KR20080059865A - Face modification of game character in game system - Google Patents

Face modification of game character in game system Download PDF

Info

Publication number
KR20080059865A
KR20080059865A KR1020060133716A KR20060133716A KR20080059865A KR 20080059865 A KR20080059865 A KR 20080059865A KR 1020060133716 A KR1020060133716 A KR 1020060133716A KR 20060133716 A KR20060133716 A KR 20060133716A KR 20080059865 A KR20080059865 A KR 20080059865A
Authority
KR
South Korea
Prior art keywords
face
game
facial feature
game character
information
Prior art date
Application number
KR1020060133716A
Other languages
Korean (ko)
Other versions
KR100859315B1 (en
Inventor
김재희
이상윤
박강령
김종선
Original Assignee
연세대학교 산학협력단
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 연세대학교 산학협력단 filed Critical 연세대학교 산학협력단
Priority to KR1020060133716A priority Critical patent/KR100859315B1/en
Priority to PCT/KR2007/006611 priority patent/WO2008078897A1/en
Publication of KR20080059865A publication Critical patent/KR20080059865A/en
Application granted granted Critical
Publication of KR100859315B1 publication Critical patent/KR100859315B1/en

Links

Images

Classifications

    • A63F13/10
    • AHUMAN NECESSITIES
    • A63SPORTS; GAMES; AMUSEMENTS
    • A63FCARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR
    • A63F13/00Video games, i.e. games using an electronically generated display having two or more dimensions
    • A63F13/60Generating or modifying game content before or while executing the game program, e.g. authoring tools specially adapted for game development or game-integrated level editor
    • A63F13/65Generating or modifying game content before or while executing the game program, e.g. authoring tools specially adapted for game development or game-integrated level editor automatically by game devices or servers from real world data, e.g. measurement in live racing competition
    • A63F13/655Generating or modifying game content before or while executing the game program, e.g. authoring tools specially adapted for game development or game-integrated level editor automatically by game devices or servers from real world data, e.g. measurement in live racing competition by importing photos, e.g. of the player
    • AHUMAN NECESSITIES
    • A63SPORTS; GAMES; AMUSEMENTS
    • A63FCARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR
    • A63F13/00Video games, i.e. games using an electronically generated display having two or more dimensions
    • A63F13/45Controlling the progress of the video game
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T13/00Animation
    • G06T13/203D [Three Dimensional] animation
    • G06T13/403D [Three Dimensional] animation of characters, e.g. humans, animals or virtual beings
    • AHUMAN NECESSITIES
    • A63SPORTS; GAMES; AMUSEMENTS
    • A63FCARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR
    • A63F2300/00Features of games using an electronically generated display having two or more dimensions, e.g. on a television screen, showing representations related to the game
    • A63F2300/60Methods for processing data by generating or executing the game program
    • A63F2300/66Methods for processing data by generating or executing the game program for rendering three dimensional images
    • AHUMAN NECESSITIES
    • A63SPORTS; GAMES; AMUSEMENTS
    • A63FCARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR
    • A63F2300/00Features of games using an electronically generated display having two or more dimensions, e.g. on a television screen, showing representations related to the game
    • A63F2300/60Methods for processing data by generating or executing the game program
    • A63F2300/66Methods for processing data by generating or executing the game program for rendering three dimensional images
    • A63F2300/6607Methods for processing data by generating or executing the game program for rendering three dimensional images for animating game characters, e.g. skeleton kinematics
    • AHUMAN NECESSITIES
    • A63SPORTS; GAMES; AMUSEMENTS
    • A63FCARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR
    • A63F2300/00Features of games using an electronically generated display having two or more dimensions, e.g. on a television screen, showing representations related to the game
    • A63F2300/60Methods for processing data by generating or executing the game program
    • A63F2300/69Involving elements of the real world in the game world, e.g. measurement in live races, real video
    • A63F2300/695Imported photos, e.g. of the player
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T19/00Manipulating 3D models or images for computer graphics
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/30Subject of image; Context of image processing
    • G06T2207/30196Human being; Person
    • G06T2207/30201Face

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Processing Or Creating Images (AREA)

Abstract

A face modification method of a game character in a game system is provided to change the face of a game character based on the face image that is selected by a user to increase the interests of a game. A face modification method of a game character in a game system includes the steps of: extracting the face area and features of the face from the selected face image; producing 2D caricature by characterizing the extracted 2D face information and face feature information; and mapping the produced 2D caricature on the face of the game character that is selected by a game user to change the 2D face of the game character selected by the game user.

Description

게임 시스템에서의 게임 캐릭터 얼굴 변경 방법{Face Modification of Game Character in Game System}Face Modification of Game Character in Game System

도 1은 본 발명에 따른 게임 시스템에서의 게임 캐릭터 얼굴 변경 방법을 나타낸 플로차트.1 is a flowchart illustrating a method of changing a game character face in a game system according to the present invention.

도 2는 본 발명에 따른 게임 시스템에서의 게임 캐릭터 얼굴 변경 방법을 게임 시스템에 적용하는 과정을 나타낸 실시예.Figure 2 is an embodiment showing a process of applying a game character face change method in the game system according to the present invention.

도 3은 본 발명에 따른 게임 시스템에서의 게임 캐릭터 얼굴 변경 방법에 따라 2D 얼굴 영상을 게임 캐릭터화하는 과정을 나타낸 제1실시예.3 is a first embodiment illustrating a process of game characterizing a 2D face image according to a method of changing a game character face in a game system according to the present invention;

도 4는 본 발명에 따른 게임 시스템에서의 게임 캐릭터 얼굴 변경 방법에 따라 2D 얼굴 영상을 게임 캐릭터화하는 과정을 나타낸 제2실시예.4 is a second embodiment showing a process of characterizing a 2D face image according to a method of changing a game character face in a game system according to the present invention;

본 발명은 게임 시스템에 관한 것이며, 더욱 상세히는 게임 시스템에서의 게임 캐릭터 얼굴 변경 방법에 관한 것이다.The present invention relates to a game system, and more particularly to a method of changing the game character face in the game system.

종래의 온라인 게임, 비디오 게임 및 아케이드 게임, 또는 1(혹은 3)인칭 사격게임, 레이싱 게임, 전략시뮬레이션 게임 및 댄스 게임 등과 같은 다양한 장르의 게임을 즐길 수 있는 게임 시스템에서 게임 사용자의 다양한 2D 혹은 3D 캐릭터 제작에 적용 가능한 얼굴 검출, 얼굴 특징점 추출, 2D 캐릭터화 및 2D 얼굴정보로부터 3D 얼굴 생성에 관한 연구는 다음의 자료에 잘 나와 있다.A variety of 2D or 3D gamers in game systems that can enjoy a variety of genres of games such as conventional online games, video games and arcade games, or first (or third) first person shooting games, racing games, strategy simulation games, and dance games. Studies on face detection, facial feature point extraction, 2D characterization, and 3D face generation from 2D face information applicable to character production are well described in the following data.

첫째로, 레인-리엔 흐수(Rein-Lien Hsu) 등에 의해 제안된 얼굴 검출 방법(Rein-Lien Hsu, Abdel-Mottaleb, M. Jain, A.K., "Face detection in color images", Pattern Analysis and Machine Intelligence, IEEE Transactions on Volume 24, Issue 5, Page(s):696 - 706, 2002)은 얼굴 영역을 색상을 이용하여 검출하는 방법으로, 기존의 RGB 색상 좌표계에서는 피부색의 분포가 얼굴 영역을 한정짓는데 어려움이 따르므로 YCbCr과 같은 다른 좌표계로 변환하여 검출하지만, 이 방법은 정교한 얼굴 영역 검출이 어렵다.First, the face detection method proposed by Rein-Lien Hsu et al. (Rein-Lien Hsu, Abdel-Mottaleb, M. Jain, AK, "Face detection in color images", Pattern Analysis and Machine Intelligence , IEEE Transactions on Volume 24, Issue 5, Page (s): 696-706, 2002), is a method of detecting the face area using color.In the conventional RGB color coordinate system, the distribution of skin color defines the face area. The difficulty is due to the conversion to other coordinate systems such as YCbCr for detection, but this method is difficult to detect sophisticated face areas.

둘째로, 리커트 티.디.(Rikert, T.D.) 등에 의해 제안된 얼굴 특징점 추출 방법(Rikert, T.D., Jones, M.J., Viola, P., "A cluster-based statistical model for object detection", Computer Vision, 1999. The Proceedings of the Seventh IEEE International Conference on Volume 2, Page(s):1046 - 1053, 1999)은 얼굴을 통계적인 자료를 바탕으로 다중스케일과 다중해상도의 필터들을 가우시안 혼합 방법을 통하여 생성하여 특징점을 추출하지만, 이 방법은 학습 영상에 의존하는 경향이 크며 그 처리시간과 계산식이 복잡하다.Second, the facial feature extraction method proposed by Rikert, TD et al. (Rikert, TD, Jones, MJ, Viola, P., "A cluster-based statistical model for object detection", Computer Vision , 1999. The Proceedings of the Seventh IEEE International Conference on Volume 2, Page (s): 1046-1053, 1999) generate face-to-face statistical data using Gaussian blending of multiscale and multiresolution filters. The feature points are extracted, but this method tends to depend on the learning images, and the processing time and calculation formulas are complicated.

셋째로, 제이.리우(J. Liu) 등에 의해 제안된 2D 캐릭터화 방법(J. Liu, Y. Chen, W. Gao, R. Fu, and R. Zhou, "Craetive cartoon face synthesis system for mobile entertainment," LNCS 3768, Page(s):1027-1038, 2005)은 캐리커처 영상이 실사에 대한 단순한 이진 영상(binary image)으로만 표현되기 때문에 사용자 흥미도가 다소 떨어진다.Third, the 2D characterization method proposed by J. Liu et al. (J. Liu, Y. Chen, W. Gao, R. Fu, and R. Zhou, "Craetive cartoon face synthesis system for mobile entertainment , " LNCS 3768 , Page (s): 1027-1038, 2005) is less interesting to users because the caricature image is represented only as a simple binary image of the live action.

넷째로, 브이.블란즈와 티. 베터(V. Blanz and T. Vetter)에 의해 제안된 2D 얼굴정보로부터 3D 얼굴 생성 방법(V. Blanz and T. Vetter, "A Morphable model for the synthesis of 3D faces," Computer Graphics Proc . SIGGRAPH, Page(s):187-194, 1999)은 2D 얼굴정보가 입력되면 3D 형상화(Morphable) 모델을 사용하여 3D 얼굴 영상을 생성하는 방법에 관한 것이며, 얼굴 영상에서 초기 특징점들의 위치를 얼굴검출단계에서 결정하지 못하기 때문에 별도의 수작업이 필요하고, 2D 영상을 3D 얼굴로 맞추기(fitting) 하는데 많은 시간이 소비되어 실시간 게임 시스템에 적용하는데 어려움이 있다.Fourth, V. Blancs and T. V. Blanz and T. Vetter, "A Morphable model for the synthesis of 3D faces," Computer proposed by V. Blanz and T. Vetter Graphics Proc . SIGGRAPH , Page (s): 187-194, 1999) relates to a method of generating a 3D face image using a 3D Morphable model when 2D face information is input, and detecting the position of initial feature points in the face image. Since it is not possible to decide at the stage, a separate manual work is required, and a lot of time is required to fit a 2D image into a 3D face, which makes it difficult to apply to a real-time game system.

한편, 상기와 같은 얼굴 검출 방법, 얼굴 특징점 추출 방법, 2D 캐릭터화 방법 및 2D 얼굴정보로부터 3D 얼굴 생성 방법 등이 적용되는 종래의 게임 시스템에서는 게임 사용자가 자신의 고유한 2D 혹은 3D 게임 캐릭터를 게임 제작사의 의도에 따라 미리 특정하게 만들어진 게임 캐릭터들 중에서 선택하여 사용한다.Meanwhile, in the conventional game system to which the above-described face detection method, facial feature point extraction method, 2D characterization method, and 3D face generation method from 2D face information are applied, a game user plays his or her own 2D or 3D game character. According to the intention of the producer, select from among the game characters that have been created in advance.

이 경우, 근본적으로 게임 사용자가 선택할 수 있는 게임 캐릭터의 수가 제한되므로 사용자 입장에서 게임의 흥미를 잃기 쉽고 몰입감이 낮아지는 단점이 있으며, 이로 인해 게임 이용 시간이 감소하면서 게임 제작사의 게임 시스템 매출 저 하가 초래될 수 있다.In this case, since the number of game characters that can be selected by the game user is fundamentally limited, it is easy for the user to lose interest in the game and the immersion is lowered. May result.

본 발명은 상기한 바와 같은 종래의 문제점을 해결하기 위한 것으로서, 본 발명의 목적은 카메라나 사진 등을 통해 취득하여 선택한 얼굴 영상으로부터 얼굴 영역 및 얼굴 특징점을 추출하고, 추출된 2D 얼굴(및 얼굴 특징점)정보를 게임 캐릭터의 2D 얼굴에 직접 매핑(mapping)하거나, 추가로 캐릭터화한 후 게임 캐릭터의 얼굴에 매핑하거나 혹은, 추출된 2D 얼굴(및 얼굴 특징점)정보로부터 3D 얼굴정보를 생성하여 3D 게임 캐릭터의 얼굴에 매핑함으로써 게임 시스템에서 사용되는 게임 캐릭터의 2D 혹은 3D 얼굴을 변경하는 게임 시스템에서의 게임 캐릭터 얼굴 변경 방법을 제공하는 것이다.SUMMARY OF THE INVENTION The present invention has been made to solve the above-described problems, and an object of the present invention is to extract a face region and a facial feature point from a selected face image acquired through a camera or a photograph, and extract the extracted 2D face (and facial feature point). Mapping the information directly to the 2D face of the game character, further characterizing and mapping to the face of the game character, or generating 3D face information from the extracted 2D face (and facial feature points) information to create a 3D game. The present invention provides a method of changing a game character face in a game system that changes a 2D or 3D face of a game character used in a game system by mapping the character's face.

상기한 바와 같은 본 발명의 목적을 달성하기 위하여, 본 발명의 제1실시예에 따른 게임 시스템에서의 게임 캐릭터 얼굴 변경 방법은, 선택된 얼굴 영상으로부터 얼굴 영역 및 얼굴 특징점들을 추출하는 단계; 및 추출된 2D 얼굴정보 및 얼굴 특징점정보를 게임 사용자가 선택한 특정 게임 캐릭터의 2D 얼굴에 직접 매핑(mapping)하여 게임 사용자가 선택한 게임 캐릭터의 2D 얼굴을 변경하는 단계;로 이루어지는 것을 특징으로 한다.In order to achieve the object of the present invention as described above, the game character face change method in the game system according to the first embodiment of the present invention, extracting a face region and facial feature points from the selected face image; And mapping the extracted 2D face information and facial feature point information directly to the 2D face of the specific game character selected by the game user to change the 2D face of the game character selected by the game user.

상기한 바와 같은 본 발명의 목적을 달성하기 위하여, 본 발명의 제2실시예 에 따른 게임 시스템에서의 게임 캐릭터 얼굴 변경 방법은, 선택된 얼굴 영상으로부터 얼굴 영역 및 얼굴 특징점들을 추출하는 단계와; 추출된 2D 얼굴정보 및 얼굴 특징점정보를 캐릭터화하여 2D 캐리커처를 생성하는 단계; 및 생성된 2D 캐리커처를 게임 사용자가 선택한 특정 게임 캐릭터의 2D 얼굴에 매핑(mapping)하여 게임 사용자가 선택한 게임 캐릭터의 2D 얼굴을 변경하는 단계;로 이루어지는 것을 특징으로 한다.In order to achieve the object of the present invention as described above, the game character face change method in the game system according to the second embodiment of the present invention, the method comprising the steps of extracting the face region and facial feature points from the selected face image; Characterizing the extracted 2D face information and facial feature point information to generate a 2D caricature; And mapping the generated 2D caricature to the 2D face of the specific game character selected by the game user to change the 2D face of the game character selected by the game user.

상기한 바와 같은 본 발명의 목적을 달성하기 위하여, 본 발명의 제3실시예에 따른 게임 시스템에서의 게임 캐릭터 얼굴 변경 방법은, 선택된 얼굴 영상으로부터 얼굴 영역 및 얼굴 특징점들을 추출하는 단계와; 추출된 2D 얼굴정보 및 얼굴 특징점정보로부터 3D 얼굴을 생성하는 단계; 및 생성된 3D 얼굴을 게임 사용자가 선택한 특정 게임 캐릭터의 3D 얼굴에 매핑(mapping)하여 게임 사용자가 선택한 게임 캐릭터의 3D 얼굴을 변경하는 단계;로 이루어지는 것을 특징으로 한다.In order to achieve the object of the present invention as described above, the game character face change method in the game system according to the third embodiment of the present invention, the method comprising the steps of extracting the face region and facial feature points from the selected face image; Generating a 3D face from the extracted 2D face information and facial feature point information; And changing the 3D face of the game character selected by the game user by mapping the generated 3D face to the 3D face of the specific game character selected by the game user.

상기한 바와 같은 본 발명의 목적을 달성하기 위하여, 본 발명의 제4실시예에 따른 게임 시스템에서의 게임 캐릭터 얼굴 변경 방법은, 선택된 얼굴 영상으로부터 얼굴 영역 및 얼굴 특징점들을 추출하는 단계와; 추출된 2D 얼굴정보 및 얼굴 특징점정보로부터 표준 3D 모델에 맞추어진 2D 얼굴을 생성하는 단계; 및 생성된 2D 얼굴을 게임 사용자가 선택한 특정 게임 캐릭터의 3D 얼굴에 텍스처 매핑(texture mapping)하여 게임 사용자가 선택한 게임 캐릭터의 3D 얼굴을 변경하는 단계;로 이루어지는 것을 특징으로 한다.In order to achieve the object of the present invention as described above, the game character face change method in the game system according to the fourth embodiment of the present invention comprises the steps of: extracting the face region and facial feature points from the selected face image; Generating a 2D face adapted to the standard 3D model from the extracted 2D face information and facial feature point information; And changing the 3D face of the game character selected by the game user by texture mapping the generated 2D face to the 3D face of the specific game character selected by the game user.

이하, 본 발명의 제1실시예, 제2실시예, 제3실시예, 및 제4실시예를 첨부된 도면을 참조하여 더욱 상세하게 설명한다.Hereinafter, a first embodiment, a second embodiment, a third embodiment, and a fourth embodiment of the present invention will be described in more detail with reference to the accompanying drawings.

도 1은 본 발명에 따른 게임 시스템에서의 게임 캐릭터 얼굴 변경 방법을 나타낸 플로차트로서, 상기한 본 발명의 제1실시예, 제2실시예, 제3실시예, 및 제4실시예를 모두 나타내고 있으며, S10, S20, S30 과정은 4개의 실시예에서 모두 공통으로 수행하는 과정이다.1 is a flowchart showing a method of changing a game character face in a game system according to the present invention, and shows all of the first, second, third, and fourth embodiments of the present invention. , S10, S20, and S30 processes are commonly performed in all four embodiments.

도 2는 본 발명에 따른 게임 시스템에서의 게임 캐릭터 얼굴 변경 방법을 게임 시스템에 적용하는 과정을 나타낸 실시예로서, 게임 시스템에서 사용되는 게임 캐릭터의 2D 혹은 3D 얼굴을 카메라나 사진 등을 통해 취득하여 선택한 얼굴 영상(예컨대, 게임 사용자 자신의 얼굴 영상, 타인의 얼굴 영상 등)을 이용하여 변경하는 과정을 나타내고 있다.2 is a view illustrating a process of applying a game character face changing method in a game system according to the present invention to a game system, wherein a 2D or 3D face of a game character used in the game system is acquired through a camera or a photograph. The process of changing using the selected face image (eg, a face image of a game user, a face image of another person, etc.) is shown.

도 1을 참조하면, 본 발명의 제1실시예, 제2실시예, 제3실시예, 및 제4실시예는 모두, 가장 먼저 카메라나 사진 등을 통해 게임 캐릭터 얼굴 변경을 위한 얼굴 영상을 취득하여 선택하고(S10), 선택한 얼굴 영상으로부터 얼굴 영역 및 얼굴 특징점들을 추출한다(S20,S30).Referring to FIG. 1, the first, second, third, and fourth embodiments of the present invention all acquire face images for changing the face of a game character through a camera or a photograph. In step S10, the face region and the facial feature points are extracted from the selected face image (S20 and S30).

이때, 카메라로는 일반적인 CCD 혹은 CMOS PC 카메라, 감시용 CCTV 카메라, 디지털 카메라 및 휴대폰 카메라 등을 이용할 수 있다.In this case, a general CCD or CMOS PC camera, a surveillance CCTV camera, a digital camera and a mobile phone camera may be used as the camera.

또한, 상기 얼굴 영상으로부터 얼굴 영역 검출을 위해서는 얼굴의 구역별 명암 대비를 이용한 학습을 통해 템플릿을 생성하여 빠르고 정교하게 얼굴을 검출하는 아다부스트 얼굴 검출(AdaBoost Face Detection) 방법, PCA(Principal Component Analysis) 기반 얼굴 검출 방법, ICA(Independent Component Analysis) 기반 얼굴 검출 방법 등을 사용할 수 있고, 얼굴 영역 검출의 정교함을 향상하기 위해 얼굴 조명 정규화(예컨대, Homomorphic Filtering 등) 과정이 수행될 수 있다.In addition, in order to detect a face region from the face image, an AdaBoost Face Detection method, a PCA (Principal Component Analysis) method for quickly and precisely detecting a face by generating a template through learning using contrast of each region of the face Based face detection method, independent component analysis (ICA) based face detection method, etc. may be used, and face illumination normalization (eg, homomorphic filtering, etc.) may be performed to improve the sophistication of face area detection.

또한, 검출된 얼굴 영역에서 빠르고 정교하게 얼굴 특징점을 추출하는 AAM(Active Appearance Model)을 이용하는 학습 기반 얼굴 특징점 추출 방법으로 양 눈꼬리, 양눈, 코, 입선, 얼굴 윤곽선, 머리 헤어 라인 전체 혹은 이중 일부 등을 얼굴 특징점으로 추출할 수 있다.In addition, it is a learning-based facial feature extraction method using AAM (Active Appearance Model) that extracts facial feature points quickly and precisely from detected face areas. Can be extracted as a facial feature point.

상기와 같이 카메라나 사진 등을 통해 취득하여 선택된 얼굴 영상으로부터 얼굴 영역 및 얼굴 특징점들을 추출한 상태에서, 본 발명의 제1실시예, 제2실시예, 제3실시예, 및 제4실시예에 따라 각각 게임 시스템에서의 게임 캐릭터 얼굴 변경 방법이 수행되는 과정을 구체적으로 설명하면 다음과 같다.According to the first embodiment, the second embodiment, the third embodiment, and the fourth embodiment of the present invention in the state in which the face region and the facial feature points are extracted from the selected face image acquired through a camera or a photograph as described above A process of performing a game character face change method in each game system will be described in detail as follows.

첫째로, 본 발명의 제1실시예에서는 상기와 같이 카메라나 사진 등을 통해 취득하여 선택한 얼굴 영상으로부터 얼굴 영역 및 얼굴 특징점들을 추출되고 나면(S10∼S30), 게임 캐릭터 변경을 위해 선택한 얼굴 영상으로부터 추출된 2D 얼굴정보 및 얼굴 특징점정보를 게임 사용자가 선택한 특정 게임 캐릭터의 2D 얼굴에 직접 매핑(mapping)하여 게임 사용자가 선택한 게임 캐릭터의 2D 얼굴을 변경한다(S40.S42).First, in the first embodiment of the present invention, after extracting a face region and facial feature points from a face image acquired through a camera or a photograph as described above (S10 to S30), from the face image selected for game character change, The extracted 2D face information and facial feature point information are directly mapped to the 2D face of the specific game character selected by the game user to change the 2D face of the game character selected by the game user (S40.S42).

둘째로, 본 발명의 제2실시예에서는 상기와 같이 카메라나 사진 등을 통해 취득하여 선택한 얼굴 영상으로부터 얼굴 영역 및 얼굴 특징점들을 추출되고 나면(S10∼S30), 게임 캐릭터 변경을 위해 선택한 얼굴 영상으로부터 추출된 2D 얼굴정보 및 얼굴 특징점정보를 캐릭터화하여 2D 캐리커처를 생성한다(S50).Secondly, in the second embodiment of the present invention, after extracting a face region and facial feature points from a face image acquired through a camera or a photograph as described above (S10 to S30), from the face image selected for changing the game character, The 2D caricature is generated by characterizing the extracted 2D face information and facial feature point information (S50).

이때, 도 3에 나타낸 바와 같이, 게임 캐릭터 디자인 전문가에 의해 사전에 게임 캐릭터의 얼굴 특징 정보를 DB화 해놓고 게임 캐릭터 변경을 위해 선택한 얼굴 영상으로부터 추출된 2D 얼굴 특징점들 사이의 유사도(예컨대, 유클리디안(Euclidian) 거리 등) 및 형태 정보 등을 기반으로 기 저장된 게임 캐릭터의 얼굴 특징 정보와의 매칭(matching) 및 융합을 통해 2D 캐리커처를 생성할 수 있다.In this case, as shown in FIG. 3, the similarity between the 2D face feature points extracted from the face image selected for the game character change by DB of the face feature information of the game character by the game character design expert in advance (eg, Euclid). 2D caricature may be generated through matching and fusion with facial feature information of pre-stored game characters based on dianclinic distance, etc.) and shape information.

또한, 도 4에 나타내 바와 같이, 게임 캐릭터 디자인 전문가에 의해 사전에 게임 캐릭터의 얼굴 특징 영역 정보를 DB화 해놓고 게임 캐릭터 변경을 위해 선택한 얼굴 영상으로부터 추출된 게임 사용자의 2D 얼굴 특징점정보를 얼굴 특징 영역으로 변환한 후, 이 얼굴 특징 영역의 변환계수들간의 유사도(예컨대, 유클리디안(Euclidian) 거리 등) 정보 등을 기반으로 기 저장된 게임 캐릭터의 얼굴 특징 영역 정보와의 매칭(matching) 및 융합을 통해 2D 캐리커처를 생성할 수 있다. 특히, 이 경우 PCA(Principal Component Analysis) 기반 얼굴 특징 영역 변환 방법, ICA(Independent Component Analysis) 기반 얼굴 특징 영역 변환 방법, LFA(Local Feature Analysis) 기반 얼굴 특징 영역 변환 방법 등을 사용하여 얼굴 특징 영역을 추출할 수 있다.In addition, as shown in FIG. 4, the facial feature region is obtained by the game character design expert in advance, and the game user's 2D facial feature point information extracted from the face image selected for the game character change is made into the DB. After conversion to, the matching and fusion with the face feature region information of the previously stored game character is performed based on the similarity (for example, Euclidian distance, etc.) information among the transformation coefficients of the face feature region. This allows you to create 2D caricatures. In particular, in this case, the facial feature region may be modified using a principal component analysis (PCA) based facial feature region transformation method, an independent component analysis (ICA) based facial feature region transformation method, or a local feature analysis (LFA) based facial feature region transformation method. Can be extracted.

이어서, 생성된 2D 캐리커처를 게임 사용자가 선택한 특정 게임 캐릭터의 2D 얼굴에 매핑(mapping)하여 게임 사용자가 선택한 게임 캐릭터의 2D 얼굴을 변경한 다(S52.S54).Subsequently, the generated 2D caricature is mapped to the 2D face of the specific game character selected by the game user to change the 2D face of the game character selected by the game user (S52.S54).

셋째로, 본 발명의 제3실시예에서는 상기와 같이 카메라나 사진 등을 통해 취득하여 선택한 얼굴 영상으로부터 얼굴 영역 및 얼굴 특징점들을 추출되고 나면(S10∼S30), 게임 캐릭터 변경을 위해 선택한 얼굴 영상으로부터 추출된 2D 얼굴정보 및 얼굴 특징점정보로부터 3D 얼굴을 생성한다(S60).Third, in the third embodiment of the present invention, after extracting the face region and the facial feature points from the face image acquired through the camera or the photograph as described above (S10 to S30), from the face image selected for changing the game character, A 3D face is generated from the extracted 2D face information and facial feature point information (S60).

이때, AAM(Active Appearance Model) 혹은 영상기반 3D 얼굴 모델링 기술 등을 사용하여 3D 얼굴을 생성할 수 있다.In this case, a 3D face may be generated using an AAM (Active Appearance Model) or an image-based 3D face modeling technology.

이어서, 생성된 3D 얼굴을 게임 사용자가 선택한 특정 게임 캐릭터의 3D 얼굴에 매핑(mapping)하여 게임 사용자가 선택한 게임 캐릭터의 3D 얼굴을 변경한다(S62.S64).Subsequently, the generated 3D face is mapped to the 3D face of the specific game character selected by the game user to change the 3D face of the game character selected by the game user (S62.S64).

넷째로, 본 발명의 제4실시예에서는 상기한 제3실시예와 비교해 볼 때 게임 시스템의 처리 속도를 더욱 향상시키기 위하여 3D 게임 캐릭터의 얼굴을 2D 얼굴로 대체하는 방법으로, 상기와 같이 카메라나 사진 등을 통해 취득한 얼굴 영상으로부터 얼굴 영역 및 얼굴 특징점들을 추출되고 나면(S10∼S30), 게임 캐릭터 변경을 위해 선택한 얼굴 영상으로부터 추출된 2D 얼굴정보 및 얼굴 특징점정보로부터 표준 3D 모델에 맞추어진 2D 얼굴을 생성한다(S70).Fourth, the fourth embodiment of the present invention is a method of replacing the face of the 3D game character with a 2D face in order to further improve the processing speed of the game system as compared with the above-described third embodiment. After the face region and the facial feature points are extracted from the face image acquired through the photograph or the like (S10 to S30), the 2D face is fitted to the standard 3D model from the 2D face information and the facial feature point information extracted from the face image selected for the game character change. To generate (S70).

이어서, 생성된 2D 얼굴을 게임 사용자가 선택한 특정 게임 캐릭터의 3D 얼굴에 텍스처 매핑(texture mapping)하여 게임 사용자가 선택한 게임 캐릭터의 3D 얼굴을 변경한다(S72.S74).Subsequently, the generated 2D face is texture mapped to the 3D face of the specific game character selected by the game user to change the 3D face of the game character selected by the game user (S72.S74).

이상에서 설명한 본 발명에 따른 게임 시스템에서의 게임 캐릭터 얼굴 변경 방법은 상기한 실시예에 한정되지 않고, 이하의 특허청구범위에서 청구하는 본 발명의 요지를 벗어남이 없이 본 발명이 속하는 분야에서 통상의 지식을 가진 자라면 누구든지 다양하게 변경하여 실시할 수 있는 범위까지 그 기술적 정신이 있다.The method of changing the game character face in the game system according to the present invention described above is not limited to the above-described embodiments, and is common in the field of the present invention without departing from the gist of the present invention as claimed in the following claims. Anyone with knowledge has the technical spirit to the extent that various changes can be made.

이상에서 설명한 바와 같이, 본 발명은 게임 사용자가 선택한 얼굴 영상(예컨대, 게임 사용자 자신의 얼굴 영상, 타인의 얼굴 영상 등)을 기반으로 게임 캐릭터의 얼굴을 변경하므로 게임의 흥미를 증대할 수 있으며, 특히 게임 사용자가 마치 가상공간에서 자신이 직접 동작을 하는 듯한 몰입감을 부여하므로 게임 사용자의 게임 이용 시간을 증대시키고 이를 통해 게임 시스템의 매출을 증대시킬 수 있게 된다.As described above, the present invention can increase the interest of the game by changing the face of the game character based on the face image selected by the game user (for example, the face image of the game user, the face image of others), In particular, the game user gives an immersive feeling as if they are directly operating in a virtual space, thereby increasing the game user's game use time and thereby increasing the sales of the game system.

Claims (10)

선택된 얼굴 영상으로부터 얼굴 영역 및 얼굴 특징점들을 추출하는 단계; 및Extracting face regions and facial feature points from the selected face image; And 추출된 2D 얼굴정보 및 얼굴 특징점정보를 게임 사용자가 선택한 특정 게임 캐릭터의 2D 얼굴에 직접 매핑(mapping)하여 게임 사용자가 선택한 게임 캐릭터의 2D 얼굴을 변경하는 단계;Mapping the extracted 2D face information and facial feature point information to a 2D face of a specific game character selected by the game user to change the 2D face of the game character selected by the game user; 로 이루어지는 것을 특징으로 하는 게임 시스템에서의 게임 캐릭터 얼굴 변경 방법.Game character face change method in the game system, characterized in that consisting of. 선택된 얼굴 영상으로부터 얼굴 영역 및 얼굴 특징점들을 추출하는 단계와;Extracting face regions and facial feature points from the selected face image; 추출된 2D 얼굴정보 및 얼굴 특징점정보를 캐릭터화하여 2D 캐리커처를 생성하는 단계; 및Characterizing the extracted 2D face information and facial feature point information to generate a 2D caricature; And 생성된 2D 캐리커처를 게임 사용자가 선택한 특정 게임 캐릭터의 2D 얼굴에 매핑(mapping)하여 게임 사용자가 선택한 게임 캐릭터의 2D 얼굴을 변경하는 단계;Mapping the generated 2D caricature to the 2D face of the specific game character selected by the game user to change the 2D face of the game character selected by the game user; 로 이루어지는 것을 특징으로 하는 게임 시스템에서의 게임 캐릭터 얼굴 변경 방법.Game character face change method in the game system, characterized in that consisting of. 제 2 항에 있어서, 상기 추출된 2D 얼굴정보 및 얼굴 특징점정보를 캐릭터화 하여 2D 캐리커처를 생성하는 단계에서는,The method of claim 2, wherein in the step of characterizing the extracted 2D face information and facial feature point information to generate a 2D caricature, 사전에 게임 캐릭터의 얼굴 특징 정보를 DB화 해놓고 상기 선택된 얼굴 영상으로부터 추출된 2D 얼굴 특징점들 사이의 유사도 및 형태 정보를 기반으로 기 저장된 게임 캐릭터의 얼굴 특징 정보와의 매칭(matching) 및 융합을 통해 2D 캐리커처를 생성하는 것을 특징으로 하는 게임 시스템에서의 게임 캐릭터 얼굴 변경 방법.Based on the DB of the feature data of the game character in advance and matching and fusion with the face feature information of the game character previously stored based on the similarity and shape information between the 2D face feature points extracted from the selected face image. A method of changing a game character face in a game system, characterized by generating a 2D caricature. 제 2 항에 있어서, 상기 추출된 2D 얼굴정보 및 얼굴 특징점정보를 캐릭터화하여 2D 캐리커처를 생성하는 단계에서는,The method of claim 2, wherein in the step of characterizing the extracted 2D face information and facial feature point information to generate a 2D caricature, 사전에 게임 캐릭터의 얼굴 특징 영역 정보를 DB화 해놓고 상기 선택된 얼굴 영상으로부터 추출된 2D 얼굴 특징점정보를 얼굴 특징 영역으로 변환한 후, 이 얼굴 특징 영역의 변환계수들간의 유사도 정보를 기반으로 기 저장된 게임 캐릭터의 얼굴 특징 영역 정보와의 매칭(matching) 및 융합을 통해 2D 캐리커처를 생성하는 것을 특징으로 하는 게임 시스템에서의 게임 캐릭터 얼굴 변경 방법.After converting the facial feature area information of the game character into a DB in advance, converting the 2D facial feature point information extracted from the selected face image into the facial feature area, and then pre-stored the game based on the similarity information between the conversion coefficients of the facial feature area. A method of changing a game character face in a game system, characterized by generating a 2D caricature through matching and fusion with character feature information of a face. 제 4 항에 있어서, 사전에 게임 캐릭터의 얼굴 특징 영역 정보를 DB화 해놓고 추출된 2D 얼굴 특징점정보를 얼굴 특징 영역으로 변환할 때, The method according to claim 4, wherein when converting the extracted 2D facial feature point information into a facial feature region by preforming a DB of the facial feature region information of the game character in advance, PCA(Principal Component Analysis) 기반 얼굴 특징 영역 변환 방법, ICA(Independent Component Analysis) 기반 얼굴 특징 영역 변환 방법, LFA(Local Feature Analysis) 기반 얼굴 특징 영역 변환 방법 중 어느 하나를 사용하여 얼굴 특징 영역을 추출하는 것을 특징으로 하는 게임 시스템에서의 게임 캐릭터 얼굴 변경 방법.Extracting a facial feature region by using any one of a principal component analysis (PCA) based facial feature region transformation method, an independent component analysis (ICA) based facial feature region transformation method, and a local feature analysis (LFA) based facial feature region transformation method A method of changing a game character face in a game system, characterized in that. 선택된 얼굴 영상으로부터 얼굴 영역 및 얼굴 특징점들을 추출하는 단계와;Extracting face regions and facial feature points from the selected face image; 추출된 2D 얼굴정보 및 얼굴 특징점정보로부터 3D 얼굴을 생성하는 단계; 및Generating a 3D face from the extracted 2D face information and facial feature point information; And 생성된 3D 얼굴을 게임 사용자가 선택한 특정 게임 캐릭터의 3D 얼굴에 매핑(mapping)하여 게임 사용자가 선택한 게임 캐릭터의 3D 얼굴을 변경하는 단계;Mapping the generated 3D face to the 3D face of the specific game character selected by the game user to change the 3D face of the game character selected by the game user; 로 이루어지는 것을 특징으로 하는 게임 시스템에서의 게임 캐릭터 얼굴 변경 방법.Game character face change method in the game system, characterized in that consisting of. 제 6 항에 있어서, 상기 추출된 2D 얼굴정보 및 얼굴 특징점정보로부터 3D 얼굴을 생성하는 단계에서는,The method of claim 6, wherein the generating of the 3D face from the extracted 2D face information and facial feature point information comprises: AAM(Active Appearance Model) 혹은 영상기반 3D 얼굴 모델링 기술을 사용하여 3D 얼굴을 생성하는 것을 특징으로 하는 게임 시스템에서의 게임 캐릭터 얼굴 변경 방법.A method of changing a game character face in a game system, wherein the 3D face is generated using an AAM (Active Appearance Model) or an image-based 3D face modeling technique. 선택된 얼굴 영상으로부터 얼굴 영역 및 얼굴 특징점들을 추출하는 단계와;Extracting face regions and facial feature points from the selected face image; 추출된 2D 얼굴정보 및 얼굴 특징점정보로부터 표준 3D 모델에 맞추어진 2D 얼굴을 생성하는 단계; 및Generating a 2D face adapted to the standard 3D model from the extracted 2D face information and facial feature point information; And 생성된 2D 얼굴을 게임 사용자가 선택한 특정 게임 캐릭터의 3D 얼굴에 텍스처 매핑(texture mapping)하여 게임 사용자가 선택한 게임 캐릭터의 3D 얼굴을 변경하는 단계;Changing the 3D face of the game character selected by the game user by texture mapping the generated 2D face to the 3D face of the specific game character selected by the game user; 로 이루어지는 것을 특징으로 하는 게임 시스템에서의 게임 캐릭터 얼굴 변경 방법.Game character face change method in the game system, characterized in that consisting of. 제 1 항, 제 2 항, 제 6 항 또는 제 8 항 중 어느 한 항에 있어서, 상기 선택된 얼굴 영상으로부터 얼굴 영역 및 얼굴 특징점들을 추출하는 단계에서는,The method of claim 1, 2, 6, or 8, wherein in the step of extracting a facial region and facial feature points from the selected face image, 아다부스트 얼굴 검출(AdaBoost Face Detection) 방법, PCA(Principal Component Analysis) 기반 얼굴 검출 방법, ICA(Independent Component Analysis) 기반 얼굴 검출 방법 중 어느 하나를 사용하여 얼굴 영역을 추출하는 것을 특징으로 하는 게임 시스템에서의 게임 캐릭터 얼굴 변경 방법.In a game system, the facial region is extracted using any one of an AdaBoost Face Detection method, a Principal Component Analysis (PCA) based face detection method, and an Independent Component Analysis (ICA) based face detection method. To change your game character face. 제 1 항, 제 2 항, 제 6 항 또는 제 8 항 중 어느 한 항에 있어서, 상기 선 택된 얼굴 영상으로부터 얼굴 영역 및 얼굴 특징점들을 추출하는 단계에서는,The method of claim 1, 2, 6, or 8, wherein in the step of extracting a facial region and facial feature points from the selected face image, AAM(Active Appearance Model)을 이용하는 학습 기반 얼굴 특징점 추출방법으로 양 눈꼬리, 양눈, 코, 입선, 얼굴 윤곽선, 머리 헤어 라인 전체 혹은 이중 일부를 얼굴 특징점으로 추출하는 것을 특징으로 하는 게임 시스템에서의 게임 캐릭터 얼굴 변경 방법.Learning-based facial feature point extraction method using AAM How to change face.
KR1020060133716A 2006-12-26 2006-12-26 Face Modification of Game Character in Game System KR100859315B1 (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
KR1020060133716A KR100859315B1 (en) 2006-12-26 2006-12-26 Face Modification of Game Character in Game System
PCT/KR2007/006611 WO2008078897A1 (en) 2006-12-26 2007-12-18 Face modification of game character in game system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
KR1020060133716A KR100859315B1 (en) 2006-12-26 2006-12-26 Face Modification of Game Character in Game System

Publications (2)

Publication Number Publication Date
KR20080059865A true KR20080059865A (en) 2008-07-01
KR100859315B1 KR100859315B1 (en) 2008-09-19

Family

ID=39562658

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1020060133716A KR100859315B1 (en) 2006-12-26 2006-12-26 Face Modification of Game Character in Game System

Country Status (2)

Country Link
KR (1) KR100859315B1 (en)
WO (1) WO2008078897A1 (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2011014467A3 (en) * 2009-07-29 2011-07-07 Microsoft Corporation Auto-generating a visual representation
WO2017003031A1 (en) * 2015-06-29 2017-01-05 김영자 Method for providing lifelike avatar emoticon-based ultralight data animation creation system, and terminal device providing lifelike avatar emoticon for implementing same
KR20190129476A (en) * 2018-05-11 2019-11-20 이재윤 Headline provision system using head and skin tone
CN111857697A (en) * 2020-05-29 2020-10-30 北京编程猫科技有限公司 Graphical programming implementation method and device based on cognitive AI

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH1166272A (en) * 1997-08-13 1999-03-09 Sony Corp Processor and processing method for image or voice and record medium
KR20010091743A (en) * 2000-03-17 2001-10-23 박호성 A formation method of an automatic caricature
KR20050033762A (en) * 2003-10-07 2005-04-13 골드피처 주식회사 Automatic caricature forming apparatus and the service method thereof
JP4474546B2 (en) 2004-10-05 2010-06-09 国立大学法人東京農工大学 Face shape modeling system and face shape modeling method
KR100629382B1 (en) * 2005-01-14 2006-09-29 (주)디지탈아이엔터테인먼트 Method for generating 3d avatar from 2d image on mobile communication terminal

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2011014467A3 (en) * 2009-07-29 2011-07-07 Microsoft Corporation Auto-generating a visual representation
CN102470274A (en) * 2009-07-29 2012-05-23 微软公司 Auto-generating a visual representation
WO2017003031A1 (en) * 2015-06-29 2017-01-05 김영자 Method for providing lifelike avatar emoticon-based ultralight data animation creation system, and terminal device providing lifelike avatar emoticon for implementing same
KR20190129476A (en) * 2018-05-11 2019-11-20 이재윤 Headline provision system using head and skin tone
CN111857697A (en) * 2020-05-29 2020-10-30 北京编程猫科技有限公司 Graphical programming implementation method and device based on cognitive AI

Also Published As

Publication number Publication date
KR100859315B1 (en) 2008-09-19
WO2008078897A1 (en) 2008-07-03

Similar Documents

Publication Publication Date Title
TWI708152B (en) Image processing method, device, and storage medium
TWI642306B (en) System and method for avatar generation, rendering and animation
CN112348969A (en) Display method and device in augmented reality scene, electronic equipment and storage medium
US20090087035A1 (en) Cartoon Face Generation
CN106778628A (en) A kind of facial expression method for catching based on TOF depth cameras
CN110942501B (en) Virtual image switching method and device, electronic equipment and storage medium
CN111638784B (en) Facial expression interaction method, interaction device and computer storage medium
CN109035415B (en) Virtual model processing method, device, equipment and computer readable storage medium
CN111182350B (en) Image processing method, device, terminal equipment and storage medium
CN113850168A (en) Fusion method, device and equipment of face pictures and storage medium
Kim et al. Exposing fake faces through deep neural networks combining content and trace feature extractors
CN114984585A (en) Method for generating real-time expression picture of game role
CN107469355A (en) Game image creation method and device, terminal device
KR20080059865A (en) Face modification of game character in game system
CN111383313B (en) Virtual model rendering method, device, equipment and readable storage medium
Reale et al. Using eye gaze, head pose, and facial expression for personalized non-player character interaction
JP6959459B2 (en) Learning device, foreground area estimation device, learning method, foreground area estimation method, and program
US20080122867A1 (en) Method for displaying expressional image
JP2003085571A (en) Coloring toy
CN114331906A (en) Image enhancement method and device, storage medium and electronic equipment
WO2022007130A1 (en) Multimedia playing system and method for application scene identification
Van Gool et al. Modeling shapes and textures from images: new frontiers
KR102316042B1 (en) Augmented reality content delivery methods and systems that multiple markers in 3D models are recognized
Krogh Building and generating facial textures using Eigen faces
Dang Nguyen Discrimination of computer generated versus natural human faces

Legal Events

Date Code Title Description
A201 Request for examination
E902 Notification of reason for refusal
E701 Decision to grant or registration of patent right
GRNT Written decision to grant
FPAY Annual fee payment

Payment date: 20120803

Year of fee payment: 5

FPAY Annual fee payment

Payment date: 20130709

Year of fee payment: 6

FPAY Annual fee payment

Payment date: 20140818

Year of fee payment: 7

FPAY Annual fee payment

Payment date: 20150922

Year of fee payment: 8

FPAY Annual fee payment

Payment date: 20170901

Year of fee payment: 10

LAPS Lapse due to unpaid annual fee