CN109166147A - Garment dimension measurement method and device based on picture - Google Patents
Garment dimension measurement method and device based on picture Download PDFInfo
- Publication number
- CN109166147A CN109166147A CN201811056058.2A CN201811056058A CN109166147A CN 109166147 A CN109166147 A CN 109166147A CN 201811056058 A CN201811056058 A CN 201811056058A CN 109166147 A CN109166147 A CN 109166147A
- Authority
- CN
- China
- Prior art keywords
- clothes
- information
- key point
- picture
- 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.)
- Withdrawn
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
-
- A—HUMAN NECESSITIES
- A41—WEARING APPAREL
- A41H—APPLIANCES OR METHODS FOR MAKING CLOTHES, e.g. FOR DRESS-MAKING OR FOR TAILORING, NOT OTHERWISE PROVIDED FOR
- A41H1/00—Measuring aids or methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
Abstract
The problem of the present invention provides garment dimension measurement methods and device based on picture, are related to dress designing field, alleviate in the prior art by artificial existing inefficiency, can be improved measurement efficiency.Wherein, this method includes the pictorial information for receiving user and uploading, and pictorial information is the picture including default object of reference and clothes to be measured presetting photo environment, being obtained under default photo angle by camera；The Pixel Dimensions and actual size for obtaining default object of reference generate the coefficient of ratio based on Pixel Dimensions and actual size；Identify the clothes classification of clothes to be measured；It is searched and the matched key point identification model of clothes classification according to clothes classification；Key point identification model is called to identify key point characteristic information；The first size information of clothes to be measured is calculated based on key point characteristic information；Wherein first size information is Pixel Dimensions；The second dimension information is calculated based on first size information and the coefficient of ratio；Wherein the second dimension information is actual size.
Description
Technical field
The present invention relates to technical field of costume design, more particularly to garment dimension measurement method and device based on picture.
Background technique
Clothes are the development with human society and constantly development and change.Phase in the time immemorial, the initial clothes of the mankind are
Made of leaf, animal skin etc., later, occur with bast-fibre and grass system etc. at clothing.And with the raising of productivity
With the development of science and technology, material becomes more and more abundant multiplicity, correspondingly, the type of the clothing of manufacture also gradually increases.In the modern times
In society, people can select the clothes for being suitble to oneself according to oneself hobby and specific requirements, in a certain sense for,
Clothes have been that everyone decorates oneself, protect oneself, can give the necessary supply of oneself and household, not just for wearing, even more one
Identity, a kind of life attitudes, one displaying charisma performance.
Therefore, it needs to measure clothes during dress designing, to obtain the measured value size of clothes, then
Subsequent improvement is carried out based on the dimensional measurements to be suitble to more consumer demands.However, traditional garment measuring method according to
The mode manually measured carries out, and there are problems that inefficiency.
Summary of the invention
In view of this, garment dimension measurement method and the dress of the embodiment of the present invention being designed to provide based on picture
The problem of setting, alleviating in the prior art by inefficiency existing for artificial mode, can be improved measurement efficiency.
In a first aspect, the embodiment of the invention provides the garment dimension measurement methods based on picture, comprising:
The pictorial information that user uploads is received, the pictorial information is the figure for including default object of reference and clothes to be measured
Piece；The pictorial information is obtained under default photo angle in default photo environment, by camera；
The Pixel Dimensions data and actual size data for obtaining the default object of reference in the pictorial information, are based on
The Pixel Dimensions data and the actual size data generate the coefficient of ratio；
Identify the clothes classification of the clothes to be measured in the pictorial information；
The clothes key point identification model to match with the clothes classification is searched according to the clothes classification；
The clothes key point identification model is called to identify the clothes key point characteristic information in the pictorial information；
The first size information that the clothes to be measured are calculated is carried out based on the clothes key point characteristic information；Its
Described in first size information include the clothes to be measured default characteristic portion Pixel Dimensions；
The second dimension information is calculated based on the first size information and the coefficient of ratio；Wherein second ruler
Very little information includes the actual size of the default characteristic portion of the clothes to be measured.
With reference to first aspect, the embodiment of the invention provides the first possible embodiments of first aspect, wherein institute
It states and the clothes key point identification model is called to identify the clothes key point characteristic information in the picture, comprising:
The clothes key point identification model is called to identify the clothes key point classification information in the picture and the clothes
Fill key point location information.
With reference to first aspect, the embodiment of the invention provides second of possible embodiments of first aspect, wherein institute
State the paper jam that default object of reference is preset shape；Include clothes identification code on the paper jam, the clothes identification code with it is described
Clothes identification code described in electronic equipment can only be identified by the electronic equipment；The electronic equipment can only identify the clothes
Identification code.
With reference to first aspect, the embodiment of the invention provides the third possible embodiments of first aspect, wherein institute
Stating default photo environment is to control to adjust to obtain by film studio.
With reference to first aspect, the embodiment of the invention provides the 4th kind of possible embodiments of first aspect, wherein institute
Stating default photo angle is to control to adjust to obtain by photography support, to reduce angular distortion when camera level is taken pictures；It is described to take the photograph
Shadow frame is for being arranged the camera.
With reference to first aspect, the embodiment of the invention provides the 5th kind of possible embodiments of first aspect, wherein institute
State method further include:
Second dimension information is exported.
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 described based on the clothes key point characteristic information to carry out that the clothes to be measured are calculated
First size information, comprising:
Transfer key point computation rule corresponding with the clothes classification；Wherein the key point computation rule includes institute
State the Pixel Dimensions computation rule of the other default characteristic portion of clothing；
It carries out being calculated described first based on the clothes key point characteristic information and the key point computation rule
Dimension information.
Second aspect, the embodiment of the invention provides the garment dimension measuring devices based on picture, comprising:
Picture receiving module, for receiving the pictorial information of user's upload, the pictorial information be include default object of reference
With the picture of clothes to be measured；The pictorial information is obtained under default photo angle in default photo environment, by camera
's；
Ratio obtain module, for obtain the default object of reference in the pictorial information Pixel Dimensions data and
Actual size data generate the coefficient of ratio based on the Pixel Dimensions data and the actual size data；
Classification identification module, for identification the clothes classification of the clothes to be measured in the pictorial information；
Searching module is identified for searching the clothes key point to match with the clothes classification according to the clothes classification
Model；
Key point identification module, for calling the clothes key point identification model to identify the clothes in the pictorial information
Key point characteristic information；
First computing module, for based on the clothes key point characteristic information carrying out that the clothes to be measured are calculated
First size information；Wherein the first size information includes the pixel ruler of the default characteristic portion of the clothes to be measured
It is very little；
Second computing module, for the second size letter to be calculated based on the first size information and the coefficient of ratio
Breath；Wherein second dimension information includes the actual size of the default characteristic portion of the clothes to be measured.
The third aspect, the embodiment of the present invention also provide a kind of electronic equipment, including memory and processor, and memory is used
Processor is supported to execute the program for the garment dimension measurement method based on picture that above-mentioned aspect provides in storage, processor is matched
It is set to for executing the program stored in memory.
Fourth aspect, the embodiment of the present invention also provide a kind of computer readable storage medium, computer readable storage medium
On be stored with computer program, when computer program is run by processor execute any of the above-described method the step of.
Garment dimension measurement method, device, electronic equipment and computer provided in an embodiment of the present invention based on picture can
Read storage medium, wherein being somebody's turn to do the garment dimension measurement method based on picture includes: the pictorial information for receiving user and uploading, picture
Information is the picture for including default object of reference and clothes to be measured；Pictorial information be default photo environment, by camera pre-
If being obtained under photo angle；The Pixel Dimensions data and actual size data of the default object of reference in pictorial information are obtained,
The coefficient of ratio is generated based on Pixel Dimensions data and actual size data；Identify the clothing of the clothes to be measured in pictorial information
Not；The clothes key point identification model to match with clothes classification is searched according to clothes classification；Clothes key point is called to identify mould
Type identifies the clothes key point characteristic information in pictorial information；Be calculated based on clothes key point characteristic information to be measured
The first size information of clothes；Wherein first size information includes the Pixel Dimensions of the default characteristic portion of clothes to be measured；Base
The second dimension information is calculated in first size information and the coefficient of ratio；Wherein the second dimension information includes clothes to be measured
The actual size of default characteristic portion.Therefore, technical solution provided in an embodiment of the present invention alleviates in the prior art by people
The problem of inefficiency existing for the mode of work, it can be improved measurement efficiency.The picture that this method is inputted based on user, to picture
It measures to obtain the dimensional measurements at multiple positions of clothes, it is middle by the existing effect of artificial mode compared with the prior art
The low problem of rate, can be improved measurement efficiency, and this method simply, easily and fast, substantially increases the measurement effect of garment dimension
Rate saves manpower, time cost.
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 shows the flow chart of the garment dimension measurement method based on picture provided by the embodiment of the present invention；
Fig. 2 shows a kind of schematic diagrames of pictorial information provided by the embodiment of the present invention；
Fig. 3 shows the schematic diagram of the key point characteristic information in a kind of garment image provided by the embodiment of the present invention；
Fig. 4 shows the application scenario diagram of the garment dimension measurement method based on picture provided by the embodiment of the present invention；
Fig. 5 shows the structural schematic diagram of the garment dimension measuring device based on picture provided by the embodiment of the present invention；
Fig. 6 shows the schematic diagram of electronic equipment provided by the embodiment of the present invention.
Specific embodiment
Below in conjunction with attached drawing in the embodiment of the present invention, technical solution in the embodiment of the present invention carries out clear, complete
Ground description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.Usually exist
The component of the embodiment of the present invention described and illustrated in attached drawing can be arranged and be designed with a variety of different configurations herein.Cause
This, is not intended to limit claimed invention to the detailed description of the embodiment of the present invention provided in the accompanying drawings below
Range, but it is merely representative of selected embodiment of the invention.Based on the embodiment of the present invention, those skilled in the art are not doing
Every other embodiment obtained under the premise of creative work out, shall fall within the protection scope of the present invention.
Currently, needing to measure clothes during dress designing, to obtain the measured value size of clothes, then
Subsequent improvement is carried out based on the dimensional measurements to be suitble to more consumer demands.However, traditional garment measuring one is
It is carried out by the mode of manual measurement, working efficiency is low；Another kind is that clothes sleeve is carried out stereo man on three-dimensional humanoid model
Shape model is taken pictures, low efficiency of taking pictures；Based on this, the embodiment of the invention provides garment dimension measurement methods and dress based on picture
It sets, to alleviate the problem of relying on artificial existing inefficiency in the prior art, can be improved measurement efficiency.
It is described in detail below by embodiment.
Embodiment one:
The garment dimension measurement method based on picture that the embodiment of the invention provides a kind of can be applied to dress designing neck
Domain is particularly suitable for the dimensional measurement of clothes.This method is executed by electronic equipment, and above-mentioned electronic equipment includes API
(Application Programming Interface, application programming interface), electronic equipment can be connect by the API
Receive the pictorial information that user uploads.
Specifically, referring to Fig.1, this method comprises:
Step S101, receives the pictorial information that user uploads, the pictorial information be include default object of reference and clothes to be measured
The picture of dress；
What needs to be explained here is that the pictorial information be default photo environment, by camera in default photo angle
Lower acquisition；
Wherein, the default photo environment is to control to adjust to obtain by film studio, is known with reducing noise object to picture
Other influence；
Specifically, obtaining default photo environment with film studio control shooting environmental (is suitable for shooting clearly picture
The good photo environment such as light intensity), so that reducing the AI of noise object contributions AI vision algorithm here includes clothes identification AI (clothes
Fill classification identification model) and clothes key point AI (clothes key point identification model).
Above-mentioned default photo angle is to control to adjust to obtain by photography support, to reduce angle when camera level is taken pictures
Distortion；The photography support is for being arranged the camera；The photography support is arranged in above-mentioned camera shooting canopy.That is, logical
It is horizontal to cross the camera being arranged on photography support using the photography support control for being located at camera shooting canopy, reduces photo angle distortion.
Compared to the mode in the prior art that clothes sleeve is carried out to stereo man shape model on three-dimensional humanoid model and is taken pictures,
The embodiment of the present invention improves efficiency of taking pictures by the way of laying flat and taking pictures.
Further, the default object of reference is the paper jam of preset shape；It include clothes identification code, institute on the paper jam
Stating clothes identification code can only be identified by the garment dimension identifying system；The garment dimension identifying system can only be known
The not described clothes identification code；Above-mentioned clothes identification code is a kind of AR code, can be encoded and be obtained in advance by AR coding techniques.
Fig. 2 shows a kind of schematic diagrames of pictorial information.Specifically, referring to fig. 2, the default object of reference is to be printed with clothes
Fill the rectangle paper jam of the specific dimensions of identification code.That is, the length of rectangle paper jam, the size of width are known；Certainly,
Default object of reference can also use the other arbitrary shapes of plane.
The embodiment of the present invention is by generating regular coding (clothes identification code) using AR coding techniques and being printed on
On specific dimensions paper jam, default object of reference of the paper jam as planar shaped is taken pictures together with the clothes to be measured laid flat, due to electronics
Equipment is only capable of the regular coding that identification has been arranged, it is therefore prevented that the pattern (such as two dimensional code, bar code etc.) of other forms is to electronics
The influence of equipment passes through exclusive PCR factor, it is ensured that the uniqueness of clothes identification improves the accuracy and height of clothes identification
Effect property.
Step S102 obtains the Pixel Dimensions data and actual size data of the default object of reference in pictorial information, is based on
Pixel Dimensions data and actual size data generate the coefficient of ratio；
Here Pixel Dimensions data refer to the Pixel Dimensions of the predeterminated position of default object of reference；Here actual size number
According to the actual size for the predeterminated position for referring to default object of reference；The actual size data of above-mentioned default object of reference be it is known,
And it can be stored in advance in the memory of electronic equipment to facilitate and call.
Wherein, Pixel Dimensions data directly can read to obtain by picture；Actual size data pass through from memory
(extraction) is transferred to obtain.
Such as predeterminated position can be a line line of the profile of default object of reference, one of the profile of the default object of reference
Sideline can be the straight line that the pixel of any two contour edge is formed by connecting.
For calculating ratio coefficient, this can be preset to predeterminated position (such as the wheel of above-mentioned default object of reference of object of reference
Wide a line line) actual size and pictorial information in the ratio between Pixel Dimensions of the identical predeterminated position obtain ratio
Coefficient；
Specifically, can use pixel distance (the i.e. Pixel Dimensions number that recognizer calculates the sideline of default object of reference
According to), referring again to the actual size (i.e. actual size data) in the sideline of the default object of reference set, removed with actual size
The coefficient of ratio is calculated with pixel distance, actual size can be measured with millimeter here, and the calculated coefficient of ratio is millimeter
To pixel rate.Here the coefficient of ratio is used to characterize the conversion relation of actual size data and Pixel Dimensions, actual size number
According to unit have no influence, therefore actual size data can also with centimetre etc. other length units measure, do not limit here
It is fixed.
In order to make it easy to understand, predeterminated position is the long side of rectangle here using the rectangle paper jam in Fig. 2 as default object of reference
The calculating process of the above-mentioned coefficient of ratio is illustrated for (i.e. the length of rectangle):
Firstly, obtaining the Pixel Dimensions of the long side of rectangle paper jam in Fig. 2 and transferring the known rectangular card from memory
The actual size of the long side of paper；It is then based on the two to carry out that the coefficient of ratio is calculated, specifically, by the actual size of the long side
The coefficient of ratio is obtained divided by the Pixel Dimensions of the long side.
Step S103 identifies the clothes classification of the clothes to be measured in pictorial information；
Specifically, transferring the clothes that the clothes classification identification model constructed in advance identifies the clothes to be measured in the pictorial information
Fill classification；Above-mentioned clothes classification includes the clothes fashions such as T-shirt, trousers, shirt, skirt.
The clothes classification identification model constructed in advance is stored in the memory of electronic equipment, in order to subsequent calls and clothes
Fill classification identification.
Therefore, this method further include: building clothes classification identification model, the building clothes classification identification model pass through following
Step executes:
1, trained garment image is obtained；Wherein training with garment image is to be labeled with the other picture of clothing；Training is used
Clothes are more than one piece, and, the corresponding clothes classification of trained clothes described in more than one piece is different.
Training with garment image is obtained under default photo angle in above-mentioned default photo environment, by camera, i.e.,
Camera carries out shooting with clothes to more than one piece training respectively and generates picture, then carries out clothing on the picture and does not mark, obtains
To trained garment image；
2, CNN model is trained with garment image based on above-mentioned training, clothes classification identification model is obtained with building.
Specifically, being trained by supervised algorithm to CNN model based on multiple described training with picture, clothes are constructed
Classification identification model.I.e. by the supervised algorithm training CNN model of deep learning to the clothing in trained garment image
Do not learnt and identified, construct clothes classification identification model, the clothes classification identification model of building can be used to a variety of clothes
Dress classification is identified.
Step S104 searches the clothes key point identification model to match with the clothes classification according to clothes classification；
The mapping table of clothes classification Yu clothes key point identification model is previously stored in the memory of electronic equipment；
Therefore, the clothes key point identification model which obtains matching with the clothes classification is searched by clothes classification.
Step S105 calls the clothes key point feature letter in above-mentioned clothes key point identification model identification pictorial information
Breath；
Above-mentioned clothes key point information includes clothes key point classification information and the clothes key point location information.Figure
3 show the key point characteristic information in a kind of garment image.T-shirt and its key point category information table referring to shown in Fig. 3,
Middle key point classification information includes that posterior neck 1, right collar 2, right shoulder 3, right sleeve be outer 4,5, right body 6, right pleat 7, left pleat 8, left body in right sleeve
9,10, left sleeve outer 11, left shoulder 12, left collar 13 in left sleeve；
In the memory of the clothes key point identification model storage electronic equipment constructed in advance, in order to subsequent calls and pass
The identification of key point feature information.
Specifically, step S105 includes:
Call the clothes key point classification information in clothes key point identification model identification picture and clothes key point position
Information, clothes key point location information can be indicated in the form of pixel；Key point location information is sat with pixel in other words
What mark indicated.
It should be noted that clothes key point identification model is the supervised algorithm by using deep learning to CNN
(Convolutional Neural Network, convolutional neural networks) model constructs after being trained to training with garment image
It obtains；Above-mentioned training is labeled with key point characteristic information with garment image in advance, that is, trains related with garment image mark
Key point classification information and key point location information；Above-mentioned key point location information is indicated in the form of pixel coordinate, in order to mention
High accuracy of identification, size, the angle of training garment image in the training process are consistent；And the key point classification of mark
For establishing key point data set, which identifies for above-mentioned clothes key point for information and key point location information
The building process of model, specifically, being labeled with key point classification and position foundation by the training CNN model identification of supervised algorithm
Key point data set training garment image crucial classification and its position.
Therefore, this method further include: building clothes key point identification model, the building clothes key point identification model include
Following steps:
1, the second trained garment image is obtained；Wherein the second training is to be labeled with key point characteristic information with garment image
Picture；Second training with clothes is more than one piece, and, the corresponding key point characteristic information of the second trained clothes described in more than one piece is not
Together；The key point characteristic information is corresponding with the clothes classification of the described second trained clothes；
Specifically, the second above-mentioned training is also to take pictures in default photo environment, by camera default with garment image
The shooting of default clothing other clothes is obtained under angle, i.e., camera presets the trained clothes of clothing other second to this
It is shot, obtains shooting picture, be then labeled in the shooting figure on piece, generate the second trained garment image.Such as
It can be marked on picture by mapping software, be not construed as limiting here.
2, CNN model is trained with garment image based on above-mentioned training, clothes classification identification model is obtained with building.
Specifically, being carried out by supervised algorithm to CNN model based on default other second training of clothing with picture
Training, building obtain clothes key point identification model.Instructed by the supervised algorithm training CNN model of deep learning to second
White silk is learnt and is identified with the key point characteristic information in garment image, and clothes key point identification model is constructed.
It should be noted that can train to obtain a variety of clothes key point identification models when default clothes classification is a variety of,
That is, clothes key point identification model is one-to-one with clothes classification.
In addition, clothes classification and the other crucial point feature of the clothing can be labeled with simultaneously by the picture that camera is shot
Information improves building efficiency to be trained simultaneously to two kinds of models, i.e., the second training is to be labeled with clothing with picture
The picture of key point characteristic information is further marked on the basis of other training picture, in other words, clothes classification identifies mould
Type and clothes key point identification model, which use in the shooting picture shot to default clothes classification, had both marked out clothes classification
With the other key point characteristic information of the clothing (referred to as study picture)；That is, trained picture and the second training are used
Garment image can be unified for a study picture, which can both be used to training and obtain clothes classification identification model,
It can be used for training and obtain clothes key point identification model.
Step S106 carries out the first size information that clothes to be measured are calculated based on clothes key point characteristic information；
Wherein the first size information includes the Pixel Dimensions of the default characteristic portion of the clothes to be measured；Above-mentioned
Default characteristic portion includes the positions such as sleeve length, chest breadth, shoulder breadth, neck width, height, waist length.
Specifically, the key based on the clothes key point characteristic information and the other default characteristic portion of the clothing
Point computation rule carries out the first size information that the clothes to be measured are calculated.
Step S106 the following steps are included:
1, key point computation rule corresponding with the clothes classification is transferred；Wherein the key point computation rule includes
The Pixel Dimensions computation rule of the other default characteristic portion of clothing；
2, it carries out being calculated described based on the clothes key point characteristic information and the key point computation rule
One dimension information.
Key point computation rule includes sleeve length computation rule, chest breadth computation rule, shoulder breadth computation rule, the wide calculating rule of neck
Then, above-mentioned acquisition clothes key point characteristic information is combined preset pass by long computation rule of height computation rule, waist etc.
The Pixel Dimensions of the default characteristic portion of clothes to be measured are calculated in key point computation rule.It is pointed out that key point meter
It calculates rule and is properly termed as distance algorithm, the distance (Pixel Dimensions) of the default characteristic portion for calculating clothes to be measured.
Below by taking the T-shirt of Fig. 3 as an example, the long computation rule of waist is as follows: the picture of right pleat 7 and left pleat 8 (7,8 be key point classification)
The difference of plain coordinate (key point position) utilizes Pythagorean theorem, it is long that waist is calculated to get the pixel coordinate long to waist, pixel coordinate
The Pixel Dimensions of (default characteristic portion)；The computation rule of other characteristic portions is referred to the long computation rule of waist, herein no longer
It repeats.
It, can be with since the different other key point characteristic informations of clothing and key point computation rule are different
By key point computation rule it is corresponding with clothes classification, key point characteristic information after store in memory, to facilitate subsequent calls
Carry out Pixel Dimensions calculating.
The second dimension information is calculated based on first size information and the coefficient of ratio in step S107.
Wherein, the second dimension information includes the actual size of the default characteristic portion of clothes to be measured.
Specifically, first size information is multiplied with the coefficient of ratio can be calculated the second dimension information.
It can be realized by step S107 and the Pixel Dimensions in pictorial information obtained into full-size(d) by size conversion,
Complete the dimensional measurement of clothes.
Garment dimension measurement method provided in an embodiment of the present invention based on picture includes: the picture letter for receiving user and uploading
Breath, pictorial information are the picture for including default object of reference and clothes to be measured；Pictorial information is in default photo environment, by imaging
What head obtained under default photo angle；Obtain the Pixel Dimensions data and actual size of the default object of reference in pictorial information
Data generate the coefficient of ratio based on Pixel Dimensions data and actual size data；Identify the clothes to be measured in pictorial information
Clothes classification；The clothes key point identification model to match with clothes classification is searched according to clothes classification；Call clothes key point
Identification model identifies the clothes key point characteristic information in pictorial information；It is calculated based on clothes key point characteristic information
The first size information of clothes to be measured；Wherein first size information includes the pixel ruler of the default characteristic portion of clothes to be measured
It is very little；The second dimension information is calculated based on first size information and the coefficient of ratio；Wherein the second dimension information includes to be measured
The actual size of the default characteristic portion of clothes.Therefore, technical solution provided in an embodiment of the present invention, alleviates in the prior art
The problem of by inefficiency existing for artificial mode, it can be improved measurement efficiency.The picture that this method is inputted based on user,
Picture is measured to obtain the dimensional measurements (true value) at multiple positions of clothes, it is middle by artificial compared with the prior art
Mode existing for inefficiency the problem of, can be improved measurement efficiency；This method combines AR in prediction clothes key point and compiles
Code identification and AI vision technique, recognition accuracy is high, and test simply, easily and fast, substantially increases the measurement of garment dimension
Efficiency saves manpower, time cost.In addition, 1) this method, which also has the advantage that, can be adapted to a variety of clothes classifications, it is not required to
Want special model；2) individual cloth parts be can recognize and measure relative dimensions；3) high efficiency, can be with snapshots more than one piece clothes；
4) simplified deployment, in addition to camera and basic stage property do not need particular device, 5) error is small, can reach the accurate of commercial requirements
Degree.
It should be noted that step S102 is only to describe to be easy to use, its sequencing in the method is not represented；Example
Such as step S102 can arbitrary steps between step S101 and step S107 before or after；Certain step S102
It can be carried out simultaneously with step S103；Therefore, above-mentioned steps number should not be construed as the limitation caused by the present invention.
Further, this method further includes output step S108；
Step S108 exports the second dimension information.
Specifically, by second dimension information export to ERP system perhaps BOM data library by ERP system or BOM
Database is stored.
In addition, above-mentioned garment image to be measured, clothes classification, key point characteristic information and the second dimension information store
In ERP system or BOM data library.
It needs exist for being illustrated, ERP system is Enterprise Resources Plan (Enterprise Resource
Planning abbreviation) integrates information technology and advanced management thought on Information Technology Foundation, and core concept is
Supply chain management.ERP system goes the resource of optimization enterprise from supply chain range, optimizes the operational mode of modern enterprise, data
The shared resources between each operation system, institute's active data need to only input once in some system, ensure that the one of data
Cause property.
BOM data library is in data format come the file for describing product structure, is the product structure that computer can identify
The master document of data file and ERP.BOM data library makes system identification product structure, and connection and communication enterprise items
The tie of business.BOM data library is the basic basis of computer identification material, is the foundation for plan of working out, and is mating and neck material
Foundation, be buying and external coordination foundation, Design seriation, standardization, generalization can be made.
In order to make it easy to understand, below with reference to Fig. 4 to the garment dimension measurement side provided in an embodiment of the present invention based on picture
The application scenarios of method are briefly described:
1, picture inputs: electronic equipment (such as terminal, server) receives the picture of input by api interface；
Picture includes clothes to be measured and the rectangle paper jam for being printed with AR code；
2, clothes are classified: electronic equipment carries out the identification of clothes classification to the picture of input, completes clothes classification；
3, clothes critical point detection: electronic equipment carries out critical point detection to sorted clothes, identifies key point；
4, distance algorithm: electronic equipment carries out key point using distance algorithm to obtain the corresponding spy of clothes apart from calculating
Levy the Pixel Dimensions at position；
5, AR code identifies: electronic equipment has been set while carrying out clothes classification using the identification of AR code recognition system
The regular coding set；
6, Pixel Dimensions algorithm: the frame pixel distance of object of reference is calculated with image recognition algorithm, referring again to having set
Actual card paper size, calculate millimeter to pixel rate using Pixel Dimensions algorithm；
7, size conversion: the Pixel Dimensions and Pixel Dimensions at the individual features position of the clothes obtained based on distance algorithm
Pixel Dimensions are converted to actual size to pixel rate by the calculated millimeter of algorithm；
8, size exports: the actual size of the clothes obtained through size conversion is exported.
Embodiment two:
As shown in figure 5, the embodiment of the invention provides a kind of garment dimension measuring device based on picture, comprising: picture
Receiving module 100, ratio obtain module 200, classification identification module 300, searching module 400, key point identification module 500, the
One computing module 600 and the second computing module 700.
Wherein, picture receiving module 100 is used to receive the pictorial information of user's upload, the pictorial information be include default
The picture of object of reference and clothes to be measured；The pictorial information be default photo environment, by camera in default photo angle
Lower acquisition；
Specifically, the default object of reference is the paper jam of preset shape；It include clothes identification code on the paper jam, it is described
Clothes identification code can only be identified with clothes identification code described in the electronic equipment by the electronic equipment；The electronic equipment is only
It can identify the clothes identification code；
The default photo environment is to control to adjust to obtain by film studio；
The default photo angle is to control to adjust to obtain by photography support, abnormal to reduce angle when camera level is taken pictures
Become；The photography support is for being arranged the camera.
Ratio obtain module 200 be used to obtain the Pixel Dimensions data of the default object of reference in the pictorial information with
And actual size data, the coefficient of ratio is generated based on the Pixel Dimensions data and the actual size data；
The clothes classification of the clothes to be measured in the pictorial information for identification of classification identification module 300；
Searching module 400 is used to search the clothes key point to match with the clothes classification according to the clothes classification and knows
Other model；
Key point identification module 500 is for calling the clothes key point identification model to identify the clothes in the pictorial information
Fill key point characteristic information；
First computing module 600 is used to based on the clothes key point characteristic information carry out that the clothes to be measured are calculated
The first size information of dress；Wherein the first size information includes the pixel ruler of the default characteristic portion of the clothes to be measured
It is very little；
Second computing module 700 is used to that the second size to be calculated based on the first size information and the coefficient of ratio
Information；Wherein second dimension information includes the actual size of the default characteristic portion of the clothes to be measured.
Further, which further includes output module 800, for exporting second dimension information.
Further, key point identification module 500 is specifically used for calling described in the clothes key point identification model identification
Clothes key point classification information and the clothes key point location information in picture.
Further, the first computing module 600 is specifically used for transferring key point calculating corresponding with the clothes classification
Rule；Wherein the key point computation rule includes the Pixel Dimensions computation rule of the other default characteristic portion of the clothing；
Based on the clothes key point characteristic information and the key point computation rule carry out that the first size information is calculated.
Garment dimension measuring device provided in an embodiment of the present invention based on picture, with provided by the above embodiment based on figure
The garment dimension measurement method technical characteristic having the same of piece reaches identical so also can solve identical technical problem
Technical effect.
Referring to Fig. 6, the embodiment of the present invention also provides a kind of electronic equipment 100, comprising: processor 40, memory 41, bus
42 and communication interface 43, above-mentioned processor 40, communication interface 43 and memory 41 are connected by bus 42；Processor 40 is for holding
The executable module stored in line storage 41, such as computer program.
Wherein, memory 41 may include high-speed random access memory (RAM, Random Access Memory),
It may further include nonvolatile memory (non-volatile memory), for example, at least a magnetic disk storage.By at least
One communication interface 43 (can be wired or wireless) realizes the communication between the system network element and at least one other network element
Connection, can be used internet, wide area network, local network, Metropolitan Area Network (MAN) etc..
Bus 42 can be isa bus, pci bus or eisa bus etc..Above-mentioned bus can be divided into address bus, data
Bus, control bus etc..Only to be indicated with a four-headed arrow convenient for indicating, in Fig. 6, it is not intended that an only bus or
A type of bus.
Wherein, memory 41 is for storing program, and above-mentioned processor 40 executes above-mentioned journey after receiving and executing instruction
Sequence, method performed by the system that the stream process that aforementioned any embodiment of the embodiment of the present invention discloses defines can be applied to handle
In device 40, or realized by processor 40.
Processor 40 may be a kind of IC chip, the processing capacity with signal.During realization, above-mentioned side
Each step of method can be completed by the integrated logic circuit of the hardware in processor 40 or the instruction of software form.Above-mentioned
Processor 40 can be general processor, including central processing unit (Central Processing Unit, abbreviation CPU), network
Processor (Network Processor, abbreviation NP) etc.；It can also be digital signal processor (Digital Signal
Processing, abbreviation DSP), specific integrated circuit (Application Specific Integrated Circuit, referred to as
ASIC), ready-made programmable gate array (Field-Programmable Gate Array, abbreviation FPGA) or other are programmable
Logical device, discrete gate or transistor logic, discrete hardware components.It may be implemented or execute in the embodiment of the present invention
Disclosed each method, step and logic diagram.General processor can be microprocessor or the processor is also possible to appoint
What conventional processor etc..The step of method in conjunction with disclosed in the embodiment of the present invention, can be embodied directly in hardware decoding processing
Device executes completion, or in decoding processor hardware and software module combination execute completion.Software module can be located at
Machine memory, flash memory, read-only memory, programmable read only memory or electrically erasable programmable memory, register etc. are originally
In the storage medium of field maturation.The storage medium is located at memory 41, and processor 40 reads the information in memory 41, in conjunction with
Its hardware completes the step of above method.
The embodiment of the present invention also provides a kind of computer readable storage medium, and meter is stored on computer readable storage medium
Calculation machine program, when computer program is run by processor the step of the method for execution any of the above-described.
It should be noted that all the embodiments in this specification are described in a progressive manner, each embodiment weight
Point explanation is the difference from other embodiments, and the same or similar parts between the embodiments can be referred to each other.
The technology effect of garment dimension measurement method and device based on picture provided by the embodiment of the present invention, realization principle and generation
Fruit is identical with preceding method embodiment, and to briefly describe, Installation practice part does not refer to place, can refer to preceding method implementation
Corresponding contents in example.
In several embodiments provided herein, it should be understood that disclosed device and method can also pass through
Other modes are realized.The apparatus embodiments described above are merely exemplary, for example, flow chart and block diagram in attached drawing
Show the device of multiple embodiments according to the present invention, the architectural framework in the cards of method and computer program product,
Function and operation.In this regard, each box in flowchart or block diagram can represent the one of a module, section or code
Part, a part of the module, section or code, which includes that one or more is for implementing the specified logical function, to be held
Row instruction.It should also be noted that function marked in the box can also be to be different from some implementations as replacement
The sequence marked in attached drawing occurs.For example, two continuous boxes can actually be basically executed in parallel, they are sometimes
It can execute in the opposite order, this depends on the function involved.It is also noted that every in block diagram and or flow chart
The combination of box in a box and block diagram and or flow chart can use the dedicated base for executing defined function or movement
It realizes, or can realize using a combination of dedicated hardware and computer instructions in the system of hardware.
In addition, each functional module or unit in each embodiment of the present invention can integrate one independence of formation together
Part, be also possible to modules individualism, an independent portion can also be integrated to form with two or more modules
Point.
It, can be with if the function is realized and when sold or used as an independent product in the form of software function module
It is stored in a computer readable storage medium.Based on this understanding, technical solution of the present invention is substantially in other words
The part of the part that contributes to existing technology or the technical solution can be embodied in the form of software products, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be a
People's computer, server or network equipment etc.) it performs all or part of the steps of the method described in the various embodiments of the present invention.
And storage medium above-mentioned includes: that USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), arbitrary access are deposited
The various media that can store program code such as reservoir (RAM, Random Access Memory), magnetic or disk.
It should be noted that, in this document, relational terms such as first and second and the like are used merely to a reality
Body or operation are distinguished with another entity or operation, are deposited without necessarily requiring or implying between these entities or operation
In any actual relationship or order or sequence, indication or suggestion relative importance can not be interpreted as.Moreover, term " packet
Include ", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion so that including the mistake of a series of elements
Journey, method, article or equipment not only include those elements, but also including other elements that are not explicitly listed, either
It further include for elements inherent to such a process, method, article, or device.In the absence of more restrictions, by sentence
The element that "including a ..." limits, it is not excluded that also deposit in the process, method, article or apparatus that includes the element
In other identical element.
The foregoing is only a preferred embodiment of the present invention, is not intended to restrict the invention, for the skill of this field
For art personnel, the invention may be variously modified and varied.All within the spirits and principles of the present invention, made any to repair
Change, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.It should also be noted that similar label and letter exist
Similar terms are indicated in following attached drawing, therefore, once being defined in a certain Xiang Yi attached drawing, are then not required in subsequent attached drawing
It is further defined and explained.
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 garment dimension measurement method based on picture characterized by comprising
The pictorial information that user uploads is received, the pictorial information is the picture for including default object of reference and clothes to be measured；Institute
Stating pictorial information is obtained under default photo angle in default photo environment, by camera；
The Pixel Dimensions data and actual size data of the default object of reference in the pictorial information are obtained, based on described
Pixel Dimensions data and the actual size data generate the coefficient of ratio；
Identify the clothes classification of the clothes to be measured in the pictorial information；
The clothes key point identification model to match with the clothes classification is searched according to the clothes classification；
The clothes key point identification model is called to identify the clothes key point characteristic information in the pictorial information；
The first size information that the clothes to be measured are calculated is carried out based on the clothes key point characteristic information；Wherein institute
State the Pixel Dimensions that first size information includes the default characteristic portion of the clothes to be measured；
The second dimension information is calculated based on the first size information and the coefficient of ratio；Wherein the second size letter
Breath includes the actual size of the default characteristic portion of the clothes to be measured.
2. the garment dimension measurement method according to claim 1 based on picture, which is characterized in that described to call the clothes
Dress key point identification model identifies the clothes key point characteristic information in the picture, comprising:
The clothes key point identification model is called to identify that the clothes key point classification information in the picture and the clothes are closed
Key dot position information.
3. the garment dimension measurement method according to claim 1 based on picture, which is characterized in that the default object of reference
For the paper jam of preset shape；It include clothes identification code on the paper jam, described in the clothes identification code and the electronic equipment
Clothes identification code can only be identified by the electronic equipment；The electronic equipment can only identify the clothes identification code.
4. the garment dimension measurement method according to claim 1 based on picture, which is characterized in that the default ring of taking pictures
Border is to control to adjust to obtain by film studio.
5. the garment dimension measurement method according to claim 1 based on picture, which is characterized in that the default angle of taking pictures
Degree is to control to adjust to obtain by photography support, to reduce angular distortion when camera level is taken pictures；The photography support is for being arranged
The camera.
6. the garment dimension measurement method according to claim 1 based on picture, which is characterized in that the method is also wrapped
It includes:
Second dimension information is exported.
7. the garment dimension measurement method according to claim 1 based on picture, which is characterized in that described to be based on the clothes
Dress key point characteristic information carries out the first size information that the clothes to be measured are calculated, comprising:
Transfer key point computation rule corresponding with the clothes classification；Wherein the key point computation rule includes the clothes
Fill the Pixel Dimensions computation rule of the default characteristic portion of classification；
Based on the clothes key point characteristic information and the key point computation rule carry out that the first size is calculated
Information.
8. a kind of garment dimension measuring device based on picture characterized by comprising
Picture receiving module, for receiving the pictorial information of user's upload, the pictorial information be include default object of reference and to
Measure the picture of clothes；The pictorial information is obtained under default photo angle in default photo environment, by camera；
Ratio obtains module, for obtaining the Pixel Dimensions data and reality of the default object of reference in the pictorial information
Dimension data generates the coefficient of ratio based on the Pixel Dimensions data and the actual size data；
Classification identification module, for identification the clothes classification of the clothes to be measured in the pictorial information；
Searching module identifies mould for searching the clothes key point to match with the clothes classification according to the clothes classification
Type；
Key point identification module, for calling the clothes key point identification model to identify, the clothes in the pictorial information are crucial
Point feature information；
First computing module, for carrying out the clothes to be measured are calculated based on the clothes key point characteristic information
One dimension information；Wherein the first size information includes the Pixel Dimensions of the default characteristic portion of the clothes to be measured；
Second computing module, for the second dimension information to be calculated based on the first size information and the coefficient of ratio；
Wherein second dimension information includes the actual size of the default characteristic portion of the clothes to be measured.
9. a kind of electronic equipment, which is characterized in that including memory and processor, the memory is for storing support processing
Device perform claim requires the program of any one of 1 to 7 the method, the processor is configured to for executing in the memory
The program of storage.
10. a kind of computer readable storage medium, it is stored with computer program on computer readable storage medium, feature exists
In when computer program is run by processor the step of any one of execution the claims 1 to 7 the method.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811056058.2A CN109166147A (en) | 2018-09-10 | 2018-09-10 | Garment dimension measurement method and device based on picture |
| PCT/CN2018/108558 WO2020051959A1 (en) | 2018-09-10 | 2018-09-29 | Image-based costume size measurement method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811056058.2A CN109166147A (en) | 2018-09-10 | 2018-09-10 | Garment dimension measurement method and device based on picture |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109166147A true CN109166147A (en) | 2019-01-08 |
Family
ID=64894808
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811056058.2A Withdrawn CN109166147A (en) | 2018-09-10 | 2018-09-10 | Garment dimension measurement method and device based on picture |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN109166147A (en) |
| WO (1) | WO2020051959A1 (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110051069A (en) * | 2019-03-13 | 2019-07-26 | 中山易裁剪网络科技有限公司 | A kind of garment dimension measuring system and its measurement method |
| CN110349201A (en) * | 2019-07-07 | 2019-10-18 | 创新奇智(合肥)科技有限公司 | A kind of suit length measurement method, system and electronic equipment neural network based |
| CN110672014A (en) * | 2019-08-27 | 2020-01-10 | 东莞市精致自动化科技有限公司 | Clothes size measuring method |
| CN111581414A (en) * | 2019-02-18 | 2020-08-25 | 北京京东尚科信息技术有限公司 | Clothing identification, classification and retrieval method, device, equipment and storage medium |
| CN111667527A (en) * | 2020-06-10 | 2020-09-15 | 创新奇智(成都)科技有限公司 | Clothing measuring method and device and electronic equipment |
| WO2020259429A1 (en) * | 2019-06-26 | 2020-12-30 | 阿里巴巴集团控股有限公司 | Information processing method, information display method, and apparatus |
| CN112205698A (en) * | 2020-09-11 | 2021-01-12 | 集美大学 | Human body three-dimensional information acquisition method and device |
| CN112418239A (en) * | 2019-08-21 | 2021-02-26 | 青岛海尔智能技术研发有限公司 | Method and device for positioning clothing key points and clothes folding machine |
| CN113066097A (en) * | 2021-05-24 | 2021-07-02 | 广东技术师范大学 | Method and system for rapidly and accurately measuring width, period and metallization ratio of interdigital transducer finger |
| CN113221928A (en) * | 2020-01-21 | 2021-08-06 | 海信集团有限公司 | Clothing classification information display device, method and storage medium |
| CN113256701A (en) * | 2021-05-31 | 2021-08-13 | 天津天瞳威势电子科技有限公司 | Distance acquisition method, device, equipment and readable storage medium |
| CN113592833A (en) * | 2021-08-05 | 2021-11-02 | 深圳潜行创新科技有限公司 | Object measuring method, device, equipment and storage medium |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111461017B (en) * | 2020-04-01 | 2024-01-19 | 杭州视在科技有限公司 | High-precision recognition method for kitchen work clothes after catering in urban scale |
| CN112363918B (en) * | 2020-11-02 | 2024-03-08 | 北京云聚智慧科技有限公司 | User interface AI automatic test method, device, equipment and storage medium |
| CN113628185B (en) * | 2021-08-09 | 2024-02-13 | 海南青峰生物科技有限公司 | Rice plant height measuring method and device based on 5G communication and image recognition processing |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1510391A (en) * | 2002-12-25 | 2004-07-07 | 鸿富锦精密工业（深圳）有限公司 | Image measuring system and method |
| JP2016004564A (en) * | 2014-06-19 | 2016-01-12 | 大日本印刷株式会社 | Try-on support system using augmented reality |
| CN105469087A (en) * | 2015-07-13 | 2016-04-06 | 百度在线网络技术（北京）有限公司 | Method for identifying clothes image, and labeling method and device of clothes image |
| CN108272154A (en) * | 2018-01-04 | 2018-07-13 | 广州唯品会研究院有限公司 | A kind of garment dimension measurement method and device |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10332179B2 (en) * | 2014-10-23 | 2019-06-25 | Tailored IP, LLC | Methods and systems for recommending fitted clothing |
| CN105595490B (en) * | 2015-08-28 | 2017-02-22 | 广州穗达服饰企业有限公司 | Method for measuring human body dimension for garment customization through pictures |
| CN106174830A (en) * | 2016-06-30 | 2016-12-07 | 西安工程大学 | Garment dimension automatic measurement system based on machine vision and measuring method thereof |
-
2018
- 2018-09-10 CN CN201811056058.2A patent/CN109166147A/en not_active Withdrawn
- 2018-09-29 WO PCT/CN2018/108558 patent/WO2020051959A1/en active Application Filing
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1510391A (en) * | 2002-12-25 | 2004-07-07 | 鸿富锦精密工业（深圳）有限公司 | Image measuring system and method |
| JP2016004564A (en) * | 2014-06-19 | 2016-01-12 | 大日本印刷株式会社 | Try-on support system using augmented reality |
| CN105469087A (en) * | 2015-07-13 | 2016-04-06 | 百度在线网络技术（北京）有限公司 | Method for identifying clothes image, and labeling method and device of clothes image |
| CN108272154A (en) * | 2018-01-04 | 2018-07-13 | 广州唯品会研究院有限公司 | A kind of garment dimension measurement method and device |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111581414B (en) * | 2019-02-18 | 2024-01-16 | 北京京东尚科信息技术有限公司 | Method, device, equipment and storage medium for identifying, classifying and searching clothes |
| CN111581414A (en) * | 2019-02-18 | 2020-08-25 | 北京京东尚科信息技术有限公司 | Clothing identification, classification and retrieval method, device, equipment and storage medium |
| CN110051069A (en) * | 2019-03-13 | 2019-07-26 | 中山易裁剪网络科技有限公司 | A kind of garment dimension measuring system and its measurement method |
| WO2020259429A1 (en) * | 2019-06-26 | 2020-12-30 | 阿里巴巴集团控股有限公司 | Information processing method, information display method, and apparatus |
| CN110349201A (en) * | 2019-07-07 | 2019-10-18 | 创新奇智(合肥)科技有限公司 | A kind of suit length measurement method, system and electronic equipment neural network based |
| CN112418239B (en) * | 2019-08-21 | 2023-01-24 | 青岛海尔智能技术研发有限公司 | Method and device for positioning clothing key points and clothes folding machine |
| CN112418239A (en) * | 2019-08-21 | 2021-02-26 | 青岛海尔智能技术研发有限公司 | Method and device for positioning clothing key points and clothes folding machine |
| CN110672014A (en) * | 2019-08-27 | 2020-01-10 | 东莞市精致自动化科技有限公司 | Clothes size measuring method |
| CN110672014B (en) * | 2019-08-27 | 2023-08-22 | 东莞市精致自动化科技有限公司 | Clothes size measuring method |
| CN113221928A (en) * | 2020-01-21 | 2021-08-06 | 海信集团有限公司 | Clothing classification information display device, method and storage medium |
| CN113221928B (en) * | 2020-01-21 | 2023-07-18 | 海信集团有限公司 | Clothing classification information display device, method and storage medium |
| CN111667527A (en) * | 2020-06-10 | 2020-09-15 | 创新奇智(成都)科技有限公司 | Clothing measuring method and device and electronic equipment |
| CN111667527B (en) * | 2020-06-10 | 2023-06-13 | 创新奇智(成都)科技有限公司 | Clothing measurement method and device and electronic equipment |
| CN112205698B (en) * | 2020-09-11 | 2022-09-20 | 集美大学 | Human body three-dimensional information acquisition method and device |
| CN112205698A (en) * | 2020-09-11 | 2021-01-12 | 集美大学 | Human body three-dimensional information acquisition method and device |
| CN113066097A (en) * | 2021-05-24 | 2021-07-02 | 广东技术师范大学 | Method and system for rapidly and accurately measuring width, period and metallization ratio of interdigital transducer finger |
| CN113256701A (en) * | 2021-05-31 | 2021-08-13 | 天津天瞳威势电子科技有限公司 | Distance acquisition method, device, equipment and readable storage medium |
| CN113592833A (en) * | 2021-08-05 | 2021-11-02 | 深圳潜行创新科技有限公司 | Object measuring method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2020051959A1 (en) | 2020-03-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109166147A (en) | Garment dimension measurement method and device based on picture | |
| CN107358648B (en) | Real-time full-automatic high quality three-dimensional facial reconstruction method based on individual facial image | |
| CN110662484B (en) | System and method for whole body measurement extraction | |
| CN109670591B (en) | Neural network training method and image matching method and device | |
| WO2017008435A1 (en) | Method for recognizing picture, method and apparatus for labelling picture, and storage medium | |
| CN110309706A (en) | Face critical point detection method, apparatus, computer equipment and storage medium | |
| CN107895160A (en) | Human face detection and tracing device and method | |
| CN110930297B (en) | Style migration method and device for face image, electronic equipment and storage medium | |
| CN108272154B (en) | A kind of garment dimension measurement method and device | |
| CN103210421A (en) | Object detection device and object detection method | |
| CN108323204A (en) | A kind of method and intelligent terminal of detection face flaw point | |
| CN110378235A (en) | A kind of fuzzy facial image recognition method, device and terminal device | |
| US11798299B2 (en) | Methods and systems for generating 3D datasets to train deep learning networks for measurements estimation | |
| CN106666903A (en) | Method and device utilizing images to measure human body shape parameter | |
| CN105354248A (en) | Gray based distributed image bottom-layer feature identification method and system | |
| CN109409994A (en) | The methods, devices and systems of analog subscriber garments worn ornaments | |
| CN109271935A (en) | The matching method of article and electronic tag, apparatus and system | |
| CN109934065A (en) | A kind of method and apparatus for gesture identification | |
| CN109117760A (en) | Image processing method, device, electronic equipment and computer-readable medium | |
| CN109655011B (en) | Method and system for measuring dimension of human body modeling | |
| CN108694719A (en) | image output method and device | |
| CN109348731A (en) | A kind of method and device of images match | |
| CN110074788A (en) | A kind of body data acquisition methods and device based on machine learning | |
| CN111695431A (en) | Face recognition method, face recognition device, terminal equipment and storage medium | |
| CN110288715A (en) | Virtual necklace try-in method, device, electronic equipment and storage medium |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20191107 Address after: 518081 Yantian Modern Industrial Service Center, 3018 Shayan Road, Shatoujiao Street, Yantian District, Shenzhen City, Guangdong Province, 33 floors Applicant after: SHENZHEN MALONG TECHNOLOGY CO., LTD. Applicant after: Shenzhen Malong artificial intelligence research center Address before: 518000 Yantian modern industrial service center 33, Sha Tin Road, No. 3018, Sha Tin Street, Yantian District, Shenzhen, Guangdong. Applicant before: SHENZHEN MALONG TECHNOLOGY CO., LTD. |
|
| TA01 | Transfer of patent application right | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20190108 |
|
| WW01 | Invention patent application withdrawn after publication |