JP6902780B2 - Makeup instruction device, makeup instruction program, and makeup instruction system - Google Patents

Description

The present invention relates to a make-up instruction device, a make-up instruction program, and a make-up instruction system for receiving make-up instruction.

Since makeup is very fashionable, various methods, cosmetics, tools, etc. are devised every day. In order to convey these methods, cosmetics, tools, etc. to users, make-up instruction is given in make-up classes and the like. In the makeup class, the students draw makeup according to the concept on the face chart, and after the students actually apply makeup to each other's face or to their own face, the students confirm the makeup performance. The general procedure is for a person to correct and show their makeup while explaining their intentions with words and gestures.

In addition to the make-up class, as a method for learning make-up techniques, a service that gives advice for making fashionable make-up and a device that assists make-up to bring the user closer to a desired image are known (for example, Patent Document 1). See).

In Patent Document 1, based on what is stored in advance by symbolizing the makeup procedure of an expert, the makeup procedure according to the user's wishes is displayed, or a face photograph for which makeup is desired is displayed as such a makeup procedure. A makeup advice device for displaying a simulation image or the like when the makeup is applied is disclosed.

Japanese Unexamined Patent Publication No. 2002-123585

In the make-up class, it is more practice for the students to make their own make-up corrections, but in order to accurately show the instructor's intentions, it was necessary for the instructor to demonstrate the corrections. This is because the makeup advice device of Patent Document 1 compares a user's face photograph taken in advance with the user's ideal face photograph and displays a makeup procedure derived based on the difference. Even if the makeup advice device of Patent Document 1 is used in the makeup class, it is not possible to confirm whether or not the makeup is performed as intended by the instructor during makeup.

The present invention has been made in view of the above problems, and is a make-up instruction device, a make-up instruction program, and a make-up instruction capable of accurately reading the position and shape of the make-up intended by the instructor to train the make-up. The purpose is to provide a system.

The characteristic configuration of the makeup instruction device according to the present invention for solving the above problems is
An imaging means that captures the user's face in real time,
A communication means that transmits a still image including at least a part of the user's face captured at a certain time by the imaging means to an external device, and receives a make-up instruction image indicating make-up instruction for the still image from the external device.
An alignment image generation means for generating an alignment image in which a part of components is reduced from the still image, and an alignment image generation means.
A compositing means for synthesizing these images with a user's real-time image captured by the imaging means so that the transmittance of the aligned image is larger than that of the make-up instruction image.
A display means for displaying a composite image by the composite means and
To have.

According to the make-up instruction device of this configuration, the component derived from the alignment image is displayed semi-transparently in the composite image, so that the user can overlap the component derived from the real-time image and the component derived from the alignment image. It is easy to align, and it is possible to accurately confirm the color of the components derived from the real-time image during makeup. In addition, since the transparency of the component derived from the alignment image is larger than the transparency of the component derived from the makeup instruction image, it is easy to visually recognize the mark line of the makeup instruction indicated by the component derived from the makeup instruction image. Become. Therefore, it is possible to accurately read the position and shape of the makeup intended by the instructor and train the makeup.

In the make-up instruction device according to the present invention
It is preferable that the compositing means synthesizes the alignment image semi-transparently with the real-time image of the user captured by the imaging means, and also synthesizes the make-up instruction image non-transparently.

According to the make-up instruction device of this configuration, since the components derived from the make-up instruction image are opaquely displayed, the mark line of the make-up instruction can be confirmed more clearly.

In the make-up instruction device according to the present invention
The make-up instruction image is an image in a vector format in which a relative position with respect to the still image is specified.
The synthesis means preferably positions the make-up instruction image with respect to the alignment image.

According to the make-up instruction device of this configuration, the position, shape, etc. of the component derived from the make-up instruction image, such as the mark line, do not deviate from the component derived from the alignment image in the composite image. It will be shown accurately. As a result, the user can accurately read the position and shape of the mark line indicated by the component derived from the makeup instruction image, and train the makeup in a state in which the result of the makeup can be visually recognized by looking at the component derived from the real-time image. Can be done.

In the make-up instruction device according to the present invention
The alignment image is preferably an image in which the contour of the user's face in the still image is extracted.

According to the make-up instruction device of this configuration, it becomes easier for the user to align the contour line, which is a component derived from the alignment image, so that the component derived from the real-time image overlaps. Further, since only the contour line is displayed as the component derived from the alignment image, it becomes easier to accurately confirm the color tone of the component derived from the real-time image during makeup.

In the make-up instruction device according to the present invention
The alignment image generation means preferably reduces low frequency components from the still image by any of a DoG filter, a Fourier transform, and a wavelet transform.

According to the make-up instruction device of this configuration, the contour of the user's face in the still image can be extracted as the aligned image by using the above-mentioned appropriate image processing.

In the make-up instruction device according to the present invention
The alignment image generation means generates the alignment image by removing a predetermined color component from the still image.
The synthesizing means uses an image obtained by removing a color component different from the predetermined color component from the image captured by the imaging means as the real-time image, and synthesizes the alignment image and the make-up instruction image. It is preferable to do so.

According to the make-up instruction device of this configuration, in the composite image, the component derived from the real-time image and the component derived from the aligned image can be easily identified by the difference in their respective shades.

In the make-up instruction device according to the present invention
It is preferable that the compositing means synthesizes the aligned image so that the transparency in the region including the compositing position of the make-up instruction image is larger than the transparency in the other region.

According to the make-up instruction device of this configuration, the alignment while looking at the composite image displayed on the display means is still easy, and the real-time image is around the component derived from the make-up instruction image in the composite image. It becomes easier to visually recognize the color of the components derived from.

In the make-up instruction device according to the present invention
It is preferable that the synthesis means uses a mirror image of each image as the real-time image, the alignment image, and the make-up instruction image.

According to the make-up instruction device of this configuration, the make-up instruction device can be used with a feeling of use similar to that of a mirror.

The characteristic structure of the makeup instruction program according to the present invention for solving the above problems is
A computer that controls a terminal having an imaging means, a communication means, and a display means.
A alignment image generation step of generating an alignment image in which a part of components is reduced from a still image including at least a part of the user's face imaged at a certain time by the imaging means.
A transmission / reception step of causing the communication means to transmit the still image to an external device and receive a make-up instruction image indicating make-up instruction for the still image from the external device.
A compositing step of synthesizing these images with a user's real-time image captured by the imaging means so that the transmittance of the aligned image is larger than that of the make-up instruction image.
A display step for displaying the composite image in the composite step on the display means,
Is to be executed.

According to the makeup instruction program of this configuration, the components derived from the alignment image are displayed semi-transparently in the display step, so that the user can overlap the components derived from the real-time image and the components derived from the alignment image. It is easy to align, and it is possible to accurately confirm the color of the components derived from the real-time image during makeup. In addition, since the transparency of the component derived from the alignment image is larger than the transparency of the component derived from the makeup instruction image, it is easy to visually recognize the mark line of the makeup instruction indicated by the component derived from the makeup instruction image. Become. Therefore, it is possible to accurately read the position and shape of the makeup intended by the instructor and train the makeup.

The characteristic configuration of the makeup instruction system according to the present invention for solving the above problems is
A make-up instruction system that includes a first terminal and a second terminal.
The first terminal is
An imaging means that captures the user's face in real time,
A first communication means for transmitting a still image including at least a part of a user's face imaged at a certain time by the image pickup means to the second terminal.
An alignment image generation means for generating an alignment image in which a part of components is reduced from the still image, and an alignment image generation means.
A compositing means for semi-transparently synthesizing the alignment image with a user's real-time image captured by the imaging means.
The first display means for displaying the composite image by the composite means and
Have,
The second terminal is
A second communication means for receiving the still image from the first terminal, and
A second display means for displaying the received still image, and
An input means for accepting input of makeup instruction for the still image and
A make-up instruction image generation means for generating a make-up instruction image from the above input,
Have,
The second communication means further transmits the make-up instruction image to the first terminal.
The first communication means further receives the make-up instruction image from the second terminal, and receives the make-up instruction image.
The synthesizing means is to synthesize the alignment image with the real-time image in a semi-transparent manner, and further synthesize the make-up instruction image so that the transmittance is smaller than that of the alignment image.

According to the make-up instruction system of this configuration, in the first terminal, the components derived from the aligned image are displayed semi-transparently in the composite image, so that the components derived from the real-time image and the components derived from the aligned image are displayed. It is easy for the user to align the colors so that they overlap, and it is possible to accurately confirm the color of the components derived from the real-time image during makeup. Further, in the first terminal, since the transmittance of the component derived from the alignment image is larger than the transmittance of the component derived from the make-up instruction image, the mark line of the make-up instruction indicated by the component derived from the make-up instruction image. Etc. are easy to see. Therefore, it is possible to accurately read the position and shape of the makeup intended by the instructor and train the makeup.

FIG. 1 is a system configuration diagram of a make-up instruction system according to an embodiment of the present invention. FIG. 2 is a block diagram showing the configuration of the first terminal. FIG. 3 is an explanatory diagram of various images used in the first terminal. FIG. 4 is a block diagram showing the configuration of the second terminal. FIG. 5 is an explanatory diagram for generating a make-up instruction image. FIG. 6 is a flowchart showing a control procedure in the first terminal. FIG. 7 is a flowchart showing a control procedure in the second terminal.

Hereinafter, embodiments relating to the make-up instruction system, the make-up instruction device, and the make-up instruction program according to the present invention will be described with reference to the drawings. The present invention is not intended to be limited to the configurations described in the embodiments and drawings described below.

<Makeup instruction system>
FIG. 1 is a system configuration diagram of a make-up instruction system 100 according to an embodiment of the present invention. The make-up instruction system 100 is configured so that the first terminal 1 and the second terminal 2 can communicate with each other via the router 3. The first terminal 1 is a terminal used by students in a make-up classroom or the like, and constitutes the make-up instruction device of the present invention. The second terminal 2 is a terminal used by an instructor in a make-up classroom or the like, and is a device used for inputting make-up instruction to the first terminal 1. For the first terminal 1 and the second terminal 2, for example, a tablet computer having a touch panel display, a smartphone, a PC, or the like can be used. In the following, a student who uses the first terminal 1 and an instructor who uses the second terminal 2 will be described as users of the respective terminals. In FIG. 1, the make-up instruction system 100 is configured to include three first terminals 1, but the make-up instruction system 100 may be configured to include at least one first terminal 1. Further, FIG. 1 shows a configuration in which the first terminal 1 and the second terminal 2 directly communicate with the same router 3 included in the LAN. For example, the first terminal 1 and the second terminal 2 have a configuration in which the first terminal 1 and the second terminal 2 communicate directly with the same router 3. It may be configured to communicate via the Internet 4.

<Terminal 1 (makeup instruction device)>
FIG. 2 is a block diagram showing the configuration of the first terminal 1. FIG. 3 is an explanatory diagram of various images used in the first terminal 1. The first terminal 1 includes an image pickup means 11, a display means 12a, a communication means 13, and a control unit 15, and further includes an input means 12b and a storage 14 as additional configurations.

The image pickup means 11 is a camera including an image pickup device such as a CCD that generates image data, and captures a user's face in real time. Here, real-time refers to the time point of every individual moment from before make-up to after make-up. Since the photographing means 11 can continuously acquire the user's image in real time during makeup, the user holds the makeup coating tool, attaches the coating portion on the face, and continuously captures images of a series of movements. Can be obtained at. By updating the image displayed by the display means 12a as needed using the images continuously acquired in this way, the user always confirms whether the image can be attached and operated according to the intended position and shape. can do. Further, as the real-time image of the user, the image as it is captured by the imaging means 11 may be used, but preferably, a mirror image obtained by flipping the image captured by the imaging means 11 left and right is used. The make-up instruction system 100 assumes a usage pattern in which various images are generated based on the user's image captured by the image pickup means 11, and the user performs make-up while looking at these images displayed on the display means 12a. Therefore, the mirror image of the image captured by the imaging means 11 is stored in the storage 14 as a real-time image, and this is used to generate another image, so that the makeup instruction system 100 is used with the same usability as a mirror. be able to.

The display means 12a is the first display means in the make-up instruction system 100, and is a display such as a liquid crystal display or an organic EL display used for displaying an image.

The input means 12b is a touch panel or the like that accepts input by the user, and it is preferable that the touch panel display 12 is configured together with the display means 12a.

The communication means 13 is the first communication means in the make-up instruction system 100, and is, for example, a wireless LAN module. The communication means 13 communicates with the second terminal 2 via the router 3.

The storage 14 is a storage for an HDD, SSD, etc., and stores the make instruction program of the present invention, which is a program for realizing the function as the first terminal 1, and is used for temporary storage of image data and the like. Be done.

The control unit 15 is composed of a CPU, a RAM, and the like, and realizes each function of the alignment image generation means 18 and the synthesis means 19 by reading the make instruction program recorded in the storage 14 into the RAM and executing the make instruction program in the CPU. Further, as an additional configuration, each function of the still image acquisition means 16 and the transmission / reception means 17 is realized.

The still image acquisition means 16 acquires the still image 101 in response to a user's instruction via the input means 12b. The still image 101 is image data captured by the imaging means 11 at the time of inputting an instruction by the user, and as shown in FIG. 3A, it is preferable that the entire face is captured, but at least the user It suffices to show the area you want to make, and not necessarily the entire face. The still image acquisition means 16 causes the display means 12a to display the image captured at the time of inputting the instruction by the user, and asks the user to confirm that the displayed image includes at least a part of the user's face. When the user confirms that the image is included, the image used for display may be acquired as the still image 101.

The transmission / reception means 17 is a functional block that controls transmission / reception of data via the communication means 13, and transfers the still image 101 acquired when the still image 101 is acquired by the still image acquisition means 16 to the second terminal 2. It transmits and receives the make-up instruction image 103 from the second terminal 2. As shown in FIG. 3C, the make-up instruction image 103 is an image such as a mark line indicating the position and shape of the make-up as the make-up instruction for the still image 101. For example, the relative position with respect to the still image 101 is designated. It is preferable that the image is in the vector format.

The alignment image generation means 18 generates the alignment image 102 by reducing some image components from the still image 101. In the generation of the alignment image 102 by the alignment image generation means 18, for example, the low-pass filter of the still image 101 is used by using a high-pass filter composed of a DoG filter, a Fourier transform, a wavelet transform, or the like alone or in combination of two or more. By reducing the frequency component, it is preferable to generate an alignment image 102 in which pixels to be edge portions are extracted from the still image 101 as shown in FIG. 3B. The still image 101 shown in FIG. 3 (a) has color information in all the pixels, but in the aligned image 102 in which the pixels to be the edge portions are extracted from the still image 101, the broken lines are shown in FIG. 3 (b). Only the indicated pixel and the pixels in the vicinity thereof have color information, and the other pixels are transparent pixels having no color information. In the still image 101, the contour line of the user's face is particularly the edge portion. Therefore, when the pixels to be the edge portion are extracted from the still image 101, the contour of the user's face in the still image 101 is extracted in the alignment image 102. It becomes the image that was made. Further, the alignment image 102 is preferably an image having the same size as the still image 101.

The synthesizing means 19 generates a synthesizing image 104 in which the alignment image 102 and the make-up instruction image 103 are combined with the real-time image of the user captured by the imaging means 11. The generated composite image 104 is displayed on the display means 12a. In the generation of the composite image 104 by the compositing means 19, these images are combined with the real-time image of the user captured by the imaging means 11 so that the transmittance of the alignment image 102 is larger than that of the make-up instruction image 103. In particular, it is preferable that the compositing means 19 synthesizes the alignment image 102 semi-transparently and the make-up instruction image 103 non-transparently with the real-time image of the user captured by the imaging means 11. By synthesizing in this way, as shown in FIG. 3D, in the composite image 104, the component 104b derived from the alignment image 102 is semi-transparently displayed on the component 104a derived from the real-time image, and further, the makeup is further formed. An image in which the component 104c derived from the instruction image 103 is opaquely displayed is displayed. Further, when the still image 101 and the alignment image 102 are images of the same size, and the makeup instruction image 103 is a vector format image in which the relative position with respect to the still image 101 is specified, the compositing means 19 is made. It is preferable to position the instruction image 103 with respect to the alignment image 102. By synthesizing in this way, the composite image 104 has a translucent component 104b derived from the alignment image 102 and an opaque component derived from the makeup instruction image 103, as shown in FIG. 3D. 104c will accurately indicate the position, shape, etc. as a mark line for makeup. On the other hand, since the real-time image is continuously acquired by the imaging means 11 and changes in conjunction with the movement of the user, the component 104c derived from the make-up instruction image 103 in the composite image 104 becomes the component 104a derived from the real-time image. On the other hand, the position, size, etc. may shift. However, the user moves back and forth, left and right, and the like so that the component 104a of the real-time image matches the component 104b of the semitransparent alignment image 102 included in the composite image 104 displayed on the display means 12a. The position and size of the opaque component 104c derived from the make-up instruction image 103 can be matched with the component 104a derived from the real-time image. As a result, the user of the first terminal 1 can accurately read the intended position and shape of the mark line shown by the make-up instruction image 103, and can visually recognize the result of the make-up by looking at the component 104a derived from the real-time image. You can train your makeup. In particular, when an image in which the contour of the user's face is extracted is used as the alignment image 102, the alignment image 102 does not have color information other than the contour and the like shown by the broken line in FIG. 3B. Therefore, in the composite image 104 of FIG. 3D, the contour portion and the like (component 104b) derived from the alignment image 102 and the opaque marker line and the like (component 104c) derived from the makeup instruction image 103 are excluded. In all other parts, the user can see the color of the real-time image as it is.

<Second terminal>
FIG. 4 is a block diagram showing the configuration of the second terminal 2. The second terminal 2 includes a display means 22a, an input means 22b, a communication means 23, and a control unit 25, and further includes a storage 24 as an additional configuration.

The display means 22a is a second display means in the make-up instruction system 100, and is a display such as a liquid crystal display or an organic EL display used for displaying an image. The display means 22a displays the still image 101 received from the first terminal 1.

The input means 22b is a touch panel or the like that accepts input by the user, and accepts input for makeup instruction. The input of the makeup instruction is, for example, an input of a drawing operation for designating a position on the screen using a touch panel or the like in a state where the still image 101 is displayed on the display means 22a. It is preferable that the display means 22a and the input means 22b form a touch panel display 22.

The communication means 23 is a second communication means in the make-up instruction system 100, and is, for example, a wireless LAN module. The communication means 23 communicates with the first terminal 1 via the router 3.

The storage 24 is a storage for an HDD, an SSD, or the like, and is used for temporarily storing image data and the like as well as storing a program for realizing the function as the second terminal 2.

The control unit 25 is composed of a CPU, a RAM, and the like, reads a program recorded in the storage 24 into the RAM, executes the program in the CPU, realizes the function of the make-up instruction image generation means 26, and further transmits and receives as an additional configuration. The function of the means 27 is realized.

The make-up instruction image generation means 26 generates the make-up instruction image 103 in response to the drawing operation input by the touch operation in the input means 22b. The make-up instruction image generation means 26 preferably has, for example, a function of generating an image in a vector format by using a known method. FIG. 5 is an explanatory diagram for generating a make-up instruction image. When the still image 101 is received from the first terminal 1, the second terminal 2 displays the still image 101 on the display means 22a as shown in FIG. 5A. As shown in FIG. 5B, an instructor who is a user of the second terminal 2 performs a drawing operation such as tracing the display means 22a on which the still image 101 is displayed with a finger 201 through the input means 22b. When the instruction of the position and shape of the make-up is input, the make-up instruction image generation means 26 generates the make-up instruction image 103 according to the drawing operation, and causes the display means 22a to display the generated make-up instruction image 103. At this time, the make-up instruction image generating means 26 associates the position where the drawing operation is performed with the position of the still image 101 displayed on the display means 22a, so that the make-up instruction image 103 includes the relative position information with respect to the still image 101. To generate. Therefore, even if a part of the still image 101 is enlarged and displayed by the display means 22a during the drawing operation as shown in FIG. 5 (b), the make-up after generation is shown as shown in FIG. 5 (c). The instruction image 103 does not deviate from the position and shape of the mark line of the make-up with respect to the still image 101 displayed in full screen on the display means 22a.

The transmission / reception means 27 is a functional block that controls transmission / reception of data via the communication means 23. A still image 101 is received from the first terminal 1, and a make-up instruction image 103 is generated by the make-up instruction image generation means 26. In this case, the make-up instruction image 103 is transmitted to the first terminal 1.

<Makeup instruction program>
The program that controls the first terminal 1 and the second terminal 2 will be described below.

FIG. 6 is a flowchart showing a control procedure in the first terminal 1. In the first terminal 1, by executing the program (makeup instruction program), the control unit 15 is controlled to repeat each process of steps S1 to S10 until the notification operation of the end of make-up is performed. First, in step S1, the imaging means 11 images the user's image, and the mirror image of the captured image is stored in the storage 14 as a real-time image. Next, in step S2, it is determined whether or not the operation instructing the acquisition of the still image has been input via the input means 12b. When the operation for instructing the acquisition of the still image is input (step S2: Yes), the real-time image stored in the storage in step S1 is acquired as the still image 101 and stored in the storage 14 (step S3). Further, the alignment image 102 is generated by reducing a part of the components from the still image 101 acquired in step S3 and stored in the storage 14 (step S4), and the generated alignment image 102 is stored in the communication means 13. Is transmitted to the second terminal 2 via (step S5). After transmitting the alignment image 102, it is determined whether or not the make-up instruction image 103 has been received from the second terminal 2 (step S6). When the make-up instruction image 103 is received from the second terminal 2 (step S6: Yes), the received make-up instruction image 103 is stored in the storage 14 (step S7). After that, the real-time image, the alignment image 102, and the makeup instruction image 103 are read out from the storage 14, and these images are combined with the real-time image so that the transparency of the alignment image 102 is larger than that of the makeup instruction image 103. Then, the composite image 104 is generated (step S8), and the generated composite image 104 is displayed on the display means 12a (step S9). After displaying the composite image 104 in step S9, it is determined whether or not the operation of notifying the end of make-up has been input by the user via the input means 12b (step S10). If the operation for notifying the end of make-up is not input (step S10: No), the process returns to step S1, and if the operation for notifying the end of make-up is input (step S10: Yes), the process ends. To do.

If the operation for instructing the acquisition of the still image is not input in step S2 (step S2: No), or if the make-up instruction image 103 is not received in step S6 (step S6: No), the process is processed. To step S8. Therefore, the alignment image 102 and the make-up instruction image 103 may not be stored in the storage 14 when the compositing process in step S8 is executed. In that case, the compositing is performed without using the image not stored in the storage 14. Execute the process.

Further, when the loop processing of steps S1 to S10 has already been repeatedly executed and the real-time image, the still image 101, the alignment image 102, and the makeup instruction image 103 are to be stored in the storage 14, the previous loop processing is performed. If these images are already stored in the storage 14, they are updated to the latest ones.

FIG. 7 is a flowchart showing a control procedure in the second terminal 2. In the second terminal 2, the control unit 25 is controlled to repeat each process of steps S11 to S16 until the notification operation of the end of the make-up instruction is performed by executing the program. First, in step S11, it is determined whether the communication means 23 has received the still image 101 from the first terminal 1 (step S11). When the still image 101 is not received from the first terminal 1 (step S11: No), the process of step S11 is repeated to wait for the reception of the still image 101. When the still image 101 is received from the first terminal 1 (step S11: Yes), the still image 101 is displayed on the display means 22a (step S12). Next, in step S13, it is determined whether or not a drawing operation indicating makeup instruction has been input via the input means 22b. When the drawing operation is not input (step S13: No), the process of step S13 is repeated to wait for the input of the drawing operation. When the drawing operation is input (step S13: Yes), the make-up instruction image 103 corresponding to the drawing operation is generated (step S14), and the generated make-up instruction image 103 is transmitted to the first terminal 1 via the communication means 23. (Step S15). After the make-up instruction image 103 is transmitted in step S15, it is determined whether or not the operation for notifying the end of the make-up instruction is input by the user via the input means 22b (step S16). If the operation for notifying the end of the makeup instruction is not input (step S16: No), the process is returned to step S11 to wait for the next still image 101 to be received, and the end of the makeup instruction is notified. When the operation is input (step S16: Yes), the process ends.

By executing the above program, the functions of the first terminal 1 and the second terminal 2 are realized.

<Another Embodiment>
Although the present invention has been described based on the above-described embodiment, it goes without saying that the present invention is not limited to the above-described embodiment. For example, as another embodiment, the following modification can be implemented.

In the above embodiment, the alignment image generation means 18 generates the alignment image 102 by reducing the low frequency component of the still image 101 by using at least one of a DoG filter, a Fourier transform, and a wavelet transform. However, in the makeup instruction system 100 according to the present invention, the alignment image 102 may be generated by another method. For example, the alignment image generation means 18 removes or reduces a predetermined color component, for example, the R component of the red (R), green (G), and blue (B) color components of the still image 101. The combined image 102 may be generated. In this case, the synthesizing means 19 generates an image in which a color component different from a predetermined color component, for example, a G component or a B component is removed or reduced from the image captured by the imaging means 11, and this is displayed in real time. It is preferable to use it as an image to generate a composite image 104. By using the image from which some color components are removed or reduced as the real-time image and the alignment image 102, the user can perform the alignment while viewing the composite image 104 displayed on the display means 12a. The component 104a derived from the image 102 and the component 104b derived from the aligned image 102 can be easily distinguished.

Further, in the make-up instruction system 100 according to the present invention, when the composite image 104 is generated by the synthesis means 19, a constant transmittance may be used for the entire alignment image 102, but the alignment image 102 may be used in a part of the region. You may increase the transmittance of. For example, the transparency of the alignment image 102 in the region including the composite position such as the mark line of the makeup shown by the makeup instruction image 103 may be larger than the transparency in the other region. With such a configuration, it is still easy to align while looking at the composite image 104 displayed on the display means 12a, and in the composite image 104, around the mark line derived from the makeup instruction image 103, It becomes easier to visually recognize the color of the components derived from the real-time image. Alternatively, the transmittance of the alignment image 102 at the position where the user touches the input means 12b, which is a touch panel, may be configured to be larger than the transmittance in other regions.

The present invention can be suitably used as a make-up instruction device, a make-up instruction program, and a make-up instruction system capable of accurately reading the position and shape of the make-up intended by the instructor during make-up to train the make-up. ..

1 First terminal (makeup instruction device)
2 Second terminal 12a Display means (first display means)
13 Communication means (first communication means)
18 Alignment image generation means 19 Compositing means 22a Display means (second display means)
22b Input means 23 Communication means (second communication means)
26 Makeup instruction image generation means 100 Makeup instruction system 101 Still image 102 Alignment image 103 Makeup instruction image 104 Composite image

Claims (9)

An imaging means that captures the user's face in real time,
A communication means that transmits a still image including at least a part of the user's face captured at a certain time by the imaging means to an external device, and receives a make-up instruction image indicating make-up instruction for the still image from the external device.
An alignment image generation means for generating an alignment image in which a part of components is reduced from the still image, and an alignment image generation means.
Wherein as the transmittance of the alignment images than makeup guidance image increases, users of these images continuously imaged into the make by the imaging unit, an image which changes with the movement of the user Compositing method to synthesize with real-time image of
A display means for displaying a composite image by the composite means and
Have,
The make-up instruction image is an image of a mark line showing the position and shape of the make-up.
The compositing means is such that the transmittance of the aligned image in the region including the composite position of the mark line indicated by the make-up instruction image is larger than the transmittance of the aligned image in the other region. A make-up instruction device that synthesizes the alignment image. The make-up instruction device according to claim 1, wherein the synthesizing means synthesizes the alignment image semi-transparently with a real-time image of a user imaged by the imaging means, and also synthesizes the make-up instruction image opaquely. The make-up instruction image is an image in a vector format in which a relative position with respect to the still image is specified.
The make-up instruction device according to claim 1 or 2, wherein the synthesis means positions the make-up instruction image with respect to the alignment image. The make-up instruction device according to any one of claims 1 to 3, wherein the alignment image is an image obtained by extracting the contour of the user's face in the still image. The make-up instruction device according to claim 4, wherein the alignment image generation means reduces low-frequency components from the still image by any of a DoG filter, a Fourier transform, and a wavelet transform. The alignment image generation means generates the alignment image by removing a predetermined color component from the still image.
The synthesizing means uses an image obtained by removing a color component different from the predetermined color component from the image captured by the imaging means as the real-time image, and synthesizes the alignment image and the make-up instruction image. The make-up instruction device according to any one of claims 1 to 3. The make-up instruction device according to any one of claims 1 to 6, wherein the synthesizing means uses a mirror image of each image as the real-time image, the alignment image, and the make-up instruction image. A computer that controls a terminal having an imaging means, a communication means, and a display means.
A alignment image generation step of generating an alignment image in which a part of components is reduced from a still image including at least a part of the user's face imaged at a certain time by the imaging means.
A transmission / reception step of causing the communication means to transmit the still image to an external device and receive a make-up instruction image indicating make-up instruction for the still image from the external device.
Wherein as the transmittance of the alignment images than makeup guidance image increases, users of these images continuously imaged into the make by the imaging unit, an image which changes with the movement of the user Compositing step to synthesize with real-time image of
A display step for displaying the composite image in the composite step on the display means,
To run ,
The make-up instruction image is an image of a mark line showing the position and shape of the make-up.
In the synthesis step, the transmittance of the aligned image in the region including the composite position of the mark line indicated by the make-up instruction image is larger than the transmittance of the aligned image in the other region. A make-up instruction program that causes the computer to synthesize the alignment image. A make-up instruction system that includes a first terminal and a second terminal.
The first terminal is
An imaging means that captures the user's face in real time,
A first communication means for transmitting a still image including at least a part of a user's face imaged at a certain time by the image pickup means to the second terminal.
An alignment image generation means for generating an alignment image in which a part of components is reduced from the still image, and an alignment image generation means.
A compositing means for semi-transparently synthesizing the alignment image with a user's real-time image, which is an image continuously captured during make-up by the imaging means and changes in accordance with the user's movement.
The first display means for displaying the composite image by the composite means and
Have,
The second terminal is
A second communication means for receiving the still image from the first terminal, and
A second display means for displaying the received still image, and
An input means for accepting input of makeup instruction for the still image and
A make-up instruction image generation means for generating a make-up instruction image from the above input,
Have,
The second communication means further transmits the make-up instruction image to the first terminal.
The first communication means further receives the make-up instruction image from the second terminal, and receives the make-up instruction image.
The synthesizing means synthesizes the alignment image with the real-time image in a semi-transparent manner, and further synthesizes the make-up instruction image so that the transmittance is smaller than that of the alignment image .
The make-up instruction image is an image of a mark line showing the position and shape of the make-up.
The compositing means is such that the transmittance of the aligned image in the region including the composite position of the mark line indicated by the make-up instruction image is larger than the transmittance of the aligned image in the other region. A makeup instruction system that synthesizes the alignment images.

Images