JPH0944556A - Trial wearing simulation method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To reduce the difference between an impression on a trial wearing simulation image and an impression of actual wearing as for trial wearing simulation. SOLUTION: A clothing image is obtained by being cut out of an image of a dummy wearing clothing. Then the basic human image of the dummy (nearly naked) and the clothing image are previously written in an external storage device 18. Then the basic human image of this dummy is deformed according information on the body build of a person who tries clothing on. Further, the clothing image is also deformed according to the information on the body build of the trying person or the deformed basic human image. Then the deformed images are both put together in one.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a fitting simulation method. In particular, the present invention relates to a fitting simulation method for displaying a virtual image of wearing clothes for which fitting is desired. In particular, the present invention relates to a fitting simulation method for displaying desired clothes by combining them with an image of a person who wants to try them on.

[0002]

2. Description of the Related Art An example of a conventional fitting simulation method of this type is disclosed in Japanese Patent Application Laid-Open No. 6-187398 (G06F 15/60) filed on July 8, 1994. In this conventional technique, a contour line is extracted from an image of a person who wants to be tried on by the image pickup unit, two points are attached at predetermined positions on the contour line, and try-on is made based on the interval. It is intended to enlarge or reduce the image of clothes to be combined with the image of the person.

[0003]

However, in such a conventional technique, an attempt is made to enlarge or reduce the image below the neck of the wearer based on the distance between the two points. Unlike the figure of the person who wants
There was a problem that it was different from the impression when actually worn.

That is, there are the following inconveniences when synthesizing clothes. The nude of the person who wants to try on the clothes may be photographed, and the clothes image may be combined with this image. Don't In addition, when synthesizing small ornaments such as watches and glasses, naturally, the image of this ornament is uniformly deformed according to the size of the part of the body to which this ornament is attached, All you have to do is paste it on the image. However, when synthesizing clothes images, this clothes image must be significantly deformed according to the body shape and pose, which puts a heavy load on the try-on simulation device, and can result in an unnatural synthesized image. The nature is enhanced.

Therefore, a main object of the present invention is to provide a try-on simulation method capable of outputting a try-on simulation image with less discomfort when the person who wants to try on the wearer actually wears it.

[0006]

According to the present invention, a basic human image and a clothing image that fits the posture of the basic human image are stored in advance, and both images are stored according to the figure data of the person to be tried on. , Transform and combine. According to the present invention, (a) a first person image arranged at a predetermined position is stored together with first contour information, and (b) a second person image arranged at the predetermined position.
The person image is stored together with the second contour information, and (c) the clothing image of the first person image which is arranged at the predetermined position and is dressed is stored together with the third contour information, and (d) the first contour information, According to a fitting simulation method, the first person image and the clothing image are transformed based on the second contour information and the third contour information, and (e) the transformed first person image is combined with the transformed clothing image. is there.

The present invention also provides (a) a basic portrait image,
A plurality of clothes images corresponding to the poses of the basic person image are stored in advance, (b) body shape information representing the body shape of the person to be tried on is stored, and (c) based on this body shape information, the basic person image is stored. It is a fitting simulation method in which an image is deformed, the clothes image is deformed based on the deformed basic person image, and (d) the deformed clothes image is combined with the deformed basic person image.

[0008]

In the present invention, the basic person image for composition and the clothes image for composition are transformed and combined according to the body type information of the person to be tried on. In the present invention, for example, the first
A first person image such as a mannequin image to which contour information (first feature points) is attached is stored in memory, and a second person image such as an image of a person who wants to try on the second contour information (second feature points). ) Is attached and memorized, and the first piece of clothing
The clothing image of the person image is stored with the third contour information (third feature point). Then, for example, the first person image and the first contour information are modified so that the first contour information matches the second contour information, and the clothing image is modified so that the third contour information matches the modified first contour information. Be transformed. And
The deformed clothing image is combined with the deformed first person image.

Further, in the present invention, for example, a basic person image such as a mannequin image is stored, and a clothing image extracted from the image of the mannequin wearing clothing is stored. Then, for example, the body type information of the person to be tried on is stored in the memory, and the basic person image is transformed according to the body type information. Then, the clothing image is transformed so as to correspond to the basic person image. Then, the deformed clothing image is combined with the deformed basic person image.

[0010]

According to the present invention, the first person image deformed according to the second person image is combined with the deformed clothes image, so that the image of the person desired to wear and the clothes image are combined. It is possible to output a try-on simulation image that does not cause a feeling of strangeness. Further, according to the present invention, the basic person image for composition which is deformed according to the body type information of the person to be tried-on and the deformed clothing image for composition are combined, so that the person to be tried on actually It is possible to output a try-on simulation image that is similar to wearing clothes.

The above and other objects, features and advantages of the present invention will become more apparent from the following detailed description of embodiments with reference to the drawings.

[0012]

DESCRIPTION OF THE PREFERRED EMBODIMENTS Each part of this embodiment will be described with reference to FIG. The simulation apparatus 10 of this embodiment has a bus 12
Including a CPU 14, a working memory 16,
External storage device 18, video memory 20, A / D converter 2
2. A keyboard 24 and a mouse 26 are connected to each other.

A CRT 30 is connected to the video memory 20 via a D / A converter 28, and an A / D converter 22 is provided.
An image input device 32 such as a camera is connected to the. In the external storage device 18, image data of the mannequin 34 (basic person image / first person image) shown in FIG. 2A, data of characteristic points of the person image by this mannequin, clothing image data,
Data of feature points of clothes images, people who want to try on clothes (people to try on)
Image data (second person image) and feature point data of the second person image are stored.

Explaining in detail, the mannequin 3 close to a naked body
2A, the mannequin 34 shown in FIG. 2A is placed at a position separated from the image input device 32 by a predetermined distance, the image is captured from the image input device 32, and the image is A / It is D-converted and stored in memory. Next, the data of the characteristic points of this mannequin image is obtained.
For this purpose, a mark is written at a position to be a characteristic point of the mannequin. The mannequin 34 shown in FIG. 2B in which the mark is written is arranged at the same position as described above, which is separated from the image input device 32 by a predetermined distance, and the image is captured from the image input device 32, and from the image, The position of the mark is extracted as a feature point. This extraction may be performed by image recognition. Alternatively, the image of FIG. 2B may be displayed and the position of this mark may be extracted by clicking with the mouse. Furthermore, the mannequin image of FIG. 2A may be displayed and then extracted by clicking with the mouse.

The image data of FIG. 2A and the data of the characteristic points corresponding to each part of this image are stored as a set in the external storage device 18. Next, storage of clothing image data will be described. First, when this mannequin is put on clothes, it becomes as shown in FIG. 3A. It is to be noted that when the feature points obtained previously are displayed on this image in a superimposed manner, it becomes as shown in FIG. 3B. The image of FIG. 3A is displayed on the CRT 30, and the outline of the clothes in this image is traced with the mouse 26. Thereby, the clothes image is cut out. The data of the clothing image is stored together with the data of the characteristic points.

Further, the storage of the image data of the person to be tried on will be described. The image input device 32 captures an image of a person 36 who wants to try on as shown in FIG. 5A. It is desirable that this person 36 also stands at the same position as the above-mentioned mannequin 34 in the same pose (posture) as the mannequin 34. This image data is written in the video memory 20 and displayed. Then, as shown in FIG. 5B, the mouse is clicked on the position corresponding to the feature point in FIG. 2B to obtain the data of this feature point. The characteristic point of this embodiment is "neck side".
It corresponds to "acromion""armpit""elbow""wrist""waistside""gluteside""kneeside""ankle".

After the various data are written in the external storage device 18 and the video memory 20 in this manner, the CPU
14 changes the body type and skin color of the mannequin 34 so as to approach the body type and skin color of the person to be tried on, and further transforms the shape of the clothes so as to match the changed mannequin image,
This mannequin image is composited. The combined image data is once written in the video memory 20, converted into an analog video signal by the D / A converter 28, and output from the CRT 30.

The cutout operation of the clothes image will be described according to the flow. The CPU 14 writes the clothing image data in the external storage device 18 according to the flow shown in FIG. That is, first, in step S1, as shown in FIG. 3A, the image of the mannequin 34 with clothes is written in the video memory 20. Next, in step S3, the feature points written in the external storage device 18 are extracted and attached to the corresponding positions of the worn mannequin image written in the video memory 20. The mannequin image with the feature points is read from the video memory 20 and output from the CRT 30. Then, in step S7, the contour of the clothes worn by the mannequin 34 is changed to the mouse 2
If it is determined that the image is traced by 6, the image of the clothes is extracted and written in the external storage device 18 in step S9.
By changing the clothes and repeating the above process,
A plurality of clothes image data as shown in FIG. 4 is written in the external storage device 18.

The CPU 14 also carries out a simulation process of putting a desired clothes on a person who wants to try on the clothes according to the flows shown in FIGS. That is, first, the fitting target person image shown in FIG.
Write to 0. In step S15, it is determined by the mouse 26 whether or not a feature point is added to this person image as shown in FIG. 5B. It should be noted here that this feature point is attached to the contour line of the body. When the feature points are added, that is, when the feature points are written in the video memory 20, the image data of the mannequin 34 shown in FIG. 2 is read from the external storage device 18 in step S17, and the working memory 1 is read.
Write to 6. Subsequently, in step S19, the feature points of the mannequin image corresponding to the feature points attached to the fitting target person image are searched, and in step S21, the mannequin image is transformed so that the feature points of both images match each other. The feature points of the mannequin image are also moved together. When transforming the mannequin image, a technique such as affine transformation is used.

When the deformation of the mannequin image is completed, it is determined in step S23 whether or not the outline of the skin portion of the human image displayed on the CRT 30 is traced by the mouse 26. If "YES", the color components (R, G, B) of the pixels within the contour are calculated in step S25, and the color components (R, G, B) of the corresponding pixels in the mannequin image are calculated in step S27. To calculate. Next, in step S29, the conversion coefficient A _i of the color component is calculated according to equation 1.

[0021]

[Formula 1] N _i = A _i · M _i (1 ≦ i ≦ n) N _i : Color component of person image M _i : Color component of mannequin image Detailed calculation of conversion coefficient A _i using foot part then, first, in step S25 for each pixel shown in FIG. 10 (a) calculates the color component n ₁ to n _n of the person 34, then the color component n ₁ as shown in FIG. 10 (B) in steps S27 ~
The color components M _{1 to} M _n of the mannequin 34 corresponding to N _n are calculated, and then the conversion coefficients A _{1 to} A _n are calculated for each pixel.
Is calculated. Each color component N _{1 to} N _n and M ₁ to
Of course, M _n is obtained for each color component (R, G, B), and the conversion coefficient A _i is also obtained for each color component (R, G, B). When the conversion coefficient is calculated in this way,
In step S31, it is determined whether or not the contour of the skin of the person image is newly designated. If "YES", step S25
However, if “NO”, in step S29, the average value of all the calculated conversion coefficients is calculated for each color component (R, G, B).
It is calculated every time.

Then, in step S35, the color components (R, G, B) of the pixels of the mannequin image are calculated, and in step S37.
Then, the conversion coefficient averaged in step S33 is added to this color component. Succeedingly, in a step S39, the pixel calculated in the step S35 is replaced with the integrated value, and in a step S41, it is determined whether or not the replacing process is performed for all the pixels of the mannequin image. If “NO” here, the process returns to step S35, but if “YES”, the face portion of the person image is combined with the mannequin image in step S43, and the process proceeds to step S35.
At 45, the face joint is smoothed. Through the above processing, the simulation data of the person 36 who is not wearing clothes is created.

Subsequently, in step S49, the external storage device 1
The clothing image data written in 8 is read out and multi-screen displayed on the CRT 30 as shown in FIG. However, before the screen is displayed, the type of clothes is narrowed down by a normal keyword search or the preference the customer has selected in the past.
Then, in step S51, it is determined whether any clothes are selected by the keyboard 24 or the mouse 26. If "YES", the selected clothes image data is written in the work memory 16 in step S53. next,
In step S55, the characteristic points of the clothes image corresponding to the characteristic points of the mannequin image are searched, and in step S57, the clothes are deformed by affine transformation or the like so that the characteristic points of both images match. Then, in step S59, the clothes are combined with the mannequin image and output from the CRT 30. by this,
The CRT 30 outputs simulation data in which desired clothes are put on the person 36.

In operation, when a person 36 who wants to try on stands at a position separated from the image input device 32 by a predetermined distance, the CPU 14 captures the image of the person by the image input device 32, and the body shape of the mannequin 34 written in advance. And the color are processed to approximate the figure and skin color of this person. Further, the clothing desired to be tried on by the person 36 is displayed on the CRT 30 in a multi-screen manner, and the clothing selected from the clothing is deformed and combined so as to fit the mannequin 34.

According to this embodiment, the mannequin 34 is deformed so as to approximate the body shape and skin color of the person 36 and the clothes are combined therewith, so that the person 36 actually wears the clothes. The state can be displayed as a simulation. In this embodiment, the average value of the conversion coefficients calculated in step S33 is simply added to the color component of each pixel of the mannequin image in step S37. The skin color component may be weighted according to the distance from the exposed pixel, and the weighted value may be integrated with the average value of the conversion coefficients to reproduce the color of the pixel to be converted. That is, for example, in the case of converting the color component of the point A of the person 36 shown in FIG. 11, the conversion coefficients of the R components of the representative points selected from the neck, the hand and the foot are α1, α2 and α3, respectively, and the respective representative points are It is assumed that the ratio of the distances from A to A is a: b: c. In this case, the converted R component R _m ′ at the point A is obtained according to the equation 2.

[0026]

## EQU2 ## R _m ′ = {(1 / a) / d} · α1 · R _m +
{(1 / b) / d} · α2 · R _m + {(1 / c) / d}
Α3 · R _m R _m : R component at point A of the mannequin image d = (1 / a) + (1 / b) + (1 / c) Further, the conversion coefficients of the G component at the representative point are β1, β2 and β
3 and the conversion coefficients of the B component are γ1, γ2, and γ3, the G component G _m ′ and B component B _m ′ after conversion at the point A can be obtained by Equations 3 and 4.

[0027]

## EQU3 ## G _m ′ = {(1 / a) / d} · β1 · G _m +
{(1 / b) / d} · β2 · G _m + {(1 / c) / d}
Β3 · G _m G _m : G component at point A of the mannequin image d = (1 / a) + (1 / b) + (1 / c)

[0028]

## EQU4 ## B _m ′ = {(1 / a) / d} · γ1 · B _m +
{(1 / b) / d} · γ2 · B _m + {(1 / c) / d}
.Gamma.3.B _m B _m : B component at the point A of the mannequin image d = (1 / a) + (1 / b) + (1 / c) As a result, lighting when the human image is captured by the image input device 32 Even if there is a difference in color components between parts of the body due to (Lighting), the color of the simulated image can be naturally changed and represented.

More specifically, step S in FIG.
The flow shown in FIG. 12 is processed instead of 33 to S41.
That is, if “NO” in the step S31, the step
In S61, specify one pixel included in the mannequin image and
Color component R_m, G_mAnd B _mTo calculate. Next,
At step S63, an arbitrary contour within the contour traced by the mouse 26 is selected.
The pixel is designated as the representative point, and the representative point is selected in step S65.
The ratio of the distance from the point to the pixel specified in step S61
calculate. Then, in step S67, follow the formulas 1 to 3.
Color component R_m′, G_m'And B_m′ Is calculated and
In step S69, the color component R of the pixel specified in step S61
_m, G_mAnd B_mThe color component R_m′, G_m'and
B_m’ Then, in step S71, all images
Judge whether the element has been processed, and if “NO”, step
Return to step S61, but if "YES", the step S43.
Move to.

In this embodiment, all the characteristic points are added when the characteristic points are added to the person image displayed on the CRT 30. However, some representative points are designated, and a part of the body of the person is specified between them. Automatically interpolating based on statistical data or the like, and further extracting the contour line of the person 34 including clothes to automatically specify all the feature points based on the statistical data of the body of the person. May be. Also, the mannequin 34
Image data of the work memory 1 in step S17 of FIG.
6 is written in the simulation device 10
May be written in the work memory in advance when is started. Further, the characteristic points indicating the contour of the mannequin 34 are attached to the mannequin 34 itself, but may be attached manually by operating the mouse 26 after inputting the mannequin image.

Furthermore, in this embodiment, only the face portion is combined with the mannequin image. However, the exposed portion of the human image such as the neck, hands and feet is cut out from the human image and cut into the mannequin. Combine it into an image,
You may make it perform a smoothing process. Further, in this embodiment, the conversion coefficient is calculated for the color components (R, G, B), but it may be calculated for the luminance component and the hue component. Further, in this embodiment, the conversion coefficient is obtained for each pixel between the person image and the mannequin image. However, in calculating the conversion coefficient of each pixel, first, the pixels having the same color component are detected in the mannequin image. , The color component values of the pixels of the person image corresponding to this pixel may be averaged, and the conversion coefficient may be obtained from this average value.

In the present embodiment, for simplification of explanation, all steps of capturing a basic human image by a mannequin, capturing a clothing image, capturing a human image of a person to be tried on, and combining are performed in one step. I went with one device. However, in the present application, the image of a person from the mannequin is captured, the image of the clothing is captured in advance at the factory to store these image information, and after shipment, at each clothing store, which is the installation location,
You may make it perform the process of taking in the person's image of a fitting subject, and combining.

Although different from the claims of the present application, clothing items such as earrings, brooches, glasses and necklaces may also be combined. Further, in the present embodiment, the mannequin is integrated, but it is possible to preliminarily capture images of the mannequin of several typical body types and their clothes, and transform the data that are physically similar to the fitting subject. By doing so, the discomfort is further reduced. As a case classification,
"Gender (male / female)""Height (medium / tall / short person)""Age (3 years, under 5 years, under 10 years, 15"
Under 20 years old, around 20 years old, 20s, 30s ... 80 years old or older) "
"By obesity level (thin type, middle meat, overweight type)" and "by posture" (pose 1, pose 2, pose 3), etc. can be considered.

Further, in the embodiment, the image of the person to be tried on is input in the same position and in the same pose as in the mannequin image, but the present application may be from photographs of different poses. If the pose is different, the wrist position, the elbow position, and the knee position themselves cannot be used when transforming the mannequin image. If the width of the wrist, the width of the elbow, the width of the knee, etc. can be extracted, use them. Further, in the present application, an image of the whole body of the person to be tried on is captured, but this may be a part. In such a case, of course, the accuracy of the simulation is lowered.

Although not described in the embodiment, it is better to provide a lot of characteristic points on the clothes portion which fits the body exactly. Further, in the embodiment, the corresponding coordinate data (feature points) for matching the body type information of the mannequin and the fitting subject and the corresponding coordinate data (feature points) for aligning the deformed mannequin image and the clothing image are the same. However, the present application is not limited to this. Further, although the corresponding coordinate data is obtained from a part of the contour of the naked body, the present application is not limited to this.

In other words, the body type information is used for height, weight, chest measurement,
It is also possible to use data such as waist circumference, hip circumference, sitting height, inseam, navel height, nipple height, and nipple width, and the basic person image may be transformed from these data values. Further, as the body shape data to be used, body shape data and the like measured by a corporation, Human Life Engineering Center, which is an external organization of the Ministry of International Trade and Industry, can be considered.

In the present embodiment, the clothing image and the basic person image are respectively transformed and then synthesized. However, if the processing for transforming these two images is the same, first, they are synthesized and then transformed. You may Further, the deformation may be performed in the area instead of the deformation based on points such as feature points. For example, as the data for deforming the mannequin and the clothes, the deforming process may be performed in the regions shown in FIGS. 13 and 14. The deformation of each area may be changed according to the physique data of the person trying on.

Further, the size of each part of the deformed clothing image may be output. Then, the clothing may be created with reference to this size. The above-described embodiment is effective when creating clothes that fit the body shape of the person to be tried on. However, the present application can also be used to determine whether ready-made clothing suits the person being tried on.

In this case, the corresponding data of the clothes image (corresponding to the above-mentioned characteristic points) is devised. That is, the mannequin image in FIG. 15 is transformed according to the body type information of the person to be tried on. The body type information you enter includes gender, age, height, weight, chest circumference,
Waist circumference, hip circumference, inseam height, etc. For women, nipple and chest circumference is all that is needed. From these, the figure information of other parts (high genital height, acromion height, thigh circumference, upper arm length, upper arm circumference, upper limb length, forearm maximum circumference, back shoulder width, etc.) is also estimated and obtained.

The mannequin image is deformed by the deformation based on the body type information. Due to this deformation, the positions of the characteristic points and the like of the respective parts in FIG. Next, the clothing image of FIG. 16 is transformed with reference to the positions of the displaced characteristic points. In this modification, the size of the clothes remains unchanged. Here, the corresponding data for deformation given to the clothing image of FIG. 16A has the following functions.

The corresponding data line of b11 and b12 is a1
The conditions are set so that 1 and a12 are located on any of the lines. b21 and b22 are also corresponding data lines that are conditionally set so that a21 and a22 are located on any of the lines. b31 and b32 are corresponding data points that are conditionally set so that the one-arm contours a31 and a32 of the mannequin image are located inward.

B33 and b34 are corresponding data points which are conditionally set so that the remaining one arms a33 and a34 of the mannequin image are located inward. b41 and b42 are a4
1, a 42 is a corresponding data line that is conditionally set so as to be located on any of the lines. b51 and b52 are a5
1 and a52 are corresponding data points that are conditionally set to be arranged.

By deforming and synthesizing the clothes image so as to meet the above-mentioned condition setting, a realistic try-on image can be obtained. In the above example, a31, a32, a3
As the contour line of the mannequin image of 3, a34, the contour line data used at the time of cutting out the mannequin image may be used. Of the correspondence data for deformation given to the clothing image of FIG. 16B, the description of the correspondence data having the same function as above will be omitted.

Note that b51 'and b52' are corresponding data points that are conditionally set so that a51 and a52 of the mannequin image are arranged inward. Also, b61, b62
Are corresponding data points that are conditionally set so that a 61 and a 62 of the mannequin image are arranged inward. In this way, when the clothes image is deformed, by deforming the clothes image so as to meet the above-mentioned condition setting, a realistic fitting image can be obtained.

The clothing image and its corresponding data are set so that the deformed mannequin image does not protrude from the clothing image. However, in order to deal with any deformation, many corresponding data must be provided,
Setting corresponding data becomes difficult. Therefore, this correspondence data may be added / deleted / condition set later, and may be added when necessary.

If the clothing image can be deformed with the contour line of the clothing image as a reference after such composition, the simulation of the clothing reform can be performed.

[Brief description of drawings]

FIG. 1 is a block diagram showing one embodiment of the present invention.

FIG. 2 is an illustrative view showing a mannequin image.

FIG. 3 is an illustrative view showing a clothing image worn on a mannequin image.

FIG. 4 is an external view showing a mannequin wearing clothes.

5A and 5B are external views showing a person image.

FIG. 6 is a flowchart showing a part of the operation of the embodiment in FIG. 1;

FIG. 7 is a flowchart showing a part of the operation of the embodiment in FIG. 1;

FIG. 8 is a flowchart showing a part of the operation of FIG. 1 embodiment.

9 is a flowchart showing a part of the operation of FIG. 1 embodiment. FIG.

FIG. 10 is an illustrative view showing corresponding pixels of a foot portion of a human image and a mannequin image.

FIG. 11 is an external view showing a person image.

FIG. 12 is a block diagram showing a part of the operation of another embodiment of the present invention.

FIG. 13 is a diagram showing a clothing image and its deformed region in a second example.

FIG. 14 is a diagram showing a mannequin image and its deformed region in a second example.

FIG. 15 is a diagram showing corresponding coordinate data for synthesizing a mannequin image and its clothing image in the third example.

FIG. 16 is a diagram showing corresponding coordinate data for synthesizing a clothing image and a mannequin image in the third example.

[Explanation of symbols]

 10 ... Simulation device 14 ... CPU 16 ... Working memory 18 ... External storage device 20 ... Video memory 24 ... Keyboard 26 ... Mouse 30 ... CRT 32 ... Image input device

─────────────────────────────────────────────────── ───

[Procedure amendment]

[Submission date] August 9, 1995

[Procedure amendment 1]

[Document name to be amended] Drawing

[Correction target item name] Figure 2

[Correction method] Change

[Correction contents]

[Fig. 2]

[Procedure amendment 2]

[Document name to be amended] Drawing

[Correction target item name] Figure 3

[Correction method] Change

[Correction contents]

[Figure 3]

[Procedure 3]

[Document name to be amended] Drawing

[Correction target item name] FIG.

[Correction method] Change

[Correction contents]

FIG. 13

[Procedure amendment 4]

[Document name to be amended] Drawing

[Correction target item name] FIG.

[Correction method] Change

[Correction contents]

FIG. 14

[Procedure Amendment 5]

[Document name to be amended] Drawing

[Correction target item name] FIG.

[Correction method] Change

[Correction contents]

FIG.

[Procedure correction 6]

[Document name to be amended] Drawing

[Correction target item name] FIG.

[Correction method] Change

[Correction contents]

FIG. 16

Claims (12)

[Claims] 1. A first person image arranged at a predetermined position is memorized together with first contour information, and a second person image arranged at said predetermined position is memorized together with second contour information. ) A clothes image of a first person image placed at the predetermined position and wearing clothes is stored together with third contour information, and (d) based on the first contour information, the second contour information and the third contour information. A fitting simulation method in which the first person image and the clothes image are deformed by the above, and (e) the deformed clothes image is combined with the deformed first person image. 2. The step (c) comprises: (c-1) writing the first person image wearing the clothes in a first memory; (c-2) adding the first person image to the clothes image written in the first memory. 1
The fitting simulation method according to claim 1, wherein a part of the contour information is attached as the third contour information, and (c-3) the clothing image with the third contour information is extracted and written in the second memory. 3. The step (d) comprises: (d-1) transforming the first person image and the first contour information so that the first contour information matches the second contour information; -2) The clothing image is transformed so that the third contour information matches the transformed first contour information.
The fitting simulation method described. 4. (a) A basic person image and a plurality of clothes images corresponding to the poses of the basic person image are stored in advance, (b) Body type information representing the body type of the person being tried-on is stored, (c) at least one of the plurality of clothes images is selected, (d) the selected clothes image is combined with the basic person image, and (e) the combined image is transformed based on the body type information. ,
Try-on simulation method. 5. (a) A basic person image and a plurality of clothing images corresponding to the poses of the basic person image are stored in advance, (b) Body type information representing the body type of the person to be tried on is stored, (c) at least one of the plurality of clothes images is selected, (d) based on the body type information, the basic person image is deformed, and the deformed basic person image is dealt with, A fitting simulation method in which the selected clothing image is transformed, and (e) the transformed basic person image is combined with the transformed clothing image. 6. A basic man image is obtained by photographing a mannequin doll, and the clothes image is obtained by extracting a portion of the clothes from an image photographed by putting clothes on the mannequin doll. The fitting simulation method according to claim 5. 7. The fitting simulation method according to claim 5, wherein the body type information is contour information representing a part of a contour of the body of the fitting-on target person image. 8. The fitting simulation method according to claim 5, wherein the body type information includes body type information of a part of the person trying on and a body type information of another part of the person trying on estimated from the body type information. . 9. The fitting simulation method according to claim 5, wherein the deformation of the clothes image is a deformation for preventing the basic person image from protruding from the clothes image during the combining. 10. The fitting simulation method according to claim 5, wherein the deformation of the clothes image is such that a predetermined position of the clothes image is located at a corresponding position of the basic person image during the combining. 11. The fitting simulation method according to claim 5, wherein correspondence data representing a correspondence relationship between the clothing image and the basic person image is stored for the deformation of the clothing image. 12. The fitting simulation method according to claim 11, wherein the corresponding data is edited such as deleting, adding, and specifying the corresponding data.