KR20100002799A - Method for making three-dimentional model using color correction - Google Patents

Abstract

PURPOSE: A 3D model generating method using a color proofreading based on a standard color table is provided to generate a 3D model of accurate color by obtaining the image without color distortion. CONSTITUTION: A reference color table is detected from a reference color table section of a front/rear images of an object individual(S120). A color value of front/rear side of the reflections is corrected(S150). The standard color table region is removed from front/rear side of the reflections. A feature point coordinate is extracted from front/rear side of the reflections(S170). A 3D(Dimensional) texture is formed by matching a feature point coordinate corresponding to the image(S180).

Description

Method for Making Three-Dimentional Model using Color Correction

The present invention relates to a three-dimensional model generation method for generating a three-dimensional model using a still image photographed from various angles for facial diagnosis, but to a method for generating a three-dimensional model close to the actual color through color correction will be.

As science and technology develops, technologies that can measure the degree of health or abnormality by analyzing images of patients at a distance without facing doctors and patients directly are being developed.

For this purpose, the technology of acquiring image information and transmitting it without noise is important.However, in order to see the image and the doctor diagnoses the patient's condition, it is necessary to correct the distortion of the image such as camera shake or color change caused by lighting. It is also important to provide an image similar to viewing the patient directly in the field.

That is, there is a need to correct distorted geometric information and color change during imaging for image diagnosis. The shape of the subject may change due to camera shake due to hand movement. Especially, since the shape of the body is three-dimensional rather than a straight line, it is difficult to correct geometric information distortion.

A conventional technique related to image recognition and analysis is as follows.

First, a shape recognition device and method (Korean Patent Publication No. 2006-0119968, published on November 24, 2006) is a device and method for recognizing a face by capturing an image. There is a problem that the image can be distorted.

Next, a photographing system (Japanese Patent Laid-Open No. 2003-209849, 2003. 07. 25 publication) relates to a method of correcting a color channel from a reference image by installing a reflective surface at a lower end of a lid for opening and closing a lens. Although sensitive to color changes, there is a problem in that correction cannot be made by reflecting a condition of light projected on a real object.

In order to create a three-dimensional model, a plurality of planar images are required. Each planar image has a problem in that colors may vary depending on shooting conditions, specifically, time, place, and lighting. If the same part has a different color, the color may be uneven when the three-dimensional model is made, and there is a risk of incorrectly determining the abnormality. In addition, if the actual subject does not consider the curvature or shape of the face does not show the correct three-dimensional color, if the diagnosis based on this is a high possibility of misdiagnosis.

The present invention has been made to solve the above problems of the prior art, to obtain an image without color distortion by matching the color standards of a plurality of plane image, to obtain the depth information by matching feature points from the image of various angles It is an object of the present invention to provide a 3D model generation method using color correction to obtain a depth information of a face by irradiating structured light and to generate a 3D model of an accurate color using the same.

In order to solve the above problems, a three-dimensional model generation method using color correction according to the first aspect of the present invention includes a front image and a plurality of side images of a target person including a reference color table including one or more sub-color areas. In a first step of obtaining by using a camera, detecting a reference color table region in the front image and the side image and correcting the color values of the front image and the side image to match the color values of the reference color table used at the time of photographing. Step 2, a third step of removing the reference color table region from the front image and the side image, the color value is corrected, the eye and mouth in the front image and the side image from which the reference color table region is removed in the third step The feature point coordinates of the corresponding region are extracted, and the feature point coordinates corresponding to each other in the front image and the side image are extracted. In the fourth step of forming a three-dimensional texture by matching the feature point coordinates extracted from the front image and the side image in the fourth step, the spatial depth information is extracted, and then the depth information is combined with the feature point coordinates. And a sixth step of mapping the three-dimensional texture generated in the fourth step to the three-dimensional model generated in the fifth step.

Here, the sub color area includes a first color area of the edge portion and second to fifth color areas surrounded by the first color area.

In addition, the first color area is black, the second color area is blue, the third color area is white, the fourth color area is red, and the fifth color area is green.

The second step may include a first step of detecting a reference color table area and a sub color area in the front image and the side image acquired in the first step, and a second step of calculating a representative color value of each sub color area. And obtaining a correction matrix for converting a representative color value of each sub color area included in the reference color table area to correspond to a color value of each sub color area of the reference color table with respect to the front image and the side image. And a fourth process of calibrating color values of all pixels of the front image and the side image using the calibration matrix.

The representative color value in the second process may be a color value of each center coordinate detected after detecting the center coordinates of each sub color region in the front image and the side image, or each sub color region in the front image and the side image. The color average value of all pixels constituting the.

The calibration matrix is calculated by applying the following determinant for each sub color region.

Where R _cs , G _cs , and B _cs are RGB values for each sub color region of the reference color table, and t ₁₁ to t ₃₃ are elements of the correction matrix for the surface color, and R _os , G _os , and B _os are photographed. The representative color values, b ₁ to b ₃ , of each sub color area of the reference color table area detected in the image are elements of a correction matrix for the surrounding color.

The fourth process is characterized in that the color values of all the pixels of the front image and the side image are corrected by the following equation.

Where P '(x, y) is the color value of the pixel at x, y coordinates after calibration, P (x, y) is the color value of the pixel at x, y coordinates before calibration, and T is the calibration matrix .

In addition, a three-dimensional model generation method using a color correction according to a second aspect of the present invention for solving the above problems is a front image and a plurality of side surfaces of the target person including a reference color table including one or more sub-color areas In a first step of acquiring an image using a camera, front and side images are irradiated by irradiating structured light having a predetermined pattern on the target person at an angle spaced from the camera by a predetermined angle. A second step of obtaining a third step of detecting a reference color table region in the front image and the side image and correcting color values of the front image and the side image to match the color values of the reference color table used at the time of photographing; The reference color table region is removed from the front image and the side image acquired in the first and second steps. In the fourth and fourth steps, the feature point coordinates of the areas corresponding to the eyes and the mouth are extracted from the front image and the side image from which the reference color table region is removed, and the corresponding feature point coordinates are matched with each other in the front image and the side image. Extracting depth information of all pixels according to the degree of deformation of the structured light from the fifth image, the front image and the side image obtained in the second step of forming a three-dimensional texture, and extracted in the fifth step A sixth step of generating a three-dimensional model reflecting the depth information based on the feature point coordinates, and a seventh step of mapping the three-dimensional texture generated in the fifth step to the three-dimensional model generated in the sixth step; .

The structured light is irradiated toward the target person at a predetermined angle with a shooting direction of the camera.

The structured light has a plurality of straight patterns spaced side by side by a set interval.

Here, the fourth step is a first step of detecting the reference color table area and the sub color area in the front image and the side image obtained in the first step, the second process of calculating the representative color value of each sub color area And obtaining a correction matrix for converting a representative color value of each sub color area included in the reference color table area to correspond to a color value of each sub color area of the reference color table with respect to the front image and the side image. And a fourth process of calibrating color values of all pixels of the front image and the side image using the calibration matrix.

The representative color value in the second process may be a color value of each center coordinate detected after detecting the center coordinates of each sub color region in the front image and the side image, or each sub color region in the front image and the side image. The color average value of all pixels constituting the.

The calibration matrix is calculated by applying the following determinant for each sub color region.

Where R _cs , G _cs , and B _cs are RGB values for each sub color region of the reference color table, and t ₁₁ to t ₃₃ are elements of the correction matrix for the surface color, and R _os , G _os , and B _os are photographed. The representative color values, b ₁ to b ₃ , of each sub color area of the reference color table area detected in the image are elements of a correction matrix for the surrounding color.

In addition, the fourth process is characterized in that the color values of all the pixels of the front image and the side image are corrected by the following equation.

Where P '(x, y) is the color value of the pixel at x, y coordinates after calibration, P (x, y) is the color value of the pixel at x, y coordinates before calibration, and T is the calibration matrix .

The sixth step may include a first process of extracting depth information according to the degree of bending of the structured light from the front image and the side image from which the reference color table region is removed, and the first process based on the feature point coordinates. And a second process of generating a 3D model reflecting depth information of two extracted images.

The three-dimensional model generation method using the color correction according to the present invention configured as described above can obtain an image of the correct color value even when shooting in an open space rather than a closed space, 3 It is possible to obtain dimensional image information, and accurate matching is possible even in a curved curved area by using light source change information during 3D modeling.

In addition, by generating a three-dimensional model reflecting the depth information of the actual face curvature, it is possible to diagnose through the three-dimensional image with the correct color value and shape, there is less risk of error.

Hereinafter, with reference to the accompanying drawings will be described specific details and embodiments of the present invention.

First, when the terms are defined, the reference color table in the present invention means the actual reference color table used in the photographing step, and the reference color table region refers to a portion of the obtained image where the reference color table is photographed.

1 is a diagram generally illustrating elements for determining color.

Referring to FIG. 1, when light shines on an object, the color of the object is determined by various factors.

Various factors affect the reflection vector (R), the light source vector (L), the normal vector (N), the half vector (H), and the camera vector (V). When the color determination formula is made using these factors, Equation 1 is as follows.

Where k _a , k _d , and k _s are constants, L _a is the ambient color, L _d is the color of the surface, and L _s is the color of the light source.

In order to construct a stereoscopic model using a plurality of planar images for face diagnosis, it is necessary to correct color differences of the plurality of planar images.

Referring to [Equation 1], it can be seen that the factor that determines color is the multiplication of the surface color by the light source and the addition of the surrounding color if the reflection of the light source is excluded (K _s = 0).

[Equation 2] is a formula representing the relationship between the original color value and the changed color value in a determinant. Referring to [Equation 2], it can be seen that the change of the color of light can be expressed by the expression of addition and multiplication.

The color (R _c , G _c , B _c ) changed in [Equation 2] is multiplied by the original color (R _o , G _o , B _o ) by the color correction matrix by the light source, and the transform vector (b) by the surrounding color. ₁ , b ₂ , b _c ) It can be seen that the form.

Based on this basic concept, the present invention will be described in detail.

3A and 3B are diagrams illustrating the configuration of a system for photographing front and side images. 3A and 3B show a top view of the imaging system according to the invention.

3A and 3B, the reference color table 20 is positioned in front of the target person 10 to be perpendicular to the photographing direction of the camera 30, and the target person and the reference color table 20 are positioned by the camera 30. ) Together.

The camera 20 is positioned so that the image is photographed horizontally from the ground.

At this time, the beam projector 40 is installed toward the target person at a predetermined distance from the camera. The beam projector 40 is a device that irradiates structured light having a predetermined pattern toward a target person. In the first embodiment of the present invention, the three-dimensional model is generated without the beam projector 40. In the second embodiment of the present invention, the three-dimensional model is generated using the beam projector 40. Thus, the first embodiment of the present invention does not require the beam projector 40.

4 is a view showing a state in which the beam project irradiated to the face of the target person in accordance with the present invention.

In the present invention, as an example, the beam projector 40 irradiates a pattern having a plurality of straight lines spaced side by side by a set interval.

The reference color table 20 is positioned not to be inclined to be horizontal to the ground.

5 is a diagram illustrating an example of a reference color table according to the present invention.

Referring to FIG. 5, the reference color table 50 includes a plurality of sub color areas.

The sub color area includes, for example, a first color area 51 of an edge portion and second to fifth color areas 52 to 55 surrounded by the first color area. The number of regions other than the edge portion is not particularly limited, but is preferably set to three or more numbers including three primary colors of color for color correction.

Here, the first color area 51 is black (R = 0, G = 0, B = 0), the second color area 52 is blue (R = 0, G = 0, B = 255), The third color area 53 is white (R = 255, G = 255, B = 255), the fourth color area 54 is red (R = 255, G = 0, B = 0), and the fifth color area ( 55) can be set to green (R = 0, G = 255, B = 0).

The reference color table is composed of colors not related to the surrounding color, and is preferably made of a material having low reflection. Since the edge portion of the reference color table is black, it is preferable that the background is taken with a bright color when shooting.

2A is a flowchart illustrating a first embodiment of a method for generating a 3D model using color correction according to the present invention.

Referring to FIG. 2A, a first embodiment of a method of generating a 3D model using color correction according to the present invention will first be described. First, a front image and a plurality of front images of a target person including a reference color table including one or more sub-color areas are described. Side images are acquired using a camera (S110).

Here, the reference color table is provided at predetermined intervals around the face of the target person.

6 is a diagram illustrating a front image and a side image obtained by a camera according to the present invention.

Referring to FIG. 6, in the present invention, the reference color table is installed beside the lower end of the face, but is not limited thereto and may be installed at a position spaced apart from the face by a predetermined distance.

However, in this case, it is preferable that the target face is sufficiently spaced apart so as not to overlap in the horizontal and vertical directions.

After capturing the general front image and the side image and the front image and the side image to which the structured light is irradiated, the color values of the general front image and the side image should be corrected to match the actual color values. .

In detail, the reference color table region is detected from the front image and the side image, and color values of the front image and the side image are corrected to match the color values of the reference color table of the first step.

The color values in the actual reference color table are the values we already know. That is, in the example described above, the black areas have R = 0, G = 0, and B = 0, the blue areas have R = 0, G = 0, and B = 255, and the white areas have R = 255 and G. = 255, B = 255, red areas are R = 255, G = 0, B = 0, and green areas are R = 0, G = 255, B = 0.

Next, a reference color table area and the sub-color area are first found for color value correction (S120).

Various methods may be used to find the reference color table region and the sub color region in the front image and the side image.

For example, if the reference color table area is located in the fourth quadrant of the lower half as shown in Fig. 6, the lower half finds the two corner points closest to black from the right edge of the figure to the left, where the corner points are Harris Corner Detection (Harris Corner). An algorithm such as Detector can be used.

From the two corner points found, find the nearest black corner point in the left part, and determine it using the RGB threshold value.

The lower part of the threshold value is set to the black part to discriminate, and the corner point of each sub color area is found inside the black part.

Next, a representative color value of each sub color area is extracted (S130).

Here, the first embodiment of obtaining the representative color value of each sub color area is to detect the center coordinates of each sub color area and to set the color value of the center coordinates to the representative color value of the corresponding sub color area. In the edge portion of each sub-color area, color values of the center coordinates are set as the representative color values because neighboring areas and color values may not be clearly distinguished and mixed colors may be photographed to some extent.

In the second embodiment of obtaining a representative color value of the sub color area, the color values of all the pixels in each sub color area are summed, divided by the number of pixels, and the average color value is obtained. It is set as the representative color value. Using this process, all representative values of each sub color area of the reference color table area are obtained.

After the representative color values of the respective sub color areas are obtained as described above, the front image and the side surface are changed by the numerical values changed by comparing each color value of the sub color areas in the reference color table used above with each representative color value calculated above. Correct the color value of the image.

To this end, first, a calibration matrix for converting a representative color value of each sub color area included in the reference color table area to match a color value of each sub color area of the reference color table is obtained (S140). That is, a correction matrix for converting the color-distorted photographed image into the color values of the original reference color table is obtained.

The calibration matrix is basically obtained by using the relation of [Equation 3].

Here, R _cs , G _cs , and B _cs are RGB values for each sub color area of the reference color table used in actual shooting, and t ₁₁ to t ₃₃ are elements of a correction matrix for surface color, R _os , G _os , B _os is a representative color value for each sub color area of the reference color table area detected in the captured image, and b ₁ to b ₃ are elements of a correction matrix for the surrounding color.

The calibration matrix can be obtained by solving an equation created by substituting the color values of the respective sub color areas of the reference color table area into [Equation 3] as shown in FIG. 7.

7 is a diagram illustrating a determinant created using each sub color region. In FIG. 7, (a) is a blue color region, (b) a white color region, (c) a red color region, and (d) is an expression made by substituting the color values of the green color region.

FIG. 8 illustrates the determinant of FIG. 7 as one determinant.

In FIG. 8, the C matrix is color values of each sub color area in the reference color table, the T matrix is a calibration matrix, and the O matrix is color values of each sub color area in the reference color table area in the captured image.

Since the C matrix and the O matrix are known values, a calibration matrix T is obtained using the determinant of FIG. 8.

When the calibration matrix is obtained as described above, color values of all pixels of the front image and the side image are corrected using the calibration matrix (S150).

In this process, color correction is performed on all pixels of the front image and the side image by Equation 4 below.

Where P '(x, y) is the color value of the pixel at x, y coordinates after calibration, P (x, y) is the color value of the pixel at x, y coordinates before calibration, and T is the calibration matrix .

When the color correction of the front image and the side image is performed, the reference color table region is removed from the front image and the side image (S160). FIG. 9 is a diagram illustrating a reference color table region removed from a front image and a side image. The reference color table region is removed as shown in the right figure of FIG. 9.

Next, the feature point coordinates of the areas corresponding to the eyes, nose, and mouth are extracted from the front image and the side image from which the reference color table region is removed, and the feature point coordinates corresponding to each other in the front image and the side image are matched. Form a dimensional texture.

In this case, first, the reference color table region is removed from the front image and the side image, and the feature point coordinates are detected from the image from which the reference color table is removed (S170).

10 is a diagram illustrating feature points in a front image and a side image.

After extracting the feature point coordinates as shown in FIG. 10, the feature point coordinates corresponding to each other are matched with each other to form one three-dimensional texture (S180).

In this case, first, the spatial depth information is detected by matching the feature point coordinates extracted from the front image and the feature point coordinates extracted from the side image (S190).

Next, a model having three-dimensional geometric information is generated by combining extracted feature point coordinates and spatial depth information (S200).

Finally, the 3D texture generated in the step S180 is mapped to the 3D model to finally complete a color model having 3D geometric information (S210).

2B is a flowchart illustrating a second embodiment of the method of generating a 3D model using color correction according to the present invention.

Referring to FIG. 2B, a second embodiment of a method of generating a 3D model using color correction according to the present invention will first be described. First, a front image and a plurality of front images of a target person including a reference color table including one or more sub-color areas are described. Side images are acquired using a camera (S310).

Next, the front image and the side image are acquired using the camera by irradiating structured light having a predetermined pattern to the target person at an angle spaced by the set angle from the camera (S320).

Here, the matter regarding the reference color table is the same as in the first embodiment.

Next, the reference color table area and the sub color area are first found in the front image and the side image for color value correction (S330).

Next, a representative color value of each sub color area is calculated (S340).

Here, the same method as that of the first embodiment of the present invention is used to obtain the representative color value of each sub color region.

After the representative color values of each sub color area are obtained as described above, the front image and the side surface are changed by the changed numerical value by comparing each color value of the sub color area in the reference color table used in the photographing with each representative color value calculated above. Correct the color value of the image.

To this end, first, a calibration matrix for converting a representative color value of each sub color area included in the reference color table area to match a color value of each sub color area of the reference color table is obtained (S350). That is, a correction matrix for converting the color-distorted photographed image into the color values of the original reference color table is obtained.

The calibration matrix is obtained by using Equation 3, 7 and 8 above.

When the calibration matrix is obtained as described above, color values of all pixels of the front image and the side image are corrected using the calibration matrix (S360).

In this process, color correction is performed on all pixels of the front image and the side image by Equation 4 above.

When the color correction of the front image and the side image is performed, the reference color table region is removed from the front image and the side image (S370). That is, the reference color table region is removed as shown in the right figure of FIG.

When the color correction of the front image and the side image is performed, the feature point coordinates of the areas corresponding to the eyes, nose, and mouth are extracted from the color corrected front image and the side image, respectively, and the feature points corresponding to each other in the front image and the side image. Coordinates are matched to form one three-dimensional texture.

In this case, first, the reference color table region is removed from the front image and the side image, and the feature point coordinates are detected from the image from which the reference color table is removed (S380).

After extracting the feature point coordinates as shown in FIG. 10, the feature point coordinates corresponding to each other are matched with each other to form one three-dimensional texture (S390).

Next, depth information of all the pixels is extracted according to the degree of deformation of the structured light from the front image and the side image obtained in step S320 (S400).

When a constantly repeating linear pattern is irradiated to the face part of the target person, the straight line is bent along the contour of the face, causing curvature. Set the height of the part that appears in a straight line on the background as 0, and set the height considering the angle of the camera according to the degree of bending and the position compared to the straight part where the height is 0, so that the depth information of all pixels corresponding to the face part can be obtained. Calculate

Next, a model having three-dimensional geometric information reflecting the two depth information is generated based on the extracted feature point coordinates (S410).

Finally, the 3D texture generated in the step S390 is mapped to the 3D model to finally complete a color model having 3D geometric information (S420).

As described above, the method for generating a three-dimensional model using color correction according to the present invention has been described with reference to the illustrated drawings, but the present invention is not limited by the embodiments and drawings disclosed herein, but the scope of the technical idea is protected. It can be applied in

1 is a diagram generally showing elements for determining color;

Figure 2a is a flow chart showing a first embodiment of a three-dimensional model generation method using color correction according to the present invention,

2b is a flowchart showing a second embodiment of the method for generating a 3D model using color correction according to the present invention;

3A and 3B are diagrams illustrating the configuration of a system for photographing front and side images;

4 is a view showing a state that the beam project irradiated to the face of the person in accordance with the present invention,

5 is a diagram illustrating an example of a reference color table according to the present invention;

6 is a view showing a front image and a side image obtained by the camera according to the present invention;

7 is a diagram showing a determinant created using each sub-color area;

FIG. 8 illustrates the determinant of FIG. 7 as one determinant; FIG.

9 is a diagram illustrating a state in which a reference color table is removed from a front image and a side image;

10 is a diagram illustrating feature points in a front image and a side image.

<Explanation of symbols on main parts of the drawings>

10: target person

20: reference color table

30: camera

40: beam projector

Claims (19)

A first step of acquiring a front image and a plurality of side images of a target person including a reference color table including at least one sub color area by using a camera; Detecting a reference color table region in the front image and the side image and correcting color values of the front image and the side image so as to match the color values of the reference color table used at the time of photographing; Removing the reference color table area from the front image and the side image of which color values are corrected; In the third step, the feature point coordinates of the areas corresponding to the eyes and the mouth are extracted from the front image and the side image from which the reference color table region is removed, and the feature point coordinates corresponding to each other in the front image and the side image are matched. A fourth step of forming a three-dimensional texture; A fifth step of extracting spatial depth information by matching feature point coordinates extracted from the front image and the side image in the fourth step, and then combining the depth information with the feature point coordinates to generate a three-dimensional model; And And a sixth step of mapping the three-dimensional texture generated in the fourth step to the three-dimensional model generated in the fifth step. The method according to claim 1, And the sub color region comprises a first color region of an edge portion and second to fifth color regions surrounded by the first color region. The method according to claim 2, Wherein the first color area is black, the second color area is blue, the third color area is white, the fourth color area is red, and the fifth color area is green. The method of claim 1, wherein the second step A first process of detecting a reference color table region and a sub color region in the front image and the side image obtained in the first step; A second step of calculating a representative color value of each sub color area; A third process of obtaining a calibration matrix for converting a representative color value of each sub color area included in the reference color table area to correspond to a color value of each sub color area of the reference color table with respect to the front image and the side image; ; And And a fourth process of correcting color values of all the pixels of the front image and the side image using the correction matrix. The method according to claim 4, The representative color value in the second process is a three-dimensional model generation method using color correction, characterized in that the detected color coordinates of the center coordinates of each sub-color area in the front image and the side image. The method according to claim 4, In the second process, the representative color value is a color average value of all pixels constituting each sub-color area in the front image and the side image. The method according to claim 4, The correction matrix is a method of generating a three-dimensional model using color correction, characterized in that obtained by applying the following determinant for each sub-color area.

(Rcs, Gcs, and Bcs are RGB values for each sub-color area of the reference color table, t ₁₁ to t ₃₃ are elements of the correction matrix for the surface color, Ros, Gos, and Bos are reference values detected in the captured image. A representative color value for each sub color region of the color table region, b ₁ to b ₃ are elements of the correction matrix for the surrounding color) The method according to claim 4, In the fourth process, the color values of all the pixels of the front image and the side image are corrected by the following equation.

Where P '(x, y) is the color value of the pixel at x, y coordinates after calibration, P (x, y) is the color value of the pixel at x, y coordinates before calibration, T is the calibration matrix) A first step of acquiring a front image and a plurality of side images of a target person including a reference color table including at least one sub color area by using a camera; A second step of obtaining a front image and a side image using a camera by irradiating structured light having a predetermined pattern to the target person at an angle spaced from the camera by a predetermined angle; Detecting a reference color table region from the front image and the side image and correcting color values of the front image and the side image to match the color values of the reference color table used at the time of photographing; A fourth step of removing reference color table areas from the front image and the side image acquired in the first and second steps; The feature point coordinates of the areas corresponding to the eyes and mouth are extracted from the front image and the side image from which the reference color table region is removed in the fourth step, and the feature point coordinates corresponding to each other in the front image and the side image are matched. A fifth step of forming a texture; Extracting depth information of all pixels according to the degree of deformation of the structured light from the front image and the side image acquired in the second step, and reflecting the depth information based on the feature point coordinates extracted in the fifth step A sixth step of generating a model; And And a seventh step of mapping the three-dimensional texture generated in the fifth step to the three-dimensional model generated in the sixth step. The method according to claim 1, And the sub color region comprises a first color region of an edge portion and second to fifth color regions surrounded by the first color region. The method according to claim 10, Wherein the first color area is black, the second color area is blue, the third color area is white, the fourth color area is red, and the fifth color area is green. The method according to claim 9, The structured light is a three-dimensional model generation method using color correction characterized in that the irradiated toward the target person by a predetermined angle and the shooting direction of the camera. The method according to claim 9, The structured light has a three-dimensional model generation method using color correction, characterized in that it has a plurality of linear patterns spaced side by side by a set interval. The method of claim 9, wherein the third step A first process of detecting a reference color table region and a sub color region in the front image and the side image obtained in the first step; A second step of calculating a representative color value of each sub color area; A third process of obtaining a calibration matrix for converting a representative color value of each sub color area included in the reference color table area to correspond to a color value of each sub color area of the reference color table with respect to the front image and the side image; ; And And a fourth process of correcting color values of all the pixels of the front image and the side image using the correction matrix. The method according to claim 14, In the second process, the representative color value is a color value of each center coordinate detected after detecting the center coordinates of each sub-color area in the front image and the side image. The method according to claim 14, In the second process, the representative color value is a color average value of all pixels constituting each sub-color area in the front image and the side image. The method according to claim 14, The correction matrix is a method of generating a three-dimensional model using color correction, characterized in that obtained by applying the following determinant for each sub-color area.

(Rcs, Gcs, and Bcs are RGB values for each sub-color area of the reference color table, t ₁₁ to t ₃₃ are elements of the correction matrix for the surface color, Ros, Gos, and Bos are reference values detected in the captured image. A representative color value for each sub color region of the color table region, b ₁ to b ₃ are elements of the correction matrix for the surrounding color) The method according to claim 14, In the fourth process, the color values of all the pixels of the front image and the side image are corrected by the following equation.

Where P '(x, y) is the color value of the pixel at x, y coordinates after calibration, P (x, y) is the color value of the pixel at x, y coordinates before calibration, T is the calibration matrix) The method of claim 9, wherein the sixth step is Extracting depth information according to the degree of bending of the structured light from the front image and the side image from which the reference color table region is removed; And And a second process of generating a 3D model reflecting depth information of the two images extracted in the first process based on the feature point coordinates.

Images