CN109214873A - A kind of intelligent shoe cabinet and shoes recommended method - Google Patents
A kind of intelligent shoe cabinet and shoes recommended method Download PDFInfo
- Publication number
- CN109214873A CN109214873A CN201811267910.0A CN201811267910A CN109214873A CN 109214873 A CN109214873 A CN 109214873A CN 201811267910 A CN201811267910 A CN 201811267910A CN 109214873 A CN109214873 A CN 109214873A
- Authority
- CN
- China
- Prior art keywords
- shoes
- information
- feature
- recommendation results
- default
- 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
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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0282—Rating or review of business operators or products
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Finance (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Development Economics (AREA)
- Accounting & Taxation (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Computing Systems (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Game Theory and Decision Science (AREA)
- Databases & Information Systems (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Image Processing (AREA)
Abstract
The present invention relates to a kind of intelligent shoe cabinet and shoes recommended methods, shoe chest includes data acquisition device, processing unit and display device, processing unit is electrically connected with data acquisition device and display device respectively, processing unit is used for: receiving the dressing human body image for the user that data acquisition device obtains, dressing human body image is handled, obtain garment feature, garment feature is matched with the feature templates in first database, the first shoes recommendation results are obtained according to matching result, first shoes recommendation results are matched with the default shoe information in the second database, the second shoes recommendation results are obtained according to matching result, the second shoes recommendation results are exported to be shown to the display device.Technical solution of the present invention more objectively can recommend suitable shoes to user.
Description
Technical field
The present invention relates to Smart Home technical field more particularly to a kind of intelligent shoe cabinet and shoes recommended methods.
Background technique
With the continuous improvement of living standards, in order to follow the fashion and beautiful, people increasingly pay attention to clothes and shoes
Collocation, according to different occasion, clothes is arranged in pairs or groups from different shoes, different styles can be obtained, show different
Glamour.But it is presently mainly arranged in pairs or groups according to the personal experience of user.On the one hand, the personal experience of user often compares
It is relatively limited, while by its subjective impact, style of arranging in pairs or groups generally compares fixation, and the shoes perhaps selected not are most suitable choosing
It selects.On the other hand, the user less for collocation experience, generally requires repeatedly to try on, can just find and be suitble to take with clothes with it
The shoes matched, collocation process requires a great deal of time and energy.
Summary of the invention
The technical problem to be solved by the present invention is to solve the above shortcomings of the prior art and to provide a kind of intelligent shoe cabinet and shoes
Sub- recommended method.
The technical scheme to solve the above technical problems is that
In a first aspect, the present invention provides a kind of intelligent shoe cabinet, including data acquisition device, processing unit and display dress
It sets, the processing unit is electrically connected with the data acquisition device and the display device respectively, and the processing unit is used for:
Receive the dressing human body image for the user that the data acquisition device obtains.
The dressing human body image is handled, garment feature is obtained.
The garment feature is matched with the feature templates in first database, wherein the first database packet
Multiple and different feature templates and the first shoes recommendation results corresponding with the feature templates are included, according to matching result
Obtain the first shoes recommendation results.
The first shoes recommendation results are matched with the default shoe information in the second database, wherein described
Second database includes a plurality of different default shoe information, and the shoes that the default shoe information and user possess are one by one
It is corresponding, the second shoes recommendation results are obtained according to matching result.
The second shoes recommendation results are exported to be shown to the display device.
Second aspect, the present invention provides a kind of shoes recommended methods, which comprises
Step 1, the dressing human body image for the user that the data acquisition device obtains is received.
Step 2, the dressing human body image is handled, obtains garment feature.
Step 3, the garment feature is matched with the feature templates in first database, wherein first number
Include multiple and different feature templates and the first shoes recommendation results corresponding with the feature templates according to library, according to
The first shoes recommendation results are obtained with result.
Step 4, the first shoes recommendation results are matched with the default shoe information in the second database,
In, second database includes a plurality of different default shoe information, what the default shoe information and user possessed
Shoes correspond, and obtain the second shoes recommendation results according to matching result.
Step 5, the second shoes recommendation results are exported to be shown to the display device.
The beneficial effects of the present invention are: the dressing human body to user can be passed through when user selects shoes collocation clothes
Image carries out feature extraction, to obtain the garment feature of the dressing human body image of user, and garment feature is counted with first respectively
It is matched according to multiple feature templates in library.Wherein, first database can be is obtained by Fashion Magazines, is also possible to
Shared by fashion bloger or other methods obtain in advance.By matching, the clothes under certain condition with user can be determined
Fill the immediate feature templates of feature, so that it may obtain corresponding with feature templates the first shoes recommendation results, then by the first shoes
Sub- recommendation results are matched with the default shoe information in the second database, the first shoes recommendation results and default shoe information
It may include the color, material and style etc. of shoes.If successful match, it can determine that recommendation is corresponding with the default shoe information
Shoes, due in the second database default shoe information and the shoes that possess of user correspond, therefore user can be gathered around
Several double shoes in some shoes closest to feature templates are pushed to user.By being handled after acquisition image, what is provided is built
Discuss it is more objective, can be found in conjunction with data sources such as Fashion Magazines be more suitable for the shoes of worn garment coordination, and pass through set
The standby process time-consuming for providing suggestion is short, does not need user and repeatedly tries shoes on, can substantially save the time and efforts of user, mention
The usage experience of high user.
Detailed description of the invention
Fig. 1 is a kind of structural schematic diagram of intelligent shoe cabinet of the embodiment of the present invention；
Fig. 2 is a kind of circuit connection diagram of intelligent shoe cabinet of the embodiment of the present invention；
Fig. 3 is a kind of structural schematic diagram of drawer of the embodiment of the present invention；
Fig. 4 is a kind of flow diagram of shoes recommended method of the embodiment of the present invention.
In attached drawing, parts list represented by the reference numerals are as follows:
1, data acquisition device, 2, display device, 3, cabinet body, 4, drawer, 5, pressure sensor.
Specific embodiment
The principle and features of the present invention will be described below with reference to the accompanying drawings, and the given examples are served only to explain the present invention, and
It is non-to be used to limit the scope of the invention.
As shown in Figure 1, 2, a kind of intelligent shoe cabinet provided in an embodiment of the present invention, including data acquisition device 1, processing unit
With display device 2, the processing unit is electrically connected with the data acquisition device 1 and the display device 2 respectively, the processing
Device is used for:
Receive the dressing human body image for the user that the data acquisition device 1 obtains.
The dressing human body image is handled, garment feature is obtained.
The garment feature is matched with the feature templates in first database, wherein the first database packet
Multiple and different feature templates and the first shoes recommendation results corresponding with the feature templates are included, according to matching result
Obtain the first shoes recommendation results.
The first shoes recommendation results are matched with the default shoe information in the second database, wherein described
Second database includes a plurality of different default shoe information, and the shoes that the default shoe information and user possess are one by one
It is corresponding, the second shoes recommendation results are obtained according to matching result.
The second shoes recommendation results are exported to be shown to the display device 2.
In the present embodiment, when user selects shoes collocation clothes, it can be carried out by the dressing human body image to user
Feature extraction, to obtain the garment feature of the dressing human body image of user, and by garment feature respectively and in first database
Multiple feature templates are matched.Wherein, first database can be is obtained by Fashion Magazines, is also possible to pass through fashion
What bloger's sharing or other methods obtained in advance.By matching, can determine under certain condition with the garment feature of user most
Close feature templates, so that it may obtain the first shoes recommendation results corresponding with feature templates, then the first shoes are recommended to tie
Fruit is matched with the default shoe information in the second database, and the first shoes recommendation results and default shoe information may include
Color, material and style of shoes etc..If successful match, it can determine that recommendation presets the corresponding shoes of shoe information with this,
Since the default shoe information in the second database is corresponded with the shoes that user possesses, therefore the shoes that user can be possessed
In closest to several double shoes of feature templates be pushed to user.By being handled after acquisition image, the suggestion provided is more objective
See, can be found in conjunction with data sources such as Fashion Magazines be more suitable for the shoes of worn garment coordination, and provided and built by equipment
The process time-consuming of view is short, does not need user and repeatedly tries shoes on, can substantially save the time and efforts of user, improve user's
Usage experience.
Specifically, CCD (Charge Coupled Device) high-definition camera, processing dress can be used in data acquisition device 1
It sets and ARM single-chip microcontroller can be used, MCGS touch screen can be used in display device 2.First shoes recommendation results are in first database
It is suitble to the shoes with the garment coordination of user.Default shoe information in first shoes recommendation results and the second database is carried out
Matching obtains the second shoes recommendation results.It is corresponded due to presetting shoe information with the shoes that user possesses, so second pushes away
Recommending result is the shoes for being suitble to arrange in pairs or groups with the clothes of user in shoes that user possesses.
Preferably, the garment feature includes clothes profile and clothing color, and the processing unit is specifically used for:
Image segmentation is carried out to the dressing human body image, obtains target image.
Based on Canny operator edge detection algorithm, the clothes profile is extracted from the target image.
Based on color histogram, the clothing color is extracted from the target image.
Specifically, grey linear transformation first can be carried out to dressing human body image, then uses Otsu Threshold segmentation by target figure
Shape is split.For the binary map that image segmentation obtains, Canny operator can accurately extract the exterior contour of clothes, no
The marginal interference generated with consideration in-profile and background dot, and the Fourier of frequency domain can be also carried out to obtained clothes profile
Filtering, after treatment, can either retain original clothes profile details, and can remove fluctuation and the noise of curve.Color
Hsv color space or RGB color can be used in histogram, and different color shared ratio in the target image can be depicted
Example.
Preferably, the feature templates include contour curvature feature point template and color template, and the processing unit is specific
For:
Extract the contour curvature characteristic point of the clothes profile, and by the contour curvature characteristic point and the contour curvature
Feature point template is matched, using contour curvature characteristic point described in mean value Hausdorff distance metric and the contour curvature
Similarity between feature point template obtains the first matching result.
Based on color histogram match algorithm, the clothing color is matched with the color template, obtains second
Matching result.
According to first matching result and second matching result, found in the first database and meanwhile with institute
State contour curvature feature point template and the corresponding first shoes recommendation results of the color template.
Specifically, feature templates may also include textural characteristics template and spatial position feature templates etc..Clothes profile is used for
Judge clothes fashion, the first matching result is the matched feature templates of style with user's clothes, according to the first matching result
The shoes being suitble on style with user's garment coordination can be found in first database, Hausdorff distance can be retouched quantitatively
The similitude between two point sets is stated, the corresponding contour curvature feature point template of minimum Hausdorff distance is exactly the first matching
It apart from corresponding contour curvature feature point template is all less than the Hausdorff of the threshold value as a result, a threshold value can also be set
One matching result.Color template corresponding with the clothing color is found in first database further according to color histogram nomography,
Obtain the second matching result.Second matching result is the feature templates with the color-match of user's clothes, according to the second matching
As a result the shoes being suitble in color with user's garment coordination can be found in first database.It is found in first database same
When corresponding with the first matching result and the second matching result the first shoes recommendation results, which is
The shoes with the garment coordination of user are suitable in one database on style and color.In clothes and shoes collocation, style is taken
With particularly important with colour match, the style of clothes may determine that according to clothes profile, in conjunction with colour match, so that it may obtain
Most suitable recommendation results.
Preferably, the default shoe information includes a plurality of default characteristic information, and the first shoes recommendation results include
With one-to-one first recommendation information of the default characteristic information, the processing unit is specifically used for:
First recommendation information is matched with the corresponding default characteristic information respectively.
When first recommendation information of the ratio of calibration and the default characteristic information successful match, recommendation and institute are determined
State the corresponding shoes of default shoe information.
Specifically, default characteristic information and the first recommendation information may include color, style and material of shoes etc..Due to can
Can not be found in the shoes that user possesses with shoes duplicate in the first recommendation results, therefore when shoes color,
In the information such as style and material a part matching when, such as 80% information matches when, so that it may determine recommend the shoes.
Preferably, the processing unit is specifically also used to:
It is modeled according to the garment feature and the second shoes recommendation results, obtains the arranging effect for being directed to user
3-D image, and export the arranging effect 3-D image and shown to the display device 2.
Specifically, user can see final arranging effect 3-D image in display device 2, then be selected, special
Not in the more than a pair of of the shoes of recommendation, multiple arranging effect 3-D images are sequentially displayed in display device 2, user Ke Gen
The shoes oneself liked are picked out according to itself preference, are not needed to try in turn, are saved the time, convenient and efficient.
Preferably, intelligent shoe cabinet includes cabinet body 3 and drawer 4, and the back of drawer 4 is connect with cabinet body 3 by transmission device, passed
Dynamic device is electrically connected with processing unit, for making 4 open or close of drawer.
Specifically, when the corresponding shoes of the determining final shoe information of selection of user, processing unit control transmission device is beaten
Open the corresponding drawer 4 of the shoes.Corresponding drawer 4 is opened according to the user's choice, and it is rapid in numerous shoes to be able to use family
The shoes for finding selection substantially save hunting time, convenient and efficient.
Preferably, as shown in figure 3, being provided with pressure sensor 5 on 4 bottom plate of drawer, pressure sensor 5 and processing unit electricity
Connection.
Specifically, when user takes the shoes of selection away, pressure sensor 5 transmits a signal to processing unit, a timing
Between after, processing unit control transmission device close drawer 4.It can be when user be inconvenient to close drawer 4 or forget to close drawer 4, certainly
Dynamic to close drawer 4, intelligence is convenient.
Preferably, it is provided with ozone generator in cabinet body 3, ozone generator is electrically connected with processing unit, for cabinet body 3
The shoes disinfection and sterilization of interior storage.
Specifically, processing unit generates ozone to the shoes in cabinet body 3 every the time control ozone generator work of calibration
Son carries out sterilizing.Since ozone has extremely strong killing effect to mould and bacterium, shoes can be made to keep hygienically clean.
Preferably, processing unit is also used to:
When user's storage shoes for the first time, the shoe information that data acquisition device 1 acquires is obtained, and control transmission device
An empty pump drawer 4 is opened, the number of the drawer 4 and shoe information are stored into the second database.
Specifically, shoes are stored in the empty pump drawer 4, when selecting shoes, processing unit can be believed according to shoes
Breath finds corresponding drawer 4, to find corresponding shoes.
Preferably, processing unit is also used to:
When user stores shoes and not stores the shoes for the first time, the shoes that data acquisition device 1 acquires are obtained
Information matches the shoe information with the shoe information in the second database, is found according to matching result and is believed with the shoes
It ceases one-to-one drawer 4 to number, opens the drawer 4 and number corresponding drawer 4.
Specifically, when user is not to store the shoes for the first time, for example, it is outgoing go home after when storing shoes, acquire user
The information of worn shoes, and matched with the shoe information in the second database, it can automatically open corresponding with the shoes
The shoes are continued to be stored in the drawer 4, facilitate next searching by drawer 4.The time that user finds drawer 4 can be reduced, intelligence
It can be efficiently convenient and efficient.
Preferably, 1 surface of cabinet body is provided with intelligent sound module, and the intelligent sound module is electrically connected with the processing unit
It connects.
Specifically, the voice messaging of user can be acquired by intelligent sound module, and voice messaging is handled, will locate
Information after reason is transmitted to processing unit, and processing unit control shoe chest is acted accordingly.For example, when user needs to open certain
When a drawer, intelligent sound module acquisition user issues the voice messaging for opening drawer and extracts the corresponding number of drawer, locates
It manages device and the corresponding drawer of transmission device opening is controlled according to the number.Also, multiple stories can be prestored in first database
Information, after receiving the broadcasting story order of user's sending, processing unit can control audio playing apparatus to play narration information.
User can also input memo information, such as commemoration day, birthday and meeting date etc., place by intelligent sound module
Reason device stores memo information in first database together with the corresponding date, when calendar is shown to the date, place
The corresponding memo information of reason device extraction is transmitted to display screen and is shown, can also be broadcasted by audio playing apparatus corresponding
Memo information.
Preferably, first database is connect with meteorogical phenomena database, for obtaining Weather information.
Specifically, the Weather information that processing unit will acquire shows on a display screen, can also by audio playing apparatus into
Row casting, shoe chest may be provided at doorway,, can be rapid by the Weather information broadcasted and/or shown when user, which changes shoes, to go out
Judgement need to not need to carry rain gear.Also, it can be recommended to user suitable according to the Weather information of acquisition in conjunction with the second recommendation results
Close the shoes of same day weather conditions.As shown in figure 4, a kind of shoes recommended method provided in an embodiment of the present invention, the method packet
It includes:
Step 1, the dressing human body image for the user that the data acquisition device 1 obtains is received.
Step 2, the dressing human body image is handled, obtains garment feature.
Step 3, the garment feature is matched with the feature templates in first database, wherein first number
Include multiple and different feature templates and the first shoes recommendation results corresponding with the feature templates according to library, according to
The first shoes recommendation results are obtained with result.
Step 4, the first shoes recommendation results are matched with the default shoe information in the second database,
In, second database includes a plurality of different default shoe information, what the default shoe information and user possessed
Shoes correspond, and obtain the second shoes recommendation results according to matching result.
Step 5, the second shoes recommendation results are exported to be shown to the display device 2.
Preferably, the garment feature includes clothes profile and clothing color, and the step 2 includes:
Step 2.1, image segmentation is carried out to the dressing human body image, obtains target image.
Step 2.2, it is based on Canny operator edge detection algorithm, the clothes profile is extracted from the target image.
Step 2.3, it is based on color histogram, the clothing color is extracted from the target image.
Preferably, the feature templates include contour curvature feature point template and color template, and the step 3 includes:
Step 3.1, extract the contour curvature characteristic point of the clothes profile, and by the contour curvature characteristic point with it is described
Contour curvature feature point template is matched, using contour curvature characteristic point described in mean value Hausdorff distance metric with it is described
Similarity between contour curvature feature point template obtains the first matching result.
Step 3.2, it is based on color histogram match algorithm, the clothing color is matched with the color template,
Obtain the second matching result.
Step 3.3, it according to first matching result and second matching result, is found in the first database
The first shoes recommendation results corresponding with the contour curvature feature point template and the color template simultaneously.
Preferably, the default shoe information includes a plurality of default characteristic information, and the first shoes recommendation results include
With one-to-one first recommendation information of the default characteristic information, the step 4 includes:
Step 4.1, first recommendation information is matched with the corresponding default characteristic information respectively.
Step 4.2, it when first recommendation information of the ratio of calibration and the default characteristic information successful match, determines
Recommend shoes corresponding with the default shoe information.
Preferably, the method also includes:
Step 6, it is modeled according to the garment feature and the second shoes recommendation results, obtains taking for user
With effect 3-D image, and exports the arranging effect 3-D image and shown to the display device 2.
The foregoing is merely presently preferred embodiments of the present invention, is not intended to limit the invention, it is all in spirit of the invention and
Within principle, any modification, equivalent replacement, improvement and so on be should all be included in the protection scope of the present invention.
Claims (10)
1. a kind of intelligent shoe cabinet, which is characterized in that including data acquisition device, processing unit and display device, the processing dress
It sets and is electrically connected respectively with the data acquisition device and the display device, the processing unit is used for:
Receive the dressing human body image for the user that the data acquisition device obtains；
The dressing human body image is handled, garment feature is obtained；
The garment feature is matched with the feature templates in first database, wherein the first database includes more
A different feature templates and the first shoes recommendation results corresponding with the feature templates, obtain according to matching result
The first shoes recommendation results；
The first shoes recommendation results are matched with the default shoe information in the second database, wherein described second
Database includes a plurality of different default shoe information, and the shoes one that the default shoe information and user possess are a pair of
It answers, the second shoes recommendation results is obtained according to matching result；
The second shoes recommendation results are exported to be shown to the display device.
2. intelligent shoe cabinet according to claim 1, which is characterized in that the garment feature includes clothes profile and clothes face
Color, the processing unit are specifically used for:
Image segmentation is carried out to the dressing human body image, obtains target image；
Based on Canny operator edge detection algorithm, the clothes profile is extracted from the target image；
Based on color histogram, the clothing color is extracted from the target image.
3. intelligent shoe cabinet according to claim 2, which is characterized in that the feature templates include contour curvature characteristic point mould
Plate and color template, the processing unit are specifically used for:
Extract the contour curvature characteristic point of the clothes profile, and by the contour curvature characteristic point and the contour curvature feature
Point template is matched, using contour curvature characteristic point described in mean value Hausdorff distance metric and the contour curvature feature
Similarity between point template obtains the first matching result；
Based on color histogram match algorithm, the clothing color is matched with the color template, obtains the second matching
As a result；
According to first matching result and second matching result, found in the first database and meanwhile with the wheel
Wide curvature feature point template and the corresponding first shoes recommendation results of the color template.
4. intelligent shoe cabinet according to claim 1, which is characterized in that the default shoe information includes a plurality of default feature
Information, the first shoes recommendation results include and one-to-one first recommendation information of the default characteristic information, the place
Reason device is specifically used for:
First recommendation information is matched with the corresponding default characteristic information respectively；
When first recommendation information of the ratio of calibration and when the default characteristic information successful match, determine recommend with it is described pre-
If the corresponding shoes of shoe information.
5. intelligent shoe cabinet according to any one of claims 1 to 4, which is characterized in that the processing unit is specifically also used to:
It is modeled according to the garment feature and the second shoes recommendation results, obtains the arranging effect three-dimensional for user
Image, and export the arranging effect 3-D image and shown to the display device.
6. a kind of shoes recommended method, which is characterized in that the described method includes:
Step 1, the dressing human body image for the user that the data acquisition device obtains is received；
Step 2, the dressing human body image is handled, obtains garment feature；
Step 3, the garment feature is matched with the feature templates in first database, wherein the first database
Including multiple and different feature templates and the first shoes recommendation results corresponding with the feature templates, tied according to matching
Fruit obtains the first shoes recommendation results；
Step 4, the first shoes recommendation results are matched with the default shoe information in the second database, wherein institute
Stating the second database includes a plurality of different default shoe information, the shoes one that the default shoe information and user possess
One is corresponding, obtains the second shoes recommendation results according to matching result；
Step 5, the second shoes recommendation results are exported to be shown to the display device.
7. shoes recommended method according to claim 6, which is characterized in that the garment feature includes clothes profile kimonos
Color is filled, the step 2 includes:
Step 2.1, image segmentation is carried out to the dressing human body image, obtains target image；
Step 2.2, it is based on Canny operator edge detection algorithm, the clothes profile is extracted from the target image；
Step 2.3, it is based on color histogram, the clothing color is extracted from the target image.
8. shoes recommended method according to claim 7, which is characterized in that the feature templates include contour curvature feature
Point template and color template, the step 3 include:
Step 3.1, the contour curvature characteristic point of the clothes profile is extracted, and by the contour curvature characteristic point and the profile
Curvature feature point template is matched, using contour curvature characteristic point described in mean value Hausdorff distance metric and the profile
Similarity between curvature feature point template obtains the first matching result；
Step 3.2, it is based on color histogram match algorithm, the clothing color is matched with the color template, is obtained
Second matching result；
Step 3.3, it according to first matching result and second matching result, is found simultaneously in the first database
The first shoes recommendation results corresponding with the contour curvature feature point template and the color template.
9. shoes recommended method according to claim 6, which is characterized in that the default shoe information includes a plurality of default
Characteristic information, the first shoes recommendation results include and one-to-one first recommendation information of the default characteristic information, institute
Stating step 4 includes:
Step 4.1, first recommendation information is matched with the corresponding default characteristic information respectively；
Step 4.2, it when first recommendation information of the ratio of calibration and the default characteristic information successful match, determines and recommends
Shoes corresponding with the default shoe information.
10. according to the described in any item shoes recommended methods of claim 6 to 9, which is characterized in that the method also includes:
Step 6, it is modeled according to the garment feature and the second shoes recommendation results, the collocation obtained for user is imitated
Fruit 3-D image, and export the arranging effect 3-D image and shown to the display device.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811267910.0A CN109214873A (en) | 2018-10-29 | 2018-10-29 | A kind of intelligent shoe cabinet and shoes recommended method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811267910.0A CN109214873A (en) | 2018-10-29 | 2018-10-29 | A kind of intelligent shoe cabinet and shoes recommended method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109214873A true CN109214873A (en) | 2019-01-15 |
Family
ID=64997555
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811267910.0A Pending CN109214873A (en) | 2018-10-29 | 2018-10-29 | A kind of intelligent shoe cabinet and shoes recommended method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109214873A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109859228A (en) * | 2019-01-18 | 2019-06-07 | 深圳壹账通智能科技有限公司 | Recommend the method, apparatus and computer equipment of shoes money type based on image recognition |
| CN112561009A (en) * | 2020-12-21 | 2021-03-26 | 深圳市金博奥科技有限公司 | Intelligent shoe cabinet and shoe management method and system thereof |
| CN112656341A (en) * | 2020-12-21 | 2021-04-16 | 深圳市金博奥科技有限公司 | Intelligent shoe cabinet |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20130049376A (en) * | 2011-11-04 | 2013-05-14 | 한국전자통신연구원 | Apparatus and method for recommending personalized clothes |
| US20150055860A1 (en) * | 2011-09-30 | 2015-02-26 | Ebay Inc. | Item recommendations using image feature data |
| CN106952142A (en) * | 2017-03-17 | 2017-07-14 | 合肥龙图腾信息技术有限公司 | Clothing matching intelligent recommendation systems, devices and methods |
| CN106980485A (en) * | 2017-03-31 | 2017-07-25 | 陈凤 | A kind of Intelligent clothes cabinet system and its management method |
| CN107248099A (en) * | 2017-06-01 | 2017-10-13 | 深圳天珑无线科技有限公司 | Clothing matching recommends method, system and storage medium |
| CN108564439A (en) * | 2018-03-28 | 2018-09-21 | 深圳市零度智控科技有限公司 | Dress ornament recommends method and system, terminal and storage medium |
| CN108596730A (en) * | 2018-04-26 | 2018-09-28 | 北京超满意科技有限责任公司 | Processing method, device and the smart machine of dress ornament information |
-
2018
- 2018-10-29 CN CN201811267910.0A patent/CN109214873A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150055860A1 (en) * | 2011-09-30 | 2015-02-26 | Ebay Inc. | Item recommendations using image feature data |
| KR20130049376A (en) * | 2011-11-04 | 2013-05-14 | 한국전자통신연구원 | Apparatus and method for recommending personalized clothes |
| CN106952142A (en) * | 2017-03-17 | 2017-07-14 | 合肥龙图腾信息技术有限公司 | Clothing matching intelligent recommendation systems, devices and methods |
| CN106980485A (en) * | 2017-03-31 | 2017-07-25 | 陈凤 | A kind of Intelligent clothes cabinet system and its management method |
| CN107248099A (en) * | 2017-06-01 | 2017-10-13 | 深圳天珑无线科技有限公司 | Clothing matching recommends method, system and storage medium |
| CN108564439A (en) * | 2018-03-28 | 2018-09-21 | 深圳市零度智控科技有限公司 | Dress ornament recommends method and system, terminal and storage medium |
| CN108596730A (en) * | 2018-04-26 | 2018-09-28 | 北京超满意科技有限责任公司 | Processing method, device and the smart machine of dress ornament information |
Non-Patent Citations (1)
| Title |
|---|
| 李东等: "基于轮廓曲率特征点的服装款式识别方法", 《东华大学学报(自然科学版)》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109859228A (en) * | 2019-01-18 | 2019-06-07 | 深圳壹账通智能科技有限公司 | Recommend the method, apparatus and computer equipment of shoes money type based on image recognition |
| CN112561009A (en) * | 2020-12-21 | 2021-03-26 | 深圳市金博奥科技有限公司 | Intelligent shoe cabinet and shoe management method and system thereof |
| CN112656341A (en) * | 2020-12-21 | 2021-04-16 | 深圳市金博奥科技有限公司 | Intelligent shoe cabinet |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11691073B2 (en) | Extended reality AR/VR system | |
| CN105118082B (en) | Individualized video generation method and system | |
| US10176642B2 (en) | Systems and methods for computer assisted operation | |
| CN109214873A (en) | A kind of intelligent shoe cabinet and shoes recommended method | |
| US10492981B1 (en) | Systems and methods for computer assisted operation | |
| US10685488B1 (en) | Systems and methods for computer assisted operation | |
| CN107123019A (en) | A kind of VR shopping commending systems and method based on physiological data and Emotion identification | |
| JP5090870B2 (en) | Makeup unit | |
| CN104484450B (en) | Clothing matching based on image recommends method and clothing matching recommendation apparatus | |
| CN105808903A (en) | Health report generation method and apparatus | |
| CN108734710A (en) | A kind of intelligence fruits and vegetables selection method | |
| CN105869217B (en) | A kind of virtual real fit method | |
| CN107773225A (en) | Pulse wave measuring apparatus, pulse wave measuring method, program and recording medium | |
| CN106951448A (en) | A kind of personalization, which is worn, takes recommendation method and system | |
| CN111612584A (en) | AI intelligent clothing recommendation method based on wearing and putting-on theory | |
| CN109902561A (en) | A kind of face identification method and device, robot applied to robot | |
| CN109448817A (en) | A kind of recipe recommendation method and apparatus based on deep neural network | |
| CN110634053A (en) | Active interactive intelligent selling system and method | |
| CN107317974A (en) | A kind of makeups photographic method and device | |
| Iosifidis et al. | The MOBISERV-AIIA Eating and Drinking multi-view database for vision-based assisted living. | |
| CN108682045A (en) | A kind of mirror and its control method based on smart home | |
| CN109978720A (en) | Wearing grading method and device, intelligent equipment and storage medium | |
| CN109284666B (en) | A kind of dress ornament recommended method based on image recognition and big data | |
| CN108771315A (en) | A kind of control method and system of intelligent cosmetic mirror | |
| CN108771539A (en) | A kind of detection method and its device of the contactless heart rate based on camera shooting |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190115 |