WO2017103985A1

WO2017103985A1 - Information provision device and information provision method

Info

Publication number: WO2017103985A1
Application number: PCT/JP2015/085022
Authority: WO
Inventors: あゆみ河野; 順治園田
Original assignee: 一般社団法人日本ファッションスタイリスト協会
Priority date: 2015-12-15
Filing date: 2015-12-15
Publication date: 2017-06-22
Also published as: JP6028188B1; CN108292418B; JPWO2017103985A1; CN108292418A

Abstract

[Problem] To provide an information provision device and information provision method which, using an evaluation result which is obtained for a face region attribute of a subject, is capable of promptly providing for the subject at least one instance of information (hereinafter "subject information") which is both useful and appropriate to such as styling which matches the subject. [Solution] This information provision device and information provision method: having selected at least one face region which configures the face of the subject, compares at least one face region attribute measurement result which has been acquired for each of the face region attributes with a reference value thereof; on the basis of the comparison result and at least one inclination which has been defined for the face region attribute, identifies a matching information category using the at least one inclination; selects a subject information group, from among a plurality of subject information groups, which is included in the matching information category; and outputs same.

Description

Information providing apparatus and information providing method

The present invention relates to an information providing apparatus and an information providing information method, and more particularly, systematically classified and accumulated based on measurement data and input data on attributes such as the shape and size of a part of a subject's face. The present invention also relates to an information providing apparatus and an information providing method for providing an information group suitable for a target person from a plurality of information groups such as styling.

Recently, not only for movie actors and TV program performers, but also for stylists who want to improve their images in situations such as shooting personal photos such as PR photos. Coordinates people (hereinafter referred to as “subjects”), costumes, clothes, accessories, and accessories that suit the scene. The stylist can observe the face part and face part attributes such as the face shape, skin color, hair color, skin quality, and hair quality of the subject as a whole, and after interviewing the subject, the experience of the stylist We provide advice and information (target person information) suitable for the target person from the information and knowledge about styling classified and arranged from above.
However, the provision of advice and information by such stylists requires accuracy, but in reality, it depends largely on the stylist's subjectivity, and the stylist's observation ability, experience, lack of knowledge, etc. There was a problem that proper styling advice and information could not be provided properly.

To solve this problem and provide objective and accurate advice and information, it is necessary to build a system that manages styling and other information using a computer. By the way, in recent years, proposals relating to entertainment such as fortune telling using a computer (for example, see Patent Document 1) and proposals regarding makeup in the beauty field (for example, see Patent Document 2) have been made. However, there is not yet a system that uses a computer to provide advice or useful information on the overall styling of the subject.

JP 2005-352803 A JP 2014-149841 A

In view of the circumstances described above, the present invention uses useful and accurate information (hereinafter referred to as “subject information”) such as styling that matches the subject with respect to the subject using the evaluation result obtained for the face part attribute of the subject. It is an object to provide an information providing apparatus and an information providing method capable of promptly providing at least one.

According to one aspect of the present invention, the object includes at least an attribute information acquisition unit, a storage unit, an evaluation unit, a compatible information category identification unit, an information selection unit, and an output unit, and the attribute information acquisition unit is a target At least one selected face part selected from face parts including eyebrows, eyes, nose, mouth, skin, and hair constituting the person's own face, and the shape / size, color, and The face part attribute including the texture and the measurement result of the face part attribute are acquired, and the storage unit belongs to a plurality of face part information, a plurality of tendencies, a plurality of matching information categories, and the respective matching information categories. A plurality of target person information groups are stored, and each of the face part information includes at least one face part attribute defined in advance for each of the face parts and at least one reference for each face part attribute. Each of the plurality of tendencies is related to the face part attribute and is defined as a straight axis including the face part attribute reference value in each face part attribute, and the at least It is stipulated to classify the plurality of target person information groups into at least two matching information categories with one face part attribute reference value as a boundary, and the evaluation unit is configured to select the selected face part through the attribute information acquisition unit. And the face part attribute measurement result is acquired, the face part attribute reference value called from the storage unit based on the former is compared with the latter, the comparison result is sent to the matching information category extracting unit, and the matching information The category specifying unit calls at least one tendency related to each face part attribute from the storage unit, and sets each inclination based on the comparison result. And extracting and specifying at least one relevant information category associated with the sex, and the information selection unit selects at least one subject information belonging to the identified relevant information category in the subject information group in the storage unit. The output unit is achieved by an information providing device configured to output each selected target person information.

The object is also according to another aspect of the present invention, in which at least one selected facial part selected from facial parts including the eyebrows, eyes, nose, mouth, skin and hair constituting the face of the subject. Attribute information acquisition for acquiring at least one face part attribute selected from the shape / size, color, and texture of the face part and a predetermined face part attribute measurement result defined for the face part attribute Receiving the process, the selected face part and the face part attribute measurement result, comparing the face part attribute reference value called from the storage unit based on the former and the latter, and comparing the comparison result with the matching information category extracting part And at least one tendency defined as a linear axis is called from the storage unit and the storage unit is associated with each tendency based on the comparison result. A matching information category identifying step for extracting and identifying at least one matching information category, and a target for selecting at least one target information belonging to the specified matching information category from the target information group in the storage unit It is achieved by an information providing method comprising a person information selection step and an output step of outputting each selected target person information.

The above object is also achieved by a program for causing a computer to execute the information providing method of the present invention.

According to the information providing apparatus and the information providing method of the present invention, a subject who uses the apparatus selects at least one face part and face part attribute of the subject, and measures at least one face part attribute for the selected face part. A plurality of matching information categories for classifying a plurality of target person information groups based on a comparison result between the face part attribute measurement result and the corresponding face part attribute reference value by inputting the result to the information providing device It is possible to specify at least one matching information category associated with at least one tendency from among the information, and output target person information belonging to the matching information category. Accordingly, it is possible to quickly provide the target person with appropriate target person information suitable for the target person using a computer.

It is a block diagram which shows roughly the hardware structural example of one Embodiment of the information provision apparatus of this invention. FIG. 2 is a block diagram schematically showing a functional configuration example of an arithmetic control unit shown in FIG. 1. It is a block diagram which shows roughly an example of the memory | storage part shown in FIG. It is a figure for demonstrating the face shape used as a reference | standard, and a reference | standard face size. It is a table | surface which shows an example of the relationship between a face part attribute and this and tendency. It is a figure which shows an example of the orthogonal coordinate system (styling map) which showed the relationship between a face part attribute and tendency, and a matching information category. It is a table | surface for demonstrating an example of the relationship between a tendency and a compatible information category. It is the table | surface which showed the relationship between a conformity information category and a subject information group. It is the table | surface which showed an example of questionnaire information. It is a conceptual diagram for demonstrating the measurement content in the face part attribute of an eyebrow. It is a conceptual diagram for demonstrating the measurement content in the face part attribute of eyes. It is a conceptual diagram for demonstrating the measurement content in a nose face part attribute. It is a conceptual diagram for demonstrating the measurement content in the face part attribute of a mouth. It is a flowchart which shows an example of the procedure of the information provision method using the information provision apparatus shown in FIG. It is a flowchart which shows the procedure until it obtains a face part attribute measurement result in case a face part attribute is a shape and a magnitude | size. It is a flowchart which shows the procedure until it obtains a face part attribute measurement result in case a face part attribute is a color.

An embodiment of the information providing apparatus of the present invention will be described in detail with reference to FIGS. 1 to 13 attached to the information providing apparatus of the present invention.
[Hardware configuration example]
1 is a block diagram schematically showing a hardware configuration example of the present embodiment, FIG. 2 is a block diagram schematically showing a functional configuration example of an arithmetic control unit shown in FIG. 1, and FIG. 3 is shown in FIG. It is a block diagram which shows a memory | storage part schematically. The information providing apparatus 1 of the present embodiment uses information useful for the target person such as statistically accumulated styling information in advance (hereinafter, this information is referred to as “target person information”, and a plurality of target person information is “targeted”. Information group))), and the shape, size, color, etc. of the parts of the subject's face such as the eyes, nose, mouth, eyebrows, and skin (hereinafter referred to as “face part”) Based on measurement data and input data (hereinafter referred to as “face part attribute value”) about attributes such as texture (hereinafter referred to as “face part attribute value”), individual information unique to the target person is extracted, It is an apparatus that provides at least one subject information suitable for the subject from the subject information group.

The information providing apparatus 1 includes an arithmetic control unit 2, a storage unit 3, an input unit 5, an output unit 7, and an internal bus 4. Here, examples of the information providing apparatus 1 include a general-purpose personal computer, a tablet terminal, and a smartphone. These may be stand-alone terminals, or may be client terminals connected to a server via a telecommunication means (not shown) in a client / server system. In the latter case, the storage unit 3 includes a storage unit (not shown) provided on the server side. The internal bus 4 has a function of mutually connecting the above-described units, that is, the arithmetic control unit 2, the storage unit 3, the input unit 5, and the output unit 7.

The arithmetic control unit 2 performs various controls on each unit by a CPU or the like. The arithmetic control unit 2 is configured by an arithmetic control device including a CPU, MPU, ROM, and the like in hardware. The arithmetic control unit 2 executes a startup program stored in the ROM after the information providing apparatus of the present invention is turned on, and stores an operating system (OS), various processing drivers, and the present invention stored in the storage unit 3. The program for executing the information providing method and various data are read into the RAM which is the main storage device, and the display information expanded in the RAM is output to the display 10 of the output unit 7 or to the printer 11. Or output. As shown in FIG. 2, the arithmetic control unit 2 in the present embodiment includes functional units such as an attribute information acquisition unit 21 including an image data analysis unit 25, an evaluation unit 22, a matching information category identification unit 23, and an information selection unit 24. It is configured. Each of these functional units will be described later.
Note that the program and various data for executing the information providing method of the present invention may be stored in a recording medium such as a CD-R or DVD-R. Accordingly, the recording medium can be stored in the storage unit 3 as necessary.

The storage unit 3 temporarily stores or stores programs executed by the arithmetic control unit 2 and various data temporarily or permanently. The storage unit 3 includes a volatile memory such as various RAMs, a magnetic disk such as a hard disk drive (HDD), an optical disk, and a secondary storage device such as a nonvolatile memory. As shown in FIG. 3, the storage unit 3 includes a reference face shape (size), a plurality of face part information, a plurality of tendencies, a plurality of matching information categories, a plurality of target person information groups, and a plurality of target person information groups. Questionnaire information is stored in advance.

(Reference face shape (size))
In the storage unit 3, two-dimensional and / or three-dimensional reference face shapes obtained as a reference face shape by statistically processing a plurality of human face shapes accumulated in the past are displayed as reference face sizes. It is remembered with. Of these, FIG. 4 shows an example of a two-dimensional reference face shape. This figure shows the reference face size. Here, the reference face size means a dimension or a product of the dimensions shown in any one of the following (1) to (4) in the reference face shape (see FIG. 4).
(1) Vertical distance L between the hairline on the mid-sagittal plane and the tip of the chin (referred to as “frontal vertical distance”; distance of L in FIG. 4)
(2) Distance M between cheek sides of left and right strokes (referred to as “distance between left and right side lifts”; distance indicated by symbol M in FIG. 4)
(3) Vertical distance N between the upper hairline of the left and right eyebrows and the tip of the jaw (distance N in FIG. 4)
(4) Product (area) of M and N above M · N

(Face part information)
The face part information includes a face part, at least one face part attribute defined in advance for each of the face parts, and at least one reference value (hereinafter referred to as “face part attribute” defined in advance in each face part attribute). It is composed of a set of “reference value”. FIG. 5 shows an example of face part information stored in the storage unit 3 of the present embodiment. As shown in this figure, the face part includes parts such as face eyes, nose, mouth, eyebrows, skin, hair, and hair. The facial part also includes a combination of at least two of these parts. In the present embodiment, the face part attribute defines three types of face part shape / size, color, and quality (texture). This face part attribute can be additionally defined by the advancement of measurement technology in the future, and is not limited to these three types. Further, the facial part attribute reference value may be changed as appropriate because it may be changed due to future advancement of measurement technology or the like. The face part attribute reference value is mainly quantitatively expressed by a numerical value, but may be expressed qualitatively by a value other than the numerical value.

Each face part attribute further includes two attributes in principle as shown in FIG. For example, when the face part is an eyebrow and the face part attribute is shape / size, the attribute is related to “straight-curve” whether linear or curved, and “thin-thick” whether thin or thick. Attributes. In addition, when the face part is a pupil and the face part attribute is a color, whether the pupil is yellowish or bluish, an attribute relating to “yellow-blue” and whether the skin color is light or dark The attribute relating to “bright-dark” is defined. In addition, when the facial part is skin and the facial part attribute is texture, the attribute relating to “thin-thick”, whether the skin is thin or thick, and “matte-gloss ( Yes) ”is specified.

On the other hand, when the face part is skin and hair and the face part attribute is color, and when the face part is eye and the face part is color, each attribute includes one attribute. In the former case, it is an attribute related to “gradation-contrast” indicating whether the color difference between the skin color and the hair is relatively smaller or larger than the facial part attribute reference value, and in the latter case, the white eye portion and the black eye portion This is an attribute relating to “gentle-bright” indicating whether the saturation is relatively larger or smaller than the reference value (face part attribute reference value).

(Tendency)
FIG. 5 also shows the relationship between the facial part attribute and the tendency. As shown in this figure, the facial part attributes are classified into three tendencies. That is, the attributes related to “straight-curve”, “yellow-blue”, “flat-concave” are cool-warm tendencies, and attributes related to “thin-thick”, “small-large”, “thin-dark”. Corresponds to the light-deep tendency, and the attributes relating to “gradation-contrast” and “gentle-bright” correspond to the gradation-contrast tendency, respectively. In this way, each tendency is related to the facial part information, and is named by the impression and image received from the two polar attributes in each facial part attribute, and is a linear axis (scale) that serves as an index of these bipolar attributes. Axis). The face part attribute reference value is included in any intermediate position on the straight line. Note that the attributes of each facial part attribute are not limited to these, and further analysis / examination will further discover attributes that have a statistically significant association with the subject information group. For example, the attribute can be replaced with the current attribute or additionally employed. Further, in the present invention, the present invention is not limited to these tendencies, and further, by repeating statistical processing, knowledge about tendencies that are more relevant between the facial part attribute and the target person information group can be obtained. Needless to say, once obtained, the tendency can be newly added or changed.

(Target information group)
The target person information group associates information recognized by the statistical processing that is highly related to the past general human face part information with each of the tendencies, and more specifically, with respect to each of the polar attributes of the tendencies. It is collected. This target person information group includes styling (product) information (tie, shirt, suit pattern, color, etc.) suitable for the target person, information on the personality of the target person (gentle, energetic, etc.), information on customer service type (early Other information and advice are included (speak, speak, proactively explain, etc.). Other information and advice include, for example, information about tableware; information about interiors such as furniture and interiors (colors of floors and walls, etc.); information about graphic designs such as logo colors; advertisements, promotions, product planning (colors of packages, etc.) ); Information on styling tests. These target person information groups can be arranged one-dimensionally according to the strength of their attributes for each tendency.

(Compliance information category)
The subject information group is classified into at least two categories related to the attributes of the two poles with at least one face part attribute reference value as a boundary according to any one tendency. Hereinafter, this category is referred to as a “conforming information category”. When the face part attribute reference value is one, the subject information group is divided into two matching information categories related to the attributes of both poles with the part attribute reference value as a boundary. For example, in the case of a cool-warm tendency, the subject information group is linear in one pole, a conforming information category (cool category) for attributes that give a cool impression such as blue, and a curvilinear in the other pole. It can be divided into conformity information categories (warm categories) for attributes that give a warm impression such as yellow. For light-deep propensity, the relevant information category (light category) for attributes that give light (lightness) impressions such as bright, small and light, and deep (heavy) such as dark, large and heavy In addition to the conformity information category (deep category) for attributes that give an impression, and for gradient-contrast tendencies, it has a gradation (gentle color impression) with a gradation such as gentle, familiarity, and matte (matte). (Giving) attribute information range (gradation category) and contrast information category (contrast category) for contrasting attributes (giving a vivid impression) such as vivid, conspicuous, and glossy Are divided. In addition, when there are two or more face part attribute reference values, the relevant information category that is greater than or equal to the maximum face part attribute reference value, the second face part attribute reference value or more, and less than the maximum face part attribute reference value The matching information category, the third face part attribute reference value or more, the second face part attribute reference value less than the matching information category, and so on.

Next, when at least two different tendencies are obtained among the three tendencies, such as when a plurality of face parts and face part attributes are selected by the target person, the at least two tendencies and the matching information category Will be described. In addition, in order to simplify the description, each tendency has a single face part attribute reference value included therein. FIG. 6 shows the relationship between the facial part attribute and tendency and the matching information category. Of the three tendencies, the cool-warm tendency is plotted on the horizontal axis, and the light-deep trend is plotted on the vertical axis. An example of the orthogonal coordinate system is shown. In addition, a virtual axis of contrast-gradient tendency is provided in a 45 ° upward and downward right direction. In this Cartesian coordinate system, the cool-warm tendency on the horizontal axis and the light-deep tendency on the vertical axis are provided so that each face part attribute reference value is the origin and intersects at this origin. In the orthogonal coordinate system, although not shown, the subject information group is two-dimensionally arranged according to the strength of the attribute from the origin, for example. In the following, this orthogonal coordinate system is referred to as a “styling map”, and in particular, the first quadrant (I) is “bright taste”, the second quadrant (II) is “aqua taste”, and the third quadrant (III) is “ The “crystal taste” and the fourth quadrant (IV) will be called “artist”.

In this styling map, the first quadrant (bright taste) and the fourth quadrant (artist) become the warm category, and the second quadrant (aqua taste) and third quadrant (crystal taste) due to the cool-warm tendency on the horizontal axis. Is a cool category. In addition, due to the light-deep tendency on the vertical axis, the first quadrant (bright taste) and the second quadrant (aqua taste) are in the light category, and the third quadrant (crystal taste) and the fourth quadrant (artist) are in the cool category. It becomes. In addition, as shown in FIG. 6, the first quadrant (bright taste) and the third quadrant (crystal taste), which include a 45-degree diagonally upward virtual axis passing through the origin, are gradation categories due to the gradation-contrast tendency. The second quadrant (aqua taste) and the fourth quadrant (artist), which include a hypothetical axis that is 45 degrees diagonally downward and passes through the origin, are the contrast category. In addition, since this styling map is suitable for explaining the relationship between the respective tendencies and the matching information category in the present embodiment, the relationship between the propensity and the matching information category has been described. Instead of using such a styling map, it can also be shown using other methods and structures, and is not limited to using a styling map. .

FIG. 7 summarizes the relationship between the conformity information categories classified by the three tendencies shown in FIG. 5 and the first to fourth quadrants shown in FIG. 6 in a table format. As shown in this table, each matching information category of each tendency is composed of a combination of two quadrants among the first to fourth quadrants. In other words, each of the first to fourth quadrants is a part of three of the six relevant information categories. That is, the “bright taste” in the first quadrant is a part of each of the matching information categories of light, warm and contrast. Further, the “aqua taste” in the second quadrant is a part of each matching information category of light, cool and gradation. Furthermore, the “Crystal taste” in the third quadrant is part of the cool, deep and contrast fit information categories. Furthermore, the “artist” in the fourth quadrant is a part of the deep, warm, and gradation matching information categories.

FIG. 8 shows the relationship between each quadrant and the subject information group. In this figure, information on the customer service type, product (styling) and personality of the target person is posted as the target person information group, but is not limited thereto. As shown in FIG. 8, the target person information group is classified by the matching information category. For example, when the relevant information category is a bright taste, “product with a casual feeling” as a product, “bright and cheerful” as a personality, and “speak early” as a customer service type are representatively cited. In addition, when the conformity information category is aqua taste, “good touch” as a product, “gentle and gentle” as a personality, and “listen to talk” as a customer service type are typically cited. Furthermore, when the conformity information category is a crystal taste, it is typically cited that the product is “shiny”, the personality is “energetic and quick”, and the customer service type is “quickly respond with quick action”. . Furthermore, when the conformity information category is “Artist”, “Deep things” as a product, “Peaceful, think carefully” as a personality, and “Provide instructions according to the procedure” as a customer service type are typically cited.

(Questionnaire information)
The storage unit 3 in the present embodiment can further store questionnaire information including a set of a plurality of questions for knowing the personality and behavior pattern of the target person and a plurality of answer sentences for the questions. . An example of this questionnaire information is shown in FIG. As shown in this figure, a plurality of answer sentences for each question are provided corresponding to “bright taste”, “aqua taste”, “crystal taste”, and “art taste”, respectively. If the content of the questionnaire information is the question "personality (your personality)", for example, "I like helping people calmly and gently", "energetic decision making and action is fast, focus on purpose and results", Answers such as "I am cheerful and cheerful and value my completion and sensibility" and "I am calm and think carefully and act" are prepared. As described above, the questionnaire information is configured so that the target person selects the items that are considered to correspond to him / herself.

The input unit 5 in the present embodiment includes an input terminal 9 and a device driver 6. Information input from the input terminal 9 or the device driver 6 is stored in the storage unit 3 via the internal bus 12. The input terminal 9 inputs the selection result of the face part and the face part attribute by the operator (usually, but not limited to the target person), and answers to questionnaire information to be described later It is a device for selecting (multiple choices). Here, the subject selects the face part and the face part attribute with reference to the combination of the face part attributes shown in FIG. By combining at least two in this way, it is possible to further narrow down the matching information category so as to match the target person as will be described later, and to provide more appropriate target person information to the target person. This is because it can. The input unit 5 mainly functions as the attribute information acquisition unit 21 (see FIG. 2).

The input terminal 9 is used mainly to input a selection instruction and necessary data. Examples of the input terminal 9 include a mouse, a pointing device, a keyboard, and a touch panel. When the input terminal 9 is a mouse or a pointing device, the input terminal 9 can be used for a selection instruction or data input using a mouse cursor or a point on the selection screen displayed on the display 10 of the output unit 7. Can be used to input various data. When the input terminal 9 is a touch panel, a selection instruction or data can be input using the operation input button on the display 10 or a display screen prepared separately.

The device driver 6 receives various data such as a facial part attribute measurement result, face image data, and 3D scanning data, which will be described later, from an external device such as a measurement device, a digital camera, a scanner device, or a 3D scanner device connected via the device driver 6. It is a driver to receive. The driver 6 reads, for example, face image data photographed by a digital camera (not shown), 3D scanning data from a 3D scanner, measurement results for a predetermined attribute, and the like based on an instruction signal from the arithmetic control unit 2. Execute processing.

The output unit 7 in this embodiment includes a display 10 and a printer 11. The output unit 7 displays various formats and data on the display 10 based on the instruction signal from the arithmetic control unit 2 or causes the printer 11 to print. Various formats include a selection screen for the target person to select the face part and face part attribute, a target person information group selected by the information providing apparatus of the present embodiment, and a plurality of targets corresponding to the information group. An output screen for outputting person information is included. Examples of the display 10 include a liquid crystal monitor and a projector.

[Calculation control unit 2]
Next, functions of the arithmetic control unit 2 will be described. As shown in FIG. 2, the arithmetic control unit 2 processes the program and various data for executing the information providing method of the present invention, thereby obtaining the attribute information acquisition unit 21, the evaluation unit 22, the conforming information category. Processing of each functional unit of the specifying unit 23 and the information selection unit 24 is executed. These processes are performed according to various command signals from the arithmetic control unit 2. The units 21 to 24 are classified by name according to function for convenience of explanation, and do not limit the software configuration. In addition, the present invention includes a form in which a part of the processing by these is executed by hardware mounted on the information providing apparatus of the present embodiment.

[Attribute information acquisition unit 21]
The attribute information acquisition unit 21 receives the selection result of the selected face part and face part attribute by the operation of the input device of the input unit 5 by the target person, or the external device (keyboard, touch panel, scanner, etc.) (not shown) via the device driver 6. A function of acquiring at least one facial part attribute measurement result (measurement value) sent in the

Specifically, for example, when the selected face part is at least one of eyebrows, eyes, nose, and mouth, and the face part attribute is a shape / size, the attribute information acquisition unit 21 selects each selected face part. Is acquired as a facial part attribute measurement result and sent to the evaluation unit. In this case, the face part attribute measurement result includes the face size Lm, Mm, Nm or Mm · Nm obtained in the same manner as the reference face size for the subject (for convenience of explanation, Lm corresponding to each of the reference face sizes) , Mm, Nm, etc., and m).

When the selected face part is at least one of skin, pupil, and hair, and the face part attribute is color, the attribute information acquisition unit 21 uses the color value in each selected face part as a face part attribute measurement result. Obtain it and send it to the evaluation unit 22. When the selected face part is an eye and the face part attribute is a color, the attribute information acquisition unit 21 calculates the color value measured for each of the white eye part and the black eye part in the selected face part. Obtained as a result and sent to the evaluation unit 22.

When the selected face part is skin and the face part attribute is texture, the attribute information acquisition unit 21 acquires a measurement value of the oil amount in the selected face part as a face part attribute measurement result and evaluates the part 22. Send to. Note that the skin texture evaluation method is not limited to the amount of oil in the skin, and other attributes such as the amount of skin moisture and the ratio between the amount of oil and the amount of moisture can also be employed. Furthermore, when the selected face part is hair and the face part attribute is texture, the attribute information acquisition unit 21 acquires and evaluates the measured value of the diameter of the hair in the selected face part as a face part attribute measurement result. Send to part 22.

The attribute information acquisition unit 21 can also acquire face image data and 3D scanning data. Therefore, the attribute information acquisition unit 21 can include an image data analysis unit 25 to analyze the acquired face image data and 3D scanning data. The face image data or the like may be the subject's own or a person other than the subject. In accordance with the selection result of the face part and the face part attribute by the target person or the operator of the information providing apparatus 1 of the present invention, the image data analyzing unit 25 selects the selected face part from the acquired face image data by a conventionally known method. After detection, a predetermined attribute such as a dimension is measured, and the result is set as a facial part attribute measurement result. In the end, the information providing apparatus 1 of the present invention provides information about the target person in the former case, and provides information about a person other than the target person in the latter case. become.

Hereinafter, in the case of two-dimensional face image data, for example, if the selected face part is at least one of eyebrows, eyes, nose, and mouth, and the face part attribute is shape / size, an image The data analysis unit 25 obtains a predetermined dimension related to the shape and size of the selected face part for the face image data sent from the attribute information acquisition part 21 and uses it as a face part attribute measurement result.

When the selected face part is skin and the face part attribute is color, the image data analysis unit 25 measures the color value of the skin area excluding the hair part from the face image data to measure the face part attribute. The measurement result. Furthermore, when the selected face part is hair or pupil (black eye part or pupil) and the face part attribute is color, the image data analysis unit 25 measures the color value of the hair region or pupil from the face image data. Color the face part attribute measurement result. Furthermore, when the selected face part is an eye and the face part attribute is a color, the image data analysis unit 25 measures color values for each of the white eye part and the black eye part in the selected face part from the face image data. And the measurement result of the facial part attribute. Color measurement can be performed by a known color measurement method. Further, the colorimetric position in the hair region and the eyes (including both the white eye part and the black eye part) at the time of color measurement can be set by a known method so as to represent each of these areas. As long as a representative value can be obtained, the color measurement may be performed for only one point, or multiple points may be measured to obtain an average value thereof.

Furthermore, when the selected face part is hair and the face part attribute is texture, the image data analysis unit 25 uses the hair of the selected face part in the face image data (in this case, 3D scanning data is preferable). The diameter is measured, and this is used as the facial part attribute measurement result. Furthermore, in this case, the image data analysis unit 25 acquires a cross-sectional shape of the hair using a known image analysis method, and uses this as a facial part attribute measurement result. The cross-sectional shape of the hair is used because this shape is a factor in the formation of straight hairs and curly hairs, and whether the hair is straight or not has a great influence on the texture of the hair.
These face part attribute measurement results are sent to the evaluation unit 22.

[Evaluation unit 22]
The evaluation unit 22 compares the face part attribute measurement result sent from the attribute information acquisition unit 21 with a face part attribute reference value called from the storage unit 3 to be described later, and compares the comparison result with the matching information category specifying unit 23 ( (To be described later). For example, when the selected face part is at least one of eyebrows, eyes, nose, and mouth, and the face part attribute is shape / size, the evaluation unit 22 sends each dimension ( The measured value in the image data analyzing unit 25 is also included) and the reference value of each dimension called from the storage unit 3 is compared. At this time, the evaluation unit 22 calls a reference face size L, M, N, or M · N (see FIG. 4) from the storage unit 3 to be described later, and the reference face size for the subject sent from the attribute information acquisition unit 21. By dividing the reference face size L, M, N or M · N by the face size Lm, Mm, Nm or Mm · Nm obtained by the same measurement as above, correction values (L / Lm, M / Mm, N / Nm or M · N / (Mm · Nm)) is obtained, and among the acquired face part attribute measurement results of the subject, each measurement value excluding the face size is multiplied by the correction value.

Hereinafter, the evaluation contents in the evaluation unit 22 relating to each of the face part and the face part attribute will be specifically described. When the face part is an eyebrow, the face part attribute “shape / size” has two attributes of “straight (target) -curve (target)” and “thin-thick” (see FIG. 5). Here, when the former attribute (“straight (linear) —curve (curve)”) is selected, as shown in FIG. 10A, the facial part attribute measurement acquired by the evaluation unit 22 is performed. The result (measured value) is a radius A (unit: cm) of an arc approximated by the upper edge of the eyebrows, and the face part attribute reference value called from the storage unit 3 is set to 5 cm. In the case where the measured value of the radius A according to the normal method for the subject is, for example, 10 cm larger than this facial part attribute reference value after being multiplied by a correction value (M · N / (Mm · Nm); the same applies hereinafter) Since the shape of the eye of the subject is a straight landscape, it becomes “straight”, and in the case of 3 cm smaller than the face part attribute reference value, the height and width are narrow, so the “curve” It becomes the target. That is, in this case, the facial part attribute measurement result for the subject is the “straight-curve” line (corresponding to the horizontal axis (cool-warm tendency) of the styling map (orthogonal coordinate system) shown in FIG. 6) on the face It belongs to the “straight line” side or the “curve” side with the site attribute reference value 5 cm as the boundary (origin).

When the latter attribute (“thin-thick”) is selected, the facial part attribute measurement results (measurement values) acquired by the evaluation unit 22 are as shown in FIG. This is the ratio B (unit:%) of the width of the eyebrow on the eye side to the product M · N (see Fig. 4) obtained by multiplying the distance between the strokes by the vertical distance, and the reference value for the facial part attribute is set to 0.03% Has been. In the case where the measured value of the width B of the subject by the usual method is 0.02% which is smaller than the reference value 0.03% after being multiplied by the correction value (M · N / (Mm · Nm)) as described above. Belongs to the “thin” side when it is 0.05% larger than the reference value of 0.03%. That is, in this case, the facial part attribute measurement result for the subject is the face part attribute reference value 0 on the “thin-thick” line (corresponding to the vertical axis (light-deep tendency) of the styling map shown in FIG. 6). It belongs to the “thin” side or “thick” side with 0.03% as the boundary (origin).

When the face part is an eye, the face part attribute “shape / size” has two attributes of “straight (linear) or curved (curve)” and “small-large” (see FIG. 5). . When the former attribute (“straight (target) —curve (target)”) is selected, the facial part attribute measurement result (measured value) is the product M · N (see FIG. 11A). 4)), and the reference value of the facial part attribute is set to 0.05%. When the measured value of the above-mentioned ratio C of the subject by the usual method is 0.03% smaller than the reference value 0.05% after being multiplied by the correction value (M · N / (Mm · Nm)), Since the shape of the eye is horizontally long, it is like a “straight line”, and in the case of a large 0.08%, there is a height, so it is like a “curve”. That is, the facial part attribute measurement result for the subject in this case is the face part attribute reference value 0 on the “straight-curve” line (corresponding to the horizontal axis (cool-warm tendency) of the styling map shown in FIG. 6). .05% as a boundary (origin) and belonging to the “straight line” side or “curve” side.

Further, when the latter attribute (“small-large”) is selected, the facial part attribute measurement result (measured value) corresponds to the product M · N (see FIG. 4) as shown in FIG. It is the ratio D (unit:%) of the lateral width of the eye, and this facial part attribute reference value is set to 0.2%. When the measured value of the eye width ratio D of the subject is 0.18% smaller than the reference value (0.2%) after being multiplied by the correction value (M · N / (Mm · Nm)) Belongs to the “small” side, and in the case of a large 0.25%, it belongs to the “large” side. That is, the facial part attribute measurement result for the subject in this case is the face part attribute reference value 0 on the “small-large” line (corresponding to the vertical axis (light-deep tendency) of the styling map shown in FIG. 6). .2% of the border (origin) belongs to the “small” side or the “large” side.

When the face part is the nose, the face part attribute “shape / size” has two attributes “straight (target) —curve (target)” and “small—large” as in the case of the eyes ( (See FIG. 5). When the former attribute (“straight-curve”) is selected, the facial part attribute measurement result (measured value) is an arc that approximates the swelling of the nose as shown in FIG. Radius E (unit: cm), and the face part attribute reference value is set to 1 cm. If the measured value of the radius E of the subject is 0.5 cm, which is smaller than the face part attribute reference value 1 cm after being multiplied by the correction value (M · N / (Mm · Nm)), it is “curved” In the case of a large 2 cm, it becomes “linear”. That is, the facial part attribute measurement result for the subject in this case is the “curve-straight line” line (corresponding to the horizontal axis (cool-warm tendency) of the styling map shown in FIG. 6), and the facial part attribute reference value 1 cm. It belongs to either the “straight line” side or the “curve” side with the border (origin).

When the latter attribute (“small-large”) is selected, the facial part attribute measurement result (measured value) is the product M · N (see FIG. 4) as shown in FIG. It is expressed by a width ratio F (unit:%) in the lateral direction of the nose, and its reference value is set to 0.2%. When the measured value of the ratio F of the subject is 0.18%, which is smaller than the facial part attribute reference value 0.2%, after being multiplied by the correction value (M · N / (Mm · Nm)), “ If it is 0.25% on the “small” side, it belongs to the “large” side. That is, the facial part attribute measurement result for the subject in this case is the face part attribute reference value 0 on the “small-large” line (corresponding to the vertical axis (light-deep tendency) of the styling map shown in FIG. 6). It belongs to the “small” side or the “large” side with a boundary (origin) of 2%.

When the face part is the mouth, the face part attribute “shape / size” has two attributes, “straight (target) —curve (target)” and “small—large”, as in the case of the eyes and nose. (See FIG. 5). When the former attribute (“straight or curved”) is selected, the facial part attribute measurement result (measured value) is the product M · N (see FIG. 4) as shown in FIG. The height ratio G of the mouth in the vertical direction (unit:%), and 0.1% is the reference value of the face part attribute. If the measured value of the subject ratio G is multiplied by the correction value (M · N / (Mm · Nm)) and is 0.08% smaller than the reference value 0.1%, the shape of the mouth Since it is horizontally long, it is like a “straight line”, and when it is 0.15%, it is like a “curve” because it has a height and is narrow. That is, the facial part attribute measurement result for the subject in this case is the face part attribute reference value 0 on the “curve-straight line” line (corresponding to the horizontal axis (cool-warm tendency) of the styling map shown in FIG. 6). It belongs to the “straight line” side or “curve” side with 1% as the boundary (origin).

When the latter attribute (“small-large”) is selected, the facial part attribute measurement result (measured value) is the product M · N (see FIG. 4), as shown in FIG. ) Of the width of the mouth in the horizontal direction (unit:%), and the reference value is set to 0.25%. When the measured value of the ratio H of the subject is 0.23% which is smaller than 0.25% of the facial part attribute reference value after being multiplied by the correction value (M · N / (Mm · Nm)), “ If it is 0.3%, it belongs to the “large” side. That is, the facial part attribute measurement result for the subject in this case is the face part attribute reference value 0 on the “small-large” line (corresponding to the horizontal axis (light-deep tendency) of the styling map shown in FIG. 6). It belongs to the “small” side or “large” side with 25% as the boundary (origin).

If the selected face part is skin and the face part attribute is color, the evaluation unit 22 compares the face part attribute measurement result with the reference value of the color value called from the storage unit 3 to be described later. In this case, the face part attributes include two attributes of “yellow (system) -blue (system)” and “bright-dark” (see FIG. 5). For any attribute (face part attribute), the face part attribute measurement result (measured value) is a color value obtained by measuring a part representing the skin color using a conventional method, and the reference value is a CIE Lab color value. Is shown. In the following, an example in which CIE Lab color values are used as color values will be described. However, the present invention is not limited to this, and other color values such as Hunter Lab, RGB, CMYK, XYZ, or Lch can also be used. .

When the selected face part is skin and the former attribute “yellow (system) -blue (system)” is selected, the face part attribute reference values are L = + 62.5, a = −1.9, b = + 11.8. If the a and b values measured for the subject are +10.2 and -7.6, respectively, the color becomes a “blue system” that is a reddish blue than the face part attribute reference value. Further, if the measured a value and b value are 83.5, +11.3, and +10.9, respectively, a “yellow system” that is reddish yellow than the face part attribute reference value (2). Judgment on the difference between two color values (color difference) follows a conventional method, and so on.) That is, the measurement result of the facial part attribute for the subject in this case is the face part attribute reference value on the “yellow-blue” line (corresponding to the horizontal axis (cool-warm tendency) of the styling map shown in FIG. 6). The boundary (origin) belongs to the “yellow” side or the “blue” side.

When the selected face part is skin and the latter attribute “bright-dark” is selected, the face part attribute reference values are L = + 62.5, a = −1.9, b = + 11, as described above. .8. If the L value measured for the subject is +87.3, it is brighter than the facial part attribute reference value L = + 62.5, and if the measured L value is +57.7, the facial part attribute reference value Darker than L = + 62.5. That is, the measurement result of the facial part attribute for the subject in this case is the face part attribute reference value on the “bright-dark” line (corresponding to the horizontal axis (light-deep tendency) of the styling map shown in FIG. 6). The boundary (origin) belongs to the “bright” side or “dark” side.

Also, when the selected face part is the hair or the pupil (pupil) and the face part attribute is color, the evaluation unit 22 also calls the reference value of the color value called from the storage unit 3 (to be described later) Contrast with face part attribute reference value). In this case, the face part attribute includes two attributes of “yellow (system) -blue (system)” and “bright-dark” (see FIG. 5). When the former “yellow (system) -blue (system)” is selected, the face part attribute reference values are L = + 31.9, a = + 5.5, and b = + 7.2. If the a and b values measured for the subject are +0.0 and +0.4, respectively, “blue (system)” is felt slightly more bluish than the face part attribute reference value. Further, if the measured a value and b value are +7.5 and +6.7, respectively, “yellow (system)” having redness and yellowishness stronger than the face part attribute reference value. That is, the measurement result of the facial part attribute for the subject in this case is the face part attribute reference value on the “yellow-blue” line (corresponding to the horizontal axis (cool-warm tendency) of the styling map shown in FIG. 6). The boundary (origin) belongs to the “yellow” side or the “blue” side.

When the selected face part is the hair or the black eye part of the eye and the latter “bright-dark” is selected, the face part attribute reference values are L = + 62.5, a = −1.9, b = + 11 .8, which is the same as described above. If the L value measured for the subject is +87.3, it becomes brighter than the face part attribute reference value L = + 62.5, and if the measured L value is +57.7, the face part attribute reference Darker than the value L = + 62.5. That is, the measurement result of the facial part attribute for the subject in this case is the face part attribute reference value on the “bright-dark” line (corresponding to the horizontal axis (light-deep tendency) of the styling map shown in FIG. 6). The boundary (origin) belongs to the “bright” side or “dark” side.

If the selected face part is an eye and the face part attribute is “gentle-bright” in color, the evaluation unit 22 obtains a difference in color value between the white-eye part and the black-eye part and calls it from the storage part. Also, it is compared with the reference value of the difference in color value. In this case, the face part attribute reference value (saturation) is L = + 94.5, a = + 1.4, b = + 7.6, and L = + 31.9, a = + 5. Since 5, b = + 7.2, c = 1.33 from the following equation.

The color values measured for the eyes of the subject are L = + 94.5, a = + 1.4, b = + 7.6 for the white eye portion, L = + 42.2 for the black eye portion, a = + 6.4, b = If it is +1.6, c = 1.1 from the above formula, and since it is smaller than the reference value 1.33, it becomes gentle. Further, the color values of the subject's eyes are L = + 95.1, a = + 1.7, b = −2.8 for the white part, and L = + 14.1, a = −0.6, b = for the black part. If it is +0.7, c = 2.36 from the above formula, which is larger than the reference value 1.33, so that it becomes vivid. In this case, if the evaluation is vivid, the face part attribute measurement result includes a first 45-degree diagonal virtual axis (contrast tendency) that passes through the origin in the orthogonal coordinate system shown in FIG. It belongs to the quadrant and the third quadrant. Further, when the evaluation is gentle, it belongs to the second quadrant and the fourth quadrant that include a 45-degree diagonal virtual axis (gradient tendency) passing through the origin in the orthogonal coordinate system.

Furthermore, when the selected face part is skin and hair and the face part attribute is “brightness-gentle” of the color, the evaluation unit 22 obtains the difference in color value between the skin part and the hair part, And the reference value of the difference between the color values called from the storage unit. In this case, the facial part attribute reference value (saturation) is L = + 62.5, a = + 1.9, b = + 11.8 in the skin part, L = + 31.9, a = + 5. Since 5, b = + 7.3, c = 2.81 from the above formula. The color values measured for the subject are L = + 62.5, a = + 1.9, b = + 11.8 in the skin portion, L = + 31.9, a = + 5.5, b = + 7. If it is 3, c = 2.66 from the above formula, and since it is smaller than the reference value 2.81, it becomes gentle. If the skin part is L = + 87.7, a = + 7.1, b = + 6.6, and the hair part is L = + 14.2, a = + 2.4, b = + 1.5, then Since c = 3.57, which is larger than the reference value 2.81, the image becomes bright. In this case, when the evaluation is vivid, the first quadrant and the third quadrant that include a 45-degree obliquely upward virtual axis (corresponding to contrast tendency) passing through the origin in the orthogonal coordinate system shown in FIG. 6 are included. Will belong. Further, when the evaluation is moderate, it belongs to the second quadrant and the fourth quadrant, which include a 45-degree diagonal virtual axis (gradient tendency) passing through the origin in the orthogonal coordinate system in FIG.

Furthermore, when the selected face part is skin, the face part attribute “texture” has two attributes of “thin-thick” and “matt (matte) -gloss (present)” (see FIG. 5). Here, when the former attribute (“thin-thick”) is selected and the thickness of the epidermis in the skin part is used as the facial part attribute measurement result, the evaluation unit 22 uses the measured thickness value of the epidermis in the skin part. Contrast with the reference value of the thickness of the skin called from the storage unit 3. The evaluation unit 22 acquires the thickness of the epidermis (unit: mm), and the epidermis thickness reference value (face part attribute reference value) called from the storage unit 3 is set to 0.2 mm. When the thickness of the epidermis measured for the subject is 0.1 mm, it is evaluated as “thin” because it is smaller than the reference value 0.2 mm. When the thickness of the epidermis is 0.3 mm, the reference value 0 Since it is larger than 2 mm, it is evaluated as “thick”. In this case, the facial part attribute value is on the “thin-thick” line (corresponding to the vertical axis (light-deep tendency) of the styling map shown in FIG. 6), and the boundary (origin) of the facial part attribute value is 0.2 mm. Thus, it belongs to the “thin” side or the “thick” side.

When the latter attribute (“matte (matte) —shiny (present)”) is selected and the skin oil amount is acquired as the facial part attribute measurement result, the evaluation unit 22 stores the skin oil amount for the subject. Contrast with the skin oil amount reference value called from 3. In this case, the reference value of the skin oil amount (facial part attribute reference value) is 12%. If the subject's measured skin oil content (facial part attribute measurement result) is 5%, it is lower than the standard value of 12%, so it is a mat, and conversely, if the measured skin oil content is 20%, the standard Since the value is higher than 12%, it is glossy. If the evaluation is a mat, the face part attribute measurement result in this case includes a second 45-degree hypothetical axis (gradient tendency) that passes through the origin in the orthogonal coordinate system of FIG. It belongs to the quadrant and the fourth quadrant. Further, when the evaluation is glossy, it belongs to the first quadrant and the third quadrant that include a 45-degree diagonal virtual axis (contrast tendency) that goes upward through the origin in the orthogonal coordinate system shown in FIG.

Furthermore, when the selected face part is hair, the face part attribute “texture” has two attributes “flat-uneven” and “thin-thick” (see FIG. 5). Here, when the former attribute (“flat-unevenness”) is selected, the evaluation unit 22 obtains the cross-sectional shape of the hair as the facial part attribute measurement result from the storage unit 3 and the reference value of the cross-sectional shape. Contrast. Here, the cross-sectional shape (face part attribute reference value) called from the storage unit 3 is set to an ellipse. When the cross-sectional shape of the hair measured for the subject is approximately a perfect circle, it is approximately evaluated as “flat”, and when the cross-sectional shape is approximately triangular, it is approximately evaluated as “with unevenness”. In this case, the facial part attribute value is on the “flat-uneven” line (corresponding to the horizontal axis (cool-warm tendency) of the styling map shown in FIG. 6), and the facial part attribute reference value ellipse is the boundary (origin). If it is a more or less perfect circle, it belongs to the “flat” side, and if it is approximately a triangle, it belongs to the “uneven” side.

When the latter attribute (“thin-thick”) is selected, the evaluation unit 22 compares the hair diameter as the facial part attribute measurement result with the reference value of the hair diameter called from the storage unit 3. In this case, the diameter reference value (face part attribute reference value) is 0.08 mm. If the measured value of the subject's diameter (facial part attribute measurement result) is 0.06 mm, it is evaluated as “thin” because it is smaller than the reference value 0.08 mm, and conversely the diameter measured value is 0.1 mm. For example, since it is larger than the reference value 0.08 mm, it is evaluated as “thick”. In this case, the facial part attribute measurement result is the face part attribute reference value on the “thin-thick” line (corresponding to the vertical axis (light-deep tendency) of the styling map shown in FIG. 6) of the orthogonal coordinate system of FIG. It belongs to the “thin” side or the “thick” side with 0.08 mm as the boundary (origin).

When there are a plurality of selections of the selected face part or face part attribute by the subject or both, the evaluation unit 22 sets the selected face part and the face part attribute and the comparison result of the face part attribute measurement result to the corresponding information category. The data is sent to the specifying unit 23.

[Compliance information category identification unit 23]
The matching information category specifying unit 23 calls at least one predetermined tendency from each of the selected face part and the face part attribute selection results sent from the evaluation unit 22, and based on the comparison result of the face part attribute measurement results It is configured to identify at least one matching information category associated with each tendency and send the identification result to the information selection unit 24. When there is one face part attribute measurement result from the evaluation unit 22, the matching information category specifying unit 23 calls a tendency corresponding to the face part attribute from the storage unit 3. Then, based on the facial part attribute measurement result, one of the two matching information categories classified by the tendency is specified, and the subject information belonging to the matching information category specified to the information selection unit 24 Issue a command to select a group.

For example, when the face part is an eyebrow, the face part attribute “shape / size” has the attribute “straight line (straight) -curve (curve)”, and the evaluation result in the evaluation unit 22 is “straight line”. The matching information category specifying unit 23 calls the cool-warm tendency from the storage unit 3, and on the styling map of FIG. 6, the second quadrant (aqua taste) and the third quadrant partitioned by the cool-warm tendency on the horizontal axis. (Crystal taste) is specified as the relevant information category. If the face part is skin, the face part attribute is the color (light and dark), and the evaluation result in the evaluation unit 22 is “bright”, the matching information category specifying unit 23 writes the light- Deep Tendency On the styling map of FIG. 6, the first quadrant (bright taste) and the second quadrant (aqua taste) partitioned by the light-deep tendency on the vertical axis are specified as the matching information category. Further, when the face part is skin and hair, the face part attribute is the color (mild-bright), and the evaluation result in the evaluation unit 22 is “gentle”, the matching information category specifying unit 23 stores the storage unit The gradation-contrast tendency is called from 3, and the second quadrant (aqua taste) and the fourth quadrant (artist) including the hypothetical axis of 45 degrees obliquely passing through the origin on the styling map in FIG. Identify as a category.

In addition, when the target person selects the face part and the face part attribute as shown in the following (a) to (c), the conformity information category specifying unit 23 causes at least two tendencies of the three tendencies. When the conformance information category is to be specified for each, the conformity information categories are superimposed on the styling map shown in FIG. 6 and the corresponding conformance information categories are identified to narrow down the category. Can be implemented. As a result, it becomes possible to provide a target information group that is more accurate (applicable to the target person) by narrowing down than those included in the compatible information category including any two quadrants in the case of one tendency. .
(A) When selecting two sets of attributes of one face part attribute for one selected face part For example, in FIG. 5, the selected face part is skin and the face part attribute “color” is 2 This is a case of selecting one set of attributes. In this case, if the comparison results in the evaluation unit 22 are “yellow” and “bright”, respectively, the matching information category specifying unit 23 is the first quadrant (bright taste) and the fourth quadrant (the former matching information category). The first quadrant (bright taste) and the second quadrant (aqua taste), which are the latter category, are overlapped to narrow down to the first quadrant (bright taste) in which both overlap, and are specified as the matching information category.

(B) When selecting at least one attribute included in each of two or more face part attributes for one selected face part For example, in FIG. 5, the selected face part is skin and the face part attribute “color” is 2 For example, the face part attribute “texture” attribute “matte” is further selected in addition to a set of attributes. In this case, if the comparison results in the evaluation unit 22 are “yellow”, “bright”, and “shiny”, respectively, the matching information category specifying unit 23 is the first category (bright taste) and the second quadrant that are the former categories. (Aqua taste), 4th quadrant (Artist), and the latter category, 1st quadrant (Bright taste), 3rd quadrant (Crystal taste) are superimposed, and the 1st quadrant (Bright taste) that overlaps is compatible Is identified as a category with a relatively high conformity, and other categories are also identified as categories for which conformance cannot be denied although the conformity is relatively lower than the first quadrant.

(C) When selecting at least one attribute from each face part attribute defined for a plurality of selected face parts For example, one selected face part is an eyebrow, and the face part attribute “shape / size” This is a case where the other selected face part is skin and the face part attribute is the color (light and dark). In this case, if the respective evaluation results in the evaluation unit 22 are “straight line” and “bright”, the conformity information category specifying unit 23 performs the second quadrant (aqua taste) and the third quadrant (crystal) of the former conformance information category. The first quadrant (bright taste) and the second quadrant (aqua taste), which are the latter category, are overlapped to specify the overlapping second quadrant (aqua taste).
Then, the matching information category specifying unit 23 sends the matching information category specified here to the next information selection unit 24.

In this way, by selecting a plurality of face parts and / or face part attributes so that different tendencies are included, it is possible to further narrow down the matching information category, and a more appropriate target person for the target person Information can be provided. In addition, if the face part attribute measurement results for a plurality of face parts belong to one or two tender bipolar attributes and cannot be narrowed down to one relevant information category, a ranking is given. To identify the relevant information category. In this case, the matching information category identification unit 23 sends the plurality of identified matching information categories to the information selection unit 24 in that order, so that the most suitable target information (group), and the next target information ( Group), ..., etc., and has an advantage that can be provided to the subject.

Next, if each of the three tendencies has two or more facial part attribute reference values, the matching information category is specified as follows. For ease of explanation, in the case of two tendencies, cool-warm propensity (horizontal axis of styling map) and light-deep propensity (vertical axis of styling map) Is greater than the maximum face part attribute reference value, greater than the second face part attribute reference value, less than the maximum face part attribute reference value, greater than the third face part attribute reference value, less than the second face part attribute reference value,・・When the styling maps are shared and projected onto the styling map, they are partitioned into a grid pattern. Since multiple face part attribute measurement results will be included (plotted) in any of the eyes of this board, the relevant information category is specified by ranking according to the number of plots in the unit of the division, and this specification The results are sent to the information selection unit 24 in this order. Next, when the gradation-contrast tendency is further included, since the plot of the measurement result on the oblique virtual axis on the styling map is included in one of the grid-like sections of the board, similarly, the section unit In order to identify the matching information category by ranking according to the number of plots, the identified result is sent to the information selection unit 24 in the ranking. When each of the three tendencies has two or more facial part attribute reference values, the subject is based on the strength of the attribute on the styling map as described above, that is, the degree of attribute according to the distance from the origin. Information (s) can be provided.

[Information Selection Unit 24 to Output Unit 25]
The information selection unit 24 selects at least one target person information belonging to the relevant information category specified based on the specification result from the relevant information category specification unit 23 from the target person information group in the storage unit 3 and outputs it. The unit 25 is configured to output each selected target person information. In this embodiment, the image is displayed on the display and printed by the printer. However, the output method is not limited to these, and another method may be used.

Information Providing Method of the Present Invention Next, an example of an information providing method using the information providing apparatus 1 according to the present invention will be described with reference to FIGS. FIG. 14 is a flowchart showing the overall procedure of the information providing method using the information providing apparatus shown in FIG. 1, and FIG. 15 is a flowchart showing the procedure of measuring the facial part attribute value when the facial part attribute has a shape and size. FIG. 16 is a flowchart showing a procedure for measuring a facial part attribute value when the facial part attribute is a color.

As shown in FIG. 14, the subject first performs a gender input operation, so that the information providing apparatus 1 of the present invention acquires the gender from the input terminal 9 (step S1). Next, the calculation control unit 2 causes the display 10 to display a list of each face part and the like, and the subject uses the input terminal 9 to select at least one face part (eyes, nose, mouth, (Skin, hair) is selected (step S2). Thereby, the selected face part is determined.

Subsequently, the information providing apparatus 1 according to the present invention uses the function of the arithmetic control unit 2 to display the face part attributes (shape / size, color, quality (texture)) on the display 10 based on FIG. ) And the attributes shown in FIG. 5 are displayed so as to be selectable, and the target person selects a face part attribute from the attributes (step S3). With respect to the face part attribute thus selected, the information providing apparatus 1 of the present invention acquires the face part attribute measurement result by any one of the following methods (1) and (2) (step S4). Thereafter, the attribute information acquisition unit 21 sends the selection result of the acquired selected face part and face part attribute and the face part attribute measurement result to the evaluation unit 22.

(1) Method for obtaining face part attribute measurement result from subject's face image data or 3D scanning data Information acquisition device 1 of the present invention obtains face image data of the face taken from the subject and then selects from the data The face part attribute measurement result is obtained by a method defined in advance for the face part and the selected face part attribute. As shown in FIG. 15, the attribute information acquisition unit 21 first acquires face image data (step S21). Specifically, the arithmetic control unit 2 acquires a front image of the subject's face and, if necessary, face image data obtained by capturing a face image from a predetermined angle using a digital camera (not shown) or a 3D scanner device. The face image data is stored in the storage unit 3 via the device driver 6. The face image data only needs to be acquired and processed as digital data. The face image data is not limited to those captured by a digital camera or a 3D scanner device. It may be a thing.

Next, the face contour and the hair portion are recognized from the face image data using a known recognition technique, and the face area is extracted (step S22). Here, the face area is defined as an area excluding the hair portion of the face. Then, the reference face size L of the reference face shape (see FIG. 4) is acquired from the storage unit 3, and the face size Lm of the face area is compared with the reference face size L acquired from the storage unit 3 for correction. A value is obtained, and size adjustment is performed by enlarging / reducing the face image data by this correction value (step S23).

Next, based on the size-matched face image data, at least one selected face part is extracted (step S24) according to the selection by the subject (see step S2 in FIG. 14), and each selected face part is defined. Each measured dimension (facial part attribute measurement result) is obtained from the face image data, and the face part attribute measurement result is obtained (step S25). At this time, it is also possible to directly input a face part attribute measurement result for another face part attribute from the input terminal 5 such as a touch panel. For example, when the face part is an eyebrow and the face part attribute is “straight-curve” in the “shape / size”, the radius of the arc of the eyebrow is measured as described above. Although not shown, the flow of 3D scanning data is almost the same as that of the above-described 2D face image data. Further, the

steps

22 and 23 may be performed in the reverse order. That is, it is possible to acquire the face part and face part attribute according to the selection result of the subject, obtain the face part attribute measurement result, and then multiply the measurement result by the correction value to perform size matching.

(2) Method by inputting the face part attribute measurement result of the subject The subject inputs the attribute measurement result obtained for the selected face part to the information providing apparatus 1 of the present invention, and uses this as the face part attribute measurement result It is. For example, when the face part is an eyebrow and the face part attribute is “straight-curve” in the attribute “shape / size”, the measurement value of the radius of the arc of the eyebrow is directly input from the input terminal 5 to measure the face part attribute. As a result. The face part attribute measurement result thus obtained is multiplied by the correction value.

Next, with reference to FIG. 16, a method for obtaining a color value as a facial part attribute measurement result from face image data will be described in detail. First, the attribute information acquisition unit 21 acquires the face image data and sends it to the image data analysis unit 25 (step S31). The image data analysis unit 25 recognizes the outline of the face and the hair from the sent face image data, and extracts a face area (step S32). In the case where the selected face portion is the color of the hair, instead of extracting the region, the hair region may be extracted by recognizing the outline of the face and the hair from the face image data. Next, a color value measurement point is selected from the face area by an appropriate method (step S33). The color value measurement point may be selected at one place or a plurality of places as long as a representative result is obtained. Then, the color value at the color value measurement point is measured (step S34). The measurement method is performed by a known method. Subsequently, the measured color measurement results (the result of averaging the color measurement results at each store when a plurality of measurement points are used) are stored in the storage unit 3 as face part attribute values (step S35). The color value can be obtained from 3D scanning data by the same method as described above.

Returning to FIG. 14, it is confirmed by the input operation of the subject whether or not another face part is to be acquired (step S5). When acquiring another face part, the process returns to step S2 again, and as a result, a plurality of face parts can be selected. If another face part is not acquired, the process proceeds to step S6.

Next, it is determined whether or not to conduct a questionnaire based on the selection operation by the input of the target person (step S6). When the target person selects a questionnaire, the attribute information acquisition unit 21 acquires a plurality of answer data of the questionnaire by the input to the input terminal 9 by the target person (step S7). When there are two or more items of questionnaire information, multiple items of questionnaire information may be displayed at a time, and the target person may select each answer sentence at one time. Answer sentences in a set) may be divided into multiple times to select answer sentences. The attribute information acquisition unit 21 stores the acquired answer data in the storage unit 3.

The evaluation unit 22 performs the following evaluation process (step S8). That is, the selected face part, the face part attribute selection result, the face part attribute measurement result, and the face part attribute reference value are called from the storage unit 3, respectively, and the face part attribute measurement result and the face part attribute reference value are compared. In this way, one or more facial part attribute evaluation results are obtained. In addition, when there are a plurality of response data for the questionnaire information by the target person, the response data is called from the storage unit 3, and the response data is allocated to each of the four quadrants of bright taste, aqua taste, crystal taste, and artist. The number of data for each quadrant (category). The evaluation unit 22 sends the comparison results and the aggregation results to the matching information category specifying unit 23.

In the matching information category specifying unit 23, when there is one face part attribute selected from the evaluation part 22, at least one face part attribute reference value is set as a boundary due to the tendency defined for the face part attribute. One of the two categories related to the attributes on both sides (the matching information category consisting of two of the four quadrants in the styling map shown in FIG. 6) is specified. Also, when two face part attributes defined for one face part are selected by the subject, or at least two belonging to different tendencies are selected from the face part attributes defined for a plurality of face parts. If there is a match, the matching information category specifying unit 23 superimposes the matching information categories by overlapping the matching information categories on the style map shown in FIG. 6 based on the tendency for each face part attribute and the comparison result in the evaluation unit 22. It is specified as a high matching information category (step S9). In this way, when at least two face part attributes are selected, the matching information category with the largest number of duplicates includes useful information suitable for the subject. Furthermore, when there is answer data of questionnaire information, the conformity information category identification unit 23 aggregates the aggregation results for the questionnaire for each quadrant on the styling map in the identification result, and the conformance that is highly compatible with the target in the order of the number of duplicates. It is specified as an information category (step S9). Next, the information selection unit 24 selects target person information from the matching information category (step S10), and outputs the selected target person information to the output unit 7 (step S11). The read target person information group is sent to the output unit 7 and can be displayed on the display 10 or printed by the printer 12.

As described above, the information providing apparatus and the information providing method according to the present invention include a plurality of subjects (including face part attribute measurement results and face image data providers) constituting their faces as described above. Useful styling (product) information (tie, shirt, suit pattern and color) suitable for the subject based on at least one face part attribute measurement result for at least one selected face part selected from , Cosmetics for makeup, etc.), information on the personality of the target person and customer service type, and other information and advice. Other information and advice include, for example, information about tableware; information about interiors such as furniture and interiors (colors of floors and walls, etc.); information about graphic designs such as logo colors; advertisements, promotions, product planning (colors of packages, etc.) ); Information on styling tests.

Further, according to the information providing apparatus and the information providing method of the present invention, when an information group showing statistically high relevance to the face part and the face part attribute is obtained, the information group is classified for each relevant information category. The information can be classified and included in the target person information group and used for subsequent information provision to the target person. In addition, when a face part attribute that is statistically highly related to the target person information group stored in the storage unit in the information providing apparatus is confirmed, the face part attribute is set to a trend or a matching information category. The information can be additionally stored in the facial part information of the storage unit in the information providing apparatus of the present invention in association with the information, and can be utilized for subsequent information provision to the subject.

In addition, this invention is not limited to the said embodiment, In an implementation stage, a component can be deform | transformed and embodied in the range which does not deviate from the summary. In addition, various inventions can be formed by appropriately combining a plurality of components disclosed in the embodiment. For example, some constituent elements can be removed from all the constituent elements shown in the embodiments, or constituent elements over different embodiments can be appropriately combined.

DESCRIPTION OF SYMBOLS 1 Information provision apparatus 2 Arithmetic control part 3 Memory | storage part 4 Internal bus 5 Input part 6 Device driver 7 Output part 9 Input terminal 10 Display 11 Printer 21 Attribute information acquisition part 22 Trend selection part 23 Conformity information category specification part 24 Information selection part 25 Image data analysis unit

Claims

It includes at least an attribute information acquisition unit, a storage unit, an evaluation unit, a compatible information category identification unit, an information selection unit, and an output unit,
The attribute information acquisition unit is defined for at least one selected face part selected from face parts including eyebrows, eyes, nose, mouth, skin, and hair constituting the subject's own face, and the selected face part. The face part attribute including the shape / size, color and texture of the face and the measurement result of the face part attribute,
The storage unit stores a plurality of face part information, a plurality of tendencies, a plurality of matching information categories, and a plurality of target person information groups belonging to each of the matching information categories,
Each of the face part information includes at least one face part attribute defined in advance for each of the face parts, and at least one face part attribute reference value serving as a reference for each face part attribute,
Each of the plurality of tendencies is related to the face part attribute and is represented as a linear axis including the face part attribute reference value in each face part attribute, and the at least one face part attribute reference value is represented on the linear axis. It is stipulated to classify the plurality of target person information groups into at least two relevant information categories on the border,
The evaluation unit acquires the selected face part and the face part attribute measurement result through the attribute information acquisition unit, and compares the face part attribute reference value called from the storage unit based on the former and the latter, Send the comparison result to the relevant information category extraction unit,
The matching information category specifying unit calls at least one tendency associated with each face part attribute from the storage unit, and at least one matching information category associated with each tendency based on the comparison result. Identify
The information selection unit selects at least one target person information belonging to the specified relevant information category from the target person information group in the storage unit,
The information providing apparatus, wherein the output unit is configured to output each selected target person information.
The storage unit further stores information on a reference face shape including at least one reference face size,
When the selected face part is at least one of eyebrows, eyes, nose, and mouth, and the face part attribute is shape / size, the attribute information acquisition unit is obtained by the same measurement as the reference face size. In addition, the predetermined size in each selected face part together with the face size of the subject is acquired as a face part attribute measurement result and sent to the evaluation unit,
The evaluation unit is configured to multiply the correction value obtained by dividing the reference face size by the face size by each measurement value excluding the face size from the acquired facial part attribute measurement results of the subject. The information providing apparatus according to claim 1, wherein the information providing apparatus is configured to compare each dimension with a reference value of each dimension called from the storage unit and send the comparison result to the matching information category extraction unit.
The attribute information acquisition unit further includes an image data analysis unit, acquires face image data instead of the face part attribute measurement result or together with the face part attribute measurement result, and performs a predetermined analysis in the image data analysis unit. The information providing device according to claim 1, wherein the information providing device is a device that performs the operation.
When the selected face part is hair and the face part attribute is texture, the image data analysis unit extracts the cross-sectional shape of the hair in the selected face part and sends it to the evaluation unit as a face part attribute measurement result, The information providing apparatus according to claim 3, wherein the evaluation unit is configured to determine whether the face part attribute measurement result approximates a perfect circle or a substantially triangular shape.
The storage unit further includes questionnaire information associated with each matching information category divided by two predetermined tendencies that intersect each other with the face part attribute reference value, and the target person performs a questionnaire. If selected, the questionnaire information is called from the storage unit and displayed on the output unit for use by the target person.
The evaluation unit, which is acquired through the attribute information acquisition unit, allocates a plurality of response data for the questionnaire information by the target person for each of the relevant information categories, and totals the number of data in each category,
The information provision according to any one of claims 1 to 4, wherein the conformity information category identification unit is configured to rank and identify the conformance information categories in the storage unit in descending order of the number of response data items. apparatus.
When a plurality of face part attributes for the selected face part or the selected face part are selected by the subject, or when a combination of the face part attribute and questionnaire information is selected, the matching information category specifying unit is At least one tendency indicating linearity specified by each face part attribute is called from the storage unit, and at least one matching information category associated with each tendency is specified based on each comparison result. In addition, the plurality of target person information groups are configured to match the face part attribute reference value and superimpose the respective matching information categories so as to be narrowed down to be identified as matching information categories. 6. The information providing device according to any one of 1 to 5.
At least one selected face part selected from the face parts including the eyebrows, eyes, nose, mouth, skin, and hair constituting the face of the subject, and the shape / size, color, and texture of the face part An attribute information acquisition step of acquiring at least one face part attribute selected from the inside and a predetermined face part attribute measurement result defined for the face part attribute;
Evaluation that receives input of the selected face part and the face part attribute measurement result, compares the face part attribute reference value called from the storage unit based on the former and the latter, and sends the comparison result to the matching information category extracting unit Process,
At least one tendency defined as a linear axis related to each face part attribute is called from the storage unit, and at least one matching information category associated with each tendency is specified based on the comparison result The conformity information category identification process to be
A subject information selection step of selecting at least one subject information belonging to the specified relevant information category from the subject information group in the storage unit;
And an output step of outputting each selected subject information.
The storage unit further stores information on a reference face shape including a reference face size,
When the selected face part is at least one of eyebrows, eyes, nose, and mouth, and the face part attribute is shape / size, the attribute information acquisition unit is obtained by the same measurement as the reference face size. In addition to the face size of the subject, the predetermined dimensions in each selected face part are acquired as face part attribute measurement results and these are sent to the evaluation step,
In the evaluation step, the correction value obtained by dividing the reference face size by the face size is multiplied by each measurement value excluding the face size in the acquired face part attribute measurement result of the subject. Item 19. The information providing method according to Item 18.
The attribute information acquisition step further includes an image data analysis step, wherein face image data is acquired instead of the face part attribute measurement result or together with the face part attribute measurement result, and a predetermined analysis is performed in the image data analysis step. The information providing method according to claim 7 or 8, wherein the information providing method is performed.
When the selected face part is hair and the face part attribute is texture, the image data analysis step extracts the cross-sectional shape of the hair in the selected face part and sends it to the evaluation step as a face part attribute measurement result, The information providing method according to claim 9, wherein the evaluation step is configured to determine whether the face part attribute measurement result approximates a perfect circle or a substantially triangular shape.
The storage unit further includes questionnaire information associated with each matching information category divided by two predetermined tendencies orthogonal to each other by the face part attribute reference value, and the target person selects a questionnaire If so, the questionnaire information is called from the storage unit and displayed on the output unit,
In the evaluation step, the plurality of response data for the questionnaire information obtained by the subject acquired through the attribute information acquisition step is allocated to each conforming information category, and the number of data in each category is totaled.
The information provision according to any one of claims 7 to 10, wherein the conformity information category identification step is configured to rank and identify the conformance information categories in the storage unit in descending order of the number of response data items. Method.
The matching information category specifying step is performed when the target person selects a plurality of face part attributes for the selected face part or the selected face part, or when a combination of the face part attribute and questionnaire information is selected. , Calling at least one tendency defined by each face part attribute and indicating linearity from the storage unit, and at least one matching information category associated with each tendency based on each comparison result Identifying the plurality of target person information groups, matching the face part attribute reference value and superimposing each relevant information category, narrowing down to overlapping information, and specifying as a relevant information category Item 12. The method for providing information according to any one of Items 7 to 11.
A program for executing the information providing method according to any one of claims 7 to 12 on a computer.