WO2023210341A1 - 顔分類方法、装置、およびプログラム - Google Patents
顔分類方法、装置、およびプログラム Download PDFInfo
- Publication number
- WO2023210341A1 WO2023210341A1 PCT/JP2023/014658 JP2023014658W WO2023210341A1 WO 2023210341 A1 WO2023210341 A1 WO 2023210341A1 JP 2023014658 W JP2023014658 W JP 2023014658W WO 2023210341 A1 WO2023210341 A1 WO 2023210341A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- face
- zone
- dimensional shape
- classification
- dimensional
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Ceased
Links
Images
Classifications
-
- 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 OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/64—Three-dimensional [3D] objects
Definitions
- the present invention relates to a face classification method, device, and program.
- the present invention aims to improve the accuracy of classification based on three-dimensional facial features.
- a face classification method includes identifying the characteristics of the three-dimensional shape of the T zone, which is a part of the face that includes the lower eyebrows, the bridge of the nose, and the area around the eyes, and the cheeks and face line of the face. and classifying the face based on the three-dimensional shape characteristics of the T-zone and the three-dimensional shape characteristics of the V zone. Including.
- FIG. 1 is an overall configuration diagram according to an embodiment of the present invention.
- FIG. 1 is a functional block diagram of a face classification device according to an embodiment of the present invention.
- 5 is a flowchart of face classification processing according to an embodiment of the present invention.
- FIG. 3 is a diagram for explaining the T-zone of a face according to an embodiment of the present invention.
- FIG. 2 is a diagram for explaining a V zone of a face according to an embodiment of the present invention.
- FIG. 3 is a diagram for explaining the characteristics of the three-dimensional shape of the T-zone of a face according to an embodiment of the present invention.
- FIG. 3 is a diagram for explaining the characteristics of the three-dimensional shape of the T-zone of a face according to an embodiment of the present invention.
- FIG. 3 is a diagram for explaining the characteristics of the three-dimensional shape of the T-zone of a face according to an embodiment of the present invention.
- FIG. 1 is an overall configuration diagram according to an embodiment of the present invention.
- 3 is a diagram for explaining the characteristics of the three-dimensional shape of the V zone of a face according to an embodiment of the present invention.
- 2 is a flowchart of face classification processing (Example 1) based on the three-dimensional shape characteristics of the V zone of a face according to an embodiment of the present invention.
- 12 is a flowchart of face classification processing (Example 2) based on the three-dimensional shape characteristics of the V zone of a face according to an embodiment of the present invention.
- 12 is a flowchart of face classification processing (Example 3) based on the three-dimensional shape characteristics of the V zone of a face according to an embodiment of the present invention.
- FIG. 12 is a flowchart of face classification processing (Example 4) based on the three-dimensional shape characteristics of the V zone of a face according to an embodiment of the present invention.
- FIG. 3 is a diagram for explaining the characteristics of the three-dimensional shape of the V zone of a face according to an embodiment of the present invention.
- FIG. 3 is a diagram for explaining the characteristics of the three-dimensional shape of the V zone of a face according to an embodiment of the present invention.
- FIG. 3 is a diagram for explaining the characteristics of the three-dimensional shape of the V zone of a face according to an embodiment of the present invention.
- FIG. 3 is a diagram for explaining the characteristics of the three-dimensional shape of the V zone of a face according to an embodiment of the present invention.
- FIG. 3 is a diagram for explaining the characteristics of the three-dimensional shape of the V zone of a face according to an embodiment of the present invention.
- FIG. 3 is a diagram for explaining the characteristics of the three-dimensional shape of the V zone of a face according to an embodiment of the present invention.
- FIG. 3 is a diagram for explaining the results of face classification and makeup suggestions based on the classification according to an embodiment of the present invention.
- FIG. 1 is a hardware configuration diagram of a face classification device according to an embodiment of the present invention.
- FIG. 1 is an overall configuration diagram according to an embodiment of the present invention.
- the face classification device 10 uses the characteristics of the three-dimensional shape of the T zone (details will be described later), which is the part of the user's 21 face that includes the area below the eyebrows, the bridge of the nose, and the area around the eyes, and the cheeks and cheeks of the user's 21 face.
- the face of the user 21 is classified based on the characteristics of the three-dimensional shape of the V zone (details will be described later), which is a portion including the face lines.
- ⁇ Example 1>, ⁇ Example 2>, and ⁇ Example 3> will be explained separately.
- the face classification device 10 includes a user terminal 20 and a server 30.
- the user 21 operates the user terminal 20.
- the user terminal 20 is a smartphone, a tablet, a personal computer, or the like.
- Server 30 is composed of one or more computers.
- the user terminal 20 and the server 30 execute the processing of the face classification device 10 described in this specification in a distributed manner.
- the user terminal 20 acquires information on the three-dimensional shape of the T-zone of the user's 21 face and information on the three-dimensional shape of the V-zone of the user's 21 face, and transmits the information to the server 30.
- the server 30 identifies the three-dimensional shape characteristics of the T zone of the user 21's face and the three-dimensional shape characteristics of the V zone of the user's 21 face, and classifies the user's 21 face based on the characteristics. and transmits the classification results to the user terminal 20.
- the face classification device 10 includes a user terminal 20.
- the user 21 operates the user terminal 20.
- the user terminal 20 is a smartphone, a tablet, a personal computer, or the like.
- the user terminal 20 executes the processing of the face classification device 10 described in this specification.
- a human such as the beauty salon staff 11 visually classifies the face of the user 21.
- FIG. 2 is a functional block diagram of the face classification device 10 according to an embodiment of the present invention.
- the face classification device 10 can include a three-dimensional shape information acquisition section 101, a three-dimensional shape feature identification section 102, a classification section 103, and a classification result presentation section 104. Further, the face classification device 10 can function as a three-dimensional shape information acquisition section 101, a three-dimensional shape feature identification section 102, a classification section 103, and a classification result presentation section 104 by executing a program.
- the three-dimensional shape information acquisition unit 101 acquires information on the three-dimensional shape of the T zone, which is the part of the user's 21 face that includes the area below the eyebrows, the bridge of the nose, and around the eyes. Furthermore, the three-dimensional shape information acquisition unit 101 acquires information on the three-dimensional shape of the V zone, which is a portion of the user's 21 face that includes the cheeks and face lines.
- the three-dimensional shape information is information used to specify the three-dimensional shape (that is, to specify the X coordinate, Y coordinate, and Z coordinate), and for example, multiple images of the user 21's face are taken. images, values measured by a 3D scanner or depth sensor, etc.
- the three-dimensional shape feature identification unit 102 identifies the characteristics of the T-zone of the user's 21 face from the information on the three-dimensional shape of the T-zone of the user's 21 face acquired by the three-dimensional shape information acquisition unit 101. Furthermore, the three-dimensional shape feature identifying unit 102 identifies the features of the V zone of the user's 21 face from the information on the three-dimensional shape of the V zone of the user's 21 face acquired by the three-dimensional shape information acquiring unit 101. Note that the three-dimensional shape feature specifying section is also referred to as a T-zone specifying section and a V-zone specifying section.
- the classification unit 103 classifies the face of the user 21 based on the characteristics of the T zone of the user's 21 face and the characteristics of the V zone of the user's 21 face identified by the three-dimensional shape feature identification unit 102.
- the classification unit 103 classifies the face of the user 21 based on whether the T-zone of the face is three-dimensional or two-dimensional. For example, the classification unit 103 determines whether the T zone is three-dimensional or two-dimensional based on the height difference between the center of the bridge of the nose and the inner corner of the eyes.
- the classification unit 103 classifies the face of the user 21 based on whether the V zone of the face has a skeletal appearance or a fleshy appearance, and if the V zone has a skeletal appearance, the classification unit 103 classifies the face according to the length of the face. Further classify faces based on. For example, the classification unit 103 determines whether the V zone has a skeletal feel or a fleshy feeling based on at least one of the shape of the cheek, the shadow of the cheek, and the shape of the face line.
- the classification result presentation unit 104 presents (for example, displays on the screen of the user terminal 20) the results classified by the classification unit 103. Note that the classification result presentation unit 104 may present a makeup method according to the classification result by the classification unit 103.
- FIG. 3 is a flowchart of face classification processing according to an embodiment of the present invention.
- step 1 (S1) the three-dimensional shape information acquisition unit 101 obtains information on the three-dimensional shape of the T zone, which is the part of the user's 21 face that includes the lower part of the eyebrows, the bridge of the nose, and the area around the eyes, and the user's 21 face.
- step 2 (S2) the three-dimensional shape feature identification unit 102 identifies the features of the T-zone of the user's 21 face from the information on the three-dimensional shape of the T-zone of the user's 21 face obtained in S1, and The characteristics of the V zone of the user's 21 face are specified from the information on the three-dimensional shape of the V zone of the user's 21 face acquired in .
- step 3 (S3) the classification unit 103 classifies the face of the user 21 based on the characteristics of the T zone of the face of the user 21 and the characteristics of the V zone of the face of the user 21 identified in S2.
- step 4 (S4) the classification result presentation unit 104 presents (for example, displays on the screen of the user terminal 20) the results classified in S3.
- the classification result presentation unit 104 may present makeup methods according to the results classified in S3.
- the present invention classifies faces based on the three-dimensional features of the T-zone of the face and the three-dimensional features of the V-zone of the face, and presents a makeup method according to the classification results.
- FIG. 4 is a diagram for explaining the T-zone of the face according to an embodiment of the present invention.
- the T-zone of the face is the area below the eyebrows (the area within the dotted line in the left image of Figure 4), the bridge of the nose (the area within the dotted line in the center image of Figure 4), and around the eyes (the area within the dotted line in the right image of Figure 4). ).
- the T zone may include the eyebrows and above the eyebrows.
- the "below eyebrow” is the area that extends from the bottom of the eyebrow to the side of the bridge of the nose.
- the "nose bridge” is a region that includes the bridge of the nose and the part above the bridge of the forehead.
- Around the eyes is an area that includes the upper and lower eyelids, inner and outer corners of the eyes.
- FIG. 5 is a diagram for explaining the V zone of the face according to an embodiment of the present invention.
- the V zone of the face includes the cheeks (the part within the dotted line in the left diagram of FIG. 5) and the face line (the diagonally shaded part in the right diagram of FIG. 5). Note that the V zone does not include the bridge of the nose.
- “Cheeks” are the sides of the face, and are the area surrounded by the eyes, ears, nose, mouth, and chin.
- the cheeks include the zygomatic bones (the bones that form the cheekbones).
- Fiber line is an area that follows the outline of the face.
- FIG. 6 shows the T-zone (the part within the line) of the face.
- the left and right direction of the front of the face is the X axis (width)
- the vertical direction of the front of the face is the Y axis (height)
- the front and back direction from the front of the face is the Z axis (depth).
- the classification unit 103 determines whether the T zone is three-dimensional or two-dimensional based on the height difference between the center of the bridge of the nose and the inner corner of the eyes.
- FIG. 7 is a diagram for explaining the characteristics of the three-dimensional shape of the T-zone of the face according to an embodiment of the present invention. Each position indicates the following parts of the face.
- TH1 The center of the face in the X direction, which has the same Y coordinate value as the tip of the eyebrows TH2: The position of the tip of the nose TH3: The position that bisects the line connecting TH1 and TH2 on the XY plane (the center of the bridge of the nose) )
- TL1 Position of the inner corner of the eye
- TL2 Position that bisects the line connecting the inner corner of the eye and the inner corner of the eyebrows on the )
- the classification unit 103 calculates the difference d TH3 - TL1 between TH3 and TL1 in the Z direction on the YZ plane when the distance from K1 to K2 on the XY plane is 1. It is determined whether the T-zone is three-dimensional or two-dimensional using the difference in height from the depression. When d TH3-TL1 >0.068, the classification unit 103 determines that the T zone is three-dimensional, uneven, and deeply carved. On the other hand, when d TH3-TL1 ⁇ 0.068, the classification unit 103 determines that the T-zone is flat, has no irregularities, and has shallow carvings.
- FIG. 8 shows the V zone (the part within the line) of the face.
- the left and right direction of the front of the face is the X axis (width)
- the vertical direction of the front of the face is the Y axis (height)
- the front and back direction from the front of the face is the Z axis (depth).
- the classification unit 103 determines whether the V zone has a skeletal feel or a fleshy feeling based on at least one of the shape of the cheek, the shadow of the cheek, and the shape of the face line, and determines whether the V zone has a skeletal feel or a fleshy feeling. If so, the face is further classified based on the length of the face. You may use any of the methods of face classification processing based on the three-dimensional shape characteristics of the V zone of the face ((Example 1) to (Example 4)) described below, or you may use multiple methods. The most common result may be used.
- FIG. 9 is a flowchart of face classification processing (Example 1) based on the three-dimensional shape characteristics of the V zone of the face according to an embodiment of the present invention.
- step 11 the classification unit 103 determines cheeks. Specifically, the classification unit 103 calculates (Z1-Z5)/(Z1-Z2). If (Z1-Z5)/(Z1-Z2) ⁇ 0.15, proceed to step 12; if (Z1-Z5)/(Z1-Z2) ⁇ 0.15, proceed to step 14.
- FIG. 13 shows the three-dimensional shape of the face when viewed from above.
- the values of the X and Z coordinates of each position are shown below (the value of the Y coordinate may be any value).
- V1 Outside position of nasal wing (X1, Z1)
- V2 Position of the outermost face line in the X direction (X2, Z2)
- V3 Position of the intersection of a straight line drawn parallel to the X-axis from V1 and a straight line drawn parallel to the Z-axis from V2 (X2, Z1)
- V4 A point on the line connecting V1 and V3, and the position of the point where V1 and the relevant point: V3 and the relevant point are 2:1 ((X1 + X2) ⁇ (2/3 or 1/3), Z1))
- V5 Intersection between the straight line drawn from V4 parallel to the Z axis and the face line ((X1+X2) x (2/3 or 1/3), Z5)
- step 12 the classification unit 103 determines the vertical width of the face when the horizontal width of the face is 1. If the vertical width of the face>1, the process proceeds to step 13; if the horizontal width of the face ⁇ 1, the process proceeds to step 15.
- S1 indicates the eyebrows
- S2 indicates the tip of the chin.
- the horizontal distance from the left hairline to the right hairline at the height of S1 is the width of the face.
- step 13 (S13) the classification unit 103 classifies the V zone of the user's 21 face as "smart".
- step 14 the classification unit 103 classifies the V zone of the user's 21 face into "round".
- step 15 (S15) the classification unit 103 classifies the V zone of the user's 21 face as "square".
- FIG. 10 is a flowchart of face classification processing (Example 2) based on the three-dimensional shape characteristics of the V zone of the face according to an embodiment of the present invention.
- step 21 the classification unit 103 determines the cheek shadow. If there is a cheek shadow, the process advances to step 22; if there is no cheek shadow, the process advances to step 24.
- the area between the straight line connecting the ⁇ bottom of the nose wing'' to the ⁇ center of the ear'' and the straight line connecting the ⁇ corner of the mouth'' to the ⁇ bottom side of the ear'' is defined as the shadow area under the cheekbone.
- step 22 the classification unit 103 determines the vertical width of the face when the horizontal width of the face is 1. If the vertical width of the face>1, the process proceeds to step 23; if the horizontal width of the face ⁇ 1, the process proceeds to step 25.
- S1 indicates the eyebrows
- S2 indicates the tip of the chin.
- the horizontal distance from the left hairline to the right hairline at the height of S1 is the width of the face.
- step 23 the classification unit 103 classifies the V zone of the user's 21 face as "smart".
- step 24 (S24) the classification unit 103 classifies the V zone of the user's 21 face into "round".
- step 25 the classification unit 103 classifies the V zone of the user's 21 face as "square".
- FIG. 11 is a flowchart of face classification processing (Example 3) based on the three-dimensional shape characteristics of the V zone of the face according to an embodiment of the present invention.
- step 31 the classification unit 103 determines the curvature of the V zone. Specifically, the classification unit 103 calculates the curvature k. If the curvature k ⁇ 0.20, the process proceeds to step 32; if the curvature k ⁇ 0.20, the process proceeds to step 34.
- step 32 the classification unit 103 determines the vertical width of the face when the horizontal width of the face is 1. If the vertical width of the face>1, the process proceeds to step 33; if the horizontal width of the face ⁇ 1, the process proceeds to step 35.
- S1 indicates the eyebrows
- S2 indicates the tip of the chin.
- the horizontal distance from the left hairline to the right hairline at the height of S1 is the width of the face.
- step 33 the classification unit 103 classifies the V zone of the user's 21 face as "smart".
- step 34 the classification unit 103 classifies the V zone of the user's 21 face into "round".
- step 35 the classification unit 103 classifies the V zone of the user's 21 face as "square".
- FIG. 12 is a flowchart of face classification processing (Example 4) based on the three-dimensional shape characteristics of the V zone of the face according to an embodiment of the present invention.
- step 41 the classification unit 103 determines the curvature of the V zone. Specifically, the classification unit 103 calculates the second-order differential value d. If the second-order differential value d ⁇ 0.54, the process proceeds to step 42, and if the second-order differential value d ⁇ 0.54, the process proceeds to step 44.
- step 42 the classification unit 103 determines the vertical width of the face when the horizontal width of the face is 1. If the vertical width of the face>1, the process proceeds to step 43; if the horizontal width of the face ⁇ 1, the process proceeds to step 45.
- S1 indicates the eyebrows
- S2 indicates the tip of the chin.
- the horizontal distance from the left hairline to the right hairline at the height of S1 is the width of the face.
- step 43 the classification unit 103 classifies the V zone of the user's 21 face as "smart".
- step 44 the classification unit 103 classifies the V zone of the user's 21 face into "round".
- step 45 the classification unit 103 classifies the V zone of the user's 21 face as "square".
- P4 to P5 are unified to 10. Let P1 (x 1 , y 1 ), P2 (x 2 , y 2 ), P3 (x 3 , y 3 ), P4 (x 4 , y 4 ), and P5 (x 5 , y 5 ). If the center of the circle C passing through the three points P1, P2, and P3 is (a, b),
- FIG. 18 is a diagram for explaining the results of face classification and makeup suggestions based on the classification according to an embodiment of the present invention.
- T-zone of the face is classified as three-dimensional, the bridge of the nose is straight and the curve of the face is steep, so a makeup method that matches the three-dimensional features of the face is presented.
- the bridge of the nose is not straight and the face has gentle unevenness, so a makeup method that matches the three-dimensional features of the face will be presented.
- the face has a skeletal appearance in the V zone and is classified as "smart", it has a skeletal appearance, is rugged, and has a clean facial line, so the three-dimensional appearance of the face A makeup method that matches your features will be presented.
- V zone of the face has a skeletal appearance and is classified as "square"
- the face has a skeletal appearance, is rugged, and the face line is rounded.
- a makeup method that matches your features will be presented.
- the face has a fleshy V-zone and is classified as "round”, it is fleshy, plump, and has a round face line, so it is suitable for the three-dimensional features of the face.
- a makeup method is presented.
- FIG. 19 is a hardware configuration diagram of a face classification device 10 according to an embodiment of the present invention.
- the face classification device 10 includes a CPU (Central Processing Unit) 1001, a ROM (Read Only Memory) 1002, and a RAM (Random Access Memory) 1003.
- the CPU 1001, ROM 1002, and RAM 1003 form a so-called computer.
- the face classification device 10 can include an auxiliary storage device 1004, a display device 1005, an operating device 1006, an I/F (Interface) device 1007, and a drive device 1008. Note that each piece of hardware of the face classification device 10 is interconnected via a bus B.
- the CPU 1001 is a computing device that executes various programs installed in the auxiliary storage device 1004.
- ROM1002 is a nonvolatile memory.
- the ROM 1002 functions as a main storage device that stores various programs, data, etc. necessary for the CPU 1001 to execute various programs installed in the auxiliary storage device 1004.
- the ROM 1002 functions as a main storage device that stores boot programs such as BIOS (Basic Input/Output System) and EFI (Extensible Firmware Interface).
- BIOS Basic Input/Output System
- EFI Extensible Firmware Interface
- the RAM 1003 is a volatile memory such as DRAM (Dynamic Random Access Memory) or SRAM (Static Random Access Memory).
- the RAM 1003 functions as a main storage device that provides a work area in which various programs installed in the auxiliary storage device 1004 are expanded when they are executed by the CPU 1001.
- the auxiliary storage device 1004 is an auxiliary storage device that stores various programs and information used when the various programs are executed.
- the display device 1005 is a display device that displays the internal state of the face classification device 10 and the like.
- the operating device 1006 is an input device through which the administrator of the face classification device 10 inputs various instructions to the face classification device 10.
- the I/F device 1007 is a communication device for connecting to a network and communicating with other devices.
- a drive device 1008 is a device for setting a storage medium 1009.
- the storage medium 1009 here includes a medium for recording information optically, electrically, or magnetically, such as a CD-ROM, a flexible disk, or a magneto-optical disk. Further, the storage medium 1009 may include a semiconductor memory that records information electrically, such as an EPROM (Erasable Programmable Read Only Memory) or a flash memory.
- EPROM Erasable Programmable Read Only Memory
- the various programs to be installed in the auxiliary storage device 1004 are installed by, for example, setting the distributed storage medium 1009 in the drive device 1008 and reading out the various programs recorded in the storage medium 1009 by the drive device 1008. be done.
- various programs to be installed in the auxiliary storage device 1004 may be installed by being downloaded from the network via the I/F device 1007.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
- Processing Or Creating Images (AREA)
- Collating Specific Patterns (AREA)
Abstract
Description
図1は、本発明の一実施形態に係る全体の構成図である。顔分類装置10は、ユーザ21の顔の眉下と鼻筋と目の周りとを含む部分であるTゾーン(詳細については後述する)の3次元形状の特徴、および、ユーザ21の顔の頬とフェイスラインとを含む部分であるVゾーン(詳細については後述する)の3次元形状の特徴に基づいて、ユーザ21の顔を分類する。以下、<実施例1>と<実施例2>と<実施例3>に分けて説明する。
実施例1では、顔分類装置10は、ユーザ端末20とサーバ30から構成される。ユーザ21は、ユーザ端末20を操作する。例えば、ユーザ端末20は、スマートフォン、タブレット、パーソナルコンピュータ等である。サーバ30は、1つまたは複数のコンピュータから構成される。実施例1では、ユーザ端末20とサーバ30が、本明細書で説明する顔分類装置10の処理を分散して実行する。
実施例2では、顔分類装置10は、ユーザ端末20から構成される。ユーザ21は、ユーザ端末20を操作する。例えば、ユーザ端末20は、スマートフォン、タブレット、パーソナルコンピュータ等である。実施例2では、ユーザ端末20が、本明細書で説明する顔分類装置10の処理を実行する。
実施例3では、美容部員11等の人間が目視でユーザ21の顔を分類する。
図2は、本発明の一実施形態に係る顔分類装置10の機能ブロック図である。顔分類装置10は、3次元形状情報取得部101と、3次元形状特徴特定部102と、分類部103と、分類結果提示部104と、を備えることができる。また、顔分類装置10は、プログラムを実行することで、3次元形状情報取得部101、3次元形状特徴特定部102、分類部103、分類結果提示部104として機能することができる。
図3は、本発明の一実施形態に係る顔分類処理のフローチャートである。
図4および図5を参照しながら、顔のTゾーンおよび顔のVゾーンについて説明する。
図6および図7を参照しながら、顔のTゾーンの3次元形状の特徴に基づく分類について説明する。図6は、顔のTゾーン(線内の部分)を示す。図6に示されるように、顔の正面の左右方向をX軸(幅)とし、顔の正面の上下方向をY軸(高さ)とし、顔の正面からの前後方向をZ軸(奥行)とする。分類部103は、鼻筋の中央と目頭との高低差から、Tゾーンが立体的であるか平面的であるかを判定する。
TH1:顔のX方向の中心であり、眉頭と同一のY座標の値を有する位置
TH2:鼻先の位置
TH3:XY平面上でTH1とTH2とを結ぶ線を2等分する位置(鼻筋の中央)
TL1:目頭の位置
TL2:XY平面上で目頭の位置と眉頭の位置とを結ぶ線を2等分する位置(なお、TL1の代わりにTL2を用いて、Tゾーンが立体的であるか平面的であるかを判定することができる)
K1:顔のX方向の中心で、眉山と同一のY座標の値を有する位置
K2:顎先のうち顔のX方向の中心の位置
図8-図17を参照しながら、顔のVゾーンの3次元形状の特徴に基づく分類について説明する。図8は、顔のVゾーン(線内の部分)を示す。図8に示されるように、顔の正面の左右方向をX軸(幅)とし、顔の正面の上下方向をY軸(高さ)とし、顔の正面からの前後方向をZ軸(奥行)とする。分類部103は、頬の形状と、頬の影と、フェイスラインの形状と、のうちの少なくとも1つから、Vゾーンに骨格感があるか肉付き感があるかを判定し、Vゾーンに骨格感がある場合、顔の長さに基づいて、顔をさらに分類する。以下で説明する顔のVゾーンの3次元形状の特徴に基づく顔分類処理((例1)-(例4))のうちのいずれかの方法を用いてもよいし、複数の方法を用いて最も多かった結果を採用してもよい。
V1:鼻翼の外側の位置(X1,Z1)
V2:X方向で一番外側のフェイスラインの位置(X2,Z2)
V3:V1からX軸に平行に引いた直線と、V2からZ軸に平行に引いた直線と、の交点の位置(X2,Z1)
V4:V1とV3とを結ぶ線上の点であり、V1と当該点:V3と当該点が2:1となる点の位置((X1+X2)×(2/3または1/3),Z1))
V5:V4からZ軸に平行に引いた直線と、フェイスラインと、の交点((X1+X2)×(2/3または1/3),Z5)
以下、図15および図16を参照しながら、Vゾーンの曲率について説明する。
図15の各位置は、以下の顔の部位を示す。
P1:耳の下の付け根
P2:下顎角(Xに対するYの傾きが大きく変わる点(二階微分の値が最も大きいところ))
P3:フェイスラインと目尻からY軸に平行に引いた直線との交点
P4:フェイスラインのうち最もYの値が低い点
P5:頭髪の生え際とP4からY軸に平行に引いた直線との交点
図16の各位置は、以下の顔の部位を示す。
P1:フェイスラインのうち最もYの値が低い点
P2:フェイスラインと目尻からY軸に平行に引いた直線との交点
P3:下顎角(Xに対するYの傾きが大きく変わる点(二階微分の値が最も大きいところ))
図18は、本発明の一実施形態に係る顔の分類の結果、および、分類を基にしたメイクアップ提案について説明するための図である。
本発明では、詳細な顔の立体的な特徴に基づいて顔を分類することができる。そのため、個々人の顔立ちに合ったメイクアップを提案することできる。
図19は、本発明の一実施形態に係る顔分類装置10のハードウェア構成図である。顔分類装置10は、CPU(Central Processing Unit)1001、ROM(Read Only Memory)1002、RAM(Random Access Memory)1003を有する。CPU1001、ROM1002、RAM1003は、いわゆるコンピュータを形成する。また、顔分類装置10は、補助記憶装置1004、表示装置1005、操作装置1006、I/F(Interface)装置1007、ドライブ装置1008を有することができる。なお、顔分類装置10の各ハードウェアは、バスBを介して相互に接続されている。
11 美容部員
20 ユーザ端末
21 ユーザ
30 サーバ
101 3次元形状情報取得部
102 3次元形状特徴特定部
103 分類部
104 分類結果提示部
1001 CPU
1002 ROM
1003 RAM
1004 補助記憶装置
1005 表示装置
1006 操作装置
1007 I/F装置
1008 ドライブ装置
1009 記憶媒体
Claims (7)
- 顔の眉下と鼻筋と目の周りとを含む部分であるTゾーンの3次元形状の特徴を特定することと、
前記顔の頬とフェイスラインとを含む部分であるVゾーンの3次元形状の特徴を特定することと、
前記Tゾーンの3次元形状の特徴、および、前記Vゾーンの3次元形状の特徴に基づいて、前記顔を分類することと
を含む方法。 - 前記Tゾーンが立体的であるか平面的であるかに基づいて、前記顔を分類し、
前記Vゾーンに骨格感があるか肉付き感があるかに基づいて、前記顔を分類し、
前記Vゾーンに骨格感がある場合、顔の長さに基づいて、前記顔をさらに分類する、
請求項1に記載の方法。 - 前記Tゾーンが立体的であるか平面的であるかは、鼻筋の中央と目頭との高低差から判定される、請求項2に記載の方法。
- 前記Vゾーンに骨格感があるか肉付き感があるかは、頬の形状と、前記頬の影と、フェイスラインの形状と、のうちの少なくとも1つから判定される、請求項2に記載の方法。
- 前記分類の結果に応じた化粧方法を提示すること、をさらに含む、請求項1に記載の方法。
- 顔の眉下と鼻筋と目の周りとを含む部分であるTゾーンの3次元形状の特徴を特定するTゾーン特定部と、
前記顔の頬とフェイスラインとを含む部分であるVゾーンの3次元形状の特徴を特定するVゾーン特定部と、
前記Tゾーンの3次元形状の特徴、および、前記Vゾーンの3次元形状の特徴に基づいて、前記顔を分類する分類部と
を備えた顔分類装置。 - 顔分類装置を
顔の眉下と鼻筋と目の周りとを含む部分であるTゾーンの3次元形状の特徴を特定するTゾーン特定部、
前記顔の頬とフェイスラインとを含む部分であるVゾーンの3次元形状の特徴を特定するVゾーン特定部、
前記Tゾーンの3次元形状の特徴、および、前記Vゾーンの3次元形状の特徴に基づいて、前記顔を分類する分類部
として機能させるためのプログラム。
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202380030181.XA CN119013706A (zh) | 2022-04-25 | 2023-04-11 | 脸部分类方法、装置及程序 |
| JP2024517965A JPWO2023210341A1 (ja) | 2022-04-25 | 2023-04-11 |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2022071413 | 2022-04-25 | ||
| JP2022-071413 | 2022-04-25 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2023210341A1 true WO2023210341A1 (ja) | 2023-11-02 |
Family
ID=88518410
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/JP2023/014658 Ceased WO2023210341A1 (ja) | 2022-04-25 | 2023-04-11 | 顔分類方法、装置、およびプログラム |
Country Status (3)
| Country | Link |
|---|---|
| JP (1) | JPWO2023210341A1 (ja) |
| CN (1) | CN119013706A (ja) |
| WO (1) | WO2023210341A1 (ja) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006119040A (ja) * | 2004-10-22 | 2006-05-11 | Kao Corp | 顔形状分類方法および顔形状評価方法および顔形状評価装置 |
| 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 |
| WO2013005447A1 (ja) * | 2011-07-07 | 2013-01-10 | 花王株式会社 | 顔印象分析方法、美容カウンセリング方法および顔画像生成方法 |
-
2023
- 2023-04-11 JP JP2024517965A patent/JPWO2023210341A1/ja active Pending
- 2023-04-11 CN CN202380030181.XA patent/CN119013706A/zh active Pending
- 2023-04-11 WO PCT/JP2023/014658 patent/WO2023210341A1/ja not_active Ceased
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006119040A (ja) * | 2004-10-22 | 2006-05-11 | Kao Corp | 顔形状分類方法および顔形状評価方法および顔形状評価装置 |
| 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 |
| WO2013005447A1 (ja) * | 2011-07-07 | 2013-01-10 | 花王株式会社 | 顔印象分析方法、美容カウンセリング方法および顔画像生成方法 |
Also Published As
| Publication number | Publication date |
|---|---|
| JPWO2023210341A1 (ja) | 2023-11-02 |
| CN119013706A (zh) | 2024-11-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| AU2018214005B2 (en) | Systems and methods for generating a 3-D model of a virtual try-on product | |
| US10739849B2 (en) | Selective peripheral vision filtering in a foveated rendering system | |
| US9697635B2 (en) | Generating an avatar from real time image data | |
| KR101259662B1 (ko) | 얼굴 분류 방법, 얼굴 분류 장치, 분류맵, 얼굴 분류프로그램, 및 상기 프로그램이 기록된 기록매체 | |
| JP5432532B2 (ja) | 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 | |
| CN109961496B (zh) | 表情驱动方法及表情驱动装置 | |
| US20220148333A1 (en) | Method and system for estimating eye-related geometric parameters of a user | |
| US10395096B2 (en) | Display method for recommending eyebrow style and electronic apparatus thereof | |
| CN113344837B (zh) | 人脸图像处理方法及装置、计算机可读存储介质、终端 | |
| CN109284778A (zh) | 人脸颜值计算方法、计算装置及电子设备 | |
| KR102804309B1 (ko) | 아바타 등록을 위한 액세서리 검출 및 결정 | |
| JP2007175384A (ja) | チークメーキャップのための顔分類方法、顔分類装置、分類見極めマップ、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 | |
| CN114502036A (zh) | 自动化妆机、方法、程序以及控制装置 | |
| TWI471807B (zh) | Face classification method, face classification device, classification chart, face classification program and recorded the program of the recording media | |
| CN119013706A (zh) | 脸部分类方法、装置及程序 | |
| CN113724366B (zh) | 3d模型生成方法、装置及设备 | |
| CN114742951A (zh) | 素材生成、图像处理方法、装置、电子设备及存储介质 | |
| JP2003030684A (ja) | 顔3次元コンピュータグラフィック生成方法及び装置及び顔3次元コンピュータグラフィック生成プログラム及び顔3次元コンピュータグラフィック生成プログラムを格納した記憶媒体 | |
| JP7832800B2 (ja) | 顔の分類法、分類装置、プログラム、分類図、および美容によるイメージ演出方法 | |
| US20240070885A1 (en) | Skeleton estimating method, device, non-transitory computer-readable recording medium storing program, system, trained model generating method, and trained model | |
| WO2023026891A1 (ja) | 眉メイクガイド方法、装置、プログラム、およびシステム | |
| JP2025051613A (ja) | 頭部モデル作成装置及び頭部モデル作成方法 | |
| CN115187703A (zh) | 一种眉妆指导方法、装置、设备及介质 | |
| HK1146579A (en) | Makeup method, makeup simulation device, and makeup simulation program | |
| HK1141614B (en) | Makeup simulation system and makeup simulation method |
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: 23796085 Country of ref document: EP Kind code of ref document: A1 |
|
| ENP | Entry into the national phase |
Ref document number: 2024517965 Country of ref document: JP Kind code of ref document: A |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 202380030181.X Country of ref document: CN |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 23796085 Country of ref document: EP Kind code of ref document: A1 |





