KR101948040B1 - Makeup recommendation method based on face type, and recording medium storing program for executing the same, and recording medium storing program for executing the same - Google Patents

Abstract

The present invention relates to a makeup recommendation method based on a face type, a recording medium storing a program for executing the same, and a computer program stored in a medium for executing the same. More specifically, provided are a method of recommending a makeup which classifies a face type into a long type and a general type and a square type and a heart type to recommend a suitable makeup method according to each face type, a recording medium storing a program for executing the same, and a computer program stored in a medium for executing the same.

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a makeup recommendation method based on facial type classification, a recording medium storing a program for implementing the method, and a computer program stored in a medium for implementing the method. STORING PROGRAM FOR EXECUTING THE SAME}

The present invention relates to a makeup recommendation method according to face type classification, a recording medium storing a program for implementing the method, and a computer program stored in a medium for implementing the method. More particularly, the present invention relates to a makeup recommendation method, A makeup recommendation method according to a face type classification that recommends a makeup method suitable for each face type, a recording medium storing a program for implementing the makeup method, and a computer program stored in a medium for implementing the method.

In general, makeup is used to make up images of each person's desired style while making use of makeup cosmetics such as foundation, powder, eyebrow, eye shadow, lipstick, ball touch, eyeliner and mascara It has been widely used.

Recently, many kinds of base and color cosmetics have been developed and released at a rapid pace. With the development of communication technology and the popularization of smart phones, the use of the internet is becoming more and more active. It is accumulating.

Many people refer to makeup methods that others put on the Internet when they make up.

However, there is a problem that the face type of the person who appears in the makeup video is different from the face type of the person, and the desired result does not come out.

As a result, makeup consumers spend a lot of time choosing which makeup method to use to make up their makeup. In particular, the "Hamlet Syndrome" has been increasing in recent years, a mass of people hesitant to make a decision in the information age. This also applies to the selection of the make-up method, and therefore, there is a need to provide customized information to the consumers for the make-up method.

The problem is that objective information about the make-up method existing on the Internet is mixed in different sites, and subjective information (make-up period etc.) of consumers who depend on consumers before purchasing is not properly filtered due to commercial information, This is a problem that arises because it is provided to users.

However, in the makeup method, the makeup method suitable for the face type of the user may be changed, which makes it difficult to accurately select a makeup method desired by the user.

That is, there is a problem that it is difficult to select a makeup method suitable for oneself among many kinds of makeup methods.

Korean Patent Laid-Open Publication No. 10-2012-0051342 discloses a system and method for recommending emotional makeup based on user's color.

Korean Published Patent [10-2012-0051342] (Publication date: May 22, 2012)

SUMMARY OF THE INVENTION Accordingly, the present invention has been made keeping in mind the above problems occurring in the prior art, and it is an object of the present invention to provide a makeup method suitable for each face type by dividing a face type into a long type and a general type, A makeup recommendation method according to type classification, a recording medium storing a program for implementing the makeup method, and a computer program stored in a medium for implementing the method.

The objects of the embodiments of the present invention are not limited to the above-mentioned objects, and other objects not mentioned can be clearly understood by those skilled in the art from the following description .

)와 얼굴의 가로길이(

)를 고려하여 긴형과 일반형으로 구분하고, 얼굴 윤곽선, 눈 윤곽선 및 입술 윤곽선을 기반으로 턱선의 형태를 고려하여 사각형과 하트형으로 구분하는 얼굴형구분 단계(S30); 및 상기 연산처리수단이 상기 얼굴형구분 단계(S30)에서 구분된 얼굴형을 근거로 적합한 메이크업 스타일을 제공하는 스타일제공 단계(S40);를 포함하는 것을 특징으로 한다.According to an aspect of the present invention, there is provided a method for recommending a makeup according to a face type classification, the method comprising the steps of: An image input step (S10) in which the operation processing means receives image information; (S20) for extracting eyes, nose, mouth, ear, and face contour using the face recognition technique based on the image information input in the image input step (S10); Wherein the calculation processing means calculates the vertical length of the face based on the face contour extracted in the face contour extracting step (S20)

) And the horizontal length of the face (

(S30), which is divided into a rectangular shape and a normal shape in consideration of the shape of the jaw line based on the facial contour line, the eye contour line, and the lip contour line in consideration of the facial contour line, the eye contour line, and the lip contour line. And a style providing step (S40) in which the arithmetic processing means provides an appropriate makeup style based on the face type classified in the face type sorting step (S30).

In addition, the face contour extracting step S20 may include a face region extracting step S21 for extracting a face region from the entire image using an AdaBoosting learning method; A binarization step (S22) of performing a binarization process using an average and a variance value of brightness values of images in the face region extracted in the face region extraction step (S21); An outline extraction step S23 for extracting outlines using a CannyEdge operator based on the result of the binarization step S22; A contour correcting step (S24) for performing a morphology operation after using a contour smoothing filter based on the result of the contour extracting step (S23); And an outline determination step (S25) of verifying the eye, nose, mouth, ear, and face contours using the structural features of the face based on the result of the outline contouring step (S24) and determining contours of the respective parts .

)는 머리 가장 위쪽 부분부터 턱의 가장 아래쪽 부분까지의 수직 길이인 것을 특징으로 하거나, 이마의 가장 위쪽 부분부터 턱의 가장 아래쪽 부분까지의 수직 길이인 것을 특징으로 한다.In addition, the vertical length of the face of the face type classification step S30 (

Is a vertical length from the uppermost portion of the head to the lowermost portion of the jaw or is a vertical length from the uppermost portion of the forehead to the lowermost portion of the jaw.

)는 왼쪽 눈꼬리 끝과 오른쪽 눈꼬리 끝을 통과하는 직선이 얼굴 윤곽선과 교차하는 지점 간의 길이인 것을 특징으로 하거나, 왼쪽 귀 끝부터 오른쪽 귀 끝까지의 길이인 것을 특징으로 한다.In addition, the horizontal length of the face of the face type classification step S30 (

) Is a length between a point where the straight line passing through the tip of the left clavicle and the tip of the right clavicle intersects with the contour of the face, or is the length from the left ear tip to the right ear tip.

In addition, the method of dividing the facial type classification step S30 into the long type and the general type,

에 해당되면 긴형으로 구분하고,

If the number is long,

에 해당되면 일반형으로 구분하는 것을 특징으로 하되,

, The classification is classified into a general type,

는 이용자의 국적, 인종, 성별 중 선택되는 하나 또는 복수의 조건에 따라 미리 결정된 것을 특징으로 한다.

Is determined in advance according to one or more conditions selected from the nationality, race, and sex of the user.

) 및 왼쪽 입꼬리 끝과 오른쪽 입꼬리 끝을 통과하는 직선이, 왼쪽 눈꼬리 끝으로부터 수직으로 내린 선과 교차하는 지점과 오른쪽 눈꼬리 끝으로부터 수직으로 내린 선과 교차하는 지점 간의 길이(

)를 기준으로,In addition, in the method of dividing the face type separation step S30 into a quadrangle and a heart type, a straight line passing through the tip of the left and right eyelids is the length between the points at which the face contour intersects

) And the distance between the point at which the line passing through the tip of the left anterior tip of the tail and the tip of the right tip of the eye intersects the line perpendicularly drawn from the tip of the left eye tail and the line intersecting perpendicularly from the tip of the right eye tail

),

에 해당되면 하트형으로 구분하고,

If it is classified as a heart type,

에 해당되면 사각형으로 구분하는 것을 특징으로 하되,

, And is divided into a quadrangle if it corresponds to < RTI ID = 0.0 >

는 이용자의 국적, 인종, 성별 중 선택되는 하나 또는 복수의 조건에 따라 미리 결정된 것을 특징으로 한다.

Is determined in advance according to one or more conditions selected from the nationality, race, and sex of the user.

If the face type is determined to be a long type in the face type sorting step S30, the style providing step S40 may be performed such that a foundation darker than a predetermined brightness is saddled horizontally at the end of the long flax and jaw, , It is recommended that the eyebrows be moved to the center rather than the base line or drawn with a straight line of a straight line, the eye shadow should be given to the eye tail, and the blusher should be dyed under the eye, , A foundation darker than a predetermined brightness is applied to both ends of the face, the sides of the forehead to the chin are shaded along the face line to make the face look longer, and the taut zone is highlighted with bright colors, Make the blusher look shrunk, blusher under the cheekbones and apply it so that it will look slimy .

In addition, in the style providing step S40, when the face type is determined to be a quadrangle in the face type sorting step S30, the point is to eliminate the angle so that the entire face can be seen smoothly. The eyebrow mountain is drawn outwardly slightly higher than the basic position It is recommended that the blusher should be long in the direction from the cheek to the tip of the jaw so that the jaw is rounded. If the face type is discriminated as a heart type in the face type sorting step (S30) To narrow the forehead and widen the cheek to jaw, make the cheeks look plump with a bright foundation, draw long eyebrows or gently curves like a gull, blushers are long horizontally on the underside of the eye, It is recommended to give a shaded line underneath to emphasize contemporary facial contours And a gong.

According to an embodiment of the present invention, there is provided a computer readable recording medium storing a program for implementing a makeup recommendation method according to the face type classification.

According to an embodiment of the present invention, a program stored in a computer-readable recording medium is provided to implement a makeup recommendation method according to the face type classification.

According to one embodiment of the present invention, a makeup recommendation method according to the facial type classification, a recording medium on which a program for implementing the method is stored, and a computer program stored in a medium for implementing the method, And provides a makeup style suitable for the divided face type, thereby providing a makeup style suited to the user without any selection or judgment of the user, and shortening the time for the user to determine the makeup style.

In addition, by providing a makeup simulation result reflecting the request of the user, it is possible to check beforehand which style suits the user.

1 is a flowchart of a makeup recommendation method according to a face type classification according to an embodiment of the present invention.
2 is a flow chart of a specific embodiment of the face contour extraction step of FIG.
FIG. 3 is an exemplary diagram for explaining a criterion used to classify a face type into a long type and a general type; FIG.
Fig. 4 is an illustration showing a face type long type and a general type. Fig.
FIG. 5 is an exemplary diagram for explaining a criterion used to divide a face type into a square shape and a heart shape; FIG.
Fig. 6 is an exemplary view showing a face type square and a heart type. Fig.

While the invention is susceptible to various modifications and alternative forms, specific embodiments thereof are shown by way of example in the drawings and will herein be described in detail. It is to be understood, however, that the invention is not to be limited to the specific embodiments, but includes all modifications, equivalents, and alternatives falling within the spirit and scope of the invention.

It is to be understood that when an element is referred to as being "connected" or "connected" to another element, it may be directly connected or connected to the other element, .

On the other hand, when an element is referred to as being "directly connected" or "directly connected" to another element, it should be understood that there are no other elements in between.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The singular expressions include plural expressions unless the context clearly dictates otherwise. In the present application, the term "comprises" or "having ", etc. is intended to specify the presence of stated features, integers, steps, operations, elements, parts, or combinations thereof, And does not preclude the presence or addition of one or more other features, integers, integers, steps, operations, elements, components, or combinations thereof.

Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. Terms such as those defined in commonly used dictionaries are to be interpreted as having a meaning consistent with the meaning in the context of the relevant art and are to be construed as ideal or overly formal in meaning unless explicitly defined in the present application Do not.

Hereinafter, the present invention will be described in more detail with reference to the accompanying drawings. Prior to this, terms and words used in the present specification and claims should not be construed as limited to ordinary or dictionary terms, and the inventor should appropriately interpret the concept of the term appropriately in order to describe its own invention in the best way. The present invention should be construed in accordance with the meaning and concept consistent with the technical idea of the present invention. Further, it is to be understood that, unless otherwise defined, technical terms and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. Descriptions of known functions and configurations that may be unnecessarily blurred are omitted. The following drawings are provided by way of example so that those skilled in the art can fully understand the spirit of the present invention. Therefore, the present invention is not limited to the following drawings, but may be embodied in other forms. In addition, like reference numerals designate like elements throughout the specification. It is to be noted that the same elements among the drawings are denoted by the same reference numerals whenever possible.

FIG. 1 is a flowchart of a makeup recommendation method according to an embodiment of the present invention, FIG. 2 is a flowchart of a face contour extracting step of FIG. 1, FIG. 4 is a diagram illustrating an example of a face type of a long type and a general type, and FIG. 5 is a diagram illustrating a standard used to classify a face type into a square type and a heart type. Fig. 6 is an exemplary view showing a face-shaped rectangle and a heart-shaped.

As shown in FIG. 1, a makeup recommendation method according to a facial type classification according to an embodiment of the present invention is a makeup recommendation method according to a face type classification, which is a program type executed by an arithmetic processing means including a computer An image input step S10, a face contour extraction step S20, a face type classification step S30, and a style providing step S40.

In the image input step S10, the operation processing means receives image information.

The image information input in the image input step S10 may be a photograph, a moving image, or the like including a user's face. In this case, a device used for acquiring the image information may be a digital camera, a camcorder, a webcam, a CCTV It is needless to say that any device can be used as long as it can acquire image information.

The face contour extracting step S20 extracts the eyes, nose, mouth, ear, and face contour using the face recognition technique based on the image information input in the image input step S10.

This is for use in distinguishing face types in the face type classification step (S30).

)와 얼굴의 가로길이(

)를 고려하여 긴형과 일반형으로 구분하고, 얼굴 윤곽선, 눈 윤곽선 및 입술 윤곽선을 기반으로 턱선의 형태를 고려하여 사각형과 하트형으로 구분한다.In the face type classification step S30, the calculation processing means calculates the face length of the face based on the face contour extracted in the face contour extraction step S20

) And the horizontal length of the face (

), And it is divided into a rectangular shape and a heart shape considering the shape of the jaw line based on the face contour line, the eye contour line, and the lip contour line.

)와 얼굴의 가로길이(

) 간의 비율을 근거로 얼굴형을 긴형과 일반형으로 구분하고,More specifically, the vertical length of the face (

) And the horizontal length of the face (

), The face type is classified into the long type and the general type,

Considering the arrangement of eyes, lips and facial contours, the face type is divided into a rectangle and a heart type based on the degree of protrusion of the jaw to the side.

In the style providing step S40, the arithmetic processing means provides an appropriate makeup style based on the face types classified in the face type sorting step S30.

The style providing step S50 may provide a makeup style matched with the face type classified in the face type sorting step S30.

That is, the method for recommending cosmetics according to an embodiment of the present invention can guide a makeup style suitable for a user on the basis of an image obtained without a user's selection or judgment.

2, the face contour extracting step S20 of the makeup recommending method according to the face type classification according to an embodiment of the present invention includes a face region extracting step S21, a binarizing step S22, (S23), a contour line organizing step (S24), and a contour line determining step (S25).

The face region extraction step (S21) extracts the face region from the entire image using the AdaBoosting learning method.

The algorithmic basic structure of face detection is to detect pyramid images in order to detect faces of various sizes and then move them by one pixel and check whether the corresponding area of a specific size (for example, 20x20 pixels) is a face or not is determined by the Adaboost classifier The face area can be extracted.

The face extraction is performed by preprocessing process for eliminating the busy signal and histogram equalization of the brightness value, region segmentation process in the form of an integral image as a certain subregion, A feature value extraction process for extracting a feature value from a difference value and an average value, and a process for determining whether a face is a face value using the learned result using an AdaBoosting learning process.

The binarization step S22 performs a binarization process using the average and variance values of the brightness values of the images in the face area extracted in the face area extraction step S21.

The contour extraction step S23 extracts contours using a CannyEdge operator based on the result of the binarization step S22.

The outline smoothing step S24 performs a morphology operation after using a contour smoothing filter based on the result of the outline extraction step S23.

That is, in order to extract detailed elements such as eyes, nose, and mouth in the face region extracted in the face region extracting step S21, a binarization process is performed by adapting using the average and variance values of the brightness values of the images, You can use the CannyEdge operator to extract the contours, smooth out the contours using a smoothing filter, which is a low-pass filter, to remove embedded portions and error contours with the effect of non-uniform illumination on the contours Subsequent morphology operations can be performed to extract the actual contours.

The outline determination step S25 verifies the eyes, nose, mouth, ear, and face contours using the structural features of the face based on the result of the outline contouring step S24 to determine the contours of the respective parts.

In the outline determination step S25, the outline of the entire eye, nose, mouth, and face is re-verified using the structural relationship of the facial elements, and finally, the facial feature points are input mesh points for applying the mesh warping technique Mesh Point) array.

The Mesh Warping algorithm processes each row in the first stage, and processes each row in the second stage to obtain the resulting image. The meshes corresponding to the input image and the output image are configured to have the same size in order to control the point, and the input array and the output array are matched one to one. A new control point array can be created by interpolation between input and output arrays during the warping process. These intermediate arrays are each used as intermediate control points for warping. There are a variety of algorithms for interpolation, but it is desirable to use a fants resampling algorithm that reduces the aliasing problem.

)는 머리 가장 위쪽 부분부터 턱의 가장 아래쪽 부분까지의 수직 길이인 것을 특징으로 하거나, 이마의 가장 위쪽 부분부터 턱의 가장 아래쪽 부분까지의 수직 길이인 것을 특징으로 할 수 있다.As shown in FIG. 3, in the makeup recommendation method according to the embodiment of the present invention, the face length sorting step (S30)

Is a vertical length from the uppermost part of the head to the lowermost part of the jaw or a vertical length from the uppermost part of the forehead to the lowermost part of the jaw.

)로 사용하는 것이다. 이는, 헤어스타일에 따라 얼굴의 세로길이(

)가 별화되는 것을 최소화 하기 위함이다.Most preferably, the vertical length from the uppermost part of the forehead to the lowest part of the jaw is the vertical length of the face

). This means that depending on the hairstyle, the vertical length of the face

) Is minimized.

Here, it is preferable that the image input in the image input step (S10) receives an image that has passed the bangs.

)와 얼굴의 가로길이(

)를 측정하기 용이하도록 하기 위함이다.When the face region is extracted, it is preferable that the face center line passing through the center of the lip and the center of the nose is vertical. This is because the vertical length of the face (

) And the horizontal length of the face (

) Is easy to measure.

The vertical length from the uppermost portion of the forehead to the lowest portion of the jaw means that a virtual line is drawn horizontally from the uppermost portion of the forehead in a face image arranged such that the center line of the face is vertical as shown in Fig. It means the shortest distance (vertical distance) between two lines after drawing a hypothetical line horizontally from the lowest part of the jaw.

The vertical length from the uppermost portion of the head to the lowermost portion of the jaw can be confirmed by the same method.

)는 왼쪽 눈꼬리 끝과 오른쪽 눈꼬리 끝을 통과하는 직선이 얼굴 윤곽선과 교차하는 지점 간의 길이인 것을 특징으로 하거나, 왼쪽 귀 끝부터 오른쪽 귀 끝까지의 길이인 것을 특징으로 할 수 있다.As shown in FIG. 3, in the make-up recommendation method according to the face type classification according to the embodiment of the present invention,

) Is a length between a point where the straight line passing through the tip of the left clavicle and the tip of the right clavicle intersects with the contour of the face, or the length from the left ear tip to the right ear tip.

)를 눈꼬리 기준으로 측정하는 방법과, 귀 끝을 기준으로 측정하는 방법을 예로 들었으나, 본 발명이 이에 한정된 것은 아니며, 얼굴영역을 추출하면 입술 중심과 코 중심을 통과하는 얼굴 중심선이 수직이 되도록 배치된 상태에서 최 외곽 윤곽선 까지의 수평거리가 가장 긴 길이, 두 눈썹을 통과하는 직선과 얼굴 윤곽선과 교차하는 지점 간의 길이, 두 눈동자를 통과하는 직선과 얼굴 윤곽선과 교차하는 지점 간의 길이 등 얼굴의 특징이 표현된 가로 길이를 얼굴의 가로길이(

)로 사용할 수 있음은 물론이다.In the above, the horizontal length of the face

) Is measured on the basis of the eye tail, and the method of measuring based on the tip of the ear is taken as an example. However, the present invention is not limited to this, and when the face region is extracted, the center line passing through the center of the lips and the nose center is vertical The length of the horizontal distance from the placed state to the outermost contour is the longest, the distance between the straight line passing through the two eyebrows and the point crossing the face contour, the straight line passing through two pupils, The horizontal length of the feature is the width of the face (

Of course).

As shown in FIG. 4, a method of dividing a face type classification step S30 of a makeup recommendation method according to a facial type classification into a long type and a general type according to an embodiment of the present invention

에 해당되면 긴형으로 구분하고,

If the number is long,

에 해당되면 일반형으로 구분하는 것을 특징으로 하되,

, The classification is classified into a general type,

는 이용자의 국적, 인종, 성별 중 선택되는 하나 또는 복수의 조건에 따라 미리 결정된 것을 특징으로 할 수 있다.

May be characterized in that it is determined in advance according to one or more conditions selected from the nationality, race, and sex of the user.

)로 하고, 왼쪽 눈꼬리 끝과 오른쪽 눈꼬리 끝을 통과하는 직선이 얼굴 윤곽선과 교차하는 지점 간의 길이를 가로길이(

)로 할 경우,

가

보다 크면 얼굴형을 긴형으로 구분하고,

가

보다 작거나 같으면 얼굴형을 일반형으로 구분할 수 있다.For example, the vertical length from the uppermost part of the forehead to the lowest part of the jaw is called the vertical length (

), And the length between the point where the straight line passing through the tip of the left cusp and the tip of the right cusp intersects with the contour of the face is the width (

),

end

The face type is divided into the long type,

end

If they are less than or equal to each other, the face type can be classified into the general type.

) 및 왼쪽 입꼬리 끝과 오른쪽 입꼬리 끝을 통과하는 직선이, 왼쪽 눈꼬리 끝으로부터 수직으로 내린 선과 교차하는 지점과 오른쪽 눈꼬리 끝으로부터 수직으로 내린 선과 교차하는 지점 간의 길이(

)를 기준으로,As shown in FIGS. 5 to 6, a method of dividing the face type sorting step S30 into a quadrangle and a heart type according to the makeup recommendation method according to the facial type classification according to an embodiment of the present invention, The distance between the straight line passing through the tip of the right tail and the point at which it intersects the face contour (

) And the distance between the point at which the line passing through the tip of the left and right eyelids intersects with the line perpendicularly drawn from the tip of the left eye and the line intersecting perpendicularly from the tip of the right eye

),

에 해당되면 하트형으로 구분하고,

If it is classified as a heart type,

에 해당되면 사각형으로 구분하는 것을 특징으로 하되,

, And is divided into a quadrangle if it corresponds to < RTI ID = 0.0 >

는 이용자의 국적, 인종, 성별 중 선택되는 하나 또는 복수의 조건에 따라 미리 결정된 것을 특징으로 할 수 있다.

May be characterized in that it is determined in advance according to one or more conditions selected from the nationality, race, and sex of the user.

가 1보다 크면 얼굴형을 하트형으로 구분하고,

가 1보다 작거나 같으면 사각형으로 구분할 수 있다.E.g,

Is greater than 1, face type is classified as heart type,

Is less than or equal to 1, it can be divided into a rectangle.

) 및 양 입꼬리 끝을 통과하는 직선이 양 눈꼬리 끝으로부터 수직으로 내린 직선과 교차하는 지점 간의 길이(

)를 기준으로 얼굴형을 사각형과 하트형으로 구분하는 예를 들었으나, 본 발명이 이에 한정된 것은 아니며, 입술과 눈과 얼굴 윤곽선 간의 상관관계를 기반으로 다양한 실시가 가능함은 물론이다.In the above, the distance between the straight line passing through the tip of the mouth and the point where the face contour line meets

) And the distance between the point at which the straight line passing through the tip of the mouth of the tail intersects the straight line descending vertically from the tip of both eyes

The present invention is not limited thereto but may be variously carried out based on the correlation between the lips and the eyes and the contours of the face.

The style providing step S40 of the makeup recommendation method according to the facial type classification according to an embodiment of the present invention may include a step of providing a makeup recommendation method according to the present invention when the face type is determined to be a long type in the face type sorting step S30, Long eyelids and jaws should be sideways horizontally so that the long face is shrunk, eyebrows are moved to the center rather than the base line, and the eyebrows are drawn with straight line, eye shadow is given to the eye tail and blusher is dyed under the eye In addition,

When the face type is determined to be a general type in the face type sorting step S30, a foundation darker than a predetermined brightness is applied to the both ends of the face, the sides of the forehead and the chin are shaded along the face line, The area is highlighted with a bright color to make the ball look shrunk by making it look higher, and the blusher is recommended to be applied in a slanting line under the cheekbones to make it look slender.

The style providing step S40 of the makeup recommending method according to the facial type classification according to an embodiment of the present invention may further include a step of providing a makeup recommending method according to an embodiment of the present invention when the face type is determined to be a rectangle in the face type sorting step S30, It is recommended that the eyebrows be drawn slightly outward from the base position, drawn in a gentle arched shape so that the length is not too long, the blusher should be long from the cheekbone to the tip of the jaw,

In the facial classification step S30, when the facial type is determined as a heart type, it is necessary to make the facial part look pale with a bright foundation on the cheek part so as to narrow the forehead and widen the part from the cheek to the jaw, And the blusher is recommended to be applied horizontally on the underside of the eye and shaded under the cheekbones to emphasize contemporary facial contours.

Although examples of makeup styles for each face type classified into a long shape, a general shape, a square shape, and a heart shape have been described above, the present invention is not limited thereto, and various makeup styles matching with specific features can be provided Of course.

For contouring makeup, the type and color of the cosmetics used vary depending on the face type, and the contouring make-up area varies.

For contouring makeup, you can use it when you want to look crisp. Apply a shading powder that is darker than the skin when you hold a face line. Add a shine with a highlighter to the area you want to be higher than the original.

In the case of Strobing Makeup, you can use it when you want to look clean. Add a highlighter to the area you want to be higher than the original.

The style providing step S40 of the makeup recommending method according to the facial type classification according to the embodiment of the present invention may include a step of performing a makeup simulation in which the request inputted by the user is applied to the face information acquired in the face contour extracting step S20 And outputs a result.

At this time, the requests inputted by the user include the type of skin (intelligence, neutrality), the age to be seen (such as twenty generation makeup), mood (sexy, (Bright tones, dark tones, etc.), cosmetics (cosmetics, etc.), weather, temperature, humidity, color (such as pink series) Smokey, shadow, etc.), and celebrity make-up (Hong Gil-dong and the like appearing in a specific drama).

It is needless to say that the weather, temperature and humidity can be acquired by the sensor.

For example, if a face type is a regular type and a user belonging to a heart type wants to play a sexy 20s style for outdoor swimming, enter 20s as an age to be seen, enter a sexy style as an atmosphere, The makeup method that matches the makeup method may be output to the face image obtained in the face contour extraction step S20.

While the present invention has been particularly shown and described with reference to exemplary embodiments thereof, it is to be understood that the invention is not limited to the disclosed exemplary embodiments, Of course, a program stored in a computer-readable recording medium for implementing the recommendation method can also be implemented.

That is, the makeup recommendation method according to the face type division described above can be easily understood by those skilled in the art that a program of instructions for implementing the makeup type can be tangibly embodied in a recording medium readable by a computer . In other words, it can be implemented in the form of a program command that can be executed through various computer means, and can be recorded on a computer-readable recording medium. The computer-readable recording medium may include program commands, data files, data structures, and the like, alone or in combination. The program instructions recorded on the computer-readable recording medium may be those specially designed and configured for the present invention or may be those known and available to those skilled in the computer software. Examples of the computer-readable medium include magnetic media such as hard disks, floppy disks and magnetic tape, optical media such as CD-ROMs and DVDs, and optical disks such as floppy disks. Magneto-optical media and hardware devices specifically configured to store and execute program instructions such as ROM, RAM, flash memory, USB memory, and the like. Examples of program instructions include machine language code such as those produced by a compiler, as well as high-level language code that can be executed by a computer using an interpreter or the like. The hardware device may be configured to operate as one or more software modules to perform the operations of the present invention, and vice versa.

It will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.

S10: Image input step
S20: Face contour extraction step
S21: face region extraction step S22: binarization step
S23: Outline Extraction Step S24: Outline Arrangement Step
S25: Outline determination step
S30: Face type classification step
S40: Style Provisioning Step

Claims (10)

A makeup recommendation method according to a facial type classification comprising a program form executed by an arithmetic processing means including a computer,
An image input step (S10) in which the operation processing means receives image information;
(S20) for extracting eyes, nose, mouth, ear, and face contour using the face recognition technique based on the image information input in the image input step (S10);
Wherein the calculation processing means calculates the vertical length of the face based on the face contour extracted in the face contour extracting step (S20)

) And the horizontal length of the face (

(S30); a facial classification step S30 for dividing the facial contour line, the eye contour line, and the lip contour line into a rectangle and a heart line; And
A style providing step (S40) in which the operation processing means provides an appropriate makeup style based on the face type classified in the face type sorting step (S30);
/ RTI >
A method of dividing the face type classification step S30 into a quadrangle and a heart type
The distance between the tip of the left hindpaw and the straight line passing through the tip of the right hindpaw, the point at which the face contour intersects (

) And
The distance between the point where the line passing through the tip of the left hindpaw and the tip of the right hindpaw is intersected with the line perpendicularly drawn from the tip of the left hindpaw and the line intersecting perpendicularly from the tip of the right hindpaw

),
If it is classified as a heart type,

, And is divided into a quadrangle if it corresponds to < RTI ID = 0.0 >

Is determined in advance according to one or more conditions selected from the nationality, race, and sex of the user,
A method of distinguishing between the long type and the general type of the face type classification step S30

If the number is long,

, The classification is classified into a general type,

Is characterized in that it is determined in advance according to one or more conditions selected from the nationality, race, and sex of the user,
The style providing step S40 is a feature of outputting a makeup simulation result in which the request inputted by the user is applied to the face information acquired in the face contour extracting step S20,
The requests entered by the user include the type of skin (intelligence, neutrality), the age to be seen (20s), mood (sexy, dodo, Temperature, humidity, color (such as pink series), brightness (light tone, dark tone, etc.), cosmetic method (smokey, A shadow, etc.), and an entertainer's makeup (e.g., Hong Gil-dong appearing in a specific drama).
The method according to claim 1,
The face contour extracting step S20
A face region extraction step (S21) for extracting a face region from the entire image using an AdaBoosting learning method;
A binarization step (S22) of performing a binarization process using an average and a variance value of brightness values of images in the face region extracted in the face region extraction step (S21);
An outline extraction step S23 for extracting outlines using a CannyEdge operator based on the result of the binarization step S22;
A contour correcting step (S24) for performing a morphology operation after using a contour smoothing filter based on the result of the contour extracting step (S23); And
An outline determination step (S25) of verifying the eye, nose, mouth, ear, and face contour using the structural features of the face based on the result of the outline contouring step (S24) and determining the outline of each part;
The makeup recommendation method according to the face type classification including the face type classification.
The method according to claim 1,
The vertical length of the face of the face type classification step S30 (

)
And a vertical length from the uppermost portion of the head to the lowermost portion of the jaw,
And a vertical length from the uppermost part of the forehead to the lowermost part of the jaw.
The method of claim 3,
The horizontal length of the face of the face type classification step S30 (

)
And the straight line passing through the tip of the left clavicle and the tip of the right clavicle is the length between the points where the line crosses the face contour,
And a length of the left ear to the right ear.
delete delete The method according to claim 1,
The style providing step (S40)
If the face type is determined to be a long type in the face type classification step S30,
A foundation darker than a predetermined brightness is shed horizontally at the tip of the long flax and jaw, shaving a long face, eyebrows are moved to the center rather than the base line, or drawn with a straight line, eye shadow gives a point toward the eye tail, It is recommended that you brush your teeth in a dongle,
If the face type is determined to be a general type in the face type classification step S30,
Make a foundation that is darker than a predetermined brightness on both sides of the face, along the sides of the forehead to the chin along the face line to make the face look longer and Tizon area to make the nose look higher with bright color highlights The makeup recommendation method according to the face type classification is characterized by that the blusher is applied in a diagonal line under the cheekbones to make it look smooth.
The method according to claim 1,
The style providing step (S40)
If the face type is determined to be a rectangle in the face type classification step S30,
The point is to remove the angle so that it looks gentle as a whole. The eyebrow mountain is drawn slightly higher than the basic position outward, and is drawn in a smooth arched shape with a long length. The blusher is long from the cheekbone to the tip of the jaw, However,
If the face type is determined to be a heart type in the face type classification step S30,
To narrow the forehead and widen the cheek to jaw, make the cheeks look plump with a bright foundation, draw a long eyebrow or a gentle curve like a gull, the blusher is long horizontally below the eye and under the cheekbones The method of recommending make-up according to the facial type classification, characterized in that it is recommended to give a shade with an oblique line to emphasize a contour of a modern face.
A computer-readable recording medium storing a program for implementing a makeup recommendation method according to any one of claims 1, 2, 3, 4, 7, and 8, media.
A makeup recommendation method according to any one of claims 1, 2, 3, 4, 7, and 8, wherein the makeup recommendation method is stored in a computer readable recording medium program.

Images