KR102422778B1 - Landmark data decomposition device, method and computer readable recording medium thereof - Google Patents

Abstract

The landmark data separation method includes the steps of receiving a plurality of images, calculating average landmark data based on faces included in the plurality of images; Calculating landmark data for a specific frame among a plurality of frames, calculating characteristic landmark data for a plurality of frames included in a specific image, and average landmark data, landmark data and characteristics for a specific frame It may include calculating the landmark data of the expression for a specific frame of a specific image by calculating the landmark data.

Description

Landmark data separation apparatus, method and computer readable recording medium

The present invention relates to an apparatus, method, and computer-readable recording medium for separating landmark data, and more particularly, to a landmark data separation apparatus, method, and computer-readable method capable of more accurately separating landmark data from a face included in an image It relates to possible recording media.

A technique for analyzing and utilizing a human face image based on a facial landmark extracted from a facial key point is being actively researched. The landmark of the face includes the result value of extracting the outline drawn by extracting the starting points of the main elements such as the eyes, eyebrows, nose, mouth, and jaw lines of the face or connecting the starting points. Facial landmarks are mainly used in technologies such as facial expression classification, pose analysis, face synthesis, and face transformation.

However, the conventional facial image analysis and utilization technology based on facial landmarks does not take into account the appearance characteristics and emotional characteristics of the face when processing the facial landmarks, resulting in a decrease in performance. Therefore, in order to improve the performance of the facial image analysis and utilization technology, there is a demand for the development of a technology for separating facial landmarks including characteristics due to facial emotions.

An object of the present invention is to provide a landmark data separation apparatus, method, and computer-readable recording medium capable of more accurately and precisely separating landmark data from a face included in an image.

The landmark data separation method according to an embodiment of the present invention includes the steps of receiving a plurality of images, calculating average landmark data based on faces included in the plurality of images, and selecting a specific face from among the plurality of images. Calculating landmark data for a specific frame among a plurality of frames included in a specific image including, calculating characteristic landmark data for a plurality of frames included in a specific image, and average landmark data, specific frame It may include calculating the landmark data and the characteristic landmark data for the expression landmark data for a specific frame of a specific image.

Alternatively, in the landmark data separation method, each of the plurality of images includes a face for one person, and the step of calculating average landmark data based on the face included in each of the plurality of images includes the faces included in the plurality of images. For calculating a plurality of landmark data, it is possible to calculate an average value of the plurality of landmark data as average landmark data.

Alternatively, the calculating of characteristic landmark data for a plurality of frames included in a specific image among a plurality of images includes calculating a plurality of landmark data for a specific face included in a plurality of frames of a specific image, and The average value of the landmark data may be calculated as the average landmark data of a specific face, and the characteristic landmark data may be calculated by calculating the average landmark data and the average landmark data of the specific face.

Alternatively, when calculating the characteristic landmark data, the value of the average expression landmark data for a specific face included in a plurality of frames of a specific image may be 0.

Alternatively, in the step of calculating the expression landmark data for a specific frame of a specific image, the expression landmark data may correspond to a value obtained by subtracting the average landmark data and the characteristic landmark data from the landmark data for the specific frame.

Alternatively, the expression landmark data may correspond to an expression of a specific face included in a specific frame and motion information such as eyes, eyebrows, nose, mouth, and jaw lines included in the specific face.

Alternatively, the landmark data for the specific frame may include information on the main origin of the specific face included in the specific image of the specific image.

An apparatus for separating landmark data according to an embodiment of the present invention calculates average landmark data based on an image receiving unit receiving a plurality of images and faces included in a plurality of images, and calculating a specific face including a specific face among a plurality of images Calculating landmark data for a specific frame among a plurality of frames included in an image, calculating characteristic landmark data for a plurality of frames included in a specific image, average landmark data, landmark data for a specific frame, and It may include a landmark data calculation unit that calculates the landmark data for a specific frame of a specific image by calculating the landmark data.

Alternatively, the landmark data separation apparatus may further include a landmark data storage unit for storing average landmark data, landmark data for a specific frame, and characteristic landmark data.

Alternatively, each of the plurality of images includes a face for one person, and the landmark data calculation unit calculates a plurality of landmark data for faces included in the plurality of images, and averages the average value of the plurality of landmark data. It can be calculated as landmark data.

Alternatively, the landmark data calculation unit calculates a plurality of landmark data for a specific face included in a plurality of frames of a specific image, calculates an average value of the plurality of landmark data as average landmark data of the specific face, and a specific face It is possible to calculate the characteristic landmark data by calculating the average landmark data and the average landmark data.

Alternatively, when calculating the characteristic landmark data, the value of the average expression landmark data for a specific face included in a plurality of frames of a specific image may be 0.

Alternatively, the expression landmark data may correspond to a value obtained by subtracting the average landmark data and the characteristic landmark data from the landmark data for a specific frame.

Alternatively, the expression landmark data may correspond to an expression of a specific face included in a specific frame and motion information such as eyes, eyebrows, nose, mouth, and jaw lines included in the specific face.

The present invention may provide a landmark data separation apparatus, method, and computer-readable recording medium capable of more accurately and precisely separating landmark data from a face included in an image.

The present invention may provide a landmark data separation apparatus, method, and computer readable recording medium capable of separating landmark data including information on facial characteristics and expression included in an image more accurately.

1 is a diagram schematically illustrating an environment in which a method of extracting landmark data from a face included in an image according to the present invention is performed.
2 is a diagram schematically showing the configuration of an apparatus for separating landmark data according to an embodiment of the present invention.
3 is a view for explaining a method of extracting landmark data of a face according to an embodiment of the present invention.
4 is a flowchart illustrating a method of extracting various types of landmark data according to an embodiment of the present invention.
5 is a diagram exemplarily illustrating a process of converting a facial expression included in an image according to another embodiment of the present invention.
6 is a comparison table for explaining the effect of converting a facial expression included in an image by using the landmark data separation method according to the present invention.
7 is a diagram schematically showing the configuration of an apparatus for separating landmark data according to an embodiment of the present invention.

Advantages and features of the present invention and methods of achieving them will become apparent with reference to the embodiments described below in detail in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but will be implemented in a variety of different forms, only these embodiments allow the disclosure of the present invention to be complete, and common knowledge in the technical field to which the present invention belongs It is provided to fully inform the possessor of the scope of the invention, and the present invention is only defined by the scope of the claims. Like reference numerals refer to like elements throughout.

Although "first" or "second" is used to describe various elements, these elements are not limited by the above terms. Such terms may only be used to distinguish one component from another. Accordingly, the first component mentioned below may be the second component within the spirit of the present invention.

The terminology used herein is for the purpose of describing the embodiment and is not intended to limit the present invention. In this specification, the singular also includes the plural, unless specifically stated otherwise in the phrase. As used herein, “comprises” or “comprising” implies that the stated component or step does not exclude the presence or addition of one or more other components or steps.

Unless otherwise defined, all terms used herein may be interpreted with meanings commonly understood by those of ordinary skill in the art to which the present invention pertains. In addition, terms defined in a commonly used dictionary are not to be interpreted ideally or excessively unless clearly specifically defined.

1 is a diagram schematically illustrating an environment in which a method of extracting landmark data from a face included in an image according to the present invention is performed.

Referring to FIG. 1 , an environment in which the method for extracting landmark data according to the present invention is performed may include a server 10 and a terminal 20 connected to the server 10 . For convenience of explanation, only one terminal is illustrated in FIG. 1, but a plurality of terminals may be included. With respect to the terminal that can be added, the description of the terminal 20 may be applied except for the description to be specifically mentioned.

In an embodiment of the present invention, the server 10 receives an image from the terminal 20, extracts landmark data from a face included in the received image, and calculates necessary data from the extracted landmark data, The calculated data may be transmitted to the terminal 20 .

Alternatively, the server 10 may function as a platform that provides services that the terminal 20 can access and use. The terminal 20 may extract landmark data from the face included in the image in the terminal 20 , calculate necessary data from the extracted landmark data, and then transmit the calculated data to the server 10 .

The server 10 may be connected to a communication network. The server 10 may be connected to other external devices through the communication network. The server 10 may transmit data to or receive data from other devices connected to each other.

The communication network connected to the server 10 may include a wired communication network, a wireless communication network, or a complex communication network. The communication network may include a mobile communication network such as 3G, LTE, or LTE-A. The communication network may include a wired or wireless communication network such as Wi-Fi, UMTS/GPRS, or Ethernet. Communication networks include Magnetic Secure Transmission (MST), Radio Frequency Identification (RFID), Near Field Communication (NFC), Zigbee, Z-Wave, Bluetooth, Bluetooth Low Energy (BLE). , or may include a local area network such as infrared communication (InfraRed communication). The communication network may include a local area network (LAN), a metropolitan area network (MAN), or a wide area network (WAN).

The server 10 may be connected to the terminal 20 through a communication network. When the server 10 is connected to the terminal 20 , the server 10 may exchange data with the terminal 20 through the communication network. The server 10 may perform an arbitrary operation using data received from the terminal 20 . The server 10 may transmit the calculation result to the terminal 20 .

The terminal 20 may be a desktop computer, a laptop computer, a smart phone, a smart tablet, a smart watch, a mobile terminal, a digital camera, a wearable device, or a portable electronic device. The terminal 20 may execute a program or application.

2 is a diagram schematically showing the configuration of an apparatus for separating landmark data according to an embodiment of the present invention.

Referring to FIG. 2 , the landmark data separation apparatus 100 according to an embodiment of the present invention may include an image receiving unit 110 , a landmark data calculating unit 120 , and a landmark data storage unit 130 . can The landmark data separation apparatus 100 may be configured through the server 10 or the terminal 20 described with reference to FIG. 1 . Accordingly, each of the components included in the landmark data separation apparatus 100 may also be configured through the server 10 or the terminal 20 .

The image receiver 110 may receive a plurality of images from a user. Each of the plurality of images may include only one person. That is, each of the plurality of images may include the face of one person, and the persons included in the plurality of images may be different people.

The image receiver 110 may extract only a face region from each of the plurality of images, and then provide the extracted face region to the landmark data calculator 120 .

The landmark data calculation unit 120 includes landmark data of a face included in each of a plurality of images, average landmark data of all faces included in a plurality of images, and a characteristic land of a specific face included in a specific image among a plurality of images. Mark data and expression landmark data of a specific face may be calculated.

In some embodiments, the landmark data may be a result of extraction of a face key point. A method of extracting landmark data may be described with reference to FIG. 3 .

3 is a view for explaining a method of extracting landmark data of a face according to an embodiment of the present invention.

The landmark data may be obtained by extracting the starting points of major elements such as the eyes, eyebrows, nose, mouth, and jaw line of the face or by extracting the outline drawn by connecting the starting points. The landmark data may be utilized in techniques such as facial expression classification, pose analysis, face synthesis of different people, or face transformation.

Referring back to FIG. 2 , the landmark data calculator 120 may calculate average landmark data of faces included in a plurality of images. The average landmark data may be assumed to be a result of extracting the shape of an average human face.

The landmark data calculator 120 may calculate landmark data from a specific image including a specific face among a plurality of images. More specifically, landmark data for a specific face included in a specific frame among a plurality of frames included in a specific image may be calculated.

Also, the data calculator 120 may calculate characteristic landmark data of a specific face included in a specific image among a plurality of images. The characteristic landmark data may be calculated based on facial landmark data included in each of a plurality of frames included in a specific image.

In addition, the data calculator may calculate the average landmark data, the landmark data for the specific frame, and the characteristic landmark data to calculate the facial expression landmark data for the specific frame of the specific image. For example, the expression landmark data may correspond to an expression of a specific face or movement information of major elements such as eyes, eyebrows, nose, mouth, and jaw lines.

The landmark data storage unit 130 may store the data calculated by the landmark data calculation unit 120 . For example, the landmark data storage unit 130 may store the average landmark data calculated by the landmark data calculation unit 120, landmark data for a specific frame, characteristic landmark data, and expression landmark data. have.

4 is a flowchart illustrating a method of extracting various types of landmark data according to an embodiment of the present invention.

2 and 4 , in step S110 , the landmark data separation apparatus 100 may receive a plurality of images. Each of the plurality of images may include only one person. That is, each of the plurality of images may include the face of one person, and the persons included in the plurality of images may be different people.

In step S120 , the landmark data separation apparatus 100 may calculate the average landmark data I _m . The average landmark data (I _m ) may be expressed as follows.

In an embodiment of the present invention, C may mean the number of a plurality of images, and T may mean the number of frames included in each of the plurality of images.

That is, the landmark data separation apparatus 100 may extract landmark data I _{( c,t )} of each of the faces included in the plurality of images C . The landmark data separation apparatus 100 may calculate an average value of all the extracted landmark data. The calculated average value may correspond to the average landmark data (I _m ).

In step S130 , the landmark data separation apparatus 100 may calculate a landmark datater (I _{(c, t)} ) for a specific frame among a plurality of frames of a specific image including a specific face among a plurality of images .

For example, the landmark data I _{( c,t )} for a specific frame may be information on the main starting point of a specific face included in the t-th frame of the c-th image among the plurality of images C. That is, it may be assumed that the specific image is the c-th image, and the specific frame is the t-th frame.

In step S140 , the landmark data separation apparatus 100 may calculate the characteristic landmark data I _{id (c)} of a specific face included in the c-th image. The characteristic landmark data I _id(c) may be expressed as follows.

)을 0으로 가정할 수 있다. 따라서, 특성 랜드마크 데이터(I_(id(c)))는 특정 얼굴의 표정 랜드마크 데이터(I_exp)의 평균값(

)을 고려하지 않고 산출될 수 있다. In an embodiment of the present invention, a plurality of frames included in the c-th image include various expressions of a specific face. Therefore, in order to calculate the characteristic landmark data (I _{id (c)} ), the _landmark data separation apparatus 100 is an average value (

) can be assumed to be 0. Therefore, the characteristic landmark data ( _{I_} (id(c))) is the average value (

) can be calculated without considering

)를 산출하고, 산출된 c번째 영상의 평균 랜드마크 데이터()에서 복수의 영상의 평균 랜드마크 데이터(I_m)를 뺀 값으로 정의될 수 있다. The characteristic landmark data (I _{id (c)} ) calculates landmark data for each of a plurality of frames included in the c-th image, and average landmark data (

), and may be defined as a value obtained by subtracting the average landmark data (I _m ) of a plurality of images from the calculated average landmark data ( ) of the c-th image.

In step S150 , the landmark data separation apparatus 100 may calculate the expression landmark data I _{exp(c, t)} of a specific face.

More specifically, the landmark data separation apparatus 100 may calculate the expression landmark data I _{exp ( c,t )} of a specific face included in the t-th frame of the c-th image. Expression landmark data (I _{exp(c, t)} ) may be expressed as follows.

The expression landmark data I _{exp ( c, t )} may correspond to an expression of a specific face included in the t-th frame and motion information such as eyes, eyebrows, nose, mouth, and jaw lines included in the specific face. More specifically, the expression landmark data (I _{exp ( c,t )} ) is the average landmark data (I _m ) and the characteristic landmark data (I) in the landmark data (I _{( c,t )} ) for a specific frame It can be defined as a value minus _{id (c)} ).

Through the same operation as described with reference to FIG. 4 , the landmark data separation apparatus 100 may separate landmark data of a face included in the image. The landmark data separation apparatus 100 may acquire not only the main starting point of the face included in the image, but also the expression of the face, and the movement information of the face.

The server 10 or the terminal 20 is a landmark data separation apparatus 100 separated from the expression landmark data (I _{exp ( c, t )} ), the average landmark data (I _m ), and the characteristic landmark data ( I _id(c) ), while maintaining the appearance of the face included in the first image, it is possible to implement a technique for converting the facial expression into the facial expression included in the second image. A specific method may be described with reference to FIG. 5 .

5 is a diagram exemplarily illustrating a process of converting a facial expression included in an image according to another embodiment of the present invention.

4 and 5, the server 10 or the terminal 20 is the facial expression landmark data (I _{exp ( c, t )} ), the average landmark data (I _m ) separated from the data separation device 100 ) , and the characteristic landmark data (I _{id (c)} ) to maintain the appearance of the face included in the first image 30, but only the expression can be converted into the expression of the face included in the second image 40 have.

For example, the first image 30 may correspond to a t _x th frame among a plurality of frames included in a c _x th image among the plurality of images. In addition, the second image 40 is t _y times among a plurality of frames included in the c _y -th image among the plurality of images? It can correspond to the frame. The c _x th image and the c _y th image may be different images.

The landmark data of the face included in the first image 30 may be separated as follows.

)는 평균 랜드마크 데이터(I_m), 특성 랜드마크 데이터(

), 및 표정 랜드마크 데이터(

)를 합한 결과로 표현될 수 있다.Landmark data of the face included in the first image 30 (

) is average landmark data (I _m ), characteristic landmark data (

), and facial landmark data (

) can be expressed as a result of adding

The landmark data of the face included in the second image 40 may be separated as follows.

)는 평균 랜드마크 데이터(I_m), 특성 랜드마크 데이터(

), 및 표정 랜드마크 데이터(

)를 합한 결과로 표현될 수 있다.The landmark data of the face included in the second image 40 (

) is average landmark data (I _m ), characteristic landmark data (

), and facial landmark data (

) can be expressed as a result of adding

The landmark data of the face included in the first image 30 is maintained in order to maintain the appearance of the face included in the first image 30, but to convert only the facial expression to the facial expression included in the second image 40. It can be expressed as

)는 유지하되, 제1 이미지(30)에 포함된 얼굴의 표정 랜드마크 데이터(

)대신 제2 이미지(40)에 포함된 얼굴의 표정 랜드마크 데이터(

)를 대입할 수 있다. The server 10 or the terminal 20 includes the characteristic landmark data of the face included in the first image 30 (

) is maintained, but facial expression landmark data (

) instead of facial expression landmark data (

) can be substituted.

Through this method, the first image 30 may be transformed like the third image 50 . The face included in the first image 30 was a smiling expression, but the face included in the third image 50 made a winking expression with a smile like the expression of the face included in the second image 40. have.

6 is a comparison table for explaining the effect of converting a facial expression included in an image by using the landmark data separation method according to the present invention.

The MarioNETte model is a model that transforms facial expressions included in images without using the landmark data separation method. When using the MarioNETte model, the result of measuring the naturalness of the transformed image is 0.147.

The MarioNETte+LT model is a model that transforms facial expressions included in images using the landmark data separation method. When using the MarioNETte model, the result of measuring the naturalness of the transformed image is 0.280. That is, it is confirmed that the image converted using the MarioNETte+LT model is 1.9 times more natural than the image converted using the MarioNETte model.

7 is a diagram schematically showing the configuration of an apparatus for separating landmark data according to an embodiment of the present invention.

Referring to FIG. 7 , the landmark data separation apparatus 200 may include a processor 210 and a memory 220 . Those of ordinary skill in the art related to the present embodiment can see that other general-purpose components other than the components shown in FIG. 7 may be further included.

The image conversion apparatus 200 may be similar to or the same as the landmark data separation apparatus 100 illustrated in FIG. 2 . The image receiver 110 and the landmark data calculator 120 included in the landmark data separation apparatus 100 may be included in the processor 210 .

The processor 210 controls the overall operation of the landmark data separation apparatus 200 and may include at least one processor such as a CPU. The processor 210 may include at least one specialized processor corresponding to each function or may be an integrated processor.

The memory 220 may store a program, data, or file for controlling the landmark data separation apparatus 200 . The memory 220 may store instructions executable by the processor 210 . The processor 210 may execute a program stored in the memory 220 , read data or files stored in the memory 220 , or store new data. In addition, the memory 220 may store program commands, data files, data structures, etc. alone or in combination.

The processor 210 may receive a plurality of images. Each of the plurality of images may include only one person. That is, each of the plurality of images may include the face of one person, and the persons included in the plurality of images may be different people.

The processor 210 may store a plurality of received images in a memory.

The processor 210 may extract landmark data I _{(c, t)} of each of the faces included in the plurality of images C. The landmark data separation apparatus 100 may calculate an average value of all the extracted landmark data. The calculated average value may correspond to the average landmark data (I _m ).

The processor 210 may calculate landmark data I _(c,t) for a specific frame among a plurality of frames of a specific image including a specific face among a plurality of images.

The landmark data (I _{( c, t )} ) for a specific frame may be main starting point information of a specific face included in the t-th frame of the c-th image among the plurality of images (C). That is, it may be assumed that the specific image is the c-th image, and the specific frame is the t-th frame.

)을 0으로 가정할 수 있다. 따라서, 특성 랜드마크 데이터(I_id(c))는 특정 얼굴의 표정 랜드마크 데이터(I_exp)의 평균값(

)을 고려하지 않고 산출될 수 있다. The processor 210 may calculate characteristic landmark data I _id(c) of a specific face included in the c-th image. The plurality of frames included in the c-th image include various expressions of a specific face. Therefore, in order to calculate the characteristic landmark data (I _{id (c)} ), the processor ₂₁₀ is an average value (

) can be assumed to be 0. Accordingly, the characteristic landmark data (I _{id (c)} ) is the average value (

) can be calculated without considering

)를 산출하고, 산출된 c번째 영상의 평균 랜드마크 데이터(

)에서 복수의 영상의 평균 랜드마크 데이터(I_m)를 뺀 값으로 정의될 수 있다. The characteristic landmark data (I _{id (c)} ) calculates landmark data for each of a plurality of frames included in the c-th image, and average landmark data (

), and average landmark data of the calculated c-th image (

) may be defined as a value obtained by subtracting the average landmark data I_m of a plurality of images.

The processor 210 may calculate the expression landmark data I _{exp ( c, t )} of a specific face included in the t-th frame of the c-th image. The expression landmark data I _{exp ( c, t )} may correspond to an expression of a specific face included in the t-th frame and motion information such as eyes, eyebrows, nose, mouth, and jaw lines included in the specific face. More specifically, the expression landmark data (I _{exp(c,t) ) is the} average landmark data (I _m ) and the characteristic landmark data ( It can be defined as a value minus I _id(c) ).

The processor 210 may store the separated expression landmark data (I _{exp ( c, t )} ), the average landmark data (I _m ), and the characteristic landmark data (I _{id (c)} ) in the memory 220 . have.

As described with reference to FIGS. 1 to 7 , the landmark data separation apparatuses 100 and 200 according to an embodiment of the present invention may separate more accurate and precise landmark data from a face included in an image.

Also, the landmark data separation apparatuses 100 and 200 may separate landmark data including information on facial characteristics and expressions included in the image more accurately.

In addition, the server 10 or the terminal 20 including the landmark data separation apparatus 100, 200 is separated expression landmark data (I _{exp ( c, t )} ), average landmark data (I _m ), And while maintaining the appearance of the face included in the first image by using the characteristic landmark data (I _{id (c)} ), it is possible to implement a technology for naturally converting the facial expression into the facial expression included in the second image.

The embodiments described above may also be implemented in the form of a recording medium including instructions executable by a computer, such as a program module executed by a computer. Computer-readable media can be any available media that can be accessed by a computer and can include both volatile and non-volatile media, removable and non-removable media.

In addition, computer-readable media may include computer storage media. Computer storage media may include both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data.

Although embodiments of the present invention have been described above with reference to the accompanying drawings, those of ordinary skill in the art to which the present invention pertains can implement the present invention in other specific forms without changing its technical spirit or essential features. You will understand that there is Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive.

Claims (15)

In the landmark data separation method,
receiving a plurality of images;
calculating average landmark data based on the faces included in the plurality of images;
calculating landmark data for a specific frame among a plurality of frames included in a specific image including a specific face among the plurality of images;
calculating characteristic landmark data for the plurality of frames included in the specific image; and
calculating the facial expression landmark data for the specific frame of the specific image by calculating the average landmark data, the landmark data for the specific frame, and the characteristic landmark data;
including,
The step of calculating the facial expression landmark data for the specific frame of the specific image,
The landmark data separation method corresponding to a value obtained by subtracting the average landmark data and the characteristic landmark data from the landmark data for the specific frame. The method of claim 1,
Each of the plurality of images includes a face for one person,
Calculating the average landmark data based on the face included in each of the plurality of images includes:
A landmark data separation method of calculating a plurality of landmark data for the faces included in the plurality of images, and calculating an average value of the plurality of landmark data as the average landmark data. The method of claim 1,
Calculating characteristic landmark data for the plurality of frames included in the specific image among the plurality of images includes:
Calculating a plurality of landmark data for the specific face included in the plurality of frames of the specific image,
Calculate the average value of the plurality of landmark data as the average landmark data of the specific face,
A landmark data separation method for calculating the characteristic landmark data by calculating the average landmark data and the average landmark data of the specific face. 4. The method of claim 3,
When calculating the characteristic landmark data, the value of the average expression landmark data for the specific face included in the plurality of frames of the specific image is 0 landmark data separation method. delete The method of claim 1,
The expression landmark data is a landmark data separation method corresponding to the expression of the specific face included in the specific frame and motion information such as eyes, eyebrows, nose, mouth, and jaw line included in the specific face. The method of claim 1,
The landmark data for the specific frame is a landmark data separation method including information on the main starting point of the specific face included in the specific image of the specific image. A computer-readable recording medium in which a program for performing the method according to any one of claims 1 to 4, 6, and 7 is recorded. an image receiving unit for receiving a plurality of images; and
calculating average landmark data based on faces included in the plurality of images, calculating landmark data for a specific frame among a plurality of frames included in a specific image including a specific face among the plurality of images, and Calculate characteristic landmark data for the plurality of frames included in a specific image, calculate the average landmark data, landmark data for the specific frame, and the characteristic landmark data to the specific frame of the specific image a landmark data calculation unit for calculating facial expression landmark data;
including,
The landmark data separation device corresponding to a value obtained by subtracting the average landmark data and the characteristic landmark data from the landmark data for the specific frame. 10. The method of claim 9,
The landmark data separation apparatus further comprising a landmark data storage unit for storing the average landmark data, the landmark data for the specific frame, and the characteristic landmark data. 10. The method of claim 9,
Each of the plurality of images includes a face for one person,
The landmark data calculation unit calculates a plurality of landmark data for the faces included in the plurality of images, and calculates an average value of the plurality of landmark data as the average landmark data. 10. The method of claim 9,
The landmark data calculation unit calculates a plurality of landmark data for the specific face included in the plurality of frames of the specific image,
Calculate the average value of the plurality of landmark data as the average landmark data of the specific face,
Landmark data separation apparatus for calculating the characteristic landmark data by calculating the average landmark data and the average landmark data of the specific face. 13. The method of claim 12,
When calculating the characteristic landmark data, the value of the average expression landmark data for the specific face included in the plurality of frames of the specific image is 0 landmark data separation apparatus. delete 10. The method of claim 9,
The expression landmark data is an apparatus for separating landmark data corresponding to the expression of the specific face included in the specific frame and motion information such as eyes, eyebrows, nose, mouth, and jaw line included in the specific face.

Images