claim 1, wherein extracting the geometrical characteristic of the house type image to be matched
Step, comprising:
Geometrical characteristic is extracted from the corresponding XML data of house type image to be matched;
Alternatively, extracting the house type image geometrical characteristic to be matched by the way of deep learning.
3. the method according to claim 1, wherein by the geometrical characteristic and the database pre-established
House type sample image carries out the step of similarity mode, comprising:
Obtain the geometrical characteristic of each house type sample image in the database pre-established;
The geometrical characteristic of the house type image to be matched is several with each house type sample image in the database respectively
What feature carries out similarity mode, obtains the corresponding similarity of each house type sample image.
4. according to the method described in claim 3, it is characterized in that, the geometrical characteristic of the house type image to be matched is distinguished
The step of carrying out similarity mode with the geometrical characteristic of each house type sample image in the database, comprising:
Fisrt feature group is extracted from the geometrical characteristic of the house type image to be matched and the geometrical characteristic of house type sample image
It closes, the fisrt feature combination includes: the contour feature, area features, full room length-width ratio in full room;
Compare the feature in the fisrt feature combination of the house type image to be matched and the house type sample image, obtains
The house type overall similarity in full room.
5. according to the method described in claim 4, it is characterized in that, the house type image to be matched and the house type sample
This image the fisrt feature combination in feature the step of, comprising:
When being compared to the contour feature in full room in fisrt feature combination, to being wrapped in the contour feature in the full room
The outline polygon that contains carries out geometric transformation, to the transformed house type image to be matched and the house type sample image
The contour feature in full room is compared;The geometric transformation, including one of translation, rotation, scaling, mirror image operation or more
Kind;
Alternatively, using profile comparison function to the profile in the full room of the house type image to be matched and the house type sample image
Feature is compared.
6. according to the method described in claim 3, it is characterized in that, the geometrical characteristic of the house type image to be matched respectively with
The geometrical characteristic of each house type sample image in the database carries out the step of similarity mode, comprising:
Second feature group is extracted from the geometrical characteristic of the house type image to be matched and the geometrical characteristic of house type sample image
It closes, the second feature combination includes: the position feature in full room and the position feature in single room;
Compare the feature in the second feature combination of the house type image to be matched and the house type sample image, obtains
Space layout similarity between single room.
7. according to the method described in claim 6, it is characterized in that, the house type image to be matched and the family
Type sample image the second feature combination in feature the step of, comprising:
Using the second feature of house type image and the house type sample image to be matched described in deep learning algorithm comparison
Feature in combination;
Alternatively, being arranged on the house type image to be matched the according to the combination of the second feature of the house type image to be matched
Normal place point;According to the combination of the second feature of the house type sample image, setting second is marked on the house type sample image
Quasi- location point;Compare the first normal place point and the second normal place point.
8. according to the method described in claim 3, it is characterized in that, the geometrical characteristic of the house type image to be matched is distinguished
The step of carrying out similarity mode with the geometrical characteristic of each house type sample image in the database, comprising:
Third feature group is extracted from the geometrical characteristic of the house type image to be matched and the geometrical characteristic of house type sample image
It closes, the third feature combination includes: the length-width ratio of the contour feature in single room, the area features in single room and single room;
Compare the feature in the third feature combination of the house type image to be matched and the house type sample image, obtains
The overall similarity in single room.
9. according to the method described in claim 8, it is characterized in that, the house type image to be matched and the house type sample
This image the third feature combination in feature the step of, comprising:
When the contour feature to each room in third feature combination is compared, to the profile in each room
The outline polygon for including in feature carries out geometric transformation, to the transformed house type image to be matched and the house type sample
The contour feature in each room of this image is compared;The geometric transformation, including translation, rotation, scaling, in mirror image operation
It is one or more;
Alternatively, using profile comparison function to each room of the house type image to be matched and the house type sample image
Contour feature is compared.
10. a kind of house type coalignment, which is characterized in that the device includes:
Input module, for obtaining house type image to be matched;
Characteristic extracting module, for extracting the geometrical characteristic of the house type image to be matched;The geometrical characteristic includes profile
Feature, area features and position feature;
Characteristic matching module, for the geometrical characteristic is similar to the house type sample image progress in the database pre-established
Degree matching, obtains the similarity between the house type sample image in the geometrical characteristic and the database;
Feature determination module obtains the house type to match with the house type image to be matched for screening from the database
Sample image.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910311235.5A CN109992693A (en) | 2019-04-17 | 2019-04-17 | House type matching process and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910311235.5A CN109992693A (en) | 2019-04-17 | 2019-04-17 | House type matching process and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109992693A true CN109992693A (en) | 2019-07-09 |
Family
ID=67133924
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910311235.5A Pending CN109992693A (en) | 2019-04-17 | 2019-04-17 | House type matching process and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109992693A (en) |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108664860A (en) * | 2017-04-01 | 2018-10-16 | 中山市琪朗灯饰厂有限公司 | The recognition methods of room floor plan and device |
CN110765540A (en) * | 2019-11-04 | 2020-02-07 | 深圳镜界智能科技有限公司 | System and method for matching house type graph with various self-contained designs |
CN110781826A (en) * | 2019-10-25 | 2020-02-11 | 珠海格力电器股份有限公司 | Three-dimensional stereogram construction method and system, storage medium and processor |
CN111274640A (en) * | 2020-01-20 | 2020-06-12 | 广东三维家信息科技有限公司 | Application method and device between sample boards and electronic equipment |
CN111400519A (en) * | 2019-12-05 | 2020-07-10 | 江苏艾佳家居用品有限公司 | Efficient customized massive similar house type searching method |
CN111563291A (en) * | 2020-05-19 | 2020-08-21 | 贝壳技术有限公司 | Home decoration scheme determination method and device and computer-readable storage medium |
CN111598972A (en) * | 2020-04-03 | 2020-08-28 | 深圳大学 | House type graph generation method and device, computer equipment and storage medium |
CN111680346A (en) * | 2020-05-19 | 2020-09-18 | 贝壳技术有限公司 | House type graph complementing method and device, computer readable storage medium, electronic device |
CN111753112A (en) * | 2020-06-04 | 2020-10-09 | 贝壳技术有限公司 | Information generation method and device and storage medium |
CN111859510A (en) * | 2020-07-28 | 2020-10-30 | 苏州金螳螂三维软件有限公司 | Rapid room changing method and intelligent terminal |
CN112417558A (en) * | 2020-11-19 | 2021-02-26 | 贝壳技术有限公司 | Wall decoration scheme determination method and device and computer readable storage medium |
CN113946900A (en) * | 2021-12-21 | 2022-01-18 | 深圳小库科技有限公司 | Method for quickly recommending similar house types based on house type profiles and distribution characteristics |
CN114187588A (en) * | 2021-12-08 | 2022-03-15 | 贝壳技术有限公司 | Data processing method, data processing device, storage medium and computer program product |
WO2023065570A1 (en) * | 2021-10-21 | 2023-04-27 | 广东三维家信息科技有限公司 | House type coding and matching method and apparatus |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20120134583A1 (en) * | 2004-05-05 | 2012-05-31 | Google Inc. | Methods and apparatus for automated true object-based image analysis and retrieval |
CN106446378A (en) * | 2016-09-13 | 2017-02-22 | 中国科学院计算技术研究所 | Room shape geometry characteristic description method and system |
CN106529445A (en) * | 2016-10-27 | 2017-03-22 | 珠海市魅族科技有限公司 | Makeup detection method and apparatus |
CN108984765A (en) * | 2018-07-20 | 2018-12-11 | 我要家网络科技有限公司 | It is a kind of based on intelligent image analysis floor plan look for room method |
CN109584005A (en) * | 2018-11-27 | 2019-04-05 | 深圳红璞公寓科技管理有限公司 | Dissemination method, device, computer equipment and the storage medium of the source of houses |
-
2019
- 2019-04-17 CN CN201910311235.5A patent/CN109992693A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20120134583A1 (en) * | 2004-05-05 | 2012-05-31 | Google Inc. | Methods and apparatus for automated true object-based image analysis and retrieval |
CN106446378A (en) * | 2016-09-13 | 2017-02-22 | 中国科学院计算技术研究所 | Room shape geometry characteristic description method and system |
CN106529445A (en) * | 2016-10-27 | 2017-03-22 | 珠海市魅族科技有限公司 | Makeup detection method and apparatus |
CN108984765A (en) * | 2018-07-20 | 2018-12-11 | 我要家网络科技有限公司 | It is a kind of based on intelligent image analysis floor plan look for room method |
CN109584005A (en) * | 2018-11-27 | 2019-04-05 | 深圳红璞公寓科技管理有限公司 | Dissemination method, device, computer equipment and the storage medium of the source of houses |
Cited By (21)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108664860A (en) * | 2017-04-01 | 2018-10-16 | 中山市琪朗灯饰厂有限公司 | The recognition methods of room floor plan and device |
CN108664860B (en) * | 2017-04-01 | 2022-02-01 | 中山市琪朗灯饰厂有限公司 | Method and device for identifying room plan |
CN110781826A (en) * | 2019-10-25 | 2020-02-11 | 珠海格力电器股份有限公司 | Three-dimensional stereogram construction method and system, storage medium and processor |
CN110765540A (en) * | 2019-11-04 | 2020-02-07 | 深圳镜界智能科技有限公司 | System and method for matching house type graph with various self-contained designs |
CN111400519A (en) * | 2019-12-05 | 2020-07-10 | 江苏艾佳家居用品有限公司 | Efficient customized massive similar house type searching method |
CN111400519B (en) * | 2019-12-05 | 2022-08-12 | 江苏艾佳家居用品有限公司 | Efficient customized massive similar house type searching method |
CN111274640A (en) * | 2020-01-20 | 2020-06-12 | 广东三维家信息科技有限公司 | Application method and device between sample boards and electronic equipment |
CN111598972A (en) * | 2020-04-03 | 2020-08-28 | 深圳大学 | House type graph generation method and device, computer equipment and storage medium |
CN111598972B (en) * | 2020-04-03 | 2021-06-29 | 深圳大学 | House type graph generation method and device, computer equipment and storage medium |
CN111680346A (en) * | 2020-05-19 | 2020-09-18 | 贝壳技术有限公司 | House type graph complementing method and device, computer readable storage medium, electronic device |
CN111680346B (en) * | 2020-05-19 | 2023-12-01 | 如你所视(北京)科技有限公司 | House type diagram complement method and device, computer readable storage medium and electronic equipment |
CN111563291A (en) * | 2020-05-19 | 2020-08-21 | 贝壳技术有限公司 | Home decoration scheme determination method and device and computer-readable storage medium |
CN111753112A (en) * | 2020-06-04 | 2020-10-09 | 贝壳技术有限公司 | Information generation method and device and storage medium |
CN111859510A (en) * | 2020-07-28 | 2020-10-30 | 苏州金螳螂三维软件有限公司 | Rapid room changing method and intelligent terminal |
CN112417558A (en) * | 2020-11-19 | 2021-02-26 | 贝壳技术有限公司 | Wall decoration scheme determination method and device and computer readable storage medium |
CN112417558B (en) * | 2020-11-19 | 2022-02-22 | 贝壳找房(北京)科技有限公司 | Wall decoration scheme determination method and device and computer readable storage medium |
WO2023065570A1 (en) * | 2021-10-21 | 2023-04-27 | 广东三维家信息科技有限公司 | House type coding and matching method and apparatus |
CN114187588A (en) * | 2021-12-08 | 2022-03-15 | 贝壳技术有限公司 | Data processing method, data processing device, storage medium and computer program product |
CN114187588B (en) * | 2021-12-08 | 2023-01-24 | 贝壳技术有限公司 | Data processing method, device and storage medium |
CN113946900B (en) * | 2021-12-21 | 2022-03-29 | 深圳小库科技有限公司 | Method for quickly recommending similar house types based on house type profiles and distribution characteristics |
CN113946900A (en) * | 2021-12-21 | 2022-01-18 | 深圳小库科技有限公司 | Method for quickly recommending similar house types based on house type profiles and distribution characteristics |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109992693A (en) | House type matching process and device | |
EP3543960B1 (en) | Information processing device, information processing method, and program | |
CN105869173B (en) | A kind of stereoscopic vision conspicuousness detection method | |
CN109035250B (en) | Method and device for establishing age prediction model and age prediction method and device | |
CN109522874A (en) | Human motion recognition method, device, terminal device and storage medium | |
CN103810506B (en) | A kind of hand-written Chinese character strokes recognition methods | |
CN104077447B (en) | Urban three-dimensional space vector modeling method based on paper plane data | |
CN106897714A (en) | A kind of video actions detection method based on convolutional neural networks | |
CN107369203B (en) | Indoor three-dimensional scene self-adaptive construction method and device | |
JP2010152884A (en) | Image recognition algorithm, method of identifying target image using the same, and method of selecting data for transmission to portable electronic device | |
CN104899883A (en) | Indoor object cube detection method for depth image scene | |
CN110827398A (en) | Indoor three-dimensional point cloud automatic semantic segmentation algorithm based on deep neural network | |
CN111091618B (en) | Combined indoor layout method and system based on house type data driving | |
CN108763813A (en) | It is a kind of to identify the method and apparatus for copying wall in figure based on deep learning | |
CN107102861B (en) | A kind of method and system obtaining the vector of function in Open Source Code library | |
CN112733246B (en) | Automatic building design method, device, terminal, storage medium and processor | |
CN110543895A (en) | image classification method based on VGGNet and ResNet | |
CN110246572A (en) | Method and system are examined in a kind of medical treatment based on term vector point | |
CN111105473A (en) | Two-dimensional house-type graph construction method and device and storage medium | |
CN110276741A (en) | The method and apparatus and electronic equipment of nodule detection and its model training | |
CN109284760A (en) | A kind of furniture detection method and device based on depth convolutional neural networks | |
CN115081087B (en) | Decoration cloud design method, device, equipment and storage medium based on Internet of things | |
CN110765540A (en) | System and method for matching house type graph with various self-contained designs | |
CN114373054A (en) | Method, system, device and medium for automatically generating three-dimensional house layout | |
CN104978583B (en) | The recognition methods of figure action and device |
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: 20190709 |
|
RJ01 | Rejection of invention patent application after publication |