WO2012056743A1 - 画像処理装置、画像処理方法、および制御プログラム - Google Patents
画像処理装置、画像処理方法、および制御プログラム Download PDFInfo
- Publication number
- WO2012056743A1 WO2012056743A1 PCT/JP2011/056449 JP2011056449W WO2012056743A1 WO 2012056743 A1 WO2012056743 A1 WO 2012056743A1 JP 2011056449 W JP2011056449 W JP 2011056449W WO 2012056743 A1 WO2012056743 A1 WO 2012056743A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- color
- skin
- image
- makeup
- person image
- Prior art date
Links
- 238000012545 processing Methods 0.000 title claims abstract description 92
- 238000003672 processing method Methods 0.000 title claims abstract description 15
- 238000000034 method Methods 0.000 claims abstract description 99
- 230000008569 process Effects 0.000 claims abstract description 88
- 238000009826 distribution Methods 0.000 claims description 57
- 238000004040 coloring Methods 0.000 claims description 50
- 238000001514 detection method Methods 0.000 claims description 34
- 239000003086 colorant Substances 0.000 claims description 21
- 239000002131 composite material Substances 0.000 abstract 1
- 210000001508 eye Anatomy 0.000 description 98
- 238000012937 correction Methods 0.000 description 21
- 235000019557 luminance Nutrition 0.000 description 21
- 238000004088 simulation Methods 0.000 description 18
- 210000000744 eyelid Anatomy 0.000 description 17
- 241001237961 Amanita rubescens Species 0.000 description 16
- 238000003384 imaging method Methods 0.000 description 15
- 230000015572 biosynthetic process Effects 0.000 description 14
- 238000003786 synthesis reaction Methods 0.000 description 14
- 230000001815 facial effect Effects 0.000 description 12
- 238000003860 storage Methods 0.000 description 12
- 239000011521 glass Substances 0.000 description 10
- 230000006870 function Effects 0.000 description 9
- 210000004209 hair Anatomy 0.000 description 8
- 238000007796 conventional method Methods 0.000 description 7
- 239000000203 mixture Substances 0.000 description 7
- 238000004891 communication Methods 0.000 description 6
- 238000005286 illumination Methods 0.000 description 6
- 210000000056 organ Anatomy 0.000 description 6
- 230000007423 decrease Effects 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 4
- 239000002537 cosmetic Substances 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 210000001747 pupil Anatomy 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 230000002194 synthesizing effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 210000004709 eyebrow Anatomy 0.000 description 1
- 210000000720 eyelash Anatomy 0.000 description 1
- 210000000887 face Anatomy 0.000 description 1
- 230000008921 facial expression Effects 0.000 description 1
- 230000000873 masking effect Effects 0.000 description 1
- 229910044991 metal oxide Inorganic materials 0.000 description 1
- 150000004706 metal oxides Chemical class 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T1/00—General purpose image data processing
-
- A—HUMAN NECESSITIES
- A45—HAND OR TRAVELLING ARTICLES
- A45D—HAIRDRESSING OR SHAVING EQUIPMENT; EQUIPMENT FOR COSMETICS OR COSMETIC TREATMENTS, e.g. FOR MANICURING OR PEDICURING
- A45D44/00—Other cosmetic or toiletry articles, e.g. for hairdressers' rooms
- A45D44/005—Other cosmetic or toiletry articles, e.g. for hairdressers' rooms for selecting or displaying personal cosmetic colours or hairstyle
-
- A—HUMAN NECESSITIES
- A45—HAND OR TRAVELLING ARTICLES
- A45D—HAIRDRESSING OR SHAVING EQUIPMENT; EQUIPMENT FOR COSMETICS OR COSMETIC TREATMENTS, e.g. FOR MANICURING OR PEDICURING
- A45D44/00—Other cosmetic or toiletry articles, e.g. for hairdressers' rooms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/001—Texturing; Colouring; Generation of texture or colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T19/00—Manipulating 3D models or images for computer graphics
- G06T19/20—Editing of 3D images, e.g. changing shapes or colours, aligning objects or positioning parts
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/162—Detection; Localisation; Normalisation using pixel segmentation or colour matching
-
- A—HUMAN NECESSITIES
- A45—HAND OR TRAVELLING ARTICLES
- A45D—HAIRDRESSING OR SHAVING EQUIPMENT; EQUIPMENT FOR COSMETICS OR COSMETIC TREATMENTS, e.g. FOR MANICURING OR PEDICURING
- A45D44/00—Other cosmetic or toiletry articles, e.g. for hairdressers' rooms
- A45D2044/007—Devices for determining the condition of hair or skin or for selecting the appropriate cosmetic or hair treatment
Definitions
- the present invention relates to an image processing apparatus and an image processing method, and more particularly to an image processing apparatus and an image processing method for correcting a face image.
- Patent Document 1 discloses a blusher makeup simulation technique in which blusher is applied to a captured user's face image.
- Patent Document 2 discloses an eye makeup simulation technique for drawing an eye shadow and an eye line on a captured user's face image. According to these techniques, since a color such as blusher or eye shadow is applied to the color of the user's face image, makeup according to the color of the user's skin can be applied.
- Japanese Patent Publication Japanese Laid-Open Patent Publication No. 2000-279228 (Released on October 10, 2000)” Japanese Patent Publication “JP 2000-285222 A (publication date: October 13, 2000)”
- Patent Document 1 and Patent Document 2 are based on the premise that an optimal face image is prepared for performing a makeup simulation.
- the above conventional technique is based on the use of an expressionless front face image in which the periphery of the eyes and cheeks is not hidden by other objects, and the entire face is exposed to uniform light. It is said. Therefore, for example, in a cosmetics store, first, a customer (user) is asked to sit at the camera, and preparations such as raising bangs and removing glasses are made. Thereafter, the salesperson captures the customer's optimal face image under illumination arranged to be illuminated uniformly and inputs the expressionless front face image to the makeup simulator. If the makeup simulation fails, the above process is repeated.
- Patent Document 1 and Patent Document 2 cannot perform a makeup simulation in a normal state, that is, in a state where the bangs are lowered or glasses are worn.
- Patent Document 1 and Patent Document 2 can be applied to a digital camera or a camera-equipped mobile phone, and software that applies makeup to a captured face image can be realized. Further, it may be applied as a makeup simulator that operates on a personal computer or a server on the Internet. In this case, it is not necessary to ask the salesperson for a makeup simulation.
- the snapshot often includes face images that are difficult to perform a makeup simulation in the first place, such as a face whose direction is not frontal or a face that is intentionally distorted. If a makeup simulation according to a conventional technique is performed on such a face image, the correction cannot be performed as intended, and an unnatural result is generated.
- the present invention has been made in view of the above problems, and an object of the present invention is to realize an image processing apparatus and an image processing method capable of appropriately performing a makeup process on a wide range of face images. is there.
- An image processing apparatus is an image processing apparatus that performs a process of coloring a pattern of a certain color on the skin of a person image, and in order to solve the above problems, at least a part of the area of the person image For each part, a skin specifying part for specifying the skin color degree of the color in the person image, and a coloring part for coloring the pattern in the person image according to the density corresponding to the skin color degree are provided. .
- An image processing method is an image processing method that performs a process of coloring a pattern of a certain color on the skin of a person image, and in order to solve the above-described problem, at least a partial region of the person image
- the skin color degree of each part of at least a partial region of the person image is specified, and the pattern is colored on the person image with a density corresponding to the skin color degree. Therefore, the pattern that is considered to be skin can be colored deeply, and the part that is not considered to be skin (for example, hair, glasses, etc.) can be lightly colored or not colored. Therefore, a pattern such as makeup can be appropriately colored on the skin of the person image. Therefore, for example, a makeup simulation can be performed using images taken under a wide range of conditions without preparing images with raised bangs, glasses, or illumination.
- the skin color level of each part of the human image is specified, and the pattern is colored on the human image with a density corresponding to the skin color level.
- a pattern such as makeup can be appropriately colored on the skin of the person image. Therefore, a makeup simulation can be performed using images taken under a wide range of conditions.
- FIG. 1 is a block diagram showing a schematic configuration of a digital camera 1 according to the present embodiment.
- the digital camera 1 includes an instruction input device 2, an imaging device 3, an image storage device 4, a display device 5, and an image processing device 6.
- the instruction input device 2 includes an input device such as a button, a key, or a touch panel, receives an imaging instruction from a user, and outputs an imaging instruction to the imaging device 3.
- the instruction input device 2 receives a makeup processing instruction from the user, and outputs a makeup processing instruction to the image processing device 6.
- the imaging device 3 includes an imaging element such as a CCD (charge coupled device) or a CMOS (complementary metal oxide semiconductor) imaging element.
- the imaging device 3 captures an image according to an imaging instruction, and outputs the captured image (image data) to the image storage device 4.
- the image storage device 4 stores various types of information, and includes a storage device such as an HDD (Hard Disk Drive) or a flash memory.
- the image storage device 4 stores and stores the image received from the imaging device 3.
- the display device 5 includes a display, displays the input image, and presents it to the user.
- the display device 5 receives the makeup-processed image from the image processing device 6 and displays the makeup-processed image.
- the image processing device 6 includes an image acquisition unit 11, a face detection unit 12, a feature detection unit (detection unit) 13, a suitability determination unit 14, a makeup shape determination unit 15, a color correction unit 16, a synthesis unit (coloring unit) 17, and A display control unit 18 is provided.
- the image acquisition unit 11 receives a makeup processing instruction from the instruction input device 2.
- the makeup processing instruction includes information indicating an image to be processed and information indicating what makeup (eye shadow or blusher, its shape, color, etc.) is to be performed.
- the image acquisition unit 11 acquires an image to be processed from the image storage device 4 based on the received makeup processing instruction. Note that the image acquisition unit 11 may directly receive an image captured from the imaging device 3.
- the image acquisition unit 11 outputs the acquired processing target image to the face detection unit 12. Further, the image acquisition unit 11 outputs a makeup processing instruction to the makeup shape determination unit 15.
- the face detection unit 12 detects a face image included in the image received from the image acquisition unit 11. When detecting the face image included in the image, the face detection unit 12 specifies the position of the face image. The position of the face image may indicate the coordinates of a predetermined point of the face image, or may indicate a region of the face image. The face detection unit 12 outputs the processing target image and the position of the face image to the feature detection unit 13. The face detection unit 12 may detect a plurality of face images from the processing target image. When a plurality of face images are detected, the face detection unit 12 may specify the position of each face image and output the positions of the plurality of face images to the feature detection unit 13.
- the feature detection unit 13 detects the position of each feature of the face of the face image from the image to be processed and the position of the face image received from the face detection unit 12.
- the feature detection unit 13 includes, for example, the eyes (the eyes, the corners of the eyes, the upper eyelid contour points, the lower eyelid contour points, etc.), the mouth (the mouth end point, the mouth center point, etc.), and the nose (the apex of the nose). And the like, and features (feature points) such as facial contours are identified and their positions are specified.
- the position of the feature may indicate the coordinates of the feature point, or may indicate an area including the feature.
- Each feature can be detected using a known technique.
- the feature detection unit 13 outputs the image to be processed, the position of the face image, and the position of the detected facial feature to the suitability determination unit 14.
- the feature detection unit 13 may specify the positions of the features of the plurality of face images and output the positions of the features of the plurality of face images to the suitability determination unit 14.
- the suitability determination unit 14 determines whether or not the face image is suitable for performing the makeup process from the processing target image, the face image position, and the face feature position received from the feature detection unit 13. For example, the suitability determination unit 14 determines a face image that faces sideways, a face image that is too small, and the like as inappropriate. A specific determination method will be described later. When a plurality of face images are included in the image to be processed, the suitability determination unit 14 may determine the suitability of performing the makeup process on each face image, or more suitable for performing the makeup process. A predetermined number (for example, one) of face images may be specified. The suitability determining unit 14 outputs the image to be processed, the position of the face image determined to be appropriate as the processing target, and the position of the facial feature to the makeup shape determining unit 15.
- the makeup shape determination unit 15 is based on the processing target image received from the suitability determination unit 14, the position of the processing target face image, the position of the facial feature, and the makeup processing instruction received from the image acquisition unit 11. Then, the shape of the makeup (pattern) to be performed on the face image to be processed and the density distribution thereof are determined.
- the makeup color designated by the user is combined with the skin color of the original face image according to the calculated weight distribution.
- the weight distribution indicates a distribution of makeup shades for each pixel.
- the makeup shape determination unit 15 specifies a weight distribution used for color synthesis as the makeup shape and the light / dark distribution.
- the makeup shape determination unit 15 includes a shape adjustment unit 21, a skin identification unit 22, a mask unit 23, and a weight distribution determination unit 24.
- the shape adjusting unit 21 determines the type of makeup (eyeline, blusher, etc.) and its basic shape based on the makeup processing instruction.
- the shape adjusting unit 21 specifies a makeup basic shape to be used for the makeup process based on a makeup processing instruction among a plurality of makeup basic shapes prepared in advance.
- the shape adjusting unit 21 may calculate the makeup basic shape by calculation using a predetermined function every time the makeup process is performed. Further, a makeup basic shape template may be used by changing the shape, density distribution and the like according to a user instruction.
- FIG. 2 is an image showing an example of the basic shape of the upper eyeline.
- FIG. 3 is an image showing an example of the basic shape of the lower eyelid eyeline.
- FIG. 4 is an image showing an example of the basic shape of the eye shadow.
- FIG. 5 is an image showing an example of the basic shape of blusher. 2 to 5, a bright (white) portion indicates that the makeup color is dark, and a dark (black) portion indicates that the makeup color is light. That is, the basic shape of the makeup represents the shape of the makeup and the shading.
- the basic shape of the eyelid eyeline shown in FIG. 2 has a value of 0 to 1 for each pixel, and the larger the value is, the brighter the pixel is.
- the basic shape of the makeup shown in FIGS. 2 to 5 is for the right eye or the right cheek. If the left and right are reversed, the basic shape for the left eye or the right cheek is obtained.
- the shape adjusting unit 21 deforms the makeup basic shape to be used according to the characteristics of the face image. For example, the shape adjusting unit 21 adjusts (scales) the size of the makeup basic shape used according to the size of the face image or the size of the eyes. In addition, the shape adjusting unit 21 is configured so that, for example, the lower outline (white portion) of the upper eyelid eyeline shown in FIG. Adjust the makeup shape. In this way, the shape adjusting unit 21 adjusts the makeup shape according to each feature.
- FIG. 6 is an image showing the makeup shape after the shape adjustment. Similar to FIGS. 2 to 5, in FIG. 6, a bright (white) portion indicates that the makeup color is dark, and a dark (black) portion indicates that the makeup color is light.
- the shape adjusting unit 21 outputs the makeup shape adjusted in size and shape to the weight distribution determining unit 24.
- the skin identification unit 22 identifies a part that is skin in the face image.
- the skin specifying unit 22 determines that a pixel whose pixel color is considered to be a skin color is skin. Specifically, the skin specifying unit 22 specifies the skin color degree for each pixel of the face image to be processed. In the present embodiment, for a portion having a low skin color degree, that is, a portion considered not to be skin, the weight is reduced and the makeup color is overlapped thinly, or the makeup color is hardly synthesized.
- the skin specifying unit 22 outputs the skin color level of each pixel of the face image to be processed to the weight distribution determining unit 24.
- the mask unit 23 generates a mask for the eye part (predetermined part) from the face image to be processed and the position of the feature.
- a makeup shape such as an eyeline is adjusted by the shape adjusting unit 21 according to the contour of the eye. If the detected position of the eye contour is shifted from the original position, the eyeline or the like is in the eye. May get in.
- an eyeline or the like is prevented from accidentally entering the eye.
- the mask unit 23 generates a mask using information on the eye contour obtained by an algorithm different from the eye contour used by the shape adjusting unit 21. By doing so, it is possible to prevent a problem (eye line or the like from entering the eye) that occurs in the shape adjusting unit 21 due to a detection error.
- the generated mask has a value between 0 and 1 for each pixel. Here, it means that the part where the mask value is 1 is not masked, and that the part where the value is small is strongly masked (makeup color is not synthesized). In addition, you may produce
- the mask unit 23 outputs the generated mask to the weight distribution determination unit 24.
- the weight distribution determination unit 24 determines a weight distribution used for color composition (composition of makeup color and skin color) based on the adjusted makeup shape, the skin color degree of the face image, and the mask. Specifically, the weight distribution determination unit 24 calculates the product of the makeup shape, the skin color degree, and the mask for each pixel corresponding to the face image, and sets this product as the weight in each pixel.
- the weight distribution for color synthesis indicates that a portion having a smaller weight value is combined with a lighter makeup color, and a portion having a larger weight value is combined with a darker makeup color.
- the weight distribution determination unit 24 outputs the determined weight distribution to the synthesis unit 17. In addition, the weight distribution determination unit 24 outputs the processing target image, the position of the processing target face image, and the position of the facial feature to the color correction unit 16.
- the color correction unit 16 identifies the representative color of the skin color of the processing target face image based on the processing target image, the position of the processing target face image, and the position of the facial feature.
- a partial color of the face area for example, an average color, a median value, a mode value color, or the like of the center part (near the nose) of the face area may be used as the representative color of the skin color. Further, the average color or the like of the entire face area may be used as the representative color of the skin color.
- an average color of an area having a face is obtained, pixels having a hue different from the average color in the area (an angle with the average color in the CbCr plane is larger than a threshold value), and / or the average color in the area
- the pixels having a large color difference may be excluded, and the average color calculated from the remaining pixels may be used as the representative color.
- the color correction unit 16 corrects the makeup color designated by the user for each pixel of the face image using the color of each pixel and the representative color of the skin color.
- the color correction unit 16 corrects the makeup color for each of the left and right makeup areas so that the difference in color between the left and right makeup areas after synthesis is reduced according to the difference in the representative colors of the left and right makeup areas.
- the color correction unit 16 outputs the makeup color corrected for each pixel to the synthesis unit 17.
- the color correction unit 16 outputs the processing target image and the position of the processing target face image to the combining unit 17.
- the synthesizing unit 17 synthesizes the face image to be processed and the corrected makeup color according to the weight distribution, and generates a face image subjected to the makeup process.
- the composition unit 17 outputs the makeup-processed image to the display control unit 18. Note that the composition unit 17 may output and store the makeup-processed image in the image storage device 4.
- the display control unit 18 outputs the makeup-processed image to the display device 5 and controls the display device 5 to display the makeup-processed image.
- the user selects an image to be processed from, for example, images captured and stored in the image storage device 4 via the instruction input device 2.
- the user can specify the type of makeup (eyeline, eyeshadow, and / or blusher, etc.), the shape of each makeup, and each makeup color applied to the image to be processed via the instruction input device 2. Select from multiple candidates.
- the instruction input device 2 outputs a makeup processing instruction including information indicating the type of makeup, the shape of the makeup, and the makeup color to the image acquisition unit 11 of the image processing device 6.
- FIG. 7 is a flowchart showing the flow of makeup processing in the image processing apparatus 6.
- the image acquisition unit (instruction receiving unit) 11 receives an instruction for the makeup process from the instruction input device 2 and acquires an image to be processed from the image storage device 4 (S1).
- the face detection unit 12 detects a face image included in the image to be processed and specifies the position of the face image (S2).
- the face detection unit 12 may detect a plurality of face images included in the processing target image.
- Feature detection unit 13 detects the position of the facial feature included in the detected facial image (S3).
- the feature detection unit 13 is a facial organ such as an eye (eye, eye corner, upper eyelid contour point, lower eyelid contour point, etc.), mouth (mouth end point, mouth center point, etc.), and nose (apex of the nose, etc.).
- Features (feature points) are detected and their positions are specified.
- the feature detection unit 13 may detect a feature such as a face outline.
- the suitability determination unit 14 determines whether or not the face image is suitable for performing a makeup process based on the detected positions of the facial features (S4). For example, the suitability determination unit 14 stores a face model created by learning in advance the luminance distribution features around the features of facial organs such as eyes, nose and mouth from a plurality of face image samples. The suitability determination unit 14 compares the face model with the detected face image to identify the reliability of the detected feature of the face image and the face orientation.
- the suitability determination unit 14 determines that the face image is not suitable for performing the makeup process.
- the suitability determination unit 14 determines that the face image is not suitable for performing the makeup process.
- the makeup process may not be performed properly.
- the determination unit 14 determines that the face image is not suitable for performing the makeup process.
- the suitability determination unit 14 performs the makeup process on the face image. It is determined that it is not suitable.
- the suitability determination unit 14 may determine that the face image is not suitable for performing the makeup process.
- the suitability determination unit 14 may determine that the face image is not suitable for performing the makeup process.
- the feature detection unit 13 may erroneously detect the object as a feature point of the face.
- the detected feature point is in an unnatural position compared to other feature points (eyes, nose, mouth, etc.)
- the detected feature point is that of another object overlapping the face Can be determined.
- the suitability determination unit 14 uses the makeup process for the face image. You may determine that it is not suitable.
- the determination criteria may differ depending on the type of makeup (eyeline, eyeshadow, blusher, etc.).
- the shape adjusting unit 21 acquires information on the skin color of the face image to be processed (S5).
- skin color information the average color of the entire skin and the average color of each region such as starboard, portside, right cheek, left cheek, and nose are obtained from the face image to be processed.
- the shape adjusting unit 21 sets the processing target to the eyes or the cheeks according to the type of the instructed makeup (S6). In addition, when it is instructed to apply a plurality of makeups, a site to be processed is set according to the type of unprocessed makeup.
- the shape adjusting unit 21 sets one of the left and right organs as a processing target (S7).
- the shape adjustment unit 21 sets the processing target to the right organ (right eye or right cheek).
- the processing target is set to the left organ (left eye or left cheek).
- the weight distribution used for the eye makeup processing (eyeline, eyeshadow, etc.) is calculated (S9).
- FIG. 8 is a flowchart showing a detailed flow of processing for calculating a weight distribution used for eye makeup processing.
- the shape adjusting unit 21 determines the basic shape of the makeup used for the makeup process (S21). For example, in the basic shape of the eye shadow, as shown in FIG. 4, the lower weight close to the outline of the eye is large (the color of the eye shadow is dark), and the weight gradually decreases as the distance from the eye shadow increases (the eye shadow is Weight distribution).
- the shape adjustment unit 21 may deform a basic shape such as an eye shadow or adjust the distribution of weights according to a makeup processing instruction.
- the shape adjusting unit 21 may calculate a makeup basic shape by calculation using a predetermined function, or may select a makeup basic shape to be used from a template of a makeup basic shape prepared in advance.
- the shape adjusting unit 21 deforms the basic makeup shape to be used according to the detected eye characteristics so as to match the eye shape of the face image (S22).
- the shape adjustment unit 21 uses the information on the detected eye characteristics (the eye head, the corner of the eye, the outline of the eye, etc.) to make the size of the makeup basic shape to be used suitable for the eye size of the face image. Change to size.
- the shape adjusting unit 21 is configured so that some representative points of the detected upper eyelid contour coincide with corresponding points of the makeup basic shape whose size has been adjusted. Then, the makeup basic shape whose size is adjusted is deformed, and the arrangement in the face image is determined.
- the portions other than the points corresponding to the representative points in the makeup basic shape may be deformed using linear interpolation, or may be deformed using high-order function interpolation such as a cubic B-spline function.
- the makeup shape whose size and shape are adjusted is used as a weight when combining makeup colors.
- the skin specifying unit 22 specifies the skin color level for each pixel of the face image to be processed (S23).
- the skin specifying unit 22 may specify the skin color degree only for a part of the face image to be processed including the periphery where the makeup process is performed.
- the skin color degree is calculated by using the distance in the color space between the representative color representing the skin color of the face image to be processed and the color of each pixel.
- the average skin color of the entire face area may be used as the representative skin color.
- an average color around the nose may be used as the skin representative color.
- the skin color level is maximized when the pixel color is the same as the representative color of the skin color (distance 0), and decreases as the distance in the color space increases.
- the skin specifying unit 22 acquires the average color near the nose and sets it as the representative color (Yc, Cbc, Crc) of the skin of the face image.
- the YCbCr color space is used as the color space.
- the present invention is not limited to this, and any color space can be used.
- the L * a * b * color space may be used.
- the skin specifying unit 22 uses the representative color (Yc, Cbc, Crc) of the skin of the face image as the center of the skin color, and each pixel value (Y, Cb, Cr) of the face image in the color space and the skin of the face image The distance from the representative colors (Yc, Cbc, Crc) is obtained.
- the skin color degree Ds is obtained for each pixel so that the value is 1 when the distance is 0 and the value is 0 when the distance is infinite.
- the formula for obtaining the skin color degree Ds can be set as follows.
- ⁇ is a constant that determines the skin color range.
- the above equation for obtaining the skin color degree Ds using exp is an example, and an exponential function that monotonously decreases with respect to distance, a sigmoid function, or the like may be used.
- the skin color degree Ds has a value of 0 to 1, and a portion having a large value is a portion having a color close to the representative color of the skin.
- the skin color degree Ds may be calculated from the average color of each block including a plurality of pixels.
- the skin specifying unit 22 compares the distance in the color space with a threshold value to specify whether each pixel is skin, and sets the skin color degree value specified as not skin to 0. You may make it not make a makeup color apply to the location which is not.
- FIG. 9 is an image showing an example of the skin color degree Ds obtained for the face image.
- a bright (white) part indicates a part where the skin color degree Ds is large, and a dark (black) part indicates a part where the skin color degree Ds is small.
- FIG. 9 shows the skin color degree Ds around the right eye. Since the skin color degree Ds is used as a weight when the makeup color is synthesized, the makeup color is darkly superposed at a place where the value of the skin color degree Ds is large (bright place). On the contrary, the makeup color is thinly overlapped or hardly overlapped at a portion where the skin color degree Ds is small and is not considered to be skin (dark portion). Therefore, as can be seen from FIG.
- the makeup color is not synthesized with the pupil and the eyebrows having a low skin color level. Further, when wearing spectacles or the like, it is possible to prevent the makeup color from being combined with the spectacles. Further, when the hair is close to the eyes, it is possible to prevent the makeup color from being combined with the hair.
- the mask unit 23 generates a mask for the eye part (S24). Specifically, an ellipse that passes through a point on the upper eyelid side, the top of the eye, and the corner of the eye corner is obtained with the line connecting the eye point and the corner of the eye as the major axis. The border of the mask on the heel side. Similarly, an ellipse that passes through one point of the lower eyelid side, the eye point, and the eye corner point is defined by taking the line connecting the eye point and the eye corner point as the major axis, and the lower arc of the ellipse is lowered. The border of the mask on the heel side. The inside of the mask surrounded by the upper and lower boundary lines is defined as a mask area.
- the mask unit 23 is configured such that the mask value at the midpoint (center of the mask area) of the corner of the eye and the top of the eye is 0, the mask value on the boundary of the mask area is 1, and the center of the mask area according to the Gaussian distribution
- the mask value of each pixel in the mask area is set so that the mask value increases as the distance from the mask increases. Note that instead of the Gaussian distribution, the mask value may be changed linearly, or the mask value may be changed using another function or table. Further, the mask may not be an ellipse but may have another shape.
- FIG. 10 is an image showing an example of an eye mask corresponding to FIG.
- a bright (white) location indicates a location with a large mask value
- a dark (black) location indicates a location with a small mask value. Since the mask value is used as a weight when combining the makeup color, a portion where the mask value is small (dark portion) is strongly masked, and the makeup color is hardly combined. On the contrary, the mask is weak at a portion where the mask value is large (bright portion), and the makeup color is synthesized without being masked.
- the weight determination unit 24 combines each element representing the weight distribution, that is, the makeup shape whose size and shape are adjusted, the skin color degree Ds, and the mask to obtain a weight distribution used for color synthesis (S25). . Specifically, the weight determination unit 24 obtains, as the weight distribution, the product of the makeup shape whose size and shape are adjusted, the skin color degree Ds, and the mask for each pixel.
- FIG. 11 is an image showing the product of the skin color degree Ds and the mask corresponding to FIG. Compared with FIG. 9, it can be seen that the eye portion is masked by the mask. It should be noted that the makeup color is overlaid darker for pixels that are brightly shown in FIG.
- the weight determination unit 24 may determine whether each pixel is skin by comparing the product of the skin color degree Ds and the mask with a predetermined threshold (for example, 0.5). . Then, for example, the value of a pixel determined to be skin may be 1, and the value of a pixel determined to be non-skin may be 0 to binarize the weight. Alternatively, the weight may be set to 0 only for pixels whose products are smaller than a predetermined threshold.
- a predetermined threshold for example, 0.5
- FIG. 12 is an image showing the weight distribution corresponding to FIG.
- the weight distribution is a product of the adjusted makeup shape, the skin color degree Ds, and the mask
- FIG. 12 shows a weight distribution obtained by multiplying the weight shown in FIG. 6 and the weight shown in FIG. 11 for each pixel.
- a bright (white) location indicates a location with a large weight
- a dark (black) location indicates a location with a low weight.
- What is shown in FIG. 12 is the final weight, and a bright (white) portion is darkly painted. This completes the calculation process of the weight distribution used for the eye makeup process.
- FIG. 13 is a flowchart showing a detailed flow of the process of calculating the weight distribution used for the cheek makeup process.
- the point that the mask processing of the eyes is not required is different, but the other processing is the same as in the case of the eyes, and thus will be described briefly.
- the shape adjusting unit 21 determines the basic shape of the makeup used for the makeup process (S31). For example, in the basic shape of blusher, as shown in FIG. 5, the weight near the center of the blusher application region is the largest (blusher color is dark), and the weight gradually decreases as the distance from the center decreases (blusher color is lighter). A weight distribution.
- the shape adjusting unit 21 deforms the basic makeup shape to be used according to the detected eye, mouth, and nose characteristics so as to match the shape of the cheek of the face image (S32).
- the shape adjusting unit 21 changes the size of the makeup basic shape to be used to a size suitable for the size of the cheek of the face image based on the positional relationship of the detected features such as eyes, mouth, and nose. .
- the shape adjusting unit 21 estimates the positions of some representative points on the cheek from the positional relationship of features such as eyes, mouth, and nose.
- the shape adjusting unit 21 deforms the makeup basic shape whose size has been adjusted so that the representative point and the corresponding point of the makeup basic shape whose size has been adjusted respectively match.
- the skin specifying unit 22 specifies the skin color degree Ds for each pixel of the face image to be processed (S33). This process is the same as in the eye makeup process.
- the weight determination unit 24 combines each element representing the weight distribution, that is, the makeup shape whose size and shape are adjusted, and the skin color degree Ds to obtain a weight distribution used for color synthesis (S34). Specifically, the weight determination unit 24 obtains the product of the makeup shape whose size and shape are adjusted and the skin color degree Ds for each pixel as the weight distribution. This completes the calculation process of the weight distribution used for the cheek makeup process.
- the color correction unit 16 corrects the makeup color designated by the user and obtains a makeup color corrected for each pixel used for composition (S11).
- the color correction unit 16 performs correction based on the difference in color of each pixel in the heel area (or cheek area) and correction based on the difference in brightness (luminance) between the left and right heel areas (or cheek areas).
- the color correction unit 16 acquires a representative color (Yo, Cbo, Cro) of the skin color of the area to be applied.
- the representative color of the skin color may be an average color of the region. Moreover, you may use the average color of the skin color of the whole face area
- the YCbCr color space is used as the color space, but the present invention is not limited to this.
- the color correction unit 16 obtains ⁇ and r from the makeup colors (Ys, Cbs, Crs) specified by the user and the representative colors (Yo, Cbo, Cro) of the skin color.
- ⁇ is an angle formed by the vector (Cbs, Crs) and the vector (Cbo, Cro) on the CbCr plane.
- R Ys / Yo.
- ⁇ can be said to be a difference in hue or hue between the makeup color and the representative color of the skin.
- R represents the ratio of the luminance between the makeup color and the representative color of the skin color.
- the color correction unit 16 obtains, for each pixel, a makeup color (Y ′, Cb ′, Cr ′) that is superimposed (synthesized) on each pixel value (Y, Cb, Cr) of the face image.
- Cb ′ and Cr ′ are determined so that the angle formed by the vector (Cb ′, Cr ′) and the vector (Cb, Cr) in the CbCr plane is ⁇ .
- the color correction unit 16 uses the luminance ratio and the hue difference between the makeup color designated by the user and the representative color of the skin, and uses the difference in hue according to the skin color (each pixel value) of the face image.
- the corrected makeup colors (Y ′, Cb ′, Cr ′) are obtained. Note that the makeup color may be corrected using only one of the luminance ratio (or difference) and the hue difference.
- FIG. 14 is a diagram showing a relationship in the color space between the corrected makeup color (Y ′, Cb ′, Cr ′) and the corresponding pixel value (Y, Cb, Cr) of the face image.
- the relationship ( ⁇ , r) in the color space between each pixel value (Y, Cb, Cr) of the face image and the corresponding corrected makeup color (Y ′, Cb ′, Cr ′). Is the same as the relationship between the representative colors (Yo, Cbo, Cro) of the skin color and the makeup colors (Ys, Cbs, Crs) specified by the user, Correct the makeup color.
- the makeup color designated by the user may be used as it is without correcting each pixel.
- ⁇ (0 ⁇ ⁇ ⁇ 0.5) is a parameter for adjusting the difference in the appearance of the left and right makeups, and may be set in advance for each type of makeup or specified by the user. Good.
- the makeup color may be corrected using a representative luminance (representative color) representative of the brightness of the makeup area, such as the median luminance of the left and right makeup areas.
- the makeup image (Y ′, Cb ′, Cr ′) after correction for each pixel is used as the face image.
- the makeup color may look different on the left and right. Therefore, the luminance Y ′ of the makeup color is corrected so that the luminance difference between the left and right of the makeup color is reduced, and Yl ′ and Yr ′ are obtained.
- the synthesizer 17 applies (colors) the makeup color to the face image by synthesizing (superimposing) the corrected makeup color on the color of the face image to be processed using the weight distribution (S12). More specifically, the combining unit 17 combines each pixel with the corrected makeup color by multiplying the weight w of the pixel with the color of the pixel of the face image.
- the color (Ya, Cba, Cra) of each pixel after synthesis is obtained using, for example, the following equation.
- Ya (1 ⁇ ⁇ w) ⁇ Y + ⁇ ⁇ w ⁇ Yl ′ (for port side, left cheek)
- Ya (1 ⁇ ⁇ w) ⁇ Y + ⁇ ⁇ w ⁇ Yr ′ (in the case of starboard, right cheek)
- Cba (1-w) ⁇ Cb + w ⁇ Cb ′
- Cra (1-w) ⁇ Cr + w ⁇ Cr ′
- w is a weight for each pixel
- ⁇ (0 ⁇ ⁇ 1) is a parameter for adjusting the weight for luminance.
- the change in luminance has a large visual influence, and when the luminance is greatly changed by makeup, it looks unnatural. Therefore, the synthesis unit 17 suppresses the change in luminance due to the makeup and synthesizes the makeup color with the face image.
- the display control unit 18 displays the image after the makeup process on the display device 5 and ends the makeup process.
- the skin color degree of the face image to be processed is determined, and the makeup process is performed on the portion considered to be skin according to the skin color degree.
- the weight of the makeup process is reduced or the makeup process is not performed. Therefore, even when a part of the area to be made up is covered with other objects such as glasses or hair, it is possible to prevent other objects from being applied with makeup, and to apply makeup only to the skin for natural makeup processing. An image can be obtained.
- the makeup process is performed according to the skin color degree, so that it is possible to prevent the makeup process from being performed in the eyes or out of the face range. Therefore, the user can easily perform the makeup simulation only by selecting the type, shape, color, etc. of the makeup first.
- the detected feature points (eye corners, eye corners, eye contours) due to individual differences in eye contour shape, face orientation of the face image is not front, or the eye contour is not clear due to lighting.
- An error may occur in the position of a point.
- an eyeline or eyeshadow may enter the eye.
- the mask unit 23 defines the eye region and masks the eye region by a method different from the method in which the shape adjusting unit 21 adjusts the makeup shape. For this reason, even when the makeup shape is arranged so as to overlap the eye, the eye region is masked, so that the makeup can be prevented from entering the eye.
- the left and right illuminations are not uniformly applied during imaging, and the left and right skins may not have the same brightness due to shadows on either the left or right side of the face image.
- combining the same makeup color with different skin colors on the left and right reflects the skin color difference, and the combined makeup color is different on the left and right. It may look like
- the makeup color to be applied to each of the left and right makeup regions is corrected according to the difference in skin color between the left and right makeup regions, and the makeup color used for the synthesis is changed to a different color on the left and right.
- the difference in color of the makeup region after the makeup has been synthesized can be reduced, and a natural-looking makeup process can be performed.
- the makeup process is performed on the face image determined to be suitable. Therefore, failure due to the makeup process can be prevented, and the makeup process can be performed only on the face image suitable for the makeup.
- a digital camera provided with an image processing apparatus has been described as an example.
- the present invention is not limited to this, and the present invention can also be applied to a digital video camera, a camera-equipped mobile phone, a computer, and the like.
- the captured image may be acquired via a web camera, a network, a removable storage device, or the like.
- the makeup process may be performed not only on the captured still image but also on a face image such as a moving image.
- a make-up process may be performed on a preview image displayed on the display device of the digital camera when imaging is performed with the digital camera.
- an arbitrary pattern may be synthesized on the face or skin of a person image.
- the applied makeup color is corrected to a different color on the left and right so that the difference in color (brightness) between the left and right makeup areas after synthesis is reduced.
- the same makeup color is not limited to the left and right.
- the difference in the skin color of each makeup area (for example, the difference from the average skin color of each makeup area) so that the difference in color (luminance) of the plurality of makeup areas after synthesis is reduced in a plurality of different makeup areas to be applied. ) May be used to correct the makeup color to be applied for each makeup region.
- An image processing apparatus is an image processing apparatus that performs a process of coloring a pattern of a certain color on the skin of a person image, and in order to solve the above-described problem, at least a partial region of the person image For each part, a skin specifying part that specifies the skin color degree of the color in the person image, and a coloring part that colors the pattern in the person image according to the density corresponding to the skin color degree are provided. .
- An image processing method is an image processing method that performs a process of coloring a pattern of a certain color on the skin of a person image, and in order to solve the above-described problem, at least a partial region of the person image
- the skin color degree of each part of at least a partial region of the person image is specified, and the pattern is colored on the person image with a density corresponding to the skin color degree. Therefore, the pattern that is considered to be skin can be colored deeply, and the part that is not considered to be skin (for example, hair, glasses, etc.) can be lightly colored or not colored. Therefore, a pattern such as makeup can be appropriately colored on the skin of the person image. Therefore, for example, a makeup simulation can be performed using images taken under a wide range of conditions without preparing images with raised bangs, glasses, or illumination.
- the image processing apparatus includes a weight distribution determining unit that determines a weight distribution reflecting the degree of the skin color of each part of the partial area of the person image, and the coloring unit determines the weight of the weight distribution.
- a configuration may be used in which the color of the pattern is superimposed on each part of the partial area of the person image.
- the original color of the person image and the color of the pattern are synthesized with the weight reflecting the skin color degree. Therefore, by reducing the weight of a portion that is not considered to be skin, it is possible to suppress the synthesis of the pattern color in a portion that is not skin (for example, hair, glasses, etc.).
- the image processing apparatus includes a detection unit that detects a position of a predetermined part of the person image, and a mask unit that generates a mask that suppresses coloring of the predetermined part based on the detected position.
- the weight distribution determining unit may determine a weight distribution reflecting the skin color degree and the mask.
- the image processing apparatus detects whether or not the face of the person image is suitable as an object to be colored based on the detection unit that detects a position of a predetermined part of the person image and the detected position.
- the pattern coloring process is performed, so that the failure of the pattern coloring process can be prevented. it can.
- the suitability determination unit specifies the face direction of the person image based on the detected position, and when the face direction of the person image is within a predetermined range, the face of the person image is It may be determined that the pattern is suitable for coloring.
- the face orientation of a person image is, for example, a sideways rather than a front side, it is difficult to color a makeup pattern on the face.
- the face orientation of the person image is within a predetermined range, it is determined that the face of the person image is suitable as an object for coloring the pattern, so that makeup processing can be performed.
- a person image can be determined appropriately.
- the skin specifying unit is configured to determine the person image based on a distance in a color space between a representative color representing the skin color of the person image and colors of each part of the partial area of the person image.
- the skin color degree may be specified for each part of the partial area.
- region of a person image is based on whether the distance in the color space with the representative color of skin is near, ie, it is a color close to the representative color of skin.
- the degree can be specified. Therefore, a pattern can be colored in the place considered to be skin appropriately.
- the coloring section may color the pattern as a makeup on the face of the person image.
- makeup can be appropriately applied to the portion of the human image that is the skin of the face.
- An image processing apparatus is an image processing apparatus that performs a process of coloring a pattern of a certain color on the skin of a person image, and in order to solve the above-described problem, the portion of the person image that is the skin And a coloring part for coloring the pattern at a location that is the specified skin.
- An image processing method is an image processing method for performing a process of coloring a pattern of a certain color on the skin of a person image, and in order to solve the above-described problem, a portion of the person image that is skin And a coloring step of coloring the pattern at the location of the specified skin.
- the portion that is the skin of the person image is specified, and the pattern is colored only on the portion that is the skin of the person image. Therefore, a pattern such as makeup can be appropriately colored on the skin of the person image.
- the image processing apparatus may be partially realized by a computer.
- a control program that causes the image processing apparatus to be realized by the computer by causing the computer to operate as the respective units, and the control program
- a computer-readable recording medium on which is recorded also falls within the scope of the present invention.
- each block of the image processing device 6, particularly the image acquisition unit 11, face detection unit 12, feature detection unit 13, suitability determination unit 14, makeup shape determination unit 15, color correction unit 16, composition unit 17, display control unit 18, the shape adjusting unit 21, the skin specifying unit 22, the mask unit 23, and the weight distribution determining unit 24 may be configured by hardware logic, or by software using a CPU (central processing unit) as follows. It may be realized.
- the image processing apparatus 6 includes a CPU that executes instructions of a control program that realizes each function, a ROM (read only memory) that stores the program, a RAM (random access memory) that develops the program, the program, and various types
- a storage device such as a memory for storing data is provided.
- An object of the present invention is a recording medium on which a program code (execution format program, intermediate code program, source program) of a control program of the image processing apparatus 6 which is software for realizing the functions described above is recorded so as to be readable by a computer. This can also be achieved by supplying the image processing apparatus 6 and reading and executing the program code recorded on the recording medium by the computer (or CPU or MPU (microprocessor unit)).
- Examples of the recording medium include a tape system such as a magnetic tape and a cassette tape, a magnetic disk such as a floppy (registered trademark) disk / hard disk, a CD-ROM (compact disk-read-only memory) / MO (magneto-optical) / Disc system including optical disc such as MD (Mini Disc) / DVD (digital versatile disc) / CD-R (CD Recordable), card system such as IC card (including memory card) / optical card, or mask ROM / EPROM ( A semiconductor memory system such as erasable, programmable, read-only memory, EEPROM (electrically erasable, programmable, read-only memory) / flash ROM, or the like can be used.
- a tape system such as a magnetic tape and a cassette tape
- a magnetic disk such as a floppy (registered trademark) disk / hard disk
- the image processing apparatus 6 may be configured to be connectable to a communication network, and the program code may be supplied via the communication network.
- the communication network is not particularly limited.
- the Internet an intranet, an extranet, a LAN (local area network), an ISDN (integrated services network, digital network), a VAN (value-added network), and a CATV (community antenna) television communication.
- a network, a virtual private network, a telephone line network, a mobile communication network, a satellite communication network, etc. can be used.
- the transmission medium constituting the communication network is not particularly limited.
- IEEE institute of electrical and electronic engineering
- USB power line carrier
- cable TV line telephone line
- ADSL asynchronous digital subscriber loop
- Bluetooth registered trademark
- 802.11 wireless high data rate
- mobile phone network satellite line, terrestrial digital network, etc. But it is available.
- the present invention can be used for a digital camera equipped with an image processing apparatus.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- General Health & Medical Sciences (AREA)
- Architecture (AREA)
- Computer Graphics (AREA)
- Computer Hardware Design (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Image Processing (AREA)
- Color Image Communication Systems (AREA)
- Studio Devices (AREA)
- Image Analysis (AREA)
- Facsimile Image Signal Circuits (AREA)
Abstract
Description
図1は、本実施の形態に係るデジタルカメラ1の概略構成を示すブロック図である。デジタルカメラ1は、指示入力装置2、撮像装置3、画像記憶装置4、表示装置5、および画像処理装置6を備える。
画像処理装置6は、画像取得部11、顔検出部12、特徴検出部(検出部)13、適否判定部14、メーキャップ形状決定部15、色補正部16、合成部(着色部)17、および表示制御部18を備える。
以下に、デジタルカメラ1におけるメーキャップ処理の流れについて説明する。
Yl’=Y’-γd
Yr’=Y’+γd
ここで、γ(0≦γ≦0.5)は左右のメーキャップの見え方の違いを調整するパラメータであり、メーキャップの種類毎にあらかじめ設定されていてもよいし、利用者が指定してもよい。なお、左右いずれかのメーキャップ色を基準にして、もう一方のメーキャップ色の輝度のみを補正してもよい。また、左右の平均輝度の比(Yl/Yr)を用いて、Yr’=Y’(Yl/Yr)のように補正してもよい。また、左右の平均輝度を用いる代わりに、左右のメーキャップ領域の輝度の中央値等、メーキャップ領域の明るさを代表する代表輝度(代表色)を用いてメーキャップ色を補正してもよい。
Ya=(1-α×w)×Y+α×w×Yl’ (左瞼、左頬の場合)
Ya=(1-α×w)×Y+α×w×Yr’ (右瞼、右頬の場合)
Cba=(1-w)×Cb+w×Cb’
Cra=(1-w)×Cr+w×Cr’
ここで、wは各ピクセルについての重みであり、α(0<α≦1)は輝度について重みを調整するパラメータである。輝度の変化は視覚的な影響が大きく、メーキャップによって輝度が大きく変化すると不自然に見えるため、合成部17は、メーキャップによる輝度の変化を抑えて、顔画像にメーキャップ色を合成する。
本発明に係る画像処理装置は、人物画像の肌に、ある色の模様を着色する処理を行う画像処理装置であって、上記の課題を解決するために、上記人物画像の少なくとも一部の領域の箇所毎に、上記人物画像における色の肌色度合いを特定する肌特定部と、上記人物画像に、上記肌色度合いに応じた濃さで上記模様を着色する着色部とを備えることを特徴としている。
2 指示入力装置
3 撮像装置
4 画像記憶装置
5 表示装置
6 画像処理装置
11 画像取得部(指示受領部)
12 顔検出部
13 特徴検出部(検出部)
14 適否判定部
15 メーキャップ形状決定部
16 色補正部
17 合成部(着色部)
18 表示制御部
21 形状調整部
22 肌特定部
23 マスク部
24 重み分布決定部
Claims (12)
- 人物画像の肌に、ある色の模様を着色する処理を行う画像処理装置であって、
上記人物画像の少なくとも一部の領域の箇所毎に、上記人物画像における色の肌色度合いを特定する肌特定部と、
上記人物画像に、上記肌色度合いに応じた濃さで上記模様を着色する着色部とを備えることを特徴とする画像処理装置。 - 上記人物画像の上記一部の領域の各箇所の上記肌色度合いを反映した重み分布を決定する重み分布決定部を備え、
上記着色部は、上記重み分布の重みを用いて、上記人物画像の上記一部の領域の各箇所の色に上記模様の色を重ねることによって着色することを特徴とする請求項1に記載の画像処理装置。 - 上記人物画像の所定の部位の位置を検出する検出部と、
検出された上記位置に基づき、上記所定の部位に着色することを抑制するマスクを生成するマスク部とを備え、
上記重み分布決定部は、上記肌色度合いと上記マスクとを反映した重み分布を決定することを特徴とする請求項2に記載の画像処理装置。 - 上記人物画像の所定の部位の位置を検出する検出部と、
検出された上記位置に基づき、上記人物画像の顔が、模様を着色する対象として適しているか否かを判定する適否判定部とを備え、
上記人物画像の顔が、模様を着色する対象として適していると判定された場合に、上記着色部は、上記人物画像の顔に対して上記模様を着色することを特徴とする請求項1または2に記載の画像処理装置。 - 上記適否判定部は、検出された上記位置に基づき、上記人物画像の顔の向きを特定し、上記人物画像の顔の向きが所定の範囲内にある場合、上記人物画像の顔が、模様を着色する対象として適していると判定することを特徴とする請求項4に記載の画像処理装置。
- 上記肌特定部は、上記人物画像の肌の色を代表する代表色と、上記人物画像の上記一部の領域の各箇所の色との間の色空間における距離に基づき、上記人物画像の上記一部の領域の各箇所について上記肌色度合いを特定することを特徴とする請求項1から5のいずれか一項に記載の画像処理装置。
- 上記着色部は、上記人物画像の顔に、メーキャップとして上記模様を着色することを特徴とする請求項1から6のいずれか一項に記載の画像処理装置。
- 人物画像の肌に、ある色の模様を着色する処理を行う画像処理装置であって、
上記人物画像の、肌である箇所を特定する肌特定部と、
上記特定された肌である箇所に、上記模様を着色する着色部とを備えることを特徴とする画像処理装置。 - 人物画像の肌に、ある色の模様を着色する処理を行う画像処理方法であって、
上記人物画像の少なくとも一部の領域の箇所毎に、上記人物画像における色の肌色度合いを特定する肌特定ステップと、
上記人物画像に、上記肌色度合いに応じた濃さで上記模様を着色する着色ステップとを含むことを特徴とする画像処理方法。 - 人物画像の肌に、ある色の模様を着色する処理を行う画像処理方法であって、
上記人物画像の、肌である箇所を特定する肌特定ステップと、
上記特定された肌である箇所に、上記模様を着色する着色ステップとを含むことを特徴とする画像処理方法。 - 人物画像の肌に、ある色の模様を着色する処理を行う画像処理装置の制御プログラムであって、
上記人物画像の少なくとも一部の領域の箇所毎に、上記人物画像における色の肌色度合いを特定する肌特定ステップと、
上記人物画像に、上記肌色度合いに応じた濃さで上記模様を着色する着色ステップとをコンピュータに実行させる制御プログラム。 - 人物画像の肌に、ある色の模様を着色する処理を行う画像処理装置の制御プログラムであって、
上記人物画像の、肌である箇所を特定する肌特定ステップと、
上記特定された肌である箇所に、上記模様を着色する着色ステップとをコンピュータに実行させる制御プログラム。
Priority Applications (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020137009836A KR101614193B1 (ko) | 2010-10-29 | 2011-03-17 | 화상 처리 장치, 화상 처리 방법, 및 제어 프로그램이 기록된 기록 매체 |
US13/878,109 US20130271485A1 (en) | 2010-10-29 | 2011-03-17 | Image-processing device, image-processing method, and control program |
EP11835887.8A EP2615576B1 (en) | 2010-10-29 | 2011-03-17 | Image-processing device, image-processing method, and control program |
CN201180050443.6A CN103180872B (zh) | 2010-10-29 | 2011-03-17 | 图像处理装置及图像处理方法 |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2010-244186 | 2010-10-29 | ||
JP2010244186A JP4862955B1 (ja) | 2010-10-29 | 2010-10-29 | 画像処理装置、画像処理方法、および制御プログラム |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2012056743A1 true WO2012056743A1 (ja) | 2012-05-03 |
Family
ID=45604577
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2011/056449 WO2012056743A1 (ja) | 2010-10-29 | 2011-03-17 | 画像処理装置、画像処理方法、および制御プログラム |
Country Status (6)
Country | Link |
---|---|
US (1) | US20130271485A1 (ja) |
EP (1) | EP2615576B1 (ja) |
JP (1) | JP4862955B1 (ja) |
KR (1) | KR101614193B1 (ja) |
CN (1) | CN103180872B (ja) |
WO (1) | WO2012056743A1 (ja) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2014167831A1 (ja) * | 2013-04-08 | 2014-10-16 | 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 | メイクアップ塗材が塗布された状態を仮想的に再現することができる画像処理装置、画像処理方法、プログラム |
Families Citing this family (31)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9082222B2 (en) * | 2011-01-18 | 2015-07-14 | Disney Enterprises, Inc. | Physical face cloning |
JP6288404B2 (ja) * | 2013-02-28 | 2018-03-07 | パナソニックIpマネジメント株式会社 | メイクアップ支援装置、メイクアップ支援方法、およびメイクアップ支援プログラム |
CN104822292B (zh) * | 2013-08-30 | 2019-01-04 | 松下知识产权经营株式会社 | 化妆辅助装置、化妆辅助***、化妆辅助方法以及化妆辅助程序 |
JP6288816B2 (ja) * | 2013-09-20 | 2018-03-07 | 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 |
CN103971389B (zh) * | 2014-04-28 | 2017-02-15 | 拓维信息***股份有限公司 | 一种面向***的迷彩脸谱实现方法 |
JP6369246B2 (ja) | 2014-09-08 | 2018-08-08 | オムロン株式会社 | 似顔絵生成装置、似顔絵生成方法 |
JP6086112B2 (ja) * | 2014-12-08 | 2017-03-01 | 株式会社メイクソフトウェア | 画像処理装置、画像処理方法及びコンピュータプログラム |
JP6458570B2 (ja) * | 2015-03-12 | 2019-01-30 | オムロン株式会社 | 画像処理装置および画像処理方法 |
JP6458569B2 (ja) | 2015-03-12 | 2019-01-30 | オムロン株式会社 | 画像処理装置および画像処理方法 |
JP6583660B2 (ja) | 2015-03-26 | 2019-10-02 | パナソニックIpマネジメント株式会社 | 画像合成装置及び画像合成方法 |
TWI537875B (zh) * | 2015-04-08 | 2016-06-11 | 大同大學 | 影像合成方法與影像處理裝置 |
JP6573193B2 (ja) * | 2015-07-03 | 2019-09-11 | パナソニックIpマネジメント株式会社 | 判定装置、判定方法、および判定プログラム |
CN105427238B (zh) * | 2015-11-30 | 2018-09-04 | 维沃移动通信有限公司 | 一种图像处理方法及移动终端 |
CN106846240B (zh) * | 2015-12-03 | 2021-05-07 | 斑马智行网络(香港)有限公司 | 一种调整融合素材的方法、装置和设备 |
US11741639B2 (en) | 2016-03-02 | 2023-08-29 | Holition Limited | Locating and augmenting object features in images |
GB2601067B (en) * | 2016-03-02 | 2022-08-31 | Holition Ltd | Locating and augmenting object features in images |
JP6314322B2 (ja) * | 2016-06-20 | 2018-04-25 | 株式会社メイクソフトウェア | 画像処理装置、画像処理方法及びコンピュータプログラム |
JP6055160B1 (ja) * | 2016-07-08 | 2016-12-27 | 株式会社オプティム | 化粧品情報提供システム、化粧品情報提供装置、化粧品情報提供方法、及びプログラム |
JPWO2018079255A1 (ja) | 2016-10-24 | 2019-09-12 | パナソニックIpマネジメント株式会社 | 画像処理装置、画像処理方法、および画像処理プログラム |
JP6753276B2 (ja) * | 2016-11-11 | 2020-09-09 | ソニー株式会社 | 情報処理装置、および情報処理方法、並びにプログラム |
JP6720882B2 (ja) * | 2017-01-19 | 2020-07-08 | 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 |
TWI731923B (zh) * | 2017-01-23 | 2021-07-01 | 香港商斑馬智行網絡(香港)有限公司 | 調整融合材料的方法、裝置和設備 |
JP2017201550A (ja) * | 2017-06-23 | 2017-11-09 | 株式会社メイクソフトウェア | 画像処理装置、画像処理方法及びコンピュータプログラム |
JP2019070870A (ja) * | 2017-10-05 | 2019-05-09 | 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 |
CN108399654B (zh) | 2018-02-06 | 2021-10-22 | 北京市商汤科技开发有限公司 | 描边特效程序文件包的生成及描边特效生成方法与装置 |
CN108564526A (zh) * | 2018-03-30 | 2018-09-21 | 北京金山安全软件有限公司 | 一种图像处理方法、装置、电子设备及介质 |
CN109102484B (zh) * | 2018-08-03 | 2021-08-10 | 北京字节跳动网络技术有限公司 | 用于处理图像的方法和装置 |
JP6635170B2 (ja) * | 2018-10-22 | 2020-01-22 | 辰巳電子工業株式会社 | 写真撮影遊戯装置、画像処理方法、及び画像処理プログラム |
CN109685713B (zh) * | 2018-11-13 | 2024-05-10 | 平安科技(深圳)有限公司 | 化妆模拟控制方法、装置、计算机设备及存储介质 |
CN110827195B (zh) * | 2019-10-31 | 2023-09-22 | 北京达佳互联信息技术有限公司 | 虚拟物品添加方法、装置、电子设备及存储介质 |
CN111583139B (zh) * | 2020-04-27 | 2023-06-20 | 抖音视界有限公司 | 腮红调整方法、装置、电子设备及计算机可读介质 |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2000279228A (ja) | 1999-03-29 | 2000-10-10 | Shiseido Co Ltd | 頬紅メーキャップシミュレーションシステム |
JP2000285222A (ja) | 1999-03-29 | 2000-10-13 | Shiseido Co Ltd | 目元メーキャップシミュレーションシステム |
JP2004303193A (ja) * | 2003-03-20 | 2004-10-28 | Omron Corp | 画像処理装置 |
JP2007257165A (ja) * | 2006-03-22 | 2007-10-04 | Kao Corp | メイクアップシミュレーション方法 |
JP2008243059A (ja) * | 2007-03-28 | 2008-10-09 | Fujifilm Corp | 画像処理装置及び画像処理方法 |
JP2008276405A (ja) * | 2007-04-26 | 2008-11-13 | Kao Corp | 顔画像の合成方法及び合成装置 |
JP2010211308A (ja) * | 2009-03-06 | 2010-09-24 | Fujifilm Corp | メイクアップアドバイス装置、メイクアップアドバイス方法及びプログラム |
Family Cites Families (21)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6137903A (en) * | 1997-06-03 | 2000-10-24 | Linotype-Hell Ag | Color transformation system based on target color image |
JP2000209425A (ja) * | 1998-11-09 | 2000-07-28 | Canon Inc | 画像処理装置及び方法並びに記憶媒体 |
DE1202209T1 (de) * | 2000-04-21 | 2002-11-28 | Shiseido Co Ltd | Schminkratgeber. |
US6937755B2 (en) * | 2000-06-27 | 2005-08-30 | Rami Orpaz | Make-up and fashion accessory display and marketing system and method |
US7079158B2 (en) * | 2000-08-31 | 2006-07-18 | Beautyriot.Com, Inc. | Virtual makeover system and method |
JP4849761B2 (ja) * | 2002-09-02 | 2012-01-11 | 株式会社 資生堂 | 質感に基づく化粧方法及び質感イメージマップ |
US7382378B2 (en) * | 2003-10-30 | 2008-06-03 | Sensable Technologies, Inc. | Apparatus and methods for stenciling an image |
US7773091B2 (en) * | 2004-09-07 | 2010-08-10 | L'oreal | Method and device for generating a synthesized image of at least one fringe of lashes |
US20070058858A1 (en) * | 2005-09-09 | 2007-03-15 | Michael Harville | Method and system for recommending a product based upon skin color estimated from an image |
WO2007063878A1 (ja) * | 2005-12-01 | 2007-06-07 | Shiseido Company, Ltd. | 顔分類方法、顔分類装置、分類マップ、顔分類プログラム、及び該プログラムが記録された記録媒体 |
WO2007074844A1 (ja) * | 2005-12-28 | 2007-07-05 | Kao Corporation | 顔パーツの位置の検出方法及び検出システム |
EP1975870B1 (en) * | 2006-01-17 | 2020-08-26 | Shiseido Co., Ltd. | Makeup simulation system, makeup simulation device, makeup simulation method, and makeup simulation program |
JP4946672B2 (ja) * | 2007-07-04 | 2012-06-06 | オムロン株式会社 | 脇見検出装置および方法、並びに、プログラム |
JP2009064423A (ja) * | 2007-08-10 | 2009-03-26 | Shiseido Co Ltd | メイクアップシミュレーションシステム、メイクアップシミュレーション装置、メイクアップシミュレーション方法およびメイクアップシミュレーションプログラム |
JP4962224B2 (ja) * | 2007-08-31 | 2012-06-27 | セイコーエプソン株式会社 | 画像処理装置、画像処理方法およびコンピュータプログラム |
JP5432532B2 (ja) * | 2008-01-22 | 2014-03-05 | 株式会社 資生堂 | 化粧方法、化粧シミュレーション装置、及び化粧シミュレーションプログラム |
US20090234716A1 (en) * | 2008-03-17 | 2009-09-17 | Photometria, Inc. | Method of monetizing online personal beauty product selections |
JP2009290660A (ja) * | 2008-05-30 | 2009-12-10 | Seiko Epson Corp | 画像処理装置、画像処理方法、画像処理プログラムおよび印刷装置 |
US8369625B2 (en) * | 2008-06-30 | 2013-02-05 | Korea Institute Of Oriental Medicine | Method for grouping 3D models to classify constitution |
JP4748271B2 (ja) * | 2009-01-28 | 2011-08-17 | 株式会社ニコン | 電子カメラおよび画像処理プログラム |
JP4760999B1 (ja) * | 2010-10-29 | 2011-08-31 | 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 |
-
2010
- 2010-10-29 JP JP2010244186A patent/JP4862955B1/ja active Active
-
2011
- 2011-03-17 WO PCT/JP2011/056449 patent/WO2012056743A1/ja active Application Filing
- 2011-03-17 KR KR1020137009836A patent/KR101614193B1/ko active IP Right Grant
- 2011-03-17 US US13/878,109 patent/US20130271485A1/en not_active Abandoned
- 2011-03-17 CN CN201180050443.6A patent/CN103180872B/zh active Active
- 2011-03-17 EP EP11835887.8A patent/EP2615576B1/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2000279228A (ja) | 1999-03-29 | 2000-10-10 | Shiseido Co Ltd | 頬紅メーキャップシミュレーションシステム |
JP2000285222A (ja) | 1999-03-29 | 2000-10-13 | Shiseido Co Ltd | 目元メーキャップシミュレーションシステム |
JP2004303193A (ja) * | 2003-03-20 | 2004-10-28 | Omron Corp | 画像処理装置 |
JP2007257165A (ja) * | 2006-03-22 | 2007-10-04 | Kao Corp | メイクアップシミュレーション方法 |
JP2008243059A (ja) * | 2007-03-28 | 2008-10-09 | Fujifilm Corp | 画像処理装置及び画像処理方法 |
JP2008276405A (ja) * | 2007-04-26 | 2008-11-13 | Kao Corp | 顔画像の合成方法及び合成装置 |
JP2010211308A (ja) * | 2009-03-06 | 2010-09-24 | Fujifilm Corp | メイクアップアドバイス装置、メイクアップアドバイス方法及びプログラム |
Non-Patent Citations (1)
Title |
---|
See also references of EP2615576A4 |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2014167831A1 (ja) * | 2013-04-08 | 2014-10-16 | 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 | メイクアップ塗材が塗布された状態を仮想的に再現することができる画像処理装置、画像処理方法、プログラム |
CN104380339A (zh) * | 2013-04-08 | 2015-02-25 | 松下电器(美国)知识产权公司 | 能够将涂敷了化妆涂料的状态虚拟地再现的图像处理装置、图像处理方法、程序 |
JPWO2014167831A1 (ja) * | 2013-04-08 | 2017-02-16 | 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Panasonic Intellectual Property Corporation of America | メイクアップ塗材が塗布された状態を仮想的に再現することができる画像処理装置、画像処理方法、プログラム |
US9603437B2 (en) | 2013-04-08 | 2017-03-28 | Panasonic Intellectual Property Corporation Of America | Image processing device, image processing method, and program, capable of virtual reproduction of makeup application state |
CN104380339B (zh) * | 2013-04-08 | 2018-11-30 | 松下电器(美国)知识产权公司 | 图像处理装置、图像处理方法、以及介质 |
Also Published As
Publication number | Publication date |
---|---|
CN103180872A (zh) | 2013-06-26 |
EP2615576B1 (en) | 2019-11-13 |
KR101614193B1 (ko) | 2016-04-20 |
KR20130101058A (ko) | 2013-09-12 |
JP4862955B1 (ja) | 2012-01-25 |
US20130271485A1 (en) | 2013-10-17 |
CN103180872B (zh) | 2016-08-10 |
EP2615576A4 (en) | 2014-05-14 |
JP2012098808A (ja) | 2012-05-24 |
EP2615576A1 (en) | 2013-07-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP4862955B1 (ja) | 画像処理装置、画像処理方法、および制御プログラム | |
JP4760999B1 (ja) | 画像処理装置、画像処理方法、および制御プログラム | |
CN108229278B (zh) | 人脸图像处理方法、装置和电子设备 | |
US9142054B2 (en) | System and method for changing hair color in digital images | |
WO2022179215A1 (zh) | 图像处理方法及装置、电子设备和存储介质 | |
US9058765B1 (en) | System and method for creating and sharing personalized virtual makeovers | |
KR101446975B1 (ko) | 얼굴 검출 기능을 사용한 얼굴 및 피부의 자동 미화 | |
EP2720190B1 (en) | Image processing device, image processing method, and control program | |
EP2685419B1 (en) | Image processing device, image processing method, and computer-readable medium | |
EP1372109A2 (en) | Method and system for enhancing portrait images | |
US20100189357A1 (en) | Method and device for the virtual simulation of a sequence of video images | |
EP1453002A2 (en) | Enhancing portrait images that are processed in a batch mode | |
JP2021144582A (ja) | メイクアップシミュレーション装置、メイクアップシミュレーション方法及びプログラム | |
JP2000151985A (ja) | 画像処理方法及び記録媒体 | |
CN114155569B (zh) | 一种化妆进度检测方法、装置、设备及存储介质 | |
JP2007299113A (ja) | ヘアカラー・メイクアップシミュレーションシステム | |
CN113421197B (zh) | 一种美颜图像的处理方法及其处理*** | |
JP2021132321A (ja) | 撮影遊戯装置およびプログラム |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 11835887 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2011835887 Country of ref document: EP |
|
ENP | Entry into the national phase |
Ref document number: 20137009836 Country of ref document: KR Kind code of ref document: A |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
WWE | Wipo information: entry into national phase |
Ref document number: 13878109 Country of ref document: US |