KR20230161907A - Apparatus for providing coronary analysis and face image according to face recognition - Google Patents

Abstract

An apparatus for providing physiognomy analysis and facial images based on facial recognition according to an embodiment of the present invention includes an input unit that receives a user's facial image; And a processor that generates feature point coordinates of each of a plurality of feature points representing characteristics of the user's facial shape based on the facial image and an eyebrow outline function representing the outline of the eyebrow, wherein the processor generates a plurality of feature point coordinates and One or more of the eyebrow outline functions are used to determine feature type information indicating each type of user's facial features, and numerical information reflecting the shape of the facial features is calculated, and the facial features type information is determined based on the numerical information. You can.

Description

Apparatus for providing coronary analysis and face image according to face recognition}

The present invention relates to a device that provides facial analysis and facial images according to facial recognition. More specifically, it extracts a plurality of feature points from the user's facial image and provides various information representing facial features using the plurality of feature points. It relates to a device that provides facial analysis and facial images based on facial recognition that can calculate eyebrow type information, frontal arch type information, eyebrow type information, overall philtrum type information, chin philtrum type information, and jaw line type information. .

Generally, the four pillars in Eastern philosophy refer to the yearly pillars, monthly pillars, daily pillars, and hourly pillars, which are the pillars for the year, month, birthday, and time of birth, respectively. .

Also, since one pillar (柱) is made up of the two characters of the kanji (干支), the four main characters are eight characters in total, which is called the four main characters.

Therefore, the interpretation of the four pillars of the four pillars refers to finding out what the relationship is between my five elements (wood, fire, earth, metal, water) and my four pillars, based on the five elements of yin and yang, and how my luck will progress from this.

Additionally, looking at body parts such as a person's face, hands, and feet and judging that person's fortune or fate is called contemplation.

Such fortune-telling or meditation can only be known through in-depth study over a long period of time or through experts such as fortune tellers. Many people who are curious about their own meditation seek out shamans to resolve these questions. They have solved their curiosity by predicting the fortunes of the year or the rest of their lives and their physiognomy, or through fortune-telling provided as a service in each daily newspaper or magazine.

As interest in physiognomy and beauty of appearance increases, interest in and demand for plastic surgery to change one's physiognomy and appearance is also increasing.

However, conventionally, the subjective and empirical analysis opinion of a service provider (a physiognomist) regarding a user's facial image is provided as physiognomy information through a popular Internet service.

Accordingly, a problem arises where physiognomy information is different for each service provider, even if it is a facial image of the same user.

Therefore, for objective physiognomy analysis of the user's facial image, a technology is needed to extract feature points and outlines of the facial image and provide numerical data.

Korean Patent Publication No. 10-2016-0062429

The purpose of the present invention is to provide physiognomy analysis based on facial recognition that can determine the user's eyebrow type information based on one or more of a plurality of eyebrow mountain relative positions, eyebrow slope, eyebrow curvature, and eyebrow thickness ratio calculated from the user's facial image. and provides a device that provides facial images.

In addition, an object of the present invention is to determine the user's front arch type information and eyebrow type information based on one or more of a plurality of eyebrow peak relative positions, eyebrow slope, eyebrow curvature, and eyebrow thickness ratio calculated from the user's facial image. The aim is to provide a device that provides physiognomy analysis and facial images based on facial recognition.

In addition, the purpose of the present invention is to provide a device that provides facial analysis and facial images based on facial recognition that can determine total population type information based on the total population ratio calculated from the user's facial image.

Additionally, the purpose of the present invention is to provide a device that provides facial images and facial analysis based on facial recognition that can determine chin philtrum type information based on the chin philtrum ratio calculated from the user's facial image.

Additionally, the purpose of the present invention is to provide a device that provides facial analysis and facial images through facial recognition that can determine jaw line type information based on the jaw line ratio calculated from the user's facial image.

The objects of the present invention are not limited to the objects mentioned above, and other objects and advantages of the present invention that are not mentioned can be understood by the following description and will be more clearly understood by the examples of the present invention. Additionally, it will be readily apparent that the objects and advantages of the present invention can be realized by the means and combinations thereof indicated in the patent claims.

An apparatus for providing physiognomy analysis and facial images based on facial recognition according to an embodiment of the present invention includes an input unit that receives a user's facial image; And a processor that generates feature point coordinates of each of a plurality of feature points representing characteristics of the user's facial shape based on the facial image and an eyebrow outline function representing the outline of the eyebrow, wherein the processor generates a plurality of feature point coordinates and One or more of the eyebrow outline functions are used to determine feature type information indicating each type of user's facial features, and numerical information reflecting the shape of the facial features is calculated, and the facial features type information is determined based on the numerical information. You can.

Preferably, the processor uses one or more of a plurality of feature point coordinates and the eyebrow outline function to provide a plurality of eyebrow peak relative positions, eyebrow tilt, and eyebrows indicating the relative position of the user's eyebrow peaks compared to the positions of one or more of the eyes and eyebrows. Eyebrow type information that calculates the curvature and eyebrow thickness ratio as the numerical information and indicates the type of the user's eyebrows based on one or more of the plurality of eyebrow mountain relative positions, the eyebrow tilt, the eyebrow curvature, and the eyebrow thickness ratio. can be determined as one of the above facial features type information.

Preferably, the processor may set a straight line connecting an upper feature point and a lower feature point representing the top and bottom of the user's face, respectively, among the plurality of feature points as the vertical axis, and set a horizontal axis perpendicular to the vertical axis.

Preferably, the processor extracts a first intersection point where an upper outline of the outlines of the eyebrows and a first vertical line passing through the eye crown feature points representing the eyelids from among the plurality of feature points, and selects the eyebrow peaks from the plurality of feature points. The slope of the first straight line connecting the indicated eyebrow peak feature point and the first intersection point can be calculated as the eyebrow slope.

Preferably, the processor calculates a first distance between the eyebrow peak feature point and the first intersection point on the horizontal axis, calculates a second distance between the upper outline and the first straight line on the vertical axis, and calculates the first distance between the upper outline and the first straight line on the vertical axis. The ratio of the first distance to the second distance can be calculated as the eyebrow curvature.

Preferably, the processor extracts a second intersection point where a lower outline intersects among the first vertical line and the outline of the eyebrow, calculates a third distance between the first intersection point and the second intersection point, and determines the eyebrow peak feature point. Extract a third intersection point where the passing second vertical line and the lower outline intersect, calculate a fourth distance between the eyebrow peak feature point and the third intersection point, and calculate a second distance ratio of the fourth distance to the third distance. It can be calculated using the eyebrow thickness ratio.

Preferably, the processor extracts a first midpoint on the horizontal axis between an eye head feature point representing the eye head and an eyebrow tail feature point representing the eyebrow tail among the plurality of feature points, and an eyebrow peak feature point representing the eyebrow peak among the plurality of feature points. and calculating a fifth distance on the horizontal axis between the vertical axes, calculating a sixth distance between the first midpoint on the horizontal axis and the vertical axis, and calculating a first distance difference between the fifth distance and the sixth distance. Among the plurality of relative positions of the eyebrow peaks, the relative position of the first eyebrow peak can be calculated.

Preferably, the processor extracts a second midpoint on the horizontal axis between the eyebrow head feature point representing the eyebrow head and the eyebrow tail feature point among the plurality of feature points, and a seventh distance between the eyebrow head feature point on the horizontal axis and the vertical axis. Calculate an eighth distance between the second midpoint on the horizontal axis and the vertical axis, calculate a distance sum between the seventh distance and the eighth distance, and calculate a second distance between the fifth distance and the distance sum. The distance difference may be calculated as the second eyebrow peak relative position among the plurality of eyebrow peak relative positions.

Preferably, the processor provides the eyebrow type information if the eyebrow slope is less than or equal to the first reference slope, the eyebrow thickness ratio is greater than or equal to the reference thickness ratio, and the first eyebrow peak relative position among the plurality of eyebrow peak relative positions is greater than or equal to the reference relative position. is determined to be a straight eyebrow type, and if the eyebrow slope is less than or equal to the first reference slope and the eyebrow thickness ratio is less than or equal to the standard thickness ratio, the eyebrow type information may be determined to be a semi-arch eyebrow type.

Preferably, the processor determines the eyebrow type information as an arched eyebrow type if the eyebrow slope is greater than or equal to the first reference slope and the eyebrow curvature is greater than or equal to the reference curvature, and if the eyebrow slope is greater than or equal to the first reference slope and the eyebrow curvature is greater than or equal to the reference curvature, the processor determines the eyebrow type information as an arched eyebrow type. If the curvature is less than the standard curvature, the eyebrow type information may be determined as an angular eyebrow type.

Preferably, the processor determines the eyebrow type information as a standard eyebrow type if the eyebrow slope exceeds the first reference slope and is less than the second reference slope that is greater than the first reference slope, and the eyebrow slope is the second reference slope. If the second eyebrow peak relative position among the plurality of eyebrow peak relative positions is greater than or equal to the reference relative position, the eyebrow type information may be determined as a raised eyebrow type.

The device for providing physiognomy analysis and facial images according to facial recognition according to the present invention is based on one or more of a plurality of eyebrow peak relative positions, eyebrow slope, eyebrow curvature, and eyebrow thickness ratio calculated from the user's facial image. By determining eyebrow type information, numerical and objective information about the user's eyebrow type can be provided.

In addition, the device for providing physiognomy analysis and facial images according to facial recognition according to the present invention is based on one or more of a plurality of eyebrow peak relative positions, eyebrow slope, eyebrow curvature, and eyebrow thickness ratio calculated from the user's facial image. By determining the user's frontal arch type and eyebrow type information, it is possible to provide numerical and objective information about the user's frontal arch type and eyebrow type.

In addition, the purpose of the present invention is to determine the total crowd type information based on the total crowd ratio calculated from the user's facial image, thereby providing numerical and objective information about the user's total crowd type.

Additionally, the purpose of the present invention is to provide numerical and objective information about the user's chin philtrum type by determining chin philtrum type information based on the chin philtrum ratio calculated from the user's facial image.

Additionally, the purpose of the present invention is to provide numerical and objective information about the user's jawline type by determining the jawline type information based on the jawline ratio calculated from the user's facial image.

Figure 1 is a diagram illustrating a device that provides physiognomy analysis and facial images based on facial recognition according to an embodiment of the present invention, receiving a user's facial image.
Figure 2 is a block diagram of a device that provides physiognomy analysis and facial images based on facial recognition according to an embodiment of the present invention.
FIG. 3 is a diagram illustrating a process in which a device that provides physiognomy analysis and facial images based on facial recognition according to an embodiment of the present invention generates a plurality of feature point coordinates and an eyebrow outline function.
Figure 4 is a diagram illustrating the process of calculating the eyebrow slope by a device that provides physiognomy analysis and facial images based on facial recognition according to an embodiment of the present invention.
FIG. 5 is a diagram illustrating a process for calculating eyebrow curvature by a device that provides physiognomy analysis and facial images based on facial recognition according to an embodiment of the present invention.
Figure 6 is a diagram illustrating a process by which a device that provides physiognomy analysis and facial images based on facial recognition according to an embodiment of the present invention calculates the eyebrow thickness ratio.
FIG. 7 is a diagram illustrating a process in which a device that provides physiognomy analysis and facial images based on facial recognition according to an embodiment of the present invention calculates a first eyebrow relative position among a plurality of eyebrow relative positions.
FIG. 8 is a diagram illustrating a process in which a device that provides facial analysis and facial images based on facial recognition according to an embodiment of the present invention calculates a second eyebrow relative position among a plurality of eyebrow relative positions.
Figure 9 is a diagram illustrating a process in which a device that provides physiognomy analysis and facial images based on facial recognition according to another embodiment of the present invention determines information on the type of facial expression.
FIG. 10 is a diagram illustrating a process in which a device that provides facial analysis and facial images based on facial recognition determines type information between the eyebrows according to another embodiment of the present invention.
FIG. 11 is a diagram illustrating a process in which a device that provides physiognomy analysis and facial images based on facial recognition determines overall philtrum type information and chin philtrum type information according to another embodiment of the present invention.
FIG. 12 is a diagram illustrating a process in which a device that provides facial analysis and facial images based on facial recognition determines jaw line type information according to another embodiment of the present invention.

Hereinafter, various embodiments of the present invention are described with reference to the accompanying drawings. However, this is not intended to limit the present invention to specific embodiments, and should be understood to include various modifications, equivalents, and/or alternatives to the embodiments of the present invention. In connection with the description of the drawings, similar reference signs may be used for similar components.

In this document, expressions such as “have,” “may have,” “includes,” or “may include” refer to the existence of the corresponding feature (e.g., a numerical value, function, operation, or component such as a part). , and does not rule out the existence of additional features.

In this document, expressions such as “A or B,” “at least one of A or/and B,” or “one or more of A or/and B” may include all possible combinations of the items listed together. . For example, “A or B,” “at least one of A and B,” or “at least one of A or B” (1) includes at least one A, (2) includes at least one B, or (3) It can refer to all cases including both at least one A and at least one B.

As used herein, expressions such as "first", "second", "first", or "second" may modify various elements in any order and/or importance, and may refer to one element. It is only used to distinguish from other components and does not limit the components. For example, a first user device and a second user device may represent different user devices regardless of order or importance. For example, a first component may be renamed a second component without departing from the scope of rights described in this document, and similarly, the second component may also be renamed to the first component.

A component (e.g., a first component) is “(operatively or communicatively) coupled with/to” another component (e.g., a second component). When “connected to” is mentioned, it should be understood that any component may be directly connected to the other component or may be connected through another component (e.g., a third component). On the other hand, when a component (e.g., a first component) is referred to as being “directly connected” or “directly connected” to another component (e.g., a second component), it is said that the component and the other component are It may be understood that no other components (e.g., third components) exist between components.

The expression "configured to" used in this document may be used depending on the context, for example, "suitable for," "having the capacity to." )", "designed to", "adapted to", "made to", or "capable of". . The term “configured (or set) to” may not necessarily mean “specifically designed to” in hardware. Instead, in some contexts, the expression “a device configured to” may mean that the device is “capable of” working with other devices or components. For example, the phrase "control configured (or set) to perform A, B, and C" means that a dedicated processor (e.g., an embedded processor) to perform the operations, or by executing one or more software programs stored in memory, , may refer to a general-purpose processor (e.g., CPU or application processor) capable of performing the corresponding operations.

In particular, in this specification, “~device” may include one or more of a central processing unit (CPU), an application processor (AP), and a communication processor (CP). .

In this specification, “˜device” refers to all types of hardware devices including at least one processor, and depending on the embodiment, it may be understood as encompassing software configurations that operate on the hardware device. For example, “~device” can be understood as including wearable devices, smartphones, tablet PCs, and user clients and applications running on each device, but is not limited thereto.

Terms used in this document are merely used to describe specific embodiments and may not be intended to limit the scope of other embodiments. Singular expressions may include plural expressions, unless the context clearly indicates otherwise. Terms used herein, including technical or scientific terms, may have the same meaning as commonly understood by a person of ordinary skill in the technical field described in this document. Among the terms used in this document, terms defined in general dictionaries may be interpreted to have the same or similar meaning as the meaning they have in the context of related technology, and unless clearly defined in this document, they may be interpreted in an ideal or excessively formal sense. It is not interpreted. In some cases, even terms defined in this document cannot be interpreted to exclude embodiments of this document.

Figure 1 is a diagram showing a device that provides facial analysis and facial images according to facial recognition according to an embodiment of the present invention, and Figure 2 is a diagram showing a device receiving a user's facial image according to an embodiment of the present invention. It is a block diagram of a device that provides facial analysis and facial images according to facial recognition, and Figure 3 shows a device that provides facial analysis and facial images according to facial recognition according to an embodiment of the present invention. This is a drawing to explain the process of creating an outline function.

Referring to Figures 1 to 3, the device 100 for providing physiognomy analysis and facial images based on facial recognition according to an embodiment of the present invention determines the shape of the user's face from the facial image generated by photographing the user's face. A plurality of feature points representing the characteristics of can be extracted, and the outline of the eyebrow can be extracted.

Afterwards, the device 100, which provides physiognomy analysis and a face image according to facial recognition, generates an eyebrow outline function of the feature point coordinates of each of the plurality of feature points and the outline of the eyebrow, and at least one of the plurality of feature point coordinates and the eyebrow outline function. Numerical information can be calculated using , and the facial feature type information can be determined based on the numerical information.

Here, the numerical information is used to determine feature type information indicating each type of user's features and may be information that reflects the shape of the features.

For example, the numerical information may be the relative positions of a plurality of eyebrow peaks, eyebrow inclination, eyebrow curvature, eyebrow thickness ratio, total philtrum ratio, chin philtrum ratio, and chin line ratio, which will be described later.

In addition, the facial features type information includes eyebrow type information indicating the user's eyebrow type, Jeontaekung type information indicating the user's eyebrow type, eyebrow type information indicating the user's eyebrow type, and overall philtrum type information indicating the user's entire philtrum type. , It may be chin philtrum type information indicating the user's chin philtrum type and jaw line type information indicating the user's jaw line type.

For this purpose, the device 100 that provides physiognomy analysis and facial images according to facial recognition according to an embodiment of the present invention includes an input unit 110, a processor 120, an output unit 130, a communication unit 140, and a storage unit. It may include unit 150.

The input unit 110 can receive the user's facial image.

At this time, the input unit 110 is connected to a photographing device and can receive a facial image output from the photographing device. Additionally, the input unit 110 may be equipped with a camera module to generate a facial image by photographing the user's face instead of receiving a facial image from a photographing device.

The processor 120 may extract a plurality of feature points representing characteristics of the user's facial shape and the outline of the eyebrows based on the facial image.

Additionally, the processor 120 may further extract feature points representing characteristics of the shape of the user's face based on the facial image.

To this end, the processor 120 may extract a plurality of feature points and the outline of the eyebrows from the facial image using one or more of a ventilation-based model, an artificial neural network model, a connection structure model, and a Markov model.

At this time, the processor 120 may extract the facial contour, the feature points of one of both eyebrows, each eye of both eyes, and the outline of one of the eyebrows described above.

Specifically, as shown in FIG. 3, the processor 120 uses a plurality of feature points, including an upper feature point (A) representing the top of the user's face, a bottom feature point (Q) representing the bottom of the user's face, and the end of the user's cheekbones. The representing clown feature point (I) can be extracted.

In addition, the processor 120 includes a plurality of feature points, including an eyebrow head feature point (C) representing the user's eyebrow hair, an eyebrow peak feature point (D) representing the user's eyebrow peak, and an eyebrow tail feature point (E) representing the user's eyebrow tail. can be extracted.

In addition, the processor 120 can extract, as a plurality of feature points, an eye-head feature point (F) representing the user's eye head, an eye-mountain feature point (R) representing the user's eye peak, and an eye-tail feature point (H) representing the user's eye corner. there is.

In addition, the processor 120 extracts, as a plurality of feature points, a nose tip feature point (M) representing the tip of the user's nose, an upper lip feature point (N) representing the top of the user's upper lip, and a lower lip feature point (P) representing the bottom of the user's lower lip. can do.

Here, the eyebrow head may refer to the innermost point among the outer edges of the eyebrows.

Here, the tail of the eyebrow may refer to the outermost point of the outline of the eyebrow.

Here, the eyebrow mountain may refer to the highest point among the outer edges of the eyebrows.

Here, the crown of the eye may refer to the innermost point among the outer edges of the eye.

Here, the corner of the eye may refer to the outermost point of the outer edge of the eye.

Here, a snow mountain may mean the highest point among the snow's outskirts.

Meanwhile, as shown in FIG. 3, the processor 120 extracts the outline of the eyebrow from the facial image and divides it into an upper outline (U) and a lower outline (L).

Here, the upper outline (U) may refer to an outline located at the top among two outlines that separate the outline of the eyebrow forming a closed curve based on the eyebrow head feature point (C) and the eyebrow tail feature point (E). That is, the upper outline (U) may mean an outline located at the top of the eyebrow outlines connecting the eyebrow head feature point (C) and the eyebrow tail feature point (E).

Here, the lower outline (L) may refer to the outline located at the lower part of the two outlines that separate the outline of the eyebrow forming a closed curve based on the eyebrow head feature point (C) and the eyebrow tail feature point (E). That is, the lower outline (L) may mean an outline located at the lower part of the eyebrow outline connecting the eyebrow head feature point (C) and the eyebrow tail feature point (E).

The processor 120 may generate feature point coordinates for each of the plurality of feature points and generate an eyebrow outline function representing the outline of the eyebrow.

At this time, the processor 120 may set a coordinate plane on the facial image and generate a plurality of feature point coordinates and an eyebrow outline function based on the set coordinate plane.

The processor 120 generates an eyebrow upper outline function (U(x)) representing the upper outline (U) and an eyebrow upper outline function (L(x)) representing the lower outline (L) among the eyebrow outlines as an eyebrow outline function. can do.

To this end, as shown in FIG. 3, the processor 120 uses a straight line connecting the upper feature point (A) and the lower feature point (Q) representing the upper and lower face of the user, respectively, among the plurality of feature points along the vertical axis (Y axis). ) and you can set the horizontal axis (X-axis) perpendicular to the vertical axis (Y-axis).

Accordingly, the processor 120 may generate the feature point coordinates of the lower feature point (Q) as (0, 0) and the feature point coordinates of the upper feature point (A) as (0, 100).

Thereafter, the processor 120 uses one or more of a plurality of feature point coordinates and the eyebrow outline function to provide a plurality of eyebrow peak relative positions, eyebrow tilt, and Eyebrow curvature and eyebrow thickness ratio can be calculated.

Figure 4 is a diagram illustrating the process of calculating the eyebrow slope by a device that provides physiognomy analysis and facial images based on facial recognition according to an embodiment of the present invention.

Referring further to FIG. 4, the processor 120 generates a first intersection point ( Z1) can be extracted.

Thereafter, the processor 120 may calculate the slope of a first straight line connecting the eyebrow peak feature point (D) representing the eyebrow peak and the first intersection point (Z1) among the plurality of feature points as the eyebrow slope.

At this time, the processor 120 can calculate the eyebrow slope using Equation 1 below.

<Equation 1>

Here, C1 is the eyebrow slope, G is the slope of the first straight line, y _d is the coordinate on the vertical axis of the eyebrow peak feature point (D), U(x _f ) is the coordinate on the vertical axis of the first intersection point (Z1), x _d is the coordinate on the horizontal axis of the eyebrow peak feature point (D), and x _f is the coordinate on the horizontal axis of the first intersection point (Z1).

FIG. 5 is a diagram illustrating a process for calculating eyebrow curvature by a device that provides physiognomy analysis and facial images based on facial recognition according to an embodiment of the present invention.

Referring further to FIG. 5, the processor 120 calculates a first distance between the eyebrow peak feature point (D) and the first intersection point (Z1) on the horizontal axis, the upper outline (U) on the vertical axis, and the above-mentioned A second distance can be calculated between the first straight lines.

Thereafter, the processor 120 may calculate a first distance ratio of the second distance to the first distance as the eyebrow curvature.

At this time, the processor 120 can calculate the eyebrow curvature using Equation 2 below.

<Equation 2>

Here, C2 is the eyebrow curvature, R1 is the first distance ratio, L1 is the first distance, L2 is the second distance, and U((x _f +x _d )/2) is the frontal feature point on the horizontal axis (F ) is the coordinate on the vertical axis of the intersection of the vertical line passing through the midpoint of the eyebrow feature point (D) and the upper outline (U), y _d is the coordinate on the vertical axis of the eyebrow feature point (D), and U (x _f ) is the first is the coordinate on the vertical axis of the intersection point (Z1), x _d is the coordinate on the horizontal axis of the eyebrow peak feature point (D), and x _f is the coordinate on the horizontal axis of the first intersection point (Z1).

Figure 6 is a diagram illustrating a process by which a device that provides physiognomy analysis and facial images based on facial recognition according to an embodiment of the present invention calculates the eyebrow thickness ratio.

Referring further to FIG. 6 , the processor 120 may extract a second intersection point Z2 where the lower outline L intersects among the above-described first vertical line and the outline of the eyebrow.

Additionally, the processor 120 may extract a third intersection point Z3 where the second vertical line passing through the eyebrow peak feature point D and the lower outline line L intersect.

Thereafter, the processor 120 calculates a third distance between the first intersection point (Z1) and the second intersection point (Z2), and calculates a fourth distance between the eyebrow peak feature point (D) and the third intersection point (Z1). can do.

Finally, the processor 120 may calculate a second distance ratio of the third distance to the third distance as the eyebrow thickness ratio.

At this time, the processor 120 can calculate the eyebrow thickness ratio using Equation 3 below.

<Equation 3>

Here, C3 is the eyebrow thickness ratio, R2 is the second distance ratio, L3 is the third distance, L4 is the fourth distance, U(x _d ) is the coordinate on the vertical axis of the eyebrow peak feature point D, and L (x _d ) is the coordinate on the vertical axis of the third intersection (Z3), U(x _f ) is the coordinate on the vertical axis of the first intersection (Z1), and L(x _f ) is the coordinate on the vertical axis of the second intersection (Z2). These are coordinates.

FIG. 7 is a diagram illustrating a process in which a device that provides physiognomy analysis and facial images based on facial recognition according to an embodiment of the present invention calculates a first eyebrow relative position among a plurality of eyebrow relative positions.

Referring further to FIG. 7, the processor 120 may extract the first midpoint on the horizontal axis between the eye head feature point (F) representing the eye head and the eyebrow tail feature point (E) representing the eyebrow tail among the plurality of feature points. there is.

Thereafter, the processor 120 calculates a fifth distance on the horizontal axis between the vertical axis and the eyebrow peak feature point (D) representing the eyebrow peak among the plurality of feature points, and a fifth distance between the first midpoint on the horizontal axis and the vertical axis. 6 Distance can be calculated.

Finally, the processor 120 may calculate a first distance difference between the fifth distance and the sixth distance as a first eyebrow peak relative position among the plurality of eyebrow peak relative positions.

At this time, the processor 120 may calculate the relative position of the first eyebrow peak using Equation 4 below.

<Equation 4>

Here, C4 is the first eyebrow peak relative position, D1 is the first distance difference, L5 is the fifth distance, L6 is the sixth distance, x _d is the coordinate on the horizontal axis of the eyebrow peak feature point (D), and x _f is the coordinate on the horizontal axis of the eye head feature point (F), and x _e is the coordinate on the horizontal axis of the eyebrow tail feature point (E).

FIG. 8 is a diagram illustrating a process in which a device that provides facial analysis and facial images based on facial recognition according to an embodiment of the present invention calculates a second eyebrow relative position among a plurality of eyebrow relative positions.

Referring further to FIG. 8, the processor 120 may extract a second midpoint on the horizontal axis between the eyebrow head feature point (C) representing the eyebrow hair and the eyebrow tail feature point (E) among the plurality of feature points.

Thereafter, the processor 120 calculates a seventh distance between the eyebrow head feature point C on the horizontal axis and the vertical axis, calculates an eighth distance between the second midpoint on the horizontal axis and the vertical axis, and calculates the seventh distance between the eyebrow head feature point C on the horizontal axis and the vertical axis. The sum of the distances can be calculated between the 7th distance and the 8th distance.

Finally, the processor 120 may calculate a second distance difference between the seventh distance and the distance sum as a second eyebrow peak relative position among the plurality of eyebrow peak relative positions.

At this time, the processor 120 may calculate the relative position of the second eyebrow peak using Equation 5 below.

<Equation 5>

Here, C5 is the second eyebrow peak relative position, D2 is the second distance difference, L5 is the fifth distance, L7 is the seventh distance, L8 is the eighth distance, and x _d is the eyebrow peak feature point (D). is the coordinate on the horizontal axis, x _c is the coordinate on the horizontal axis of the eyebrow head feature point (C), and x _e is the coordinate on the horizontal axis of the eyebrow tail feature point (E).

Thereafter, the processor 120 may determine eyebrow type information indicating the type of the user's eyebrows based on one or more of the relative positions of the plurality of eyebrow peaks, the eyebrow slope, the eyebrow curvature, and the eyebrow thickness ratio.

At this time, the processor 120 may determine the user's eyebrow type information as one or more of a straight eyebrow type, a semi-arch eyebrow type, an arched eyebrow type, an angled eyebrow type, a standard eyebrow type, and a raised eyebrow type.

Specifically, the processor 120 operates the eyebrow when the eyebrow slope is less than or equal to the first reference slope, the eyebrow thickness ratio is greater than or equal to the reference thickness ratio, and the first eyebrow peak relative position among the plurality of eyebrow peak relative positions is greater than or equal to the reference relative position. The type information can be determined as a straight eyebrow type.

Additionally, the processor 120 may determine the eyebrow type information to be a semi-arch eyebrow type if the eyebrow slope is less than or equal to the first reference slope and the eyebrow thickness ratio is less than or equal to the standard thickness ratio.

Additionally, the processor 120 may determine the eyebrow type information as an arched eyebrow type if the eyebrow slope is greater than or equal to the first reference slope and the eyebrow curvature is greater than or equal to the reference curvature.

Additionally, the processor 120 may determine the eyebrow type information as an angular eyebrow type if the eyebrow slope is greater than or equal to the first reference slope and the eyebrow curvature is less than the reference curvature.

Additionally, the processor 120 may determine the eyebrow type information to be a standard eyebrow type if the eyebrow slope exceeds the first reference slope and is less than the second reference slope that is greater than the first reference slope.

Additionally, the processor 120 may determine the eyebrow type information as a raised eyebrow type if the eyebrow slope is greater than or equal to the second reference slope and the second eyebrow peak relative position among the plurality of eyebrow peak relative positions is greater than or equal to the reference relative position.

Here, the first reference slope may be 0.1, and the second reference slope may be 0.3.

Here, the reference thickness ratio may be 2/3.

Here, the reference curvature may be 0.05.

Here, the reference relative position may be 0.

Through this, the device 100, which provides facial analysis and facial images according to facial recognition, uses a plurality of feature points and the outline of the eyebrows to numerically represent the shape of the eyebrows (relative positions of a plurality of eyebrow peaks, eyebrow slope, eyebrow curvature and eyebrow thickness ratio) can be calculated, and the type of eyebrow can be determined using the calculated information.

The processor 120 can perform the operation of each of the above-described components, and one or more cores (not shown) and a graphics processing unit (not shown) and/or a connection passage for transmitting and receiving signals with other components ( For example, it may include a bus, etc.).

The processor 120 may be configured to perform the operation of each of the components described above by executing one or more instructions stored in the storage unit 150.

The storage unit 150 may store programs (one or more instructions) for processing and controlling the processor 120. Programs stored in the storage unit 150 may be divided into a plurality of modules according to their functions.

The output unit 130 may display the user's facial image, information numerically representing the shape of the eyebrows (relative positions of a plurality of eyebrow peaks, eyebrow slope, eyebrow curvature, and eyebrow thickness ratio), and determined eyebrow type information on the screen. .

For this purpose, the output unit 130 may include a display module.

The device 100 that provides physiognomy analysis and facial images based on facial recognition may be any one of a smartphone, tablet PC, desktop, and laptop, and is preferably a smartphone.

Hereinafter, the process by which the device 100, which provides facial analysis and facial images based on facial recognition according to another embodiment of the present invention, determines the frontal arch type information and the eyebrow type information will be described.

The device 100 for providing physiognomy analysis and facial images according to facial recognition according to another embodiment of the present invention is compared to the device 100 for providing facial analysis and facial images according to facial recognition according to an embodiment of the present invention. Since only the role of the processor 120 is different, repeated descriptions will be omitted.

Figure 9 is a diagram illustrating a process in which a device that provides physiognomy analysis and facial images according to facial recognition according to another embodiment of the present invention determines the type information of the front door, and Figure 10 shows another embodiment of the present invention. This is a diagram to explain the process by which a device that provides physiognomy analysis and facial images according to facial recognition determines the type information between the eyebrows.

Referring further to FIG. 9, the processor 120 of the device 100 that provides facial analysis and facial images according to facial recognition according to another embodiment of the present invention uses one or more of a plurality of feature point coordinates and the eyebrow outline function. Using this, the Jeontaekung ratio can be calculated, and based on the Jeontaekung ratio, Jeontaekung type information indicating the type of the user's Jeontaekung can be determined.

Specifically, the processor 120 may extract, from among the plurality of feature points, a fourth intersection point Z4 where the third vertical line passing through the snowy mountain feature point R representing a snowy mountain and the lower outline line L intersect.

Thereafter, the processor 120 calculates the ninth distance on the horizon between the eye tail feature point (H) and the eye corner feature point (F) representing the outer corners of the eyes among the plurality of feature points, and between the eye ridge feature point (R) and the fourth intersection point (Z4). The 10th distance can be calculated.

Finally, the processor 120 may calculate the third distance ratio of the tenth distance to the ninth distance as the Jeontaekung ratio.

At this time, the processor 120 can calculate the battle arch ratio using Equation 6 below.

<Equation 6>

Here, C6 is the cross-section ratio, R3 is the third distance ratio, L9 is the ninth distance, L10 is the tenth distance, L(x _r ) is the coordinate on the vertical axis of the fourth intersection (Z4), and y _r is the coordinate on the vertical axis of the eye peak feature point (R), x _h is the coordinate on the horizontal axis of the eye tail feature point (H), and x _r is the coordinate on the horizontal axis of the eye cap feature point (R).

Thereafter, the processor 120 may determine the Jeontaekung type information as one of the small Taekung type and the large Taekung type based on the Jeontaekung ratio.

Here, the Small Taekung Palace type may be a Jeontaekung Palace type indicating that the Jeontaekung Palace is narrow, and the Daejeon Taekung Type may be a Jeontaekung Type indicating a wide Jeontaekung Palace.

Specifically, the processor 120 may determine the Jeontaekung type information as a small Jeontaekung type if the Jeontaekung ratio is less than the first standard Jeontaekung ratio.

Additionally, the processor 120 may determine the battle arch type information as the battle arch arch type if the battle arch ratio exceeds the second standard battle arch ratio.

Here, the first standard all-out arch ratio may be 0.1, and the second standard all-out arch ratio may be 0.5.

Referring further to FIG. 10, the processor 120 calculates a plurality of relative lengths between the eyebrows using one or more of a plurality of feature point coordinates and the eyebrow outline function, and determines the type of the user's eyebrows based on the plurality of relative lengths between the eyebrows. The type information between the eyebrows can be determined.

Specifically, the processor 120 may calculate a first relative length between the eyebrows and a second relative length between the eyebrows as a plurality of relative lengths between the eyebrows.

First, the process by which the processor 120 calculates the first relative length between the eyebrows will be described.

The processor 120 calculates an 11th distance on the horizontal axis between the eyebrow hair feature point (C) representing the eyebrow hair among the plurality of feature points and the vertical axis, and an eyebrow tail feature point (E) representing the eyebrow tail among the plurality of feature points. and the twelfth distance on the horizontal axis between the eye head feature points (F) representing the eye head can be calculated.

Thereafter, the processor 120 may calculate the correction distance by reducing the twelfth distance by a preset magnification factor.

Finally, the processor 120 may calculate the third distance difference between the eleventh distance and the correction distance as the first relative length between the eyebrows among the plurality of relative lengths between the eyebrows.

At this time, the processor 120 may calculate the first relative length between the eyebrows using Equation 7 below.

<Equation 7>

Here, C7 is the first relative length between the eyebrows, D3 is the third distance difference, L11 is the eleventh distance, L12' is the correction distance, L12 is the twelfth distance, and j is a preset magnification (e.g., 3 ), x _c is the coordinate on the horizontal axis of the eyebrow head feature point (C), x _e is the coordinate on the horizontal axis of the eyebrow tail feature point (E), and x _f is the coordinate on the horizontal axis of the eye head feature point (F).

Next, the process by which the processor 120 calculates the second relative length between the eyebrows will be described.

The processor 120 may calculate the above-described 11th distance and calculate the 13th distance on the vertical axis between the first intersection Z1 and the horizontal axis.

Finally, the processor 120 may calculate the fourth distance difference between the 11th distance and the 13th distance as the second relative length between the eyebrows among the plurality of relative lengths between the eyebrows.

At this time, the processor 120 may calculate the second relative length between the eyebrows using Equation 8 below.

<Equation 8>

Here, C8 is the second relative length between the eyebrows, D4 is the fourth distance difference, L11 is the eleventh distance, L13 is the thirteenth distance, x _c is the coordinate on the horizontal axis of the eyebrow head feature point (C), and U(x _f ) is the coordinate on the vertical axis of the first intersection (Z1).

The processor 120 determines the type information between the eyebrows as the small-brow type based on the first relative length between the eyebrows among the plurality of relative lengths between the eyebrows, and sets the type information between the eyebrows to the large-brow type based on the second relative length between the eyebrows among the plurality of relative lengths between the eyebrows. It can be determined by type.

Here, the small glabella type may be a glabella type indicating a narrow glabella, and the large glabella type may be a glabellar type indicating a wide glabella.

Specifically, the processor 120 may determine the type information between the eyebrows as the type between the eyebrows when the first relative length between the eyebrows exceeds the reference relative length.

Additionally, the processor 120 may determine the type information between the eyebrows as the type between the eyebrows when the second relative length between the eyebrows exceeds the reference relative length.

Here, the reference relative length may be 0.

Hereinafter, a process in which the device 100, which provides physiognomy analysis and facial images based on facial recognition according to another embodiment of the present invention, determines overall philtrum type information and chin philtrum type information will be described.

A device 100 for providing physiognomy analysis and facial images according to facial recognition according to another embodiment of the present invention is a device 100 for providing facial analysis and facial images according to facial recognition according to an embodiment of the present invention. Since only the role of the comparison processor 120 is different, repeated descriptions will be omitted.

FIG. 11 is a diagram illustrating a process in which a device that provides physiognomy analysis and facial images based on facial recognition determines overall philtrum type information and chin philtrum type information according to another embodiment of the present invention.

Referring further to FIG. 11, the processor 120 of the device 100 that provides physiognomy analysis and facial images according to facial recognition according to another embodiment of the present invention uses one or more of a plurality of feature point coordinates and the eyebrow outline function. The total audience ratio can be calculated using and based on the total audience ratio, total audience type information indicating the user's total audience type can be determined.

Specifically, the processor 120 calculates the 14th distance on the vertical line between the upper feature point (A) and the lower feature point (Q), and calculates the 15th distance on the vertical line between the tip of the nose feature point (M) and the upper lip feature point (N) can do.

Finally, the processor 120 may calculate the fourth distance ratio of the 15th distance to the 14th distance as the total crowd ratio.

At this time, the processor 120 can calculate the total population ratio using Equation 9 below.

<Equation 9>

Here, C9 is the total philtrum ratio, R4 is the 4th distance ratio, L14 is the 14th distance, L15 is the 15th distance, y _a is the coordinate on the vertical axis of the top feature point (A), and y _q is the bottom is the coordinate on the vertical axis of the feature point (Q), y _m is the coordinate on the vertical axis of the nose tip feature point (M), and y _n is the coordinate on the vertical axis of the upper lip feature point (N).

Thereafter, the processor 120 may determine the total audience type information as the total audience type based on the total audience ratio.

Here, the full philtrum type may be a full philtrum type that indicates the length of the philtrum compared to the vertical length of the face.

Specifically, the processor 120 may determine the total audience type information as the total audience type if the total audience ratio is greater than or equal to the standard total audience ratio.

Here, the standard total population ratio may be 0.1.

Meanwhile, the processor 120 of the device 100 that provides physiognomy analysis and facial images according to facial recognition according to another embodiment of the present invention uses one or more of a plurality of feature point coordinates and the eyebrow outline function to determine chin impression. The ratio can be calculated, and based on the chin philtrum ratio, chin philtrum type information indicating the user's chin philtrum type can be determined.

Specifically, the processor 120 may calculate the 16th distance on a vertical line between the lower lip feature point (P) and the bottom feature point (Q).

Finally, the processor 120 may calculate the fifth distance ratio of the 15th distance to the 16th distance as the tuck-in ratio.

At this time, the processor 120 can calculate the chin pull ratio using Equation 10 below.

<Equation 10>

Here, C10 is the chin paw ratio, R5 is the 5th distance ratio, L15 is the 15th distance, L16 is the 16th distance, y _a is the coordinate on the vertical axis of the upper feature point (A), and y _p is the lower lip. is the coordinate on the vertical axis of the feature point (P), y _m is the coordinate on the vertical axis of the nose tip feature point (M), and y _n is the coordinate on the vertical axis of the upper lip feature point (N).

Thereafter, the processor 120 may determine the chin philtrum type information as the long chin philtrum type based on the chin philtrum ratio.

Here, the long chin philtrum type may be a chin philtrum type in which the philtrum is longer compared to the vertical length from the bottom of the lower lip to the bottom of the face.

Specifically, the processor 120 may determine the chin philtrum type information as a long chin philtrum type if the chin philtrum ratio is greater than or equal to the standard chin philtrum ratio.

Here, the standard jaw traction ratio may be 1.

Hereinafter, a process in which the device 100, which provides facial analysis and facial images based on facial recognition according to another embodiment of the present invention, determines jaw line type information will be described.

A device 100 for providing physiognomy analysis and facial images according to facial recognition according to another embodiment of the present invention is a device 100 for providing facial analysis and facial images according to facial recognition according to an embodiment of the present invention. Since only the role of the comparison processor 120 is different, repeated descriptions will be omitted.

FIG. 12 is a diagram illustrating a process in which a device that provides facial analysis and facial images based on facial recognition determines jaw line type information according to another embodiment of the present invention.

Referring further to FIG. 12, the processor 120 of the device 100 that provides physiognomy analysis and facial images according to facial recognition according to another embodiment of the present invention uses one or more of a plurality of feature point coordinates and the eyebrow outline function. The jawline ratio can be calculated using and jawline type information indicating the user's jawline type can be determined based on the jawline ratio.

Specifically, the processor 120 may detect a fifth intersection point (O) where the jaw line and the vertical line passing through the midpoints of the cheek feature point (I) and the bottom feature point (Q) on the horizontal axis intersect.

Thereafter, the processor 120 may detect a vertical line passing through the fifth intersection (O) as an orthogonal line among the vertical lines perpendicular to the straight line connecting the upper feature point (I) and the lower feature point (Q).

Next, the processor 120 may detect a sixth intersection point (V) where a straight line and a perpendicular line connecting the upper feature point (I) and the lower feature point (Q) intersect.

The processor 120 may calculate a 17th distance between the upper feature point (I) and the lower feature point (Q), and may calculate an 18th distance between the fifth intersection point (O) and the sixth intersection point (V).

Finally, the processor 120 may calculate the sixth distance ratio of the 18th distance to the 17th distance as the chin line ratio.

At this time, the processor 120 can calculate the jaw line ratio using Equation 11 below.

<Equation 11>

Here, C11 is the jaw line ratio, R6 is the 6th distance ratio, L17 is the 17th distance, L18 is the 18th distance, y _o is the coordinate on the vertical axis of the 6th intersection (O), and y _v is the 7th distance. is the coordinate on the vertical axis of the intersection point (V), y _q is the coordinate on the vertical axis of the lower feature point (Q), y _i is the coordinate on the vertical axis of the cheek feature point (I), and x _o is the coordinate on the horizontal axis of the sixth intersection point (O) coordinates, x _v is the coordinate on the horizontal axis of the seventh intersection (V), x _q is the coordinate on the horizontal axis of the lower feature point (Q), and x _i is the coordinate on the horizontal axis of the cheek feature point (I).

Thereafter, the processor 120 may determine the jawline type information as a sharp jawline type based on the jawline ratio.

Here, the sharp jawline type may be a jawline type that indicates a sharp jawline.

Specifically, the processor 120 may determine the jawline type information as a long jawline type if the jawline ratio is less than or equal to the reference jawline ratio.

Here, the reference jaw line ratio may be 0.1.

Meanwhile, the processor 120 of the device 100 that provides physiognomy analysis and facial images according to facial recognition according to another embodiment may correct the user's facial image based on deformation type information.

To this end, the device 100, which provides physiognomy analysis and facial images according to facial recognition according to another embodiment, selects the type to be changed among eyebrow type information, frontal arch type information, and eyebrow type information according to the current facial image. Information on the type of transformation indicated can be obtained.

For example, if the eyebrow type information determined according to the current facial image is a straight eyebrow type, the modified type information may be a standard eyebrow type that is different from the eyebrow type information.

At this time, the processor 120 may correct the facial image by changing one or more of the eye position, eye shape, eyebrow position, and eyebrow shape so that the facial image is of the type indicated by the deformation type information.

Continuing to explain the above-mentioned example, the eyebrow slope of the facial image whose eyebrow type information is determined as a straight eyebrow type is less than or equal to the first reference slope, but when a standard eyebrow type is obtained as the deformed type information, the processor 120 determines the eyebrow slope The facial image may be corrected by changing one or more of the eye position, eye shape, eyebrow position, and eyebrow shape so that it exceeds the first reference slope and is less than the second reference slope.

Thereafter, the processor 120 may control the output unit 130 so that a facial image corrected to correspond to the deformation type information is output on the screen.

Through this, before performing plastic surgery or plastic surgery, the user can preview the facial image after performing plastic surgery or plastic surgery according to the type of type to be changed among the eyebrow type, front arch type, and glabella type.

So far, the present invention has been examined with a focus on preferred embodiments. A person skilled in the art to which the present invention pertains will understand that the present invention can be implemented in a modified form without departing from the essential characteristics of the present invention. Therefore, the disclosed embodiments should be considered from an illustrative rather than a restrictive perspective. The scope of the present invention is indicated in the claims rather than the foregoing description, and all differences within the equivalent scope should be construed as being included in the present invention.

As described above, although the present invention has been described with limited examples and drawings, the present invention is not limited thereto, and the technical idea of the present invention and the following will be understood by those skilled in the art to which the present invention pertains. Of course, various modifications and variations are possible within the scope of equivalence of the patent claims to be described.

100: A device that provides physiognomy analysis and facial images based on facial recognition
110: input unit
120: processor
130: output unit
140: Department of Communications
150: storage unit

Claims (1)

An input unit that receives the user's facial image; and
A processor that generates feature point coordinates of each of a plurality of feature points representing characteristics of the user's face shape based on the facial image and an eyebrow outline function representing the outline of the eyebrows;
The processor is
One or more of a plurality of feature point coordinates and the eyebrow outline function is used to determine feature type information indicating each type of feature of the user, and numerical information reflecting the shape of the feature is calculated, and based on the numerical information, the Determine facial features type information,
The processor is
A plurality of eyebrow peak relative positions, eyebrow tilt, eyebrow curvature, and eyebrow thickness ratio indicating the relative position of the user's eyebrow peaks compared to the position of one or more of the eyes and eyebrows using one or more of the plurality of feature point coordinates and the eyebrow outline function. is calculated as the numerical information, and eyebrow type information indicating the type of the user's eyebrows is provided based on one or more of the relative positions of the plurality of eyebrow peaks, the eyebrow slope, the eyebrow curvature, and the eyebrow thickness ratio, and the facial features type information. Decide on one of the
The processor is
Among the plurality of feature points, a straight line connecting the top feature point and the bottom feature point representing the top and bottom of the user's face, respectively, is set as the vertical axis, and a horizontal axis perpendicular to the vertical axis is set,
The processor is
Calculating a ratio of the arch of the plurality of features using one or more of the coordinates of the plurality of feature points and the eyebrow outline function, and determining type of arch of the user based on the ratio of the arch of the arch, and determining type information of the arch of the user,
The processor is
Among the plurality of feature points, a third vertical line passing through a snowy mountain feature point representing a snowy mountain and a fourth intersection point where a lower outline of the outlines of the eyebrows intersect are extracted, and among the plurality of feature points, an eyetail feature point representing an eye corner and an eye head representing an eye head are extracted. Calculate the 9th distance on the horizontal axis between feature points, calculate the 10th distance between the Nunsan feature point and the fourth intersection, and calculate the third distance ratio of the 10th distance to the 9th distance as the Jeontaekung ratio, , Calculate the above-mentioned arch ratio using Equation 6 below,
The processor is
If the Jeontaekung ratio is less than the first standard Jeontaekung ratio, the Jeontaekung type information is determined as a small Jeontaekung type indicating that the Jeontaekung is narrow, and if the Jeontaekung ratio exceeds the second standard Jeontaekung ratio, The Jeontaekung type information is determined as the Daejeontaekung type, which indicates the width of the Jeontaekung palace.
The processor is
A plurality of relative lengths between the eyebrows are calculated using one or more of the plurality of feature point coordinates and the eyebrow outline function, and as the plurality of relative lengths between the eyebrows, a first relative length between the eyebrows and a second relative length between the eyebrows are calculated, and the plurality of relative lengths between the eyebrows are calculated. Determine the type information between the eyebrows indicating the type of the user's eyebrows based on the relative length between the eyebrows,
The processor is
An 11th distance on the horizontal axis is calculated between an eyebrow hair feature point representing the eyebrow head among the plurality of feature points and the vertical axis, and an 11th distance on the horizontal axis is calculated between the eyebrow tail feature point representing the eyebrow tail among the plurality of feature points and the eye head feature point. 12 distance is calculated, the 12th distance is reduced by a preset magnification to calculate the correction distance, and the 3rd distance difference between the 11th distance and the correction distance is calculated as the first relative length between the eyebrows, using the following math Calculate the first relative length between the eyebrows using Equation 7,
The processor is
Extracting a first intersection point where the upper outline of the first vertical line passing through the eye head feature point and the outline of the eyebrows intersects among the plurality of feature points, and calculating a 13th distance on the vertical axis between the first intersection point and the horizontal axis, The fourth distance difference between the 11th distance and the 13th distance is calculated as the second relative length between the eyebrows, and the second relative length between the eyebrows is calculated using Equation 8 below,
The processor is
If the first relative length between the eyebrows exceeds the standard relative length, the glabella type information is determined as a small glabella type indicating that the glabella is narrow, and if the second relative length between the eyebrows exceeds the reference relative length, the glabella type information is determined as the glabella type information. Decide on the type between the eyes that represents this wideness.
The processor is
Calculating a total crowd ratio using one or more of the plurality of feature point coordinates and the eyebrow outline function, and determining total crowd type information indicating the user's overall crowd type based on the total crowd ratio,
The processor is
Calculating a 14th distance on the vertical axis between the upper feature point and the lower feature point, and calculating a 15th distance on the vertical axis between a nose tip feature point representing the tip of the user's nose and an upper lip feature point representing the top of the user's upper lip among the plurality of feature points. And, the fourth distance ratio of the 15th distance to the 14th distance is calculated as the total crowd ratio, and the total crowd ratio is calculated using Equation 9 below,
The processor is
If the total people ratio is more than the standard total people ratio, the total people type information is determined as a long total people type indicating the length of the philtrum compared to the vertical length of the user's face,
The processor is
Calculating a chin philtrum ratio using one or more of the plurality of feature point coordinates and the eyebrow outline function, and determining chin philtrum type information indicating the user's chin philtrum type based on the chin philtrum ratio,
The processor is
Among the plurality of feature points, a 16th distance on the vertical axis is calculated between a lower lip feature point representing the bottom of the user's lower lip and the bottom feature point, and a fifth distance ratio of the 15th distance to the 16th distance is calculated as the chin paw ratio. Calculated as,
The processor is
If the chin philtrum ratio is more than the standard chin philtrum ratio, the chin philtrum type information is determined as a long chin philtrum type indicating the length of the philtrum compared to the vertical length from the bottom of the user's lower lip to the bottom of the face,
The processor is
Obtaining transformation type information indicating a type to be changed among the determined eyebrow type information, the Jeontaekung type information, and the eyebrow type information,
The processor is
The facial image of the user is corrected based on the deformation type information, and one or more of the eye position, eye shape, eyebrow position, and eyebrow shape is changed so that the facial image is the type indicated by the deformation type information. Correcting the facial image,
The processor is
Controlling the output unit so that the corrected facial image is displayed on the screen so that the user can check the facial image after plastic surgery and cosmetic procedures in advance,
The processor is
If the eyebrow inclination exceeds the first reference inclination and is less than the second reference inclination greater than the first reference inclination, the eyebrow type information is determined as a standard eyebrow type, and if the eyebrow inclination is more than the second reference inclination and the plurality of eyebrows If the second eyebrow mountain relative position among the mountain relative positions is greater than or equal to the reference relative position, the eyebrow type information is determined as a raised eyebrow type,
The processor is
Calculate a jawline ratio using one or more of the plurality of feature point coordinates and the eyebrow outline function, and determine jawline type information indicating the user's jawline type based on the jawline ratio,
The processor is
Detecting a fifth intersection point where a vertical line passing through the midpoint on the horizontal axis between the cheek feature point indicating the tip of the user's cheekbone and the lower feature point intersects the jaw line, and detecting the fifth intersection point among the vertical lines perpendicular to a straight line connecting the cheekbone feature point and the lower feature point 5 Detecting a vertical line passing through an intersection as an orthogonal line, detecting a sixth intersection where a straight line connecting the wide feature point and the bottom feature point, and the orthogonal line intersect, calculating a 17th distance between the wide feature point and the bottom feature point, , calculating an 18th distance between the 5th intersection and the 6th intersection, calculating a 6th distance ratio of the 18th distance to the 17th distance as the jaw line ratio,
The processor is
If the jawline ratio is less than or equal to the reference jawline ratio, the jawline type information is determined as a long jawline type.
A device that provides physiognomy analysis and facial images based on facial recognition.

<Equation 6>

Here, C6 is the cross-section ratio, R3 is the third distance ratio, L9 is the ninth distance, L10 is the tenth distance, L(x _r ) is the coordinate on the vertical axis of the fourth intersection (Z4), and y _r is the coordinate on the vertical axis of the eye peak feature point (R), x _h is the coordinate on the horizontal axis of the eye tail feature point (H), and x _r is the coordinate on the horizontal axis of the eye cap feature point (R).
<Equation 7>

Here, C7 is the first relative length between the eyebrows, D3 is the third distance difference, L11 is the eleventh distance, L12' is the correction distance, L12 is the twelfth distance, and j is a preset magnification (e.g., 3 ), x _c is the coordinate on the horizontal axis of the eyebrow head feature point (C), x _e is the coordinate on the horizontal axis of the eyebrow tail feature point (E), and x _f is the coordinate on the horizontal axis of the eye head feature point (F).
<Equation 8>

Here, C8 is the second relative length between the eyebrows, D4 is the fourth distance difference, L11 is the eleventh distance, L13 is the thirteenth distance, x _c is the coordinate on the horizontal axis of the eyebrow head feature point (C), and U(x _f ) is the coordinate on the vertical axis of the first intersection (Z1).
<Equation 9>

Here, C9 is the total philtrum ratio, R4 is the 4th distance ratio, L14 is the 14th distance, L15 is the 15th distance, y _a is the coordinate on the vertical axis of the top feature point (A), and y _q is the bottom is the coordinate on the vertical axis of the feature point (Q), y _m is the coordinate on the vertical axis of the nose tip feature point (M), and y _n is the coordinate on the vertical axis of the upper lip feature point (N).