KR102322810B1 - Method for manufacturing an apparel sample using solution for generating 3d patterns - Google Patents

Abstract

According to one embodiment, a clothing sample manufacturing method comprises the steps of: creating a sample work order; creating a final pattern through a CAD program for pattern creation driven in a computer on the basis of specifications described in the sample work order; and producing a clothing sample from the final pattern. The step of producing the clothing sample from the final pattern includes the steps of: creating a basic pattern on the basis of the specifications described in the sample work order; retrieving a plurality of pattern designs of a clothing company requesting the sample work order from a computer-accessible database; selecting one among the plurality of pattern designs of the clothing company to match the specifications described in the sample work order and the type of the clothing sample; and creating the final pattern by changing the basic pattern on the basis of the selected pattern design. In the database, the pattern designs and size specifications related to the pattern designs are divided and stored at least for each clothing company and for each clothing type, and when the clothing sample manufactured on the basis of the final pattern is valid, the pattern design and size specification of the final pattern are stored in the database as one of the pattern designs according to the type of the clothing sample of the clothing company. According to the present invention, the clothing sample manufacturing method has the effect of reducing manufacturing costs of clothing products.

Description

How to make a garment sample using a 3D pattern generation solution

The following embodiments relate to a method of manufacturing a clothing sample, and more particularly, to a technique for creating a pattern and producing a sample by using a CAD program for pattern creation and a database in which design data is stored.

In general, in the process of designing a clothing product and completing it to the actual product, the seller receives feedback from the buyer from the sample of the clothing product before mass-producing the final product, then revises the sample and confirms the product. In order to produce these samples, the seller cooperates with a fabric maker, a pattern maker, and a sewing maker.

Typically, the seller receives a sketched drawing of a sample design, called a sample work order, prepared by his hired designer or a co-designer, reviews it, and purchases the related fabrics and subsidiary materials. Pattern companies use fabrics and subsidiary materials to make patterns based on sample work instructions, and sewing companies complete samples of clothing products by sewing the manufactured patterns. The buyer checks the finished sample, checks whether the intention is reflected, and makes a fitting to check the modifications and give feedback to the seller. The seller prepares the main work instruction as a finalized design by reflecting the modifications based on the feedback of the buyer, and through this, the clothing product is completed.

In this way, collaboration between several companies is required to complete a single garment product, and every time a modified sample is produced, a new pattern must be made and sewn with a new fabric, and the real product must be exchanged between several companies. Therefore, it takes time and money.

Recently, in order to handle pattern work and subsequent work more easily, a method of creating a pattern by implementing a pattern image on a computer using a CAD program for pattern writing and outputting the pattern image through an output machine is used. In addition, a method in which a buyer confirms an image of a non-real sample by realizing a virtual 3D image of a sample from a pattern image implemented in a CAD program for pattern creation is used. As a CAD program for pattern creation, for example, CAD programs of companies such as Gerber, Modal, Lectra, Yucca, Style CAD, and Asahi Kasei are widely used. Each company's CAD program for pattern writing has a function to draw a pattern directly, a function to digitize a pattern made by hand using a digitizer, a grading function, a marker making function, and an auto-cutting function. functions, etc.

On the other hand, each apparel company that produces apparel products has a unique style of design according to its own design philosophy. In addition, even if size specifications including total length, waist circumference, chest circumference, shoulder width, etc. are expressed as, for example, 30 inches and 32 inches, these size specifications vary from clothing company to clothing company, so the buyer's body type, body It is difficult to choose a clothing product that suits you only with the size specifications that are not unified according to the balance, etc.

Therefore, when creating a pattern with the CAD program for pattern creation, it is difficult to properly reflect the unique design philosophy possessed by each clothing company only by reflecting the contents of the sample work instruction, and it is difficult to reflect the unique design philosophy of each clothing company. is difficult to manufacture.

Patent Application Publication No. 10-2020-0109755

An object of the present invention is to solve the above problems, and to provide a method of manufacturing a clothing sample in which the unique style of clothing companies is accurately reflected and to fit a buyer's body type or preferred design.

However, the object of the present invention is not limited to the above-mentioned objects, and other objects not mentioned will be clearly understood from the description below.

According to one embodiment, there is provided a method of making a garment sample, the method comprising: creating a sample work order; creating a final pattern through a CAD program for pattern creation driven in a computer based on the specifications described in the sample work instruction; and producing a clothing sample from the final pattern, wherein the creating of the final pattern includes: creating a basic pattern based on a specification described in the sample work instruction; retrieving a plurality of pattern designs of a clothing company requesting the sample work instruction from the computer-accessible database; selecting one of a plurality of pattern designs of the clothing company to match the specifications described in the sample work instruction and the type of the clothing sample; and changing the basic pattern based on the selected pattern design to create the final pattern, wherein the database stores at least a pattern design and a size specification related to the pattern design divided by clothing company and clothing type. and, when the clothing sample produced based on the final pattern is valid, the pattern design and size specification of the final pattern are stored in the database as one of the pattern designs according to the type of the clothing sample of the clothing company. this is provided

The method for producing a clothing sample further includes receiving user data on a body shape and size from a user, wherein the receiving of the user data includes: acquiring data of a 3D image on the body shape of the user ; acquiring data of the user's body size of the user; and generating the user data by modifying the data of the 3D image based on the data of the body size, wherein the writing of the final pattern includes modifying the changed basic pattern to match the user data, It may include the step of writing the final pattern.

The method for producing a clothing sample further includes processing a pattern design stored in the database and a size specification related to the pattern design, wherein the processing includes at least the pattern design stored separately for each clothing company and clothing type. generating statistical data of the size specification based on the relevant size specification; and templateizing the stored pattern design and the size specification related to the pattern design for each clothing company and clothing type, wherein in the step of creating the sample work instruction, based on the statistical data of the size specification Thus, in the step of preparing the sample work instruction sheet or selecting one of a plurality of pattern designs of the clothing company, the templated pattern design may be selected.

In the clothing sample production method, the generation of the basic pattern may include drawing a pattern based on the sample operation instruction and then inputting the pattern into the pattern creation CAD program through a scanner, or based on the sample operation instruction It is performed by drawing on a CAD program for pattern creation, and the step of producing a clothing sample from the final pattern is to output the final pattern through an output machine, and sew a piece of fabric cut according to the final pattern to produce a real sample step; Alternatively, the method may include producing a virtual sample implemented as a 3D image from the 2D image of the final pattern.

The method for producing a clothing sample further includes the step of classifying the degree of matching of the clothing sample with respect to the body shape and size of the user, and the classifying the degree of matching of the clothing sample may include: obtaining, in the device, data of a 3D image of the clothing sample, and data of a 3D image of the user's body shape and data of a body size; To extract the first data by generating a corrected 3D image by applying a corresponding numerical value of the data of the body size to the data of the 3D image regarding the body shape of the user, and synthesizing with the data of the 3D image for the clothing sample step; generating a first input signal by encoding the first data; inputting the first input signal to a first artificial neural network in the first device, and obtaining a first output signal based on a result of the input of the first artificial neural network; generating, based on the first output signal, a first classification result for a degree to which the clothing sample matches the user's body shape and size; transmitting the first data and the first classification result to a second device connectable to the computer; analyzing the first data transmitted to the second device to detect an error of the clothing sample with respect to the body shape and size of the user; identifying the error for each region of the clothing sample, and classifying a normal region in which an error is detected less than a first reference value and a defective region in which an error is detected greater than or equal to the first reference value; extracting second data from which the defective area is deleted from the first data; generating a second input signal by encoding the second data; inputting the second input signal to a second artificial neural network in the second device, and obtaining a second output signal based on a result of the input of the second artificial neural network; generating, based on the second output signal, a second classification result for the degree to which the clothing sample matches the user's body type and size; and setting a final classification result for a degree to which the clothing sample matches the user's body type and size based on the first classification result and the second classification result.

The apparatus according to an embodiment may be controlled by a computer program stored in the medium to execute the method of any one of the above-described methods in combination with hardware.

According to one embodiment, it is possible to create a pattern and make a sample by reflecting the design of the clothing company as well as the sample work instruction, and it is possible to produce a sample more suitable for the body shape or preferred design of the purchaser. In addition, since the unique design of the clothing company is well reflected, the number of times to modify the sample can be reduced, thereby reducing the cost and time required for sample production. Furthermore, since the unit cost of making the sample is reduced, it has an effect in reducing the unit cost of the finally produced clothing product, thereby having an advantageous effect not only on the seller but also on the buyer.

On the other hand, effects according to the embodiments are not limited to those mentioned above, and other effects not mentioned will be clearly understood by those of ordinary skill in the art from the following description.

1 is a diagram illustrating a flowchart of a method of creating a clothing sample according to an embodiment.
2 is a diagram illustrating an exemplary form of a sample work instruction sheet according to an embodiment.
3 is a diagram illustrating a flowchart of a method of creating a pattern according to an exemplary embodiment.
4 is a diagram illustrating an example of creating a basic pattern according to an embodiment.
5 is a diagram illustrating a result of selecting a pattern design according to an exemplary embodiment.
6 is a diagram illustrating a method of changing a basic pattern according to an exemplary embodiment.
7 is a flowchart illustrating a method of creating a pattern for manufacturing a user-customized clothing sample according to an exemplary embodiment.
8 is a diagram illustrating a modified flowchart of creating a clothing sample according to an embodiment.
9 is a flowchart illustrating a method of classifying a matching degree of a clothing sample with respect to a user's body shape and size according to an exemplary embodiment.

Hereinafter, embodiments will be described in detail with reference to the accompanying drawings. However, since various changes may be made to the embodiments, the scope of the patent application is not limited or limited by these embodiments. It should be understood that all modifications, equivalents and substitutes for the embodiments are included in the scope of the rights.

Specific structural or functional descriptions of the embodiments are disclosed for purposes of illustration only, and may be changed and implemented in various forms. Accordingly, the embodiments are not limited to a specific disclosure form, and the scope of the present specification includes changes, equivalents, or substitutes included in the technical spirit.

Although terms such as first or second may be used to describe various components, these terms should be interpreted only for the purpose of distinguishing one component from another. For example, a first component may be termed a second component, and similarly, a second component may also be termed a first component.

When a component is referred to as being “connected to” another component, it may be directly connected or connected to the other component, but it should be understood that another component may exist in between.

The terms used in the examples are used for description purposes only, and should not be construed as limiting. The singular expression includes the plural expression unless the context clearly dictates otherwise. In the present specification, terms such as “comprise” or “have” are intended to designate that a feature, number, step, operation, component, part, or combination thereof described in the specification exists, but one or more other features It should be understood that this does not preclude the existence or addition of numbers, steps, operations, components, parts, or combinations thereof.

Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which the embodiment belongs. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with the meaning in the context of the related art, and should not be interpreted in an ideal or excessively formal meaning unless explicitly defined in the present application. does not

In addition, in the description with reference to the accompanying drawings, the same components are given the same reference numerals regardless of the reference numerals, and the overlapping description thereof will be omitted. In the description of the embodiment, if it is determined that a detailed description of a related known technology may unnecessarily obscure the gist of the embodiment, the detailed description thereof will be omitted.

The embodiments may be implemented in various types of products, such as personal computers, laptop computers, tablet computers, smart phones, televisions, smart home appliances, intelligent cars, kiosks, wearable devices, and the like.

1 shows a flowchart 100 of creating a clothing sample according to an embodiment. First, in step S110 , a designer employed by a clothing company or a designer cooperating with a clothing company scraps data and determines a design for a clothing product. For example, in order to create a new design for cargo shorts that a clothing company wants to sell for summer, the designer scraps various materials such as the silhouette of the existing cargo shorts, the location of pockets, fabrics, buttons, zippers, etc. to determine the design of cargo shorts.

In step S120, the designer creates a sample work order. 2 illustrates an exemplary form 200 of a sample work order in accordance with one embodiment. As the specifications described in the sample work instruction manual, a schematic 210 of a clothing sample to be designed, a size specification 220, a necessary subsidiary material 230, a swatch 240 that is a sample of the fabric, and the like can be given.

According to one embodiment, in the schematic 210 of the design, silhouettes such as the front, back, lining, etc. of the clothing sample, the position of auxiliary materials, etc. may be illustrated through the designer's manual work or through computer program work such as illustration. .

According to one embodiment, in the size specification 220, the dimensions of each part of the sample, such as total length, shoulder width, chest circumference, waist circumference, hip circumference, hem circumference, sleeve, etc. are defined and recorded as numerical values, Size grades such as S, M, L, etc. or size dimensions such as 30 inches and 32 inches according to the wearer's weight class may be recorded together. In the sample work instructions for cargo shorts as in the case of FIG. 2, measurement points such as waist, waistband height, hip position, thigh position, leg length, etc. are described respectively corresponding to the size dimension of 32 inches.

According to an embodiment, the necessary subsidiary material 230 is a subsidiary material attached to a clothing sample or product, such as a button, a zipper, a poly bag, a label, and a price tag, and detailed contents such as a product name and quantity are described. In addition, the necessary auxiliary material 230 may be attached to the actual sample work instruction sheet.

According to one embodiment, the swatch 240 cuts a part of the real fabric and is attached to the sample work instruction, and the lining and the outer fabric should be clearly distinguished, and it is preferable that the real fabric be attached separately when printing or color matching is included. do.

According to an embodiment, in the sample work instruction sheet, in addition to the above, information related to a clothing sample and a manufacturer, such as a brand name, a vendor name, a style number, a designer's contact information, an item name, and a material of a fabric, may be described together. In addition, points to be noted when creating patterns and samples may be described in the comment field.

Returning to Fig. 1, in step S130, a pattern is created based on the specifications described in the sample work instruction sheet. A pattern means a pattern of a clothing product, and creating a pattern of a clothing sample may be understood as creating a blueprint for manufacturing a clothing sample. In addition, the creation of the pattern is usually performed by a pattern maker (modelist) who works for a subcontractor hired or contracted by a clothing company, write

In the past, creating a pattern meant drawing a pattern manually on paper, but recently, the outline of the pattern is expressed as a 2D image using a CAD program for pattern creation driven by a computer, and this is printed on paper through a plotter. The printing method is widely used.

According to an embodiment, the creation of a pattern using a CAD program for pattern creation may use a method of drawing a pattern on paper based on a sample work instruction and inputting the pattern into a CAD program for pattern creation through an input device such as a scanner. Alternatively, it may be performed by drawing directly on a CAD program for pattern creation according to a sample work instruction.

In step S140, a sample of the clothing product is manufactured by sewing the fabric pattern cut from the created pattern. Sewing may include a temporary stitch or a straight stitch. Production of the sample is usually performed by a sewing thread or a sample thread, but pattern work, sewing work, and sample work may be performed together.

According to an embodiment, in producing a sample by sewing when using a CAD program for creating a pattern, the created pattern may be output through an output machine, and a piece of fabric cut according to the pattern may be sewn to produce a real sample, or A virtual sample implemented as a 3D image may be produced by virtually sewing a pattern image implemented as a 2D image using a CAD program for pattern creation.

In step S150 , it is checked whether the design intention of the sample of the clothing product is reflected by the designer or the purchaser, or whether there is a correction by fitting. If the sample is judged to be valid because there are only minor modifications to the sample, some corrections are made to the underlying pattern, and the Gabon sample is modified (so-called Dachi) and cut, and the final sample is completed. After that, moving to step S160, the designer creates a main work order, which includes corrections reflected in the sample work order, and the production of clothing products such as specifications, colors, quantities, and subsidiary materials of the standard size. The necessary items are described in detail.

In step S150 , if it is determined that the sample is invalid due to significant modifications to the sample, the sample is discarded, and the process returns to step S130 to perform pattern and sample production again.

3 is a diagram illustrating a flowchart 300 of a method of creating a pattern according to an embodiment. Among the steps of the flowchart of FIG. 3 , steps S131 to S134 and S135 represent detailed steps included in step S130 of the flowchart of FIG. 1 . In addition, steps S140 and S150 of the flowchart of FIG. 3 are the same as steps S140 and S150 of the flowchart of FIG. 1 , respectively.

In step S131 , a basic pattern is created based on the specifications described in the sample work instruction sheet created in step S120 of FIG. 1 .

As an exemplary embodiment, FIG. 4 is a diagram illustrating an example 400 of a basic pattern created based on the schematics described in the sample work instructions and the specifications described in the sample work instructions. FIG. 4( a ) is a schematic described in the sample work instruction, which is the same as the schematic 210 of the sample work instruction 200 illustrated in FIG. 2 . Figure 4 (b) is based on the specifications described in the sample work instruction 200, the schematic 210, the size specification 220, the necessary subsidiary materials 230, the swatch 240 that is a sample of the fabric, etc. A pattern design created by a program, showing the front and back sides of the sample. FIG. 4(c) shows a basic pattern prepared by separating each pattern piece cut in the pattern design of FIG. 4(b).

Returning to FIG. 3 , in step S132 , pattern designs prepared for a clothing company requesting a sample work order are searched for in a computer-accessible database. The database may be recorded on a computer-readable medium in a computer in which the person creating the pattern works, or it may be recorded on a server on a network connected to the computer.

According to an embodiment, data of a pattern design and a size specification related to the pattern design may be stored in the database, and such data may be stored separately for at least each clothing company and clothing type. As an exemplary embodiment, the clothing type may be divided into a large category such as a set, top, bottom, underwear, swimwear, etc., a medium category such as an overcoat or a middle category such as pants, and a small category such as a blazer of the overcoat or jeans among pants, etc. , may be further classified into a smaller classification, and there is no limitation as long as the type of clothing is classified.

According to one embodiment, the pattern designs in the database are displayed on a computer screen, may be displayed in a CAD program for illustration or pattern creation, or may be displayed in another computer program connected to a CAD program for illustration or pattern creation. . For example, a person who creates a pattern inputs a clothing company name, a clothing type name, etc., so that pattern designs related thereto may be arranged and displayed on a computer screen.

In step S133 , one design is selected from among the searched pattern designs in consideration of the specifications described in the sample work instruction and the type of the clothing sample.

As an exemplary embodiment, FIG. 5 shows a result 500 of selecting a pattern design similar to the specification described in the sample work instruction, but having the same type of clothing sample as cargo pants. Figure 5 (a) is a schematic diagram of the selected pattern design, Figure 5 (b) shows the front and back of the sample for the selected pattern design, Figure 5 (c) is a cutaway in the pattern design of Figure 5 (b) Each of the pattern pieces is separated to represent the illustrated pattern design. 5(a), 5(b), and 5(c) related to the searched pattern design may be compared with FIGS. 4(a), 4(b), and 4(c) related to the basic pattern, respectively.

Returning to FIG. 3 , in step S134, a final pattern is created by applying a change to the previously created basic pattern based on the selected pattern design. In this regard, FIG. 6 shows a method 600 of changing a basic pattern according to an embodiment of the present invention.

According to an embodiment, as shown in FIG. 6A , the basic pattern 610 and the selected pattern design 620 are displayed side by side on the screen of the computer. In an exemplary embodiment, either one of the basic pattern 610 and the selected pattern design 620 may be scaled and displayed so that the size can be matched.

According to an embodiment, as shown in FIG. 6B , the basic pattern 610 and the selected pattern design 620 are displayed overlapping each other on the screen of the computer. In an exemplary embodiment, either one of the basic pattern 610 and the selected pattern design 620 may be scaled and displayed so that the size can be matched.

In an exemplary embodiment, the arrangement and scaling of the basic pattern 610 and the selected pattern design 620 may be performed by a person who creates the pattern, or is automatically performed by a computer program in accordance with a predetermined format. could be

In the embodiment of FIG. 6 , the basic pattern 610 and the selected pattern design 620 have the same waist circumference, hip circumference, and thigh circumference size specifications, and the angle at which the pocket is attached is also the same. In addition, the clothing company that requested this sample creation instruction has its own side silhouette and unique pocket angle as its design identity. On the other hand, compared with the side silhouette 612 of the selected pattern design 620, it can be seen that the side silhouette 611 of the basic pattern 610 has a narrow thigh, so that the pelvis is excessively emphasized. Also, compared to the angle of the pocket 622 of the selected pattern design 620, it can be seen that the angle of the pocket 612 of the basic pattern 610 is less inclined and does not give the feeling of the unique pocket angle of the apparel company. can This difference can be seen more clearly when looking at FIG. 6( b ) in which the basic pattern 610 and the selected pattern design 620 are overlapped and displayed.

Therefore, based on the selected pattern design 620, which can be said that the sample has already been adopted and that it has been verified that the unique side silhouette and unique pocket angle of the clothing company are reflected, the side silhouette 611 of the basic pattern 610 By changing the angle of the pocket 612 and the pocket 612, it is possible to create a final pattern that reflects the unique design of the clothing company.

Originally, even with the same sample work instruction, the basic pattern may appear differently depending on the person who writes the pattern, and even if the same person writes it, if the writing time is different, the created basic pattern may appear differently each time. At this time, if there is a difference in minute parts in the basic pattern, the design of the final sample or the feeling of fitting it may be completely different. In addition, each apparel company or designer has its own design that gives a unique feeling, and it is not easy for the person who creates the pattern to create a pattern consistently so that the apparel company or designer can bring out the unique feeling. .

In contrast, when a pattern is created with reference to a pattern design selected in consideration of the specifications and types of clothing samples described in the sample work instruction, the unique design of the clothing company or designer can be accurately reflected, and the The possibility that the sample is valid can be increased, and the pattern can be created more quickly because the pattern is created based on the reference.

Returning to FIG. 3, when the creation of the final pattern in step S134 is completed, the sewing and sample production of step S140 (same as step S140 of FIG. 1) are made, and the sample of step S150 (same as step S150 of FIG. 1) A validity judgment is made.

At this time, if it is determined that the sample is valid because there are only minor corrections to the sample in step S150, the final sample is completed, and the main work instruction writing step of step S160 of FIG. 1 is moved on, along with step S135 of FIG. is executed, and the data on the pattern design of the final pattern for the final sample is stored in the database in which the data on the pattern design is stored, divided by the clothing company and the type of the clothing sample described above, and the clothing company and the type of the clothing sample. are stored separately.

By storing the pattern design data for this verified pattern in the database, the unique design of each clothing company is well reflected in the database, and pattern designs that are the basis of valid samples can be accumulated, and more It has the effect of being able to select from a variety of pattern designs.

7 is a diagram illustrating a flowchart 700 of a method for creating a pattern for manufacturing a user-customized clothing sample according to an embodiment. The method for creating a pattern for producing a user-customized clothing sample is characterized by including an additional step in addition to the flowchart of the method for creating a pattern of FIG. 3 described above.

According to an embodiment, the method of manufacturing a clothing sample further includes receiving user data on a body shape and size from a user. According to an embodiment, the step of receiving user data may be performed in an additional step S170 separately from the pattern creation. For example, the user may be an individual buyer, or an individual seller or designer who makes a sample. In some cases, it may be a concept including a real person, such as a specific mannequin.

For example, data of a 3D image regarding the user's body shape may be acquired as user data in step S171. For example, acquisition of a 3D image of a user's body type may use a method of generating a 3D image by combining 2D images captured by two 2D image sensors spaced apart from each other by a predetermined distance, -of-Flight) A method of generating a 3D image according to a correlation function by measuring the delay or phase shift of the modulated optical signal for all pixels of the image captured by the sensor may be used. Another approach is to convert the distortion of the projected light pattern into a 3D image by calculating the depth using a surveying algorithm. However, it is not limited to any one method and does not exclude using these methods as a hybrid or using another method.

In one exemplary embodiment, the input of the 3D image data on the body type may be performed by a dedicated device capable of scanning the body, or may be performed through a scannable portable device such as a smartphone and then input to the computer. may be

In one exemplary embodiment, the user data may be data of a 3D image related to a user's partial body shape or data of a 3D image related to a user's full body shape. For example, the user data for the upper body sample may be data of a 3D image relating to the upper body of the user. In addition, the data of the 3D image may be generated based on any one side facing the user, or may be generated for all 360 degrees of the user's circumference.

In step S172, data of the user's body size may be acquired as user data. Even if data of a 3D image about a user's body shape is obtained, for example, when data of a 3D image is obtained while the user is wearing clothes, an accurate body shape may not be obtained depending on the wearing state of the clothes. Therefore, the body size can be accurately obtained by actually measuring the user.

In step S173, data of the 3D image regarding the user's body shape may be corrected based on the data of the body size. Through this, it is possible to produce patterns and samples by accurately reflecting the body type of the user to be actually worn.

According to an embodiment, changing the basic pattern to create the final pattern includes reflecting the user data again on the changed basic pattern based on the pattern design selected from the database as in step S134 of FIG. You can also make it match your body type and size.

In one exemplary embodiment, there may be samples created for ready-to-wear garments, and there are instances where a buyer would like to have these ready-to-wear garments tailored to fit them. In this case, only grading to change the size of the conventional pattern or repairing the completed sample may damage the original design, and there is a high possibility that it may not fit the user's body type or body balance. Accordingly, in this case, when user data is additionally reflected when the basic pattern is modified to create the final pattern in the step of producing the pattern, it is possible to produce a pattern and a sample suitable for the user's body type while preserving the original design.

8 is a diagram illustrating a modified flowchart 800 of creating a clothing sample according to an embodiment. The method for creating a clothing sample in a modified manner is characterized by including additional steps in the flow chart of the method of creating a pattern of FIG. 3 or the flow chart of creating a clothing sample of FIG. 1 described above.

According to an embodiment, the method of creating a clothing sample further includes a step S180 of processing a pattern design stored in a database and a size specification related to the pattern design.

According to an embodiment, the step S180 of processing the pattern design stored in the database and the size specification related to the pattern design is the size specification of the size specification based on the size specification related to the pattern design stored at least for each clothing company and the clothing type stored in the database. Step S181 of generating statistical data may be included, or step S182 of templating the stored pattern design and size specifications related to the pattern design for each clothing company and clothing type may be included.

In an exemplary embodiment, the data of the size specification may be statistically stored for each clothing company, for each type of clothing, or for each clothing company and for each type of clothing, and then stored in the database. In an exemplary embodiment, the statistical data of the size specification may include an arithmetic mean value, a mode, a median, a standard deviation, etc. of the size specification, but is not limited thereto. Any statistic that is useful is sufficient.

In an exemplary embodiment, a pattern design having the highest frequency among pattern designs stored for each clothing company and for each clothing type may be selected and determined as a template for the clothing type of the clothing company together with the size specification. In an exemplary embodiment, a person who makes a pattern may manually set a template, and similar images are classified according to a known image analysis method for pattern design, and one of the similar images is selected to form a plurality of templates. may be

According to an embodiment, in step S120 of creating a sample work instruction, the sample work instruction may be written in consideration of the statistical data of the size specification generated through step S182. For example, if the pants of clothing company A are size M when the waist circumference is 32 inches, the average value of the length of the waist circumference of the sample may be 86 centimeters, and the pants of clothing company B have a waist circumference of 32 inches. Although the case is the same as the size M, the average value of the length of the waist circumference of the sample may be 82 centimeters.

Therefore, the designer can make the sample's waist length close to 86 centimeters when designing the pants for clothing company A, but can make the sample's waist length close to 82 centimeters when designing the pants for clothing company B. have. Accordingly, even when writing design and sample work instructions, it is possible to easily reflect the characteristics of the design or fit of each apparel company.

8 , according to an embodiment, in step S133 of selecting one of a plurality of pattern designs of a clothing company as a detailed step of S130 of creating a pattern, a templated pattern design may be selected through step S182. have. For example, when creating a pattern for the pants of clothing company A, you can select from among the templates of the pattern design for the pants of clothing company A, thereby making it easier and faster to create the pattern. have

On the other hand, even when the purchaser requests the production of customized clothing, as described above, the sample can be manufactured. In this case, if it is possible to quantitatively determine how well the customized clothing sample is made to fit the buyer's body type or size, it will be easy to modify the sample, and it will be reflected in the creation of the sample in the future to make accurate customized clothing becomes

FIG. 9 is a flowchart 900 of a method of classifying a matching degree of a clothing sample with respect to a user's body type and size according to an exemplary embodiment.

According to one embodiment, by processing data transmitted and received through an artificial neural network included in each of the first device 910 connectable to the computer and the second device 920 connectable to the computer, the clothing sample is transferred to the user's body. The degree of matching with the body type and size can be classified.

In an exemplary embodiment, the first device 910 may be implemented as a computing device having a communication function, and may be implemented as, for example, a mobile phone, a desktop PC, a laptop PC, a tablet PC, a smart phone, etc. , but is not limited thereto, and may be implemented as various types of communication devices that can be connected to a computer or connected to other devices. The first device 910 may acquire 3D data of the manufactured clothing sample through a sensor or a camera, and the 3D data may be image data. Also, the first device 910 may be used to train a first artificial neural network, which will be described later, or to use the learned first artificial neural network.

In an exemplary embodiment, the second device 920 may communicate with the first device 910 and may be implemented as, for example, a desktop PC, a laptop PC, a tablet PC, a server, etc., but is not limited thereto. , may be implemented as various types of communication devices that can be connected to a computer or connected to other devices. Also, the second device 920 may be used to train a second artificial neural network, which will be described later, or to use the learned second artificial neural network.

Referring to FIG. 9 , the first device 910 acquires 3D image data for a clothing sample in step S901, and 3D image data about the user's body shape and body size data in step S902 can be acquired. have. The body size data may be text data regarding a size specification according to a body part of the user.

In operation S903 , the first device 910 may extract the first data by reflecting the data of the 3D image of the user's body shape and the data of the body size in the data of the 3D image of the clothing sample.

Specifically, the first device 910 generates a corrected 3D image by applying the data of the body size to the data of the 3D image about the user's body shape, and synthesizes the first data by synthesizing the 3D image with the 3D image of the clothing sample. can be extracted. Here, the first data may be composed of 4 channels, 3 channels may be 2D data representing an RGB value, and 1 channel may be data representing a 3D depth value.

In operation S904 , the first device 910 generates a first classification result for the degree to which the clothing sample matches the user's body shape and size.

In detail, the first device 910 may generate a first input signal by encoding the first data. Specifically, the first device 910 may generate a first input signal by encoding pixels of the first data with color information. The color information may include, but is not limited to, RGB color information, brightness information, saturation information, and depth information. The first device 910 may convert the color information into a numerical value, and may encode the first data in the form of a data sheet including the value.

The first device 910 may input the first input signal to the first artificial neural network learned in advance in the first device 910, and may obtain a first output signal based on a result of the input of the first artificial neural network. can

As an exemplary embodiment, the first artificial neural network is composed of a feature extraction neural network and a classification neural network, and the feature extraction neural network sequentially stacks a convolutional layer and a pooling layer on an input signal. The convolution layer includes a convolution operation, a convolution filter, and an activation function. The calculation of the convolution filter is adjusted according to the matrix size of the target input, but a 9X9 matrix is generally used. The activation function generally uses, but is not limited to, a ReLU function, a sigmoid function, and a tanh function. The pooling layer is a layer that reduces the size of the input matrix, and uses a method of extracting representative values by tying pixels in a specific area. In general, the average value or the maximum value is often used for the calculation of the pooling layer, but is not limited thereto. The operation is performed using a square matrix, usually a 9x9 matrix. The convolutional layer and the pooling layer are repeated alternately until the corresponding input becomes small enough while maintaining the difference.

As an exemplary embodiment, the classification neural network has a hidden layer and an output layer. Classification of the first artificial neural network for classifying the error level of the clothing sample The neural network consists of five or less hidden layers, and may include a total of 50 or less hidden layer nodes. The activation function of the hidden layer uses a ReLU function, a sigmoid function, and a tanh function, but is not limited thereto. There is a total of one output layer node of the classification neural network, and an output value for the classification of the error stage of the clothing sample may be output to the output layer node.

Based on the first output signal, the first device 910 may generate a first classification result for the degree to which the clothes sample matches. Here, the first classification result may include information on what level of error the clothing sample is classified into when compared with the user's body shape or size. For example, as a result of checking the output value of the first output signal, when the output value is 1, the first device 910 generates the first classification result as an error step 1 of the clothing sample, and when the output value is 2, the clothing sample is A first classification result may be generated that corresponds to the error step 2 .

When the first classification result is generated through the analysis of the first data, the first device 910 may transmit the first data and the first classification result to the second device 920 in step S905 .

In operation S906 , the second device 920 may analyze the first data received from the first device 910 to detect an error occurring in the clothing sample. When an error is detected, only a portion identified as having a size greater than or equal to a certain size through image analysis of the first data may be detected as an error occurring in the clothing sample.

In operation S907 , the second device 920 may identify an error occurring in the clothing sample for each area of the clothing sample, and may distinguish a normal area from a defective area. Specifically, the second device 920 divides the first data into a plurality of regions such as the first region and the second region, and can check how many errors are detected for each region, and the error is less than the first reference value. An area in which is detected may be classified as a normal area, and an area in which an error greater than or equal to the first reference value is detected may be classified as a defective area. In this case, the first reference value may be set differently depending on the embodiment.

In operation S908 , the second device 920 may extract second data from which the defective area is deleted from the first data. For example, the image in the first data consists of a first region, a second region, and a third region, wherein the first region is divided into a defective region, and the second region and the third region are divided into a normal region. In this case, the second device 920 may extract an image including only the second area and the third area as the second data.

In operation S909 , the second device 920 generates a second classification result for the degree to which the clothing sample matches the user's body shape and size.

In detail, the second device 920 may generate a second input signal by encoding the second data. Specifically, the second device 920 may generate a second input signal by encoding pixels of the second data with color information. The color information may include, but is not limited to, RGB color information, brightness information, saturation information, and depth information. The second device 920 may convert the color information into a numerical value, and may encode the second data in the form of a data sheet including the value.

The second device 920 may input a second input signal to a second artificial neural network previously learned in the second device 920 and obtain a second output signal based on a result of the input of the second artificial neural network. . The second artificial neural network according to an embodiment may be the same as that described in the first artificial neural network.

Based on the second output signal, the second device 920 may generate a second classification result for the matching degree of the clothing sample. Here, the second classification result may include information on how much error level the clothing sample is classified as compared with the user's body shape or size. A method of generating the second classification result according to an embodiment may be the same as that described in the method of generating the first classification result.

In operation S910 , the second device 920 may set a final classification result for the degree to which the clothing sample matches the user's body shape and size based on the first classification result and the second classification result. For example, when the first classification result and the second classification result are the same, the second device 920 sets any one of the first classification result and the second classification result as the final classification result for the matching degree of the clothing sample. If the first classification result and the second classification result are different from each other, the first degree of agreement calculated through image comparison analysis between the image in the first data and the reference image of the clothing sample, and the image in the second data By comparing the second degree of agreement calculated through image comparison analysis with the reference image of the clothing sample, a classification result having a high degree of agreement may be set as a final classification result.

Through this method, since the matching degree of the clothing sample can be more accurately checked using the two artificial intelligences in the two devices, it is easy to correct the part with the error in the clothing sample when there is an error in the clothing sample. In addition, by checking the error of the clothing sample, the matching degree of the clothing sample to be created later can be improved, so that more accurate customized clothing can be manufactured.

The embodiments described above may be implemented by a hardware component, a software component, and/or a combination of a hardware component and a software component. For example, the apparatus, methods and components described in the embodiments may include, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate (FPGA) array), a programmable logic unit (PLU), a microprocessor, or any other device capable of executing and responding to instructions, may be implemented using one or more general purpose or special purpose computers. The processing device may execute an operating system (OS) and one or more software applications running on the operating system. The processing device may also access, store, manipulate, process, and generate data in response to execution of the software. For convenience of understanding, although one processing device is sometimes described as being used, one of ordinary skill in the art will recognize that the processing device includes a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that can include For example, the processing device may include a plurality of processors or one processor and one controller. Other processing configurations are also possible, such as parallel processors.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded in a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc. alone or in combination. The program instructions recorded on the medium may be specially designed and configured for the embodiment, or may be known and available to those skilled in the art of computer software. Examples of the computer-readable recording medium include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic such as floppy disks. - includes magneto-optical media, and hardware devices specially configured to store and carry out program instructions, such as ROM, RAM, flash memory, and the like. Examples of program instructions include not only machine language codes such as those generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

The software may comprise a computer program, code, instructions, or a combination of one or more thereof, which configures a processing device to operate as desired or is independently or collectively processed You can command the device. The software and/or data may be any kind of machine, component, physical device, virtual equipment, computer storage medium or apparatus, to be interpreted by or to provide instructions or data to the processing device. , or may be permanently or temporarily embody in a transmitted signal wave. The software may be distributed over networked computer systems, and stored or executed in a distributed manner. Software and data may be stored in one or more computer-readable recording media.

As described above, although the embodiments have been described with reference to the limited drawings, those skilled in the art may apply various technical modifications and variations based on the above. For example, the described techniques are performed in a different order than the described method, and/or the described components of the system, structure, apparatus, circuit, etc. are combined or combined in a different form than the described method, or other components Or substituted or substituted by equivalents may achieve an appropriate result.

Therefore, other implementations, other embodiments, and equivalents to the claims are also within the scope of the following claims.

Claims (3)

A method for making a clothing sample, comprising:
creating a sample work order;
creating a final pattern through a CAD program for pattern creation driven in a computer based on the specifications described in the sample work instruction; and
producing a clothing sample from the final pattern;
The step of creating the final pattern is,
creating a basic pattern based on the specifications described in the sample work instruction;
retrieving a plurality of pattern designs of a clothing company requesting the sample work instruction from the computer-accessible database;
selecting one of a plurality of pattern designs of the clothing company to match the specifications described in the sample work instruction and the type of the clothing sample;
changing the basic pattern based on the selected pattern design to create the final pattern; and
Including the step of processing the size specification related to the pattern design and pattern design stored in the database,
In the database, pattern design and size specifications related to pattern design are stored separately for at least each clothing company and clothing type,
When the clothing sample produced based on the final pattern is valid, the pattern design and size specification of the final pattern are stored in the database as one of the pattern designs according to the type of the clothing sample of the clothing company,
The processing step is
generating statistical data of size specifications for each clothing company and for each clothing type based on the size specifications for pattern designs stored separately for each clothing company and for each clothing type; and
and templateizing the size specifications related to the stored pattern design for each clothing company and clothing type,
In the step of creating the sample work order, it characterized in that the sample work order is written based on the statistical data of the size specification,
How to make clothing samples. According to claim 1,
The clothing sample production method further comprises the step of receiving user data on a body type and size from a user,
The step of receiving the user data is,
acquiring data of a 3D image on the body type of the user;
acquiring data of the user's body size of the user; and
Generating the user data by modifying the data of the 3D image based on the data of the body size,
The step of creating the final pattern comprises the step of creating the final pattern by modifying the changed basic pattern to match the user data,
How to make clothing samples. delete

Images