JP2021099750A - Method for adjusting wrinkles or blemishes in skin image - Google Patents

Abstract

To provide a method for adjusting wrinkles or blemishes in a skin image.SOLUTION: There is provided a method for adjusting wrinkles or blemishes in a skin image. The method includes the steps of: acquiring a skin image which has wrinkles or blemishes; acquiring a luminance profile of a region with wrinkles or blemishes and a luminance profile obtained by performing smoothing processing on the luminance profile A from the region with wrinkles or blemishes in the skin image; acquiring a corrected luminance profile M for the region with wrinkles or blemishes by using the luminance profiles; and replacing the luminance of the region with wrinkles or blemishes by the luminance of the corrected luminance profile M.SELECTED DRAWING: None

Description

The present invention relates to a method for adjusting wrinkles or stains on a skin image.

The face image may be processed to make the skin color, stains, wrinkles, etc. of the face inconspicuous in order to make a face photo that gives a good impression, or to simulate the face after surgery such as make-up and cosmetic shaping. is there. On the contrary, in order to predict how one's face will change in the future, a face image with emphasized spots and wrinkles may be created. By using these processed facial images, for example, beauty counseling can be performed while simulating the skin condition in the future or after surgery.

The nasolabial fold (nasolabial fold) is easy to pay attention to when observing changes in the skin due to aging. The nasolabial fold is a groove extending from the end of the nasal wing of the face to the end of the corner of the mouth. Nasolabial folds are usually less noticeable when young, but become deeper with age as the surrounding skin sags and changes in the skeleton. The depth of the nasolabial fold greatly affects the age of appearance.

Patent Document 1 describes that a wrinkle-free face image is obtained by cutting out a wrinkle portion from the captured face image and then smoothing the remaining image. Patent Documents 2 and 3 describe that wrinkles and stain components are removed by filtering the brightness of a predetermined skin region of a facial image.

Japanese Unexamined Patent Publication No. 2002-304619 Japanese Unexamined Patent Publication No. 2004-234571 Japanese Unexamined Patent Publication No. 2006-53859

When processing a face image, it is preferable that the image is modified so that the processed image is not known. However, when correcting a large facial groove such as a nasolabial fold, the correction may be insufficient or the boundary between the corrected part and the periphery may become unnatural. Therefore, it is desired to correct wrinkles and stains on the facial image so that the corrected portion is difficult to understand and the corrected skin looks more natural.

The present invention provides a method for adjusting wrinkles or blemishes in a skin image, which makes it possible to create a skin image in which wrinkles or blemishes are reduced or emphasized with a more natural appearance. The present invention uses the original brightness profile of a wrinkle or spot area on a skin image and a smoothed brightness profile to create masking data for the wrinkle or spot area, which is then obtained. By masking the wrinkle or spot area of the original skin image with the masking data, it is possible to create a skin image in which wrinkles or spots are reduced or emphasized with a more natural appearance.

Therefore, the present invention is a method for adjusting wrinkles or blemishes on a skin image.
Obtaining skin images with wrinkles or spots;
Obtaining the following A and B from the region having wrinkles or stains in the skin image A: Luminance profile of the region having wrinkles or stains B: Luminance profile obtained by smoothing the luminance profile A;
Obtaining the modified luminance profile M for the region having the wrinkles or stains by the following equation (1) M (x, y) = A (x, y) + α {B (x, y) -2 × A ( x, y)} (1)
((X, y) represents the coordinates corresponding to the skin image, and α represents a positive or negative constant);
Replacing the brightness of the wrinkled or spotted area with the brightness of the modified brightness profile M,
Provide methods, including.
The present invention also provides a method for creating an aged skin image, which comprises creating a skin image in which wrinkles or stains are emphasized by using the method for adjusting wrinkles or stains.
The present invention also provides a method for creating a skin image with improved wrinkles or stains, which comprises creating a skin image with reduced wrinkles or stains using the method for adjusting wrinkles or stains.
The present invention also provides a method for predicting skin after improvement of wrinkles or stains, using the skin image with improved wrinkles or stains.
The present invention also provides an apparatus for carrying out any of the above-mentioned methods.
The present invention also provides a program for carrying out any of the methods described above.

According to the present invention, wrinkles or stains such as nasolabial folds on the skin image can be reduced or emphasized so that the boundary between the corrected portion and the periphery does not look unnatural. According to the present invention, it is possible to create a skin image in which wrinkles or spots are reduced or emphasized with a more natural appearance.

The flowchart which shows the process of the adjustment method of a wrinkle or a stain. Outline of the procedure for acquiring the brightness profile and the smoothed brightness profile. Conceptual diagram of brightness gradation processing. A conceptual diagram showing the change in the brightness of the wrinkle area before and after the gradation processing. The conceptual diagram which shows one Embodiment of the apparatus for carrying out the method of adjusting a wrinkle or a stain which concerns on this invention. Face image after nasolabial fold adjustment processing. Left: Face image before processing, Center: Face image with wrinkle reduction processing, Right: Face image with wrinkle enhancement processing.

Hereinafter, aspects of the present invention will be described in detail with reference to the drawings. In each of the figures below, the same reference numerals represent the same or equivalent components.

[1. How to adjust wrinkles or stains]
In one aspect, the present invention provides a method for adjusting wrinkles or blemishes on a skin image. FIG. 1 is a flowchart showing a process of a method for adjusting wrinkles or stains (hereinafter, also referred to as the present method) in a skin image according to the present invention. This method basically includes a brightness profile acquisition step (S1), a smoothing brightness profile acquisition step (S2), a correction brightness profile creation step (S3), and a correction skin image creation step (S4). If necessary, the method may include a skin image acquisition step (S0) for obtaining a skin image to be corrected. Next, each of these steps will be described in detail.

(1-1. Acquisition of skin image)
In the skin image acquisition step (S0), a human skin image is acquired. The skin image obtained here may be an image including the skin, and examples thereof include an image of the skin such as a face, neck, arms, hands, legs, legs, and trunk, and a face image is preferable. The face image is preferably a front face image, but may be an image of an oblique face or a profile, or an image in which a part of the front face, the oblique face, or the profile is missing.

The skin image can be obtained by a general image acquisition means, for example, taking a picture with a camera. For example, the skin image may be an image taken by a camera or the like, or may be data obtained by scanning a photograph, a film, or the like. Further, the skin image may be a color image or a grayscale image. The obtained skin image is converted into data in a computer-readable format for the luminance profile acquisition step (S1) described later, if necessary. For example, the skin image may be acquired as an arbitrary image file such as a JPEG (Joint Photographic Experts Group) format or a BMP (Bitmap image) format, or may be acquired as data enumerating the brightness information of each pixel. Good. The data format of the skin image used in this method is not particularly limited.

The acquired skin image may be corrected. For example, when the skin image is a face image and the face on the image is tilted to the left or right, the image may be corrected so that the tilt is eliminated and the face stands upright.

Next, in the skin image, a region having wrinkles or stains (hereinafter, also referred to as a wrinkle / stain region) to be adjusted by this method is specified. There is no limit to the size and type of wrinkles or stains to be adjusted by this method. Examples of wrinkles include fine wrinkles, large wrinkles, and spinal lines, and examples of spots include darkening spots (black spots, freckles, chloasma, and pigmentation due to aging and inflammation). Examples include whitening spots (white spots, etc.), red wrinkles, discoloration of the skin due to scars, and the like. The wrinkle / stain region refers to an region that includes not only the wrinkle or stain portion itself to be adjusted by this method but also the periphery thereof. For example, the wrinkle / stain region surrounds the wrinkle or stain on the skin image and corresponds to a region that appears discolored (for example, darker or brighter) than the surrounding area, and the wrinkle or stain portion and its surroundings. The area on the including skin image.

As a method for identifying the wrinkle / stain region, any method for detecting wrinkles or stains on the skin image can be used, and the method is not particularly limited. As an example of the method of identifying the wrinkle / stain region, a method of visually identifying the wrinkle / stain region from the image; the face image is binarized, and the wrinkle / stain region is detected based on the binarized image. Method (for example, Japanese Patent Application Laid-Open No. 2014-219781, Japanese Patent Application Laid-Open No. 2015-64823); Method for detecting wrinkle / stain region based on the value of brightness of face image (for example, Japanese Patent Application Laid-Open No. 2016-22093) A method for obtaining the gradient intensity (wrinkle intensity) and gradient histogram (wrinkle direction) of each pixel of a gray scale image of a face (for example, Japanese Patent Application Laid-Open No. 2012-53813); based on facial feature points extracted from the facial image. A method of measuring the shape of facial grooves such as creases and wrinkles at the corners of the eyes by setting a measurement range and tracking the darkest part of the difference image between the pixel of interest and the average pixel within the measurement range (for example). Japanese Patent Application Laid-Open No. 2006-81846), and the like. Of these, from the viewpoint of simplicity, a method of visually identifying the wrinkle / stain region on the image is preferable. For example, when visually identifying a wrinkle / stain region, pointing is performed while visually determining a region where the skin color looks darker than the surrounding skin centered on the wrinkle or stain portion on the skin image as the wrinkle / stain region. The position of the wrinkle / stain area on the skin image can be input using a device or the like. Such a procedure for inputting a position on an image can be performed using general image processing software (for example, image J [imagej.nih.gov/ij/]).

(1-2. Acquisition of brightness profile)
In this method, the luminance profile of the wrinkle / stain region identified above is acquired (step S1), the smoothed luminance profile is acquired using it (step S2), and then the modified luminance profile is created. (Step S3), then the skin image is modified using the modified luminance profile (step S4). Hereinafter, this method will be described by taking the case of adjusting wrinkles as an example. However, the same procedure can be applied to the adjustment of stains.

In step S1, a brightness profile for a wrinkled region (for example, the wrinkled region described above) on the skin image is acquired. More specifically, the luminance information may be collected from all the pixels included in the wrinkle region and acquired as the luminance profile of the wrinkle region. Next, those luminance profiles are subjected to a smoothing process, and the obtained data is acquired as a smoothed luminance profile for the wrinkle region (step S2). FIG. 2 illustrates an outline of the procedure for acquiring the luminance profile and the smoothed luminance profile in this method. FIG. 2A is a schematic view showing a wrinkle region including a face image and a nasolabial fold. The area shown in gray is the wrinkle area, and the dotted line in it is the wrinkle (nasolabial fold) part. FIG. 2B is an enlarged view of the wrinkle region of FIG. 2A. FIG. 2C shows the luminance value of the wrinkle region along the line XX'that connects the two ends of the wrinkle region and is orthogonal to the nasolabial fold in FIG. 2B. The nasolabial fold is located at the point where the luminance value is minimized in FIG. 2C. By performing a smoothing process on the luminance value data obtained along the line XX', a smoothed luminance value (dotted line) as shown in FIG. 2D can be obtained. The obtained smoothing data may be collected and acquired as a smoothing luminance profile of the wrinkle region. Examples of the smoothing process include a smoothing process using a filter. As the filter, an average value filter, a Gaussian filter and the like are preferably used. The kernel size of the filter is preferably 1/10 to 10 times the data length to be smoothed (that is, the number of pixels L included in XX').

(1-3. Creation of modified brightness profile)
Next, a modified luminance profile is created using the obtained luminance profile of the wrinkle region and the smoothed luminance profile (step S3). More specifically, the corrected luminance profile M is obtained from the luminance profile and the smoothed luminance profile of the wrinkle region based on the following equation (1):
M (x, y) = A (x, y) + α {B (x, y) -2 x A (x, y)} (1)
here,
(X, y) represents the coordinates on the skin image.
A (x, y) and B (x, y) represent the luminance profile and the smoothed luminance profile of the wrinkle region at the coordinates (x, y), respectively.
α represents a positive or negative constant.

In this method, when it is desired to reduce wrinkles, α is set to a positive value in the equation (1), and when it is desired to emphasize wrinkles, α is set to a negative value in the equation (1). The value of α can be set arbitrarily, but when α is positive, α is preferably 0.1 to 3.0, and when α is negative, α is −0.1 to -1. .5 is preferable. When adjusting stains, if α is set to a positive value in equation (1), dark areas can be brightened, so blackening stains (mole, freckles, chloasma, pigmentation, etc.) are reduced. , Whitening spots (white spots, etc.) are emphasized. Conversely, if α is set to a negative value, blackening stains are emphasized and whitening stains are reduced.

(1-4. Creation of modified skin image)
The obtained corrected brightness profile M is replaced with the brightness of the wrinkle region of the original skin image to create a corrected skin image (step S4). In other words, the brightness value of the wrinkle region of the original skin image is replaced with the brightness value of the corresponding coordinates in the modified brightness profile M. The obtained modified skin image is a skin image adjusted so that wrinkles are reduced or emphasized.

(1-5. Gradation processing)
In the modified skin image, if the boundary portion of the wrinkle region replaced with the modified luminance profile M has an unnatural appearance, in this method, the wrinkle region to which the modified luminance profile M is applied (that is, the wrinkle region) A brightness gradation is applied to the area on the corresponding corrected skin image (hereinafter, also referred to as the corrected wrinkle area). That is, if the modified brightness profile M is simply applied to the wrinkle region, the brightness changes abruptly at the boundary portion between the wrinkle region and the periphery, so that the modified skin image tends to have an unnatural appearance. Therefore, in the corrected wrinkle region, from the inside to the end of the region, [brightness of the corrected brightness profile M: brightness of the wrinkle region of the original skin image] = 100%: 0% → 0%: 100%. By applying a gradation to the brightness of the corrected wrinkle area so that it changes to, the unnatural boundary part does not appear in the corrected skin image. The gradation is preferably a linear gradation, but is not particularly limited.

FIG. 3 is a conceptual diagram of luminance gradation processing. In the figure, the horizontal axis represents the pixels of the skin image, and the vertical axis represents the ratio of the brightness value of the modified brightness profile M to the brightness value of the pixels. The "edge" indicates the end of the corrected wrinkle region, and the right side thereof is the corrected wrinkle region. The brightness of the corrected wrinkle area before the gradation processing is represented by "before", and the brightness of the corrected wrinkle area after the gradation processing is represented by "after". The part to which the gradation processing is applied is shown as an "edge part" in the figure. The range of the edge portion can be arbitrarily set between the range from the end portion of the corrected wrinkle region to the wrinkle portion. For example, the entire range from the end portion to the wrinkle portion of the corrected wrinkle region, or the range from the end portion to the midpoint between the end portion and the wrinkle portion can be set as the edge portion. Alternatively, the gradation is in the range of 1/5 to 1/2 of the number of pixels L included in the line XX'including the end of the correction wrinkle region along the above-mentioned arbitrary line XX'. Can be applied. The position of the wrinkle portion in the corrected wrinkle region may be determined based on the position of the wrinkle portion visually detected from the original skin image, or the brightness profile of the wrinkle region of the original skin image acquired in step S1. It can be decided based on.

FIG. 4 is a conceptual diagram showing a change in the brightness of the corrected wrinkle region before and after the gradation processing. The region of 100% luminance derived from the modified luminance profile M is represented by white, the region of 0% is represented by black, and the region between them is represented by gray. The corrected wrinkle area before and after the gradation processing (Before) and after the processing (After) are both surrounded by a black area, but after the processing, a gradation is added to the brightness of the outer edge of the corrected wrinkle area. The gradation processing makes it possible to create a corrected skin image with a more natural appearance by blurring the boundary between the corrected wrinkle area and its surroundings on the corrected skin image.

(1-6. Correction of other image information)
Further, the corrected skin image may have image information other than the brightness in the wrinkle region, for example, color information (R, G, B), brightness (Y), and the like corrected. In particular, in the case of spot adjustment, it is preferable to create a corrected skin image including correction of color information (R, G, B) in addition to the corrected luminance profile M.

The correction of the color information (R, G, B) is described in 1-2. ~ 1-4. It can be done according to the procedure of. More specifically, only the color information of each of R, G, and B is extracted from all the pixels included in the wrinkle region, and a color profile (R profile, G profile, and B profile, respectively) is created (step S1'. ). Next, for each of the R profile, G profile, and B profile, the above 1-2. The smoothed R profile, G profile, and B profile are created by performing the smoothing process in the same procedure as in (Step S2'), and the smoothed profiles are used in the above 1-3. A modified R profile, a modified G profile, and a modified B profile are created by the same procedure as in (Step S3'). At this time, α in the equation (1) may be a positive value when the color of the region is to be close to white, and a negative value when the color of the region is to be close to black. The numerical range may be the same as above. These modified profiles can be described in 1-4. By substituting the RGB information of the original skin image according to the procedure of (step S4'), a corrected skin image including color correction can be created (step S4').

When correcting the brightness (Y), a Y profile is created from the following formula (2) using the above R profile, G profile, and B profile.
Y = 0.299 × R + 0.587 × G + 0.114 × B (2)
Using the obtained Y profile, the above-mentioned 1-2. ~ 1-4. Create a modified Y profile according to the procedure in. At this time, α in the equation (1) may be a positive value when the region is to be brightened, and a negative value when the region is to be darkened. Just do it.

Cr and Cb represent a red color difference signal and a blue color difference signal, respectively, and Cr and Cb can be obtained from RGB according to the following equations (3) and (4).
Cr = 0.713 × (RY)
= 0.500 x R-0.419 x G-0.08 x B (3)
Cb = 0.564 × (BY)
= -0.169 x R-0.331 x G + 0.500 x B (4)
By replacing the Cr, Cb and the modified Y profile calculated from the formulas (3) and (4) with the brightness information of the original skin image, the modified YCbCr can be obtained. Further, the RGB profile can be obtained from YCbCr according to the following formulas (5) to (7), and a modified skin image can be created.
R = Y + 1.402 × Cr (5)
G = Y-0.3444136 × Cb-0.714136 × Cr (6)
B = Y + 1.772 × Cb (7)

Further, if necessary, the above 1-5. The gradation processing for the color information (R, G, B) or the brightness (Y) may be performed according to the procedure of.

[2. Equipment, programs]
In a further aspect, the present invention provides an apparatus and a program for carrying out the method for adjusting wrinkles or stains in a skin image according to the present invention described above.

FIG. 5 is a conceptual diagram of an embodiment of a configuration of a device (hereinafter, also referred to as a device of the present invention, or simply a device) for carrying out a method for adjusting wrinkles or stains in a skin image according to the present invention. The device 1 of the present invention shown in FIG. 5 includes a control unit 10, an operation unit 20, an output unit 30, and may further include a skin image acquisition unit 40. However, the configuration of the device 1 is not limited to the contents shown in FIG.

The control unit 10 includes one or more computers (computers), which include a CPU (Central Processing Unit) 11, a memory 12, an input / output interface (I / F) 13 and the like as needed. Examples of the CPU 11 include a general CPU, an integrated circuit (ASIC) for a specific application, a DSP (Digital Signal Processor), a GPU (Graphics Processing Unit), and the like. Examples of the memory 12 include a RAM (Random Access Memory), a ROM (Read Only Memory), and an auxiliary storage device (hard disk, etc.). The input / output I / F 13 is connected to the operation unit 20 and the output unit 30, and further to the skin image acquisition unit 40, if present. Further, the control unit 10 may be connected to other devices such as an external medium and an external computer (host computer or the like), in which case the control unit 10 may include a communication unit 14. For example, the communication unit 14 can be used when directly receiving a skin image data file from an external medium, an external computer, or the like, or when transmitting a processing result by the control unit to an external media or an external computer.

The control unit 10 receives an operator's command from the operation unit 20, captures skin image data from the skin image acquisition unit 40, and processes a skin image according to this method (acquisition of wrinkle / stain area, brightness profile, smoothing brightness). Acquisition of profile and modified brightness profile, creation of masking area, creation of modified skin image), output of processing result to output unit 30, and the like are performed. In the control unit 10, the computer that receives commands from the operation unit 20, captures skin image data, outputs the processing result, and the like and the computer that processes the skin image according to this method are the same but different. You may.

The operation unit 20 includes a user interface (UI) that receives instructions from operators such as a keyboard, mouse, touch panel, and microphone. The output unit 30 includes a display device, a projection device (projector), a printing device (printer), a speaker, and the like. Examples of the display device include a device including a screen for displaying the processing result by the control unit 10, such as an LCD (Liquid Crystal Display) or a CRT (Cathode Ray Tube) display. The skin image acquisition unit 40 acquires skin image data from a camera, a scanner, or the like. The skin image acquisition unit 40 may include an imaging device (camera, video, etc.).

In the apparatus of the present invention, the operation unit 20 and the output unit 30 may be integrated to form a touch panel display. Alternatively, the control unit 10, the operation unit 20, the output unit 30, and the skin image acquisition unit 40 may be integrated to form a computer with a camera, a mobile terminal with a camera, or the like.

The device 1 may include hardware elements other than those described above. The number and types of the other hardware elements are not limited. For example, the device 1 may include a plurality of CPUs 11 or a plurality of output units 30.

An embodiment of an implementation process of a method for adjusting wrinkles or stains in a skin image according to the present invention by the device 1 will be described. First, the skin image acquisition step (step S0) is performed by the skin image acquisition unit 40, and the obtained skin image data is sent to the control unit 10 via the input / output I / F 13. The image data to be sent is preferably an image file in the format of JPEG, BMP, TIFF, GIF, etc. as described above, or data in which light and dark information is listed. Alternatively, these image files and data acquired externally may be sent to the control unit 10 via the input / output I / F 13 and the communication unit 14. Alternatively, analog data of the skin image may be sent to the control unit 10 and converted into an image file of the above format in the control unit 10. The obtained image file and data are stored in the memory 12 and called up as needed.

The CPU 11 processes a series of skin images according to this method (acquisition of wrinkle / stain area, brightness profile, acquisition of smoothed brightness profile and corrected brightness profile, creation of masking area, and creation of corrected skin image; steps S1 to S4. ) Is executed. These processes are executed by a program for implementing the method for adjusting wrinkles or stains in the skin image according to the present invention (hereinafter, the program of the present invention). The program of the present invention may be installed in the calculator of the control unit 10 in advance and stored in the memory 12, or may be stored in an external device connected to the control unit 10 and called as needed. .. The program of the present invention processes the skin image file and data stored in the memory according to the present method according to the command received from the operation unit 20 as necessary, and creates a modified skin image. The created modified skin image may be stored in the memory 12, may be output directly from the output unit 30, or may be output to an external device via the communication unit 14.

The output format of the created modified skin image is not particularly limited. In one embodiment, it is displayed on the display of the output unit 30 or the like. In another embodiment, the information in the modified skin image created is stored as a mere numerical value and used for other analyzes (eg, cosmetology counseling, cosmetic evaluation, etc.).

The modified skin image with reduced or emphasized wrinkles or stains produced by the present invention can be used for various purposes. For example, a skin image in which wrinkles or stains are emphasized can be used as an image of aged skin in order to predict future aged skin in beauty counseling and the like. On the other hand, the skin image with reduced wrinkles or stains can be used to create a facial photograph that gives a good impression, or as a skin image with improved wrinkles or stains, the skin with improved wrinkles or stains after beauty treatment can be used. It can be used to make predictions. However, the use of the modified skin image created by the present invention is not limited to the above.

Hereinafter, the present invention will be described in more detail based on Examples, but the present invention is not limited thereto.

Example 1 Adjustment of wrinkles in facial image 1) Acquisition of wrinkle area A female facial image in which the nasolabial fold can be visually recognized was used. By visually selecting the position of the wrinkle (nasolabial fold) region on the face image using image processing software (image J), the coordinates of the wrinkle region on the image were acquired. As shown in FIG. 2B, a straight line XX'connecting the positions of both ends of the wrinkle region in the direction orthogonal to the nasolabial fold was extracted, and the length L was calculated.

2) Acquisition of smoothed luminance profile The luminance profile A of the wrinkle region along XX'was acquired. The obtained luminance profile A was smoothed with a Gaussian filter. The kernel of the Gaussian filter was set to 120 pixels (3 cm), which is twice L. By repeating this procedure, the luminance profile A and the smoothed luminance profile B for the entire coordinates of the wrinkle region were acquired.

3) Acquisition of Corrected Luminance Profile From the luminance profile A and the smoothed luminance profile B acquired in 2), the modified luminance profile M for the entire coordinates of the wrinkle region was calculated by the following equation (1). α was set to 1 for wrinkle reduction and -1 for wrinkle enhancement.
M (x, y) = A (x, y) + α {B (x, y) -2 x A (x, y)} (1)

4) Creation of corrected face image The brightness value of the wrinkle region was replaced with the brightness value of the obtained corrected brightness profile M. Next, a luminance gradation was applied to the edge portion of the wrinkle region after the luminance information was replaced. The edge portion was set to the inside of 30 pixels (0.75. cm) from the end of the wrinkle region. The gradation is from the inside to the end of the edge portion of the wrinkle region [brightness of the modified brightness profile M: brightness of the wrinkle region of the original face image] = 100%: 0% → 0%: 100%. It was changed linearly (see FIG. 3). The face image after the gradation processing was acquired as a modified face image.

The obtained modified face image was an image in which wrinkles were reduced when α was 1 in the above formula (1), and an image in which wrinkles were emphasized when α was -1. FIG. 6 shows a face image before correction, a face image in which wrinkles are improved by wrinkle reduction (α = 1) treatment, and a face image in which wrinkles are imparted by wrinkle enhancement (α = -1) treatment.

Claims (18)

A method for adjusting wrinkles or blemishes on skin images.
Obtaining skin images with wrinkles or spots;
Obtaining the following A and B from the region having wrinkles or stains in the skin image A: Luminance profile of the region having wrinkles or stains B: Luminance profile obtained by smoothing the luminance profile A;
Obtaining the modified luminance profile M for the region having the wrinkles or stains by the following equation (1) M (x, y) = A (x, y) + α {B (x, y) -2 × A ( x, y)} (1)
((X, y) represents the coordinates corresponding to the skin image, and α represents a positive or negative constant);
Replacing the brightness of the wrinkled or spotted area with the brightness of the modified brightness profile M,
Including methods. The method according to claim 1, wherein the smoothing process is a smoothing process using a filter, and the kernel size of the filter is 1/10 to 10 times the data length to which the smoothing process is performed. The method according to claim 1 or 2, wherein the region containing wrinkles or stains is a region containing wrinkles and surrounding skin, or a region including stains and surrounding skin. The method according to any one of claims 1 to 3, wherein the adjustment of the wrinkles or stains is the reduction of wrinkles or stains, and the α is a positive value. The method according to claim 4, wherein α is 0.1 to 3. The method according to any one of claims 1 to 3, wherein the adjustment of the wrinkles or stains is the emphasis of wrinkles or stains, and the α is a negative value. The method according to claim 6, wherein α is −0.1 to −1.5. The method according to any one of claims 1 to 7, wherein the skin image is a face image or a part thereof. The method according to claim 8, wherein the wrinkles or stains are nasolabial folds. The method according to any one of claims 1 to 9, further comprising applying a gradation to the luminance from the inside to the end of the region having wrinkles or stains in which the luminance is replaced with the modified luminance profile M. The gradation changes from the inside to the end of the area having wrinkles or stains, from the brightness of the modified brightness profile M: the brightness of the skin image = 100%: 0% → 0%: 100%. The method according to claim 10. The method according to any one of claims 1 to 11, further comprising correcting the color or brightness of the wrinkled or spotted area. A method for creating an aged skin image, which comprises creating a skin image with emphasized wrinkles or blemishes using the method according to any one of claims 1 to 12. A method for predicting aging skin using an aging skin image created by the method according to claim 13. A method for creating a skin image with improved wrinkles or stains, which comprises creating a skin image with reduced wrinkles or stains using the method according to any one of claims 1 to 12. A method for predicting skin after improvement of wrinkles or stains, using a skin image with improved wrinkles or stains prepared by the method according to claim 15. An apparatus for carrying out the method according to any one of claims 1 to 16. A program for carrying out the method according to any one of claims 1 to 16.

Images