WO2009090948A1 - 肌色評価方法、肌色評価装置、肌色評価プログラム、及び該プログラムが記録された記録媒体 - Google Patents
肌色評価方法、肌色評価装置、肌色評価プログラム、及び該プログラムが記録された記録媒体 Download PDFInfo
- Publication number
- WO2009090948A1 WO2009090948A1 PCT/JP2009/050347 JP2009050347W WO2009090948A1 WO 2009090948 A1 WO2009090948 A1 WO 2009090948A1 JP 2009050347 W JP2009050347 W JP 2009050347W WO 2009090948 A1 WO2009090948 A1 WO 2009090948A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- skin color
- evaluation
- color distribution
- feature points
- face
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20021—Dividing image into blocks, subimages or windows
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30088—Skin; Dermal
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
- G06T2207/30201—Face
Definitions
- the present invention relates to a skin color evaluation method, a skin color evaluation device, a skin color evaluation program, and a recording medium on which the program is recorded, and in particular, a skin color evaluation method, a skin color evaluation device, a skin color evaluation program for evaluating skin color with high accuracy, And a recording medium on which the program is recorded.
- Non-patent documents 1 and 2 Conventionally, as a method for diagnosing and evaluating the skin color of a face, for example, a method of measuring one to several points of a face using a colorimeter and evaluating the result as skin color data has been used (for example, Non-patent documents 1 and 2).
- the advantage of this method is that, by acquiring a lot of data for a certain part, for example, the distribution range and average value of Japanese women in that part can be calculated. It exists in the point which can be evaluated by comparing.
- FIG. 1 is a diagram showing an example of skin color evaluation in the conventional method.
- the vertical axis indicates lightness
- the horizontal axis indicates hue.
- an average value 11 of the skin color of the cheeks of a Japanese woman and a 95% confidence ellipse 12 of the skin color of the cheeks of a Japanese woman are shown from a large number of measurement results.
- a subject measures the skin color under cheeks, and determines the position where the measured result is relative to the average value 11 or the region (for example, whether it is outside or inside the 95% confidence ellipse 12).
- Personal skin color assessment is also performed.
- the relative position in the face differs depending on the person even if the coordinates are the same (x, y), and the same person. Even if it exists, the position may be different for each shooting. For this reason, high-precision evaluation cannot be performed by simply comparing or comparing data between coordinate points.
- the present invention has been made in view of the above-described problems, and provides a skin color evaluation method, a skin color evaluation apparatus, a skin color evaluation program, and a recording medium on which the program is recorded, for evaluating skin color with high accuracy. For the purpose.
- the present invention employs means for solving the problems having the following characteristics.
- the present invention provides at least 25 first feature points preset for the entire face area of the image, and the first feature.
- a skin color distribution evaluation step for generating a skin color distribution based on an average value using the two and performing an evaluation based on a measurement result, and a screen generation step for displaying the measurement result or the evaluation result on a screen.
- the dividing step is characterized in that a plurality of the at least 25 locations are set for each of the forehead, the vicinity of the left and right eyes, the nose, the mouth, and the face line below the eyes in the entire face image.
- the dividing step is characterized by dividing into 93 regions surrounded by three or more feature points selected from the first feature points and the second feature points.
- the skin color distribution evaluation step L * in the L * a * b * color system, a *, b *, C ab *, h ab, tristimulus values in the XYZ color system X, Y, Z,
- a skin color distribution created using an average value of each divided region is prepared in advance using at least one of RGB values, hue H, lightness V, saturation C, melanin amount, and hemoglobin amount.
- a plurality of face images are synthesized by morphing processing, and evaluation is performed in association with a skin color distribution for each region divided from the average face obtained by averaging the face shapes.
- a plurality of face shapes can be synthesized by morphing processing and evaluated with high accuracy based on the average face obtained by averaging the face shapes.
- the skin color distribution evaluation step L * in the L * a * b * color system, a *, b *, C ab *, h ab, tristimulus values in the XYZ color system X, Y, Z, Calculate at least one average value among the RGB values, hue H, lightness V, saturation C, melanin amount, and hemoglobin amount, and aggregate the similar regions according to the obtained average value.
- the evaluation is performed based on the skin color distribution.
- the skin color distribution evaluation step includes, as a comparison skin color distribution, an ideal skin color distribution set in advance, a past skin color distribution, another person's skin color distribution, an average value of a plurality of skin color distributions, and the aggregated area At least one of the skin color distributions is generated, compared with the target personal data, and the skin color distribution is evaluated.
- the average value data of people who belong to a certain category (age, occupation, gender), ideal person data such as talent, individual past data, and other person's data, etc. Can be used for counseling when selling cosmetics.
- the skin color evaluation apparatus that evaluates the skin color from an image including the input face area, the first feature point including at least 25 preset points for the entire face area of the image; dividing means for dividing the predetermined region by the second feature points set by using a feature point for each divided area by the dividing means, L * a * b * L * in the color system, a * , B * , C ab * , h ab , tristimulus values X, Y, Z, RGB values in the XYZ color system, hue H, lightness V, saturation C, melanin amount, and hemoglobin amount
- a skin color distribution evaluation unit that generates a skin color distribution based on an average value using one and performs evaluation based on a measurement result, and a screen generation unit that displays the measurement result or the evaluation result on a screen, To do.
- the dividing means is characterized in that a plurality of the at least 25 locations are set for each of the forehead, the vicinity of the left and right eyes, the nose, the mouth, and the face line below the eyes in the entire face image.
- the dividing means divides the image into 93 regions surrounded by three or more feature points selected from the first feature point and the second feature point.
- the skin color distribution evaluation unit L * in the L * a * b * color system, a *, b *, C ab *, h ab, tristimulus values in the XYZ color system X, Y, Z
- a skin color distribution created using an average value of each divided region is prepared in advance using at least one of RGB values, hue H, lightness V, saturation C, melanin amount, and hemoglobin amount.
- a plurality of face images are synthesized by morphing processing, and evaluation is performed in association with a skin color distribution for each region divided from the average face obtained by averaging the face shapes.
- a plurality of face shapes can be synthesized by morphing processing and evaluated with high accuracy based on the average face obtained by averaging the face shapes.
- the skin color distribution evaluation unit L * in the L * a * b * color system, a *, b *, C ab *, h ab, tristimulus values in the XYZ color system X, Y, Z, Calculate at least one average value of RGB values, hue H, lightness V, saturation C, melanin amount, and hemoglobin amount, and aggregate the similar regions according to the obtained average value. The evaluation is performed based on the skin color distribution.
- the skin color distribution evaluation unit is configured as a comparison ideal skin color distribution, an ideal skin color distribution set in advance, a past skin color distribution, another person's skin color distribution, an average value of a plurality of skin color distributions, and the aggregated area At least one of the skin color distributions is generated, compared with the target personal data, and the skin color distribution is evaluated.
- the average value data of people who belong to a certain category (age, occupation, gender), ideal person data such as talent, individual past data, and other person's data, etc. Can be used for counseling when selling cosmetics.
- the present invention provides a skin color evaluation program for evaluating skin color from an image including an input face area, wherein at least 25 first feature points set in advance for the entire face area of the image on a computer, dividing step of dividing the predetermined region by the second feature points set by using the first feature point, the divided every divided region in step, L * a * b * L in color system *, a * , b * , C ab * , h ab , tristimulus values X, Y, Z, RGB values in the XYZ color system, hue H, lightness V, saturation C, melanin amount, and hemoglobin amount Executing a skin color distribution evaluation step of generating an average skin color distribution using at least one and performing an evaluation based on the measurement result, and a screen generation step of displaying the measurement result or the evaluation result on the screen
- a computer-readable recording medium that records a skin color evaluation program for evaluating skin color from an image including an input face area
- at least 25 preset for the entire face area of the image is stored in the computer.
- a division step of dividing into a predetermined region by a first feature point composed of locations and a second feature point set using the first feature point, and for each region divided by the division step, L * a * b * L * in the color system, a *, b *, C ab *, h ab, tristimulus values X, Y, Z, each value of RGB in the XYZ color system, the hue H, lightness V, chroma C
- a skin color distribution evaluation step of generating an average skin color distribution using at least one of melanin amount and hemoglobin amount, and performing evaluation based on the measurement result, and the measurement result or evaluation
- the computer-readable recording medium which recorded the skin color evaluation program for performing the screen production
- the skin color can be evaluated with high accuracy.
- FIG. 6 is a diagram (part 1) illustrating an example of a positional relationship of 109 feature points in the face corresponding to FIG. 5 described above.
- FIG. 10 is a diagram (part 2) illustrating an example of a positional relationship of 109 feature points in the face corresponding to FIG.
- FIG. 6 is a diagram (part 3) illustrating an example of a positional relationship in the face of 109 feature points corresponding to FIG. 5 described above.
- FIG. 6 is a diagram (part 4) illustrating an example of a positional relationship of 109 feature points in the face corresponding to FIG. 5 described above;
- FIG. 6 is a diagram (part 1) illustrating an example of a combination of feature points that configure each region corresponding to FIG. 5 described above.
- FIG. 6 is a diagram (part 2) illustrating an example of a combination of feature points constituting each region corresponding to FIG. 5 described above.
- FIG. 6 is a diagram (No. 3) illustrating an example of a combination of feature points constituting each region corresponding to FIG. 5 described above.
- FIG. 10 is a diagram (part 1) of an example for explaining a flow of face division for an image obtained by shooting;
- FIG. 10 is an example diagram (part 2) for explaining a flow of face division for an image obtained by photographing;
- FIG. 10 is a third diagram illustrating an exemplary flow of face division for an image obtained by shooting;
- FIG. (1) which shows an example of the skin color distribution for a comparison.
- FIG. (2) which shows an example of the skin color distribution for a comparison.
- FIG. (3) which shows an example of the skin color distribution for a comparison.
- FIG. (4) which shows an example of the skin color distribution for a comparison.
- FIG. (1) which shows an example of the skin color distribution for a comparison.
- FIG. (2) which shows an example of the skin color distribution for a comparison.
- FIG. (3) which shows an example of the skin color distribution for a comparison.
- FIG. (4) which shows an example of the skin color distribution for a comparison.
- the present invention can grasp the facial skin color distribution by dividing the input face image by a predetermined method, and replace the color with a standard face such as an average face to eliminate the face shape. Allows easy-to-understand expression of information only. In addition, it is possible to obtain an average value of people belonging to a certain category and a difference value between the two.
- FIG. 2 is a diagram illustrating an example of a functional configuration of the skin color evaluation apparatus according to the present embodiment.
- the skin color evaluation apparatus 20 shown in FIG. 2 includes an input unit 21, an output unit 22, a storage unit 23, a face division unit 24, a skin color distribution evaluation unit 25, a screen generation unit 26, and a control unit 27. It is configured as follows.
- the input means 21 accepts inputs such as the start and end of various instructions such as a face division instruction, a skin color distribution evaluation instruction, and a screen generation instruction for an image (or video or the like) including a face area input by a user or the like.
- the input unit 21 includes, for example, a keyboard and a pointing device such as a mouse.
- the input unit 21 also has a function of inputting an image including an imaging part of a user (for example, a patient) taken by an imaging unit such as a digital camera.
- the output means 22 displays / outputs the contents input by the input means 21 and the contents executed based on the input contents.
- the output means 22 includes a display, a speaker, and the like.
- the output unit 22 may have a function of a printer or the like. In this case, for example, each screen generated by the screen generation unit 26 such as an input image, a face area division result, a skin color distribution evaluation result, etc. Can be printed on a printing medium such as paper and provided to a user or the like.
- the storage means 23 stores various data such as a face division result by the face division means 24, a skin color distribution evaluation by the skin color distribution evaluation means 25, and various screen generation results by the screen generation means 26.
- the storage means 23, when storing data such as various images and processing results, personal identification such as file name, date and time, name and age (age) of photographed person (subject), sex, race, etc. Information or the like may be added and accumulated. Further, the storage means 23 can read out various data stored as required.
- the face dividing means 24 divides the input image into predetermined areas by a preset method. Specifically, the face dividing unit 24 sets feature points in advance for the entire face, selects at least three points from the set feature points, and divides by a region surrounded by the selected feature points, etc. By using, it is possible to divide in an appropriate region for evaluating the skin color distribution. The details of the face division method in this embodiment will be described later.
- the skin color distribution evaluation unit 25 performs L * , a * , b * , C ab * , L ab in the L * a * b * color system for each divided area based on the division result obtained by the face dividing unit 24.
- h ab tristimulus values in the XYZ color system X, Y, Z, RGB values, hue H, lightness V, saturation C, melanin amount, and hemoglobin amount, depending on the average value Measure skin color distribution.
- the skin color distribution evaluation unit 25 evaluates the skin color distribution based on the measurement result.
- melanin amount and hemoglobin amount are described in, for example, Tomita et al., “Development of a new stain measurement method”, Cosmetic Technology Journal, Vol. 35, no. 4, as shown in 2001, can be obtained by a measurement method calculated using a relational expression between a preset melanin amount, hemoglobin amount and tristimulus values X, Y, Z, etc. It is not limited to the method.
- the skin color distribution evaluation unit 25 synthesizes a plurality of face images prepared in advance for the skin color distribution based on the measurement result by, for example, a morphing process which is one of computer graphics techniques, and averages the face shape. Evaluation is performed in association with the skin color distribution for each region divided from the average face.
- the skin color distribution evaluation means 25 uses, for example, a plurality of image data and skin color distribution data stored in advance as a comparison skin color distribution, for example, an ideal skin color distribution, a past skin color distribution, and others set in advance. At least one of the skin color distribution, the average value of the plurality of skin color distributions, and the skin color distribution of the region aggregated for each predetermined region, and using the generated skin color distribution, by taking the difference, comparison of skin color distribution, L * a * b * L in color system *, a *, b *, C ab *, h ab, tristimulus values in the XYZ color system X, Y, Z , RGB values, hue H, lightness V, saturation C, melanin amount, and hemoglobin amount are aggregated (grouped) for each region having a similar average value using at least one of the values, Skin color distribution (skin color distribution profile E).
- a comparison skin color distribution for example, an ideal skin color distribution, a past skin color distribution, and others set in advance.
- an average facial skin color distribution or a human skin color distribution by age is generated by using personal identification information or the like added to the accumulated data.
- the skin color distribution evaluation means 25 can also perform evaluation by comparing the above-described skin color distribution profile with a comparative skin color distribution profile prepared in advance.
- the screen generation means 26 is based on the input instruction from the input means 21 from the user or the like, based on the image data obtained from the face division means 24, the evaluation result obtained by the skin color distribution evaluation means 25, or the like. A screen to be presented is generated and output by the output means 22.
- the screen generation means 26 can also color, for example, a predetermined area or generate a graph, a table, or the like from the obtained image or numerical data.
- control means 27 controls the entire components of the evaluation device 20. Specifically, the control unit 27 performs various controls such as face division processing, skin color distribution evaluation processing, and screen generation processing based on, for example, an instruction from the input unit 21 by a user or the like.
- ⁇ Skin Color Evaluation Device 20 Hardware Configuration>
- an execution program skin color evaluation program
- the execution program is installed in, for example, a general-purpose personal computer or server.
- FIG. 3 is a diagram illustrating an example of a hardware configuration capable of realizing the skin color evaluation process according to the present embodiment.
- 3 includes an input device 31, an output device 32, a drive device 33, an auxiliary storage device 34, a memory device 35, a CPU (Central Processing Unit) 36 for performing various controls, and a network connection device. 37, and these are connected to each other by a system bus B.
- a system bus B for connecting input device 31, an output device 32, a drive device 33, an auxiliary storage device 34, a memory device 35, a CPU (Central Processing Unit) 36 for performing various controls, and a network connection device. 37, and these are connected to each other by a system bus B.
- the input device 31 has a pointing device such as a keyboard and a mouse operated by a user or the like, and inputs various operation signals such as execution of a program from the user or the like.
- the input device 31 has an input unit that inputs an image including a part or all of the face of the subject photographed by an imaging means such as a camera.
- the output device 32 has a display for displaying various windows and data necessary for operating the computer main body for performing the processing according to the present invention, and displays the program execution progress and results by the control program of the CPU 36. can do.
- the input device 31 and the output device 32 may be integrated input / output means such as a touch panel, for example.
- a predetermined position using a user's finger or a pen-type input device is used. You can input by touching.
- the execution program installed in the computer main body in the present invention is provided by, for example, a portable recording medium 38 such as a USB (Universal Serial Bus) memory or a CD-ROM.
- the recording medium 38 on which the program is recorded can be set in the drive device 33, and the execution program included in the recording medium 38 is installed in the auxiliary storage device 34 from the recording medium 38 via the drive device 33.
- the auxiliary storage device 34 is a storage means such as a hard disk, and can store an execution program in the present invention, a control program provided in a computer, and the like, and can perform input / output as necessary.
- the memory device 35 stores an execution program or the like read from the auxiliary storage device 34 by the CPU 36.
- the memory device 35 includes a ROM (Read Only Memory), a RAM (Random Access Memory), and the like.
- the CPU 36 controls processing of the entire computer, such as various operations and data input / output with each hardware component, based on a control program such as an OS (Operating System) and an execution program stored in the memory device 35.
- a control program such as an OS (Operating System) and an execution program stored in the memory device 35.
- OS Operating System
- execution program stored in the memory device 35.
- the network connection device 37 acquires an execution program from another terminal connected to the communication network by connecting to a communication network or the like, or an execution result obtained by executing the program or an execution in the present invention
- the program itself can be provided to other terminals.
- the skin color evaluation process in the present invention can be executed by the hardware configuration as described above. Further, by installing the program, the skin color evaluation process in the present invention can be easily realized by a general-purpose personal computer or the like.
- FIG. 4 is a flowchart showing an example of a skin color evaluation processing procedure in the present embodiment.
- an evaluation target image including a face imaged by an imaging means such as a camera is input (S01), and the input face image is divided into a predetermined number by a preset division method ( S02).
- the image obtained by S01 can be, for example, an image obtained by photographing a whole face uniformly illuminated by a photographing device such as a digital camera.
- a photographing device such as a digital camera.
- an illumination box for capturing face images under the same conditions is used, and in order to illuminate the face uniformly within the illumination box, a plurality of halogen bulbs are arranged in front of the illumination box, and the face is captured by a TV camera. , And acquire the captured face image.
- the image used in the present invention is not particularly limited to this, and an image taken in a general lighting environment such as a fluorescent lamp can be used.
- a skin color distribution is generated from an image divided for each predetermined area (S03), and for example, a comparative skin color distribution is generated using various data stored in advance (S04). Further, the skin color and the like are compared using the individual skin color distribution obtained by the process of S03 and the comparative skin color distribution obtained by the process of S04 (S05), and evaluation is performed using the skin color distribution profile (S06).
- a screen or the like to be displayed to the user or the like is generated from the evaluation result obtained by the processing of S06 (S07), and the generated screen (evaluation result content or the like) is output (S08).
- S09 it is determined whether or not the skin color evaluation is continued (S09).
- the process returns to the process of S02, for example, a division by a division method different from the previous time is performed, which will be described later. Perform the process. If the skin color evaluation is not continued in the process of S09 (NO in S09), the process ends.
- the skin color distribution can be grasped by dividing the input face image into a predetermined number by the dividing method of the present invention. Further, when the screen is generated, for example, by replacing the skin color measured with a standard face such as an average face, it is possible to express easily only the color information excluding the face shape.
- the average value data of people belonging to a certain category (age, occupation, gender), ideal person data such as talent, past data of individuals, data of others, etc. Since it can be acquired, it can be used for counseling when selling cosmetics.
- the face dividing unit 24 performs predetermined division on a digital image including an input face.
- FIG. 5 is a diagram illustrating an example of feature points and divided areas in the present embodiment.
- the entire face is divided into 93 areas, the average skin color of each divided area is obtained, and the distribution of the face skin color is expressed by 93 skin color data. Skin color is evaluated from the distribution.
- the division method shown in FIG. 5 has 109 feature points as an example.
- the divided regions shown in FIG. 5 are, for example, 93 regions (for example, indicated by numbers 1 to 93 in FIG. 5 having a triangular shape or a quadrangular shape constituted by three or four feature points. Area).
- FIGS. 6A to 6D are diagrams showing an example of the positional relationship in the face of 109 feature points corresponding to FIG. 5 described above.
- FIG. 7A to FIG. 7C are diagrams showing an example of combinations of feature points constituting each region corresponding to FIG. 5 described above. It should be noted that “No.” and “name” of each feature point shown in FIGS. 6A to 6D, and “area No.” and “composition point” names of each region shown in FIGS. 7A to 7C. Corresponds to the contents shown in FIG.
- the face dividing means 24 first selects No. 1 among the feature points shown in FIGS. 6A to 6D, for example.
- Feature points 1 to 37 are set as the first feature points.
- the 37 feature points are, for example, 5 points in the forehead area, 10 points in the vicinity of the left and right eyes, 7 points in the nose, 9 points in the mouth, and 6 points in the face line below the eyes. It is preferable.
- the face dividing means 24 uses, for example, No. 1 shown in FIG. 6B to FIG.
- Feature points 38 to 109 are set as second feature points.
- points 38 to 49 obtained by intersections of a plurality of straight lines passing between at least two of the feature points, and a line segment between the two points
- the points 50 to 57 and 67 to 109 that are internally divided by the ratio and the points 58 to 66 that are on the straight line passing between the two feature points and have the same ordinate or abscissa as a specific point are 109 in total. Points are earned.
- At least three of the first and second feature points (109 points) are divided into regions surrounded by constituent points as shown in FIGS. 7A to 7C. Note that the number of points constituting the region may be three or four as shown in FIGS. 7A to 7C, or may be five or more.
- each region (region Nos. 1 to 93) shown in FIG. 5 is set to be a physiologically meaningful division based on the experience of observing many skin colors. That is, by performing the setting as shown in FIG. 5, a portion where color unevenness is likely to occur is divided so that the region is narrowed, and a portion where it is not so is divided so that the region is widened.
- the forehead portion has a wide area to be divided, and the area around the eyes, the mouth, the cheeks, etc. has a narrow area.
- the divided areas to be set can be evaluated in more detail and with high accuracy by setting the area narrow for the important part (area) in evaluating the skin color.
- the divided areas can be aggregated (grouped) based on the degree of color or the like by determining in advance past data or the like what kind of skin color is likely to appear in each area. Thereby, it can evaluate easily for every group.
- FIG. 8 is a diagram illustrating an example of another first feature point setting.
- the first feature point 4 to 5 points (for example, 4 points indicated by “ ⁇ ” in FIG. 8) on the forehead portion and 8 to 10 points (for example, FIG. 8 for 8 points indicated by “ ⁇ ”), 5 to 7 points for the nose (for example, 5 points indicated by “ ⁇ ” in FIG. 8), and 4 to 9 points for the mouth (for example, “ At least 25 first feature points so that there are 4 to 6 points (for example, 4 points indicated by “+” in FIG. 8) on the face line below the eyes)
- By setting the second feature point based on the first feature point it is possible to realize the same region division as when using the feature points shown in FIGS. 5 to 7C described above.
- FIGS. 9A to 9C are diagrams illustrating an example of the flow of face division for an image obtained by photographing.
- an image of a 30s female model A photographed using the above-described conventional photographing apparatus is used.
- a subject set at a predetermined position is photographed, and for example, 37 first feature points are designated by the face dividing means 24 as described above, so that a total of 109 feature points are obtained. Can be calculated.
- the face dividing means 24 divides from 109 feature points into 93 regions by setting as shown in FIGS. 7A to 7C described above.
- the image shown in FIG. 9B is the result of filling the area with the average color of each area.
- the skin color distribution for each region for each region L * in the L * a * b * color system, a *, b *, C ab *, h ab, tristimulus values X in the XYZ color system,
- RGB values hue H, lightness V, saturation C, melanin amount, and hemoglobin amount are used to generate an average value.
- an L * a * b * color system, an XYZ color system, and three elements of hue H, lightness V, and saturation C are used to generate an image.
- FIG. 9B since the outside of the entire region and the portion that is not the skin color even within the region are excluded from the evaluation target, for example, they are colored with a specific color such as a cyan color greatly separated from the skin color. Further, in FIGS. 9B and 9C, the fine skin information disappears and the facial skin color distribution is easily grasped. For example, in the case of the model A shown in FIG. 9A, the feature that “the skin color around the eyes is dark” I understand.
- the skin color distribution evaluation unit 25 can exclude the data of the peripheral part because the peripheral part of the photographed face may have low illumination uniformity. Specifically, the skin color distribution evaluation unit 25 sets a predetermined frame 41 as shown in FIGS. 9B and 9C among a total of 93 divided regions, and a predetermined number of regions in the frame 41. (61 in FIG. 9B and FIG. 9C) is set as valid data, and the evaluation process is performed using the valid data.
- evaluation can be performed based on the divided areas, so that the face shape information of a person can be excluded, and comparison of skin color distribution between people having different face shapes can be easily performed. Therefore, taking advantage of this feature, for example, the facial skin color distribution of Model A can be evaluated by comparing with the average value of the same age.
- 9B and 9C described above are generated by the image generation means 26. Further, the generated image may be displayed to the user or the like by the output unit 22 or may be stored in the storage unit 23.
- FIG. 10A to FIG. 10E are diagrams showing examples of comparative skin color distributions.
- FIGS. 10A to 10E an example of the skin color distribution for each age is shown.
- 10A to 10E show the color distribution results for each age group in their 20s to 60s, respectively.
- a face image in which a person of a corresponding age is photographed from the accumulation means 23 is subjected to region decomposition, and then, for example, an L * a * b * table L * , a * , b * , C ab * , h ab in the color system, tristimulus values X, Y, Z, RGB values in the XYZ color system, hue H, lightness V, saturation C, melanin amount
- the skin color distribution by the average value is obtained using at least one of the amounts of hemoglobin, and the average skin color distribution is obtained by calculating the average value for each age.
- each area of the average face is colored using the obtained average skin color distribution data of Japanese women of each ages from the 20s to the 60s.
- the colored image is generated by the screen generation unit 26 and is output by the output unit 22 or stored in the storage unit 23.
- a highly accurate evaluation target image can be generated. Skin color evaluation can be performed.
- the skin color distribution evaluation means 25 compares the skin color distributions by taking the difference. For example, when the model A (30s) shown in FIG. 9A described above is compared with the average skin color distribution of the 30s in FIG. 10B, it can be seen that the upper color of the model A is darker.
- FIG. 11 is a diagram for explaining a comparative example of the skin color distribution by taking the difference.
- the difference between the average face and the face of the model A is taken, and the portion where the model A has a larger amount of melanin in the frame 41 is hatched. Show.
- the target to be compared may be not only the average value of the skin color distribution but also the ideal facial skin color distribution.
- the face skin color distribution can be grasped by dividing the face image into predetermined regions, and the color excluding the face shape can be obtained by replacing the color with a standard face such as an average face.
- a standard face such as an average face.
- An easy-to-understand expression of only information is possible.
- the average value data of people belonging to a certain category (age, occupation, gender), ideal person data such as talents, past data of individuals, data of others, etc. Since it becomes possible, it can be used for counseling when selling cosmetics.
- the skin color distribution evaluation unit 25 aggregates (groups) the skin color regions by analyzing the past data or the like as principal components and obtaining the principal components for regions having similar color tendencies. can do. Thereby, it can evaluate easily for every group.
- FIG. 12 is a diagram showing an example of grouped areas.
- FIG. 13 is a diagram showing an example of the color characteristics of each group corresponding to FIG. 12 and the area numbers constituting each group. Note that the feature points constituting the regions shown in FIGS. 12 and 13 correspond to FIGS. 5 to 7 described above.
- hue H was performed on effective 57 areas excluding 4 areas of the lips in 59 people aged 20 to 67 years old, and as a result, 90. 1% was found to be accountable.
- 57 regions based on the above-described main components are described in (1) cheek lower, (2) cheek front, (3) eyelid / bearing part, (4) forehead, and (5) nose. Classify around (6) around the mouth.
- the skin color distribution can also be evaluated by the balance of the main component scores (skin color profile).
- FIG. 14 is a diagram showing an example of the evaluation result of the skin color distribution.
- the main component score for the main components (1) to (6) described above is shown as a radar chart.
- the line 51 shows the average value of the principal component scores of women in their 30s as an example
- the line 52 shows the principal component scores in the model A described above.
- the skin color and the like are compared using the individual skin color distribution obtained in the process of S03 and the comparative skin color distribution obtained in the process of S04.
- the present invention is not limited to this.
- a skin color distribution profile is generated from the measurement result, and the generated skin color distribution profile is compared in advance. It can also be evaluated in correspondence with the skin color distribution profile.
- images and values generated as shown in FIGS. 12 to 14 may be displayed to the user or the like by the output means 22 or may be stored in the storage means 23.
- FIG. 15 is a diagram illustrating an example for explaining hue H and lightness V due to group differences
- FIG. 16A is a diagram illustrating an example of a histogram of hue H corresponding to FIG. 15, and FIG. It is a figure which shows an example of the histogram of the brightness V corresponding to FIG.
- the horizontal axis indicates the range of hue H
- the vertical axis indicates frequency (%)
- the horizontal axis indicates the range of brightness V
- the vertical axis indicates frequency (%).
- the present invention performs skin color evaluation with a digital camera, and compares the face of the subject in detail as compared with the prior methods (Non-patent Document 1 and Non-Patent Document 2) using a colorimeter that acquires a certain point of data. It can be divided and evaluated, and it is easy to further subdivide as necessary.
- the statistical method called principal component analysis is used, so that the accuracy is high.
- the face area excluding is divided into four groups, but in the present invention, it can be seen that it is divided into six groups by statistical analysis, and the method of division is also different from the conventional method.
- non-patent document 2 displays the measured values on the plane of hue and lightness.
- a radar chart for one color value is displayed.
- the forehead center ( ⁇ 1) and ( ⁇ 2) are classified into zone A (dark and reddish).
- zone A the left forehead
- zone C zone C (dark and yellowish)
- the center of the forehead (corresponding to the areas No. 13 and 18 in the present invention), the left forehead (area Nos. 14 and 19), the upper left eye and the lower left eye (area Nos. 26 and 28). 37), the color characteristics are as shown in FIG.
- the center of the forehead is close to the left forehead, and the lightness is low at the top of the left eye and the bottom of the left eye. You can see that it should be. The same can be said from the histogram shown in FIG. 16B.
- the skin color evaluation can be performed with higher accuracy by using the grouping by the face division method in the present invention.
- the skin color can be evaluated with high accuracy regardless of the shape of the face.
- the skin color distribution can be grasped by dividing the input face image into predetermined areas, and the face shape is excluded by replacing the color with a standard face such as an average face. This makes it possible to express easily only the color information.
- the skin color evaluation target is described as a face.
- the present invention is not limited to this, and may be another part of the arm or hand.
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Medical Informatics (AREA)
- Quality & Reliability (AREA)
- Radiology & Medical Imaging (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
Description
柴谷他、「皮膚色とメークアップ効果に関する研究(第1報)-皮膚色測定法の開発とベースメークアップ効果研究-」、粧技誌、Vol.17、No.2、1983. J.Shibatani et al.,「Measurements of Aging Effect of Facial Color Distribution and Applications」,J.Soc.Cosmet.Chem.Japan.V19、N1、1985. 渋江他、「女性顔面の肌色及び色ムラ評価の新しい試み-偏光画像解析システムの開発と色ムラ評価への応用-」、粧技誌、Vol.26、No.2、1992. L.Caisey他、「異なった人種グループに属する女性の皮膚の色とメイクアップ戦略」、FRAGRANCE JOURNAL 2007-4.
12 95%信頼楕円
20 肌色評価装置
21 入力手段
22 出力手段
23 蓄積手段
24 顔分割手段
25 肌色分布評価手段
26 画面生成手段
27 制御手段
31 入力装置
32 出力装置
33 ドライブ装置
34 補助記憶装置
35 メモリ装置
36 CPU
37 ネットワーク接続装置
38 記録媒体
41 枠
51,52 線
本発明は、入力される顔画像を所定の手法により分割することで顔肌色分布が把握でき、また平均顔等の標準的な顔に、その色を置き換えることで、顔の形状を除外した色情報のみのわかりやすい表現を可能とする。また、あるカテゴリーに属する人々の平均値や二者間の差分値の取得が可能となる。
本実施形態における肌色評価装置の機能構成の一例について図を用いて説明する。図2は、本実施形態における肌色評価装置の機能構成の一例を示す図である。図2に示す肌色評価装置20は、入力手段21と、出力手段22と、蓄積手段23と、顔分割手段24と、肌色分布評価手段25と、画面生成手段26と、制御手段27とを有するよう構成されている。
ここで、上述した肌色評価装置20における各構成については、各機能をコンピュータに実行させることができる実行プログラム(肌色評価プログラム)を生成し、例えば汎用のパーソナルコンピュータ、サーバ等にその実行プログラムをインストールすることにより、本発明における肌色評価処理等を実現することができる。
次に、本実施形態における肌色評価処理手順について説明する。図4は、本実施形態における肌色評価処理手順の一例を示すフローチャートである。
次に、上述した顔分割手段24における顔分割手法について具体的に説明する。顔分割手段24は、入力される顔を含むデジタル画像に対して所定の分割を行う。
次に、分割した顔について顔肌色分布の生成について具体的に説明する。なお、本実施形態として、顔全体を均一に照明する照明装置とデジタルカメラを用いた撮影装置は、例えば、「舛田他、画像解析を用いたしみ・そばかす定量化システムの開発、粧技誌、V28、N2、1994.」等を用いて取得した顔画像に対して肌色分布図を生成する例について説明するが、本発明において用いられる撮影されたデジタル画像の撮影方法については、特にこれに制限されるものではない。
次に、肌色分布評価手段25における比較用の顔肌色分布の生成例について説明する。図10A~図10Eは、比較用の顔肌色分布の一例を示す図である。なお、図10A~図10Eに示す例では、各年代別の肌色分布の一例を示している。また、図10A~図10Eは、それぞれ20代~60代の各年代別の色分布結果を示している。
次に、肌色分布の比較例について具体的に説明する。本実施形態では、肌色分布評価手段25により、差分を取ることによる肌色分布の比較を行う。例えば、上述した図9Aに示すモデルA(30代)を図10Bにおける30代平均肌色分布と比較すると、モデルAの方が顔の上部の色が濃いことがわかる。
ここで、本実施形態において、肌色分布評価手段25は、肌色の領域において、色の傾向が類似する領域を、過去のデータ等を主成分分析し、主成分を求めることで集約(グループ分け)することができる。これにより、そのグループ毎に容易に評価することができる。
次に、従来手法と本手法との比較について説明する。図15は、グループの差による色相H、明度Vを説明するための一例を示す図であり、図16Aは、図15に対応する色相Hのヒストグラムの一例を示す図であり、図16Bは、図15に対応する明度Vのヒストグラムの一例を示す図である。また、図16Aは、横軸に色相Hの範囲を示し、縦軸に頻度(%)を示している。また、図16Bは、横軸に明度Vの範囲を示し、縦軸に頻度(%)を示している。
Claims (14)
- 入力された顔領域を含む画像から肌色を評価する肌色評価方法において、
前記画像の顔領域全体に対して予め設定される少なくとも25箇所からなる第1特徴点と、前記第1特徴点を用いて設定される第2特徴点とにより所定の領域に分割する分割ステップと、
前記分割ステップにより分割された領域毎に、L*a*b*表色系におけるL*,a*,b*、Cab *、hab、XYZ表色系における三刺激値X、Y、Z、RGBの各値、色相H、明度V、彩度C、メラニン量、及びヘモグロビン量のうち、少なくとも1つを用いて平均値による肌色分布を生成し、測定結果に基づく評価を行う肌色分布評価ステップと、
前記測定結果又は評価結果を画面に表示する画面生成ステップとを有することを特徴とする肌色評価方法。 - 前記分割ステップは、
前記少なくとも25箇所を、顔全体画像における額、左右目付近、鼻、口、及び目より下のフェースライン毎に複数設定することを特徴とする請求項1に記載の肌色評価方法。 - 前記分割ステップは、
前記第1特徴点及び前記第2特徴点から選択される3箇所以上の特徴点により囲まれる93の領域に分割することを特徴とする請求項1に記載の肌色評価方法。 - 前記肌色分布評価ステップは、
前記L*a*b*表色系におけるL*,a*,b*、Cab *、hab、XYZ表色系における三刺激値X、Y、Z、RGBの各値、色相H、明度V、彩度C、メラニン量、及びヘモグロビン量のうち、少なくとも1つを用いて、分割された各領域の平均値により作成した肌色分布について、予め用意される複数の顔画像をモーフィング処理により合成し、顔形状を平均化させた平均顔から分割した各領域毎の肌色分布と対応付けて評価を行うことを特徴とする請求項1に記載の肌色評価方法。 - 前記肌色分布評価ステップは、
前記L*a*b*表色系におけるL*,a*,b*、Cab *、hab、XYZ表色系における三刺激値X、Y、Z、RGBの各値、色相H、明度V、彩度C、メラニン量、及びヘモグロビン量のうち、少なくとも1つの平均値を求め、求められた平均値により類似する領域毎に集約し、集約した領域の肌色分布に基づいて評価を行うことを特徴とする請求項1に記載の肌色評価方法。 - 前記肌色分布評価ステップは、
比較用の肌色分布として、予め設定される理想的な肌色分布、過去の肌色分布、他人の肌色分布、複数の肌色分布の平均値、及び前記集約した領域の肌色分布のうち、少なくとも1つを生成して、対象となる個人データとの比較を行い、肌色分布の評価を行うことを特徴とする請求項5に記載の肌色評価方法。 - 入力された顔領域を含む画像から肌色を評価する肌色評価装置において、
前記画像の顔領域全体に対して予め設定される少なくとも25箇所からなる第1特徴点と、前記第1特徴点を用いて設定される第2特徴点とにより所定の領域に分割する分割手段と、
前記分割手段により分割された領域毎に、L*a*b*表色系におけるL*,a*,b*、Cab *、hab、XYZ表色系における三刺激値X、Y、Z、RGBの各値、色相H、明度V、彩度C、メラニン量、及びヘモグロビン量のうち、少なくとも1つを用いて平均値による肌色分布を生成し、測定結果に基づく評価を行う肌色分布評価手段と、
前記測定結果又は評価結果を画面に表示するための画面生成手段とを有することを特徴とする肌色評価装置。 - 前記分割手段は、
前記少なくとも25箇所を、顔全体画像における額、左右目付近、鼻、口、及び目より下のフェースライン毎に複数設定することを特徴とする請求項7に記載の肌色評価装置。 - 前記分割手段は、
前記第1特徴点及び前記第2特徴点から選択される3箇所以上の特徴点により囲まれる93の領域に分割することを特徴とする請求項7に記載の肌色評価装置。 - 前記肌色分布評価手段は、
前記L*a*b*表色系におけるL*,a*,b*、Cab *、hab、XYZ表色系における三刺激値X、Y、Z、RGBの各値、色相H、明度V、彩度C、メラニン量、及びヘモグロビン量のうち、少なくとも1つを用いて、分割された各領域の平均値により作成した肌色分布について、予め用意される複数の顔画像をモーフィング処理により合成し、顔形状を平均化させた平均顔から分割した各領域毎の肌色分布と対応付けて評価を行うことを特徴とする請求項7に記載の肌色評価装置。 - 前記肌色分布評価手段は、
前記L*a*b*表色系におけるL*,a*,b*、Cab *、hab、XYZ表色系における三刺激値X、Y、Z、RGBの各値、色相H、明度V、彩度C、メラニン量、及びヘモグロビン量のうち、少なくとも1つの平均値を求め、求められた平均値により類似する領域毎に集約し、集約した領域の肌色分布に基づいて評価を行うことを特徴とする請求項7に記載の肌色評価装置。 - 前記肌色分布評価手段は、
比較用の肌色分布として、予め設定される理想的な肌色分布、過去の肌色分布、他人の肌色分布、複数の肌色分布の平均値、及び前記集約した領域の肌色分布のうち、少なくとも1つを生成して、対象となる個人データとの比較を行い、肌色分布の評価を行うことを特徴とする請求項11に記載の肌色評価装置。 - 入力された顔領域を含む画像から肌色を評価する肌色評価プログラムにおいて、
コンピュータに、
前記画像の顔領域全体に対して予め設定される少なくとも25箇所からなる第1特徴点と、前記第1特徴点を用いて設定される第2特徴点とにより所定の領域に分割する分割ステップ、
前記分割ステップにより分割された領域毎に、L*a*b*表色系におけるL*,a*,b*、Cab *、hab、XYZ表色系における三刺激値X、Y、Z、RGBの各値、色相H、明度V、彩度C、メラニン量、及びヘモグロビン量のうち、少なくとも1つを用いて平均値による肌色分布を生成し、測定結果に基づく評価を行う肌色分布評価ステップ、及び、
前記測定結果又は評価結果を画面に表示する画面生成ステップを実行させるための肌色評価プログラム。 - 入力された顔領域を含む画像から肌色を評価する肌色評価プログラムを記録したコンピュータ読み取り可能な記録媒体において、
コンピュータに、
前記画像の顔領域全体に対して予め設定される少なくとも25箇所からなる第1特徴点と、前記第1特徴点を用いて設定される第2特徴点とにより所定の領域に分割する分割ステップ、
前記分割ステップにより分割された領域毎に、L*a*b*表色系におけるL*,a*,b*、Cab *、hab、XYZ表色系における三刺激値X、Y、Z、RGBの各値、色相H、明度V、彩度C、メラニン量、及びヘモグロビン量のうち、少なくとも1つを用いて平均値による肌色分布を生成し、測定結果に基づく評価を行う肌色分布評価ステップ、及び、
前記測定結果又は評価結果を画面に表示する画面生成ステップを実行させるための肌色評価プログラムを記録したコンピュータ読み取り可能な記録媒体。
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US12/812,274 US20100284610A1 (en) | 2008-01-17 | 2009-01-14 | Skin color evaluation method, skin color evaluation apparatus, skin color evaluation program, and recording medium with the program recorded thereon |
CN2009801023563A CN101911118B (zh) | 2008-01-17 | 2009-01-14 | 肤色评价方法、肤色评价装置、肤色评价程序、以及存储了该程序的存储介质 |
EP09702552A EP2234063A1 (en) | 2008-01-17 | 2009-01-14 | Skin color evaluation method, skin color evaluation apparatus, skin color evaluation program, and recording medium with the program recorded thereon |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2008-008370 | 2008-01-17 | ||
JP2008008370A JP5290585B2 (ja) | 2008-01-17 | 2008-01-17 | 肌色評価方法、肌色評価装置、肌色評価プログラム、及び該プログラムが記録された記録媒体 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2009090948A1 true WO2009090948A1 (ja) | 2009-07-23 |
Family
ID=40885337
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2009/050347 WO2009090948A1 (ja) | 2008-01-17 | 2009-01-14 | 肌色評価方法、肌色評価装置、肌色評価プログラム、及び該プログラムが記録された記録媒体 |
Country Status (6)
Country | Link |
---|---|
US (1) | US20100284610A1 (ja) |
EP (1) | EP2234063A1 (ja) |
JP (1) | JP5290585B2 (ja) |
KR (1) | KR20100105627A (ja) |
CN (1) | CN101911118B (ja) |
WO (1) | WO2009090948A1 (ja) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2009294958A (ja) * | 2008-06-05 | 2009-12-17 | Kao Corp | 顔画像の合成方法 |
CN106846421A (zh) * | 2017-02-14 | 2017-06-13 | 深圳可思美科技有限公司 | 一种肤色检测方法及装置 |
CN109300164A (zh) * | 2017-07-25 | 2019-02-01 | 丽宝大数据股份有限公司 | 皮肤基底色调判断方法与电子装置 |
Families Citing this family (29)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8319857B2 (en) * | 2009-02-26 | 2012-11-27 | Access Business Group International Llc | Apparatus and method for correcting digital color photographs |
JP5405994B2 (ja) * | 2009-12-03 | 2014-02-05 | 花王株式会社 | 画像処理装置、画像処理方法、画像処理システム、肌評価方法 |
JP5650012B2 (ja) * | 2011-02-25 | 2015-01-07 | 花王株式会社 | 顔画像処理方法、美容カウンセリング方法および顔画像処理装置 |
JP4831259B1 (ja) * | 2011-03-10 | 2011-12-07 | オムロン株式会社 | 画像処理装置、画像処理方法、および制御プログラム |
JP5733032B2 (ja) * | 2011-06-06 | 2015-06-10 | ソニー株式会社 | 画像処理装置および方法、画像処理システム、プログラム、および、記録媒体 |
US9668653B2 (en) | 2012-03-15 | 2017-06-06 | Access Business Group International Llc, A Michigan Limited Liability Company | Quantification of under-eye skin color |
JP2013212177A (ja) * | 2012-03-30 | 2013-10-17 | Shiseido Co Ltd | 画像解析方法、画像解析装置、及び画像解析プログラム |
CN103152476B (zh) * | 2013-01-31 | 2015-01-28 | 广东欧珀移动通信有限公司 | 检测皮肤状态的手机及其使用方法 |
US9542595B2 (en) * | 2013-03-25 | 2017-01-10 | Brightex Bio-Photonics Llc | Systems and methods for recommending cosmetic products for users with mobile devices |
FR3004536B1 (fr) * | 2013-04-15 | 2016-04-15 | Oreal | Dispositif d'evaluation d'un produit a l'application |
WO2014208067A1 (ja) * | 2013-06-28 | 2014-12-31 | パナソニック インテレクチュアル プロパティ コーポレーション オブ アメリカ | 肌の官能評価装置および肌の評価方法 |
US20150030243A1 (en) * | 2013-07-24 | 2015-01-29 | Di Qu | Chart for evaluating skin color and its application to efficacy evaluation of anti-aging and skin lightening products |
CN104732200B (zh) * | 2015-01-28 | 2018-04-03 | 广州远信网络科技发展有限公司 | 一种皮肤类型和皮肤问题的识别方法 |
JP6566240B2 (ja) * | 2015-04-16 | 2019-08-28 | ソニー株式会社 | 情報処理装置、情報処理方法、およびプログラム |
EP3530142A4 (en) * | 2016-10-24 | 2019-10-30 | Panasonic Intellectual Property Management Co., Ltd. | PICTURE PROCESSING DEVICE, PICTURE PROCESSING METHOD AND PICTURE PROCESSING PROGRAM |
CN106570909B (zh) * | 2016-11-02 | 2020-01-17 | 华为技术有限公司 | 一种肤色检测方法、装置及终端 |
CN106952313A (zh) * | 2017-03-21 | 2017-07-14 | 北京工商大学 | 基于HSI和Lab混合颜色模型的皮肤肤色评价方法 |
JP6677221B2 (ja) * | 2017-06-06 | 2020-04-08 | カシオ計算機株式会社 | 画像処理装置、画像処理方法及びプログラム |
EP3664016B1 (en) | 2017-08-24 | 2022-06-22 | Huawei Technologies Co., Ltd. | Image detection method and apparatus, and terminal |
CN107633443A (zh) * | 2017-08-29 | 2018-01-26 | 昆山市那美信息科技有限公司 | 一种智能全景展示的评价贴标系统 |
CN111316329A (zh) * | 2017-12-26 | 2020-06-19 | 株式会社资生堂 | 信息处理装置、程序 |
KR102631708B1 (ko) * | 2018-06-19 | 2024-01-31 | 삼성전자주식회사 | 항산화 지수 측정 장치 및 방법 |
JP2020012668A (ja) * | 2018-07-13 | 2020-01-23 | 株式会社リコー | 評価装置、計測装置、評価方法および評価プログラム |
CN113711277A (zh) | 2019-04-23 | 2021-11-26 | 宝洁公司 | 用于确定美容皮肤属性的设备和方法 |
CN113767439A (zh) | 2019-04-23 | 2021-12-07 | 宝洁公司 | 用于将美容皮肤属性可视化的设备和方法 |
US11341759B2 (en) * | 2020-03-31 | 2022-05-24 | Capital One Services, Llc | Image classification using color profiles |
CN111539932B (zh) * | 2020-04-22 | 2023-03-14 | 四川省肿瘤医院 | 一种血色素测量仪及测量方法 |
CN111831193A (zh) * | 2020-07-27 | 2020-10-27 | 北京思特奇信息技术股份有限公司 | 自动换肤方法、装置、电子设备及存储介质 |
CN113139930B (zh) * | 2021-03-17 | 2022-07-15 | 杭州迪英加科技有限公司 | 甲状腺切片图像分类方法、装置、计算机设备和存储介质 |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH06282614A (ja) * | 1993-03-26 | 1994-10-07 | A T R Tsushin Syst Kenkyusho:Kk | 物体形状表示装置 |
JPH08308634A (ja) * | 1995-05-23 | 1996-11-26 | Pola Chem Ind Inc | 肌の評価装置 |
JPH08329278A (ja) * | 1995-02-02 | 1996-12-13 | Matsushita Electric Ind Co Ltd | 画像処理装置 |
JP2001000419A (ja) * | 1999-06-14 | 2001-01-09 | Procter & Gamble Co:The | 肌のイメージング及び分析システムとその方法 |
JP2004265406A (ja) * | 2003-02-28 | 2004-09-24 | Eastman Kodak Co | バッチモードで処理されるポートレート画像を向上する方法及びシステム |
JP2004321793A (ja) * | 2003-04-29 | 2004-11-18 | Inforward Inc | 皮膚画像のコンピュータ解析のための方法およびシステム |
WO2006043702A1 (ja) * | 2004-10-22 | 2006-04-27 | Shiseido Company, Ltd. | 肌状態診断システムおよび美容のためのカウンセリングシステム |
Family Cites Families (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP0725364B1 (en) * | 1995-02-02 | 2006-11-15 | Matsushita Electric Industrial Co., Ltd. | Image processing apparatus |
FR2749077B1 (fr) * | 1996-05-23 | 1999-08-06 | Oreal | Procede et dispositif de mesure de la couleur |
US7058209B2 (en) * | 2001-09-20 | 2006-06-06 | Eastman Kodak Company | Method and computer program product for locating facial features |
ES2534190T3 (es) * | 2005-04-28 | 2015-04-20 | Shiseido Company, Limited | Método de análisis del estado de la piel, dispositivo de análisis del estado de la piel y medio de grabación en el que se graba un programa de análisis del estado de la piel |
CN101371272B (zh) * | 2006-01-17 | 2012-07-18 | 株式会社资生堂 | 化妆模拟系统,化妆模拟装置,化妆模拟方法 |
US8290257B2 (en) * | 2007-03-02 | 2012-10-16 | The Procter & Gamble Company | Method and apparatus for simulation of facial skin aging and de-aging |
US8218862B2 (en) * | 2008-02-01 | 2012-07-10 | Canfield Scientific, Incorporated | Automatic mask design and registration and feature detection for computer-aided skin analysis |
US8401300B2 (en) * | 2009-12-14 | 2013-03-19 | Conopco, Inc. | Targeted image transformation of skin attribute |
-
2008
- 2008-01-17 JP JP2008008370A patent/JP5290585B2/ja active Active
-
2009
- 2009-01-14 EP EP09702552A patent/EP2234063A1/en not_active Withdrawn
- 2009-01-14 US US12/812,274 patent/US20100284610A1/en not_active Abandoned
- 2009-01-14 CN CN2009801023563A patent/CN101911118B/zh not_active Expired - Fee Related
- 2009-01-14 KR KR1020107013924A patent/KR20100105627A/ko not_active Application Discontinuation
- 2009-01-14 WO PCT/JP2009/050347 patent/WO2009090948A1/ja active Application Filing
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH06282614A (ja) * | 1993-03-26 | 1994-10-07 | A T R Tsushin Syst Kenkyusho:Kk | 物体形状表示装置 |
JPH08329278A (ja) * | 1995-02-02 | 1996-12-13 | Matsushita Electric Ind Co Ltd | 画像処理装置 |
JPH08308634A (ja) * | 1995-05-23 | 1996-11-26 | Pola Chem Ind Inc | 肌の評価装置 |
JP2001000419A (ja) * | 1999-06-14 | 2001-01-09 | Procter & Gamble Co:The | 肌のイメージング及び分析システムとその方法 |
JP2004265406A (ja) * | 2003-02-28 | 2004-09-24 | Eastman Kodak Co | バッチモードで処理されるポートレート画像を向上する方法及びシステム |
JP2004321793A (ja) * | 2003-04-29 | 2004-11-18 | Inforward Inc | 皮膚画像のコンピュータ解析のための方法およびシステム |
WO2006043702A1 (ja) * | 2004-10-22 | 2006-04-27 | Shiseido Company, Ltd. | 肌状態診断システムおよび美容のためのカウンセリングシステム |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2009294958A (ja) * | 2008-06-05 | 2009-12-17 | Kao Corp | 顔画像の合成方法 |
CN106846421A (zh) * | 2017-02-14 | 2017-06-13 | 深圳可思美科技有限公司 | 一种肤色检测方法及装置 |
CN109300164A (zh) * | 2017-07-25 | 2019-02-01 | 丽宝大数据股份有限公司 | 皮肤基底色调判断方法与电子装置 |
Also Published As
Publication number | Publication date |
---|---|
EP2234063A1 (en) | 2010-09-29 |
JP2009169758A (ja) | 2009-07-30 |
JP5290585B2 (ja) | 2013-09-18 |
US20100284610A1 (en) | 2010-11-11 |
KR20100105627A (ko) | 2010-09-29 |
CN101911118B (zh) | 2013-06-12 |
CN101911118A (zh) | 2010-12-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP5290585B2 (ja) | 肌色評価方法、肌色評価装置、肌色評価プログラム、及び該プログラムが記録された記録媒体 | |
TWI585711B (zh) | 獲得保養信息的方法、分享保養信息的方法及其電子裝置 | |
TWI514291B (zh) | 年齡估計方法 | |
US8094186B2 (en) | Skin condition diagnosis system and beauty counseling system | |
US20150099947A1 (en) | Skin youthfulness index, methods and applications thereof | |
US8591414B2 (en) | Skin state analyzing method, skin state analyzing apparatus, and computer-readable medium storing skin state analyzing program | |
TWI669660B (zh) | 斑點評估裝置、斑點評估方法及程式 | |
US20160106198A1 (en) | Transparency evaluation device, transparency evaluation method and transparency evaluation program | |
CN108024719B (zh) | 肌肤的光泽评价装置、光泽评价方法及记录介质 | |
TWI452998B (zh) | System and method for establishing and analyzing skin parameters using digital image multi-area analysis | |
Bernardis et al. | Quantifying alopecia areata via texture analysis to automate the salt score computation | |
KR20170117840A (ko) | 맞춤형 피부 진단 및 관리 시스템 | |
JP2009082338A (ja) | エントロピーを用いた肌の鑑別方法 | |
Imai et al. | Facial cues to age perception using three-dimensional analysis | |
JP3920747B2 (ja) | 画像処理装置 | |
JP2013212177A (ja) | 画像解析方法、画像解析装置、及び画像解析プログラム | |
Bellavia et al. | A non-parametric segmentation methodology for oral videocapillaroscopic images | |
Flament et al. | Developing an artificial intelligence (AI)‐based descriptor of facial appearance that fits with the assessments of makeup experts | |
JP2014093043A (ja) | 顔画像分析装置及び顔画像分析方法 | |
TWI528296B (zh) | 皮脂量的推定方法、皮脂量推定裝置及皮脂量推定程式 | |
JP2017192767A (ja) | 画像解析方法、画像解析装置、及び画像解析プログラム | |
WO2023060720A1 (zh) | 情绪状态展示方法、装置及系统 | |
TW201535320A (zh) | 增齡分析方法及增齡分析裝置 | |
TW201028963A (en) | Evaluation method of skin color, evaluation apparatus of skin color, evaluation program of skin color and recording media thereof | |
JP6028188B1 (ja) | 情報提供装置及び情報提供方法 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
WWE | Wipo information: entry into national phase |
Ref document number: 200980102356.3 Country of ref document: CN |
|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 09702552 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 20107013924 Country of ref document: KR Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: 12812274 Country of ref document: US |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2009702552 Country of ref document: EP |
|
NENP | Non-entry into the national phase |
Ref country code: DE |