公开(公告)号：KR101306576B1

公开(公告)日：2013-09-26

申请号：KR1020120127561

申请日：2012-11-12

Applicant: 재단법인대구경북과학기술원

Inventor： 이상헌 ,  손명규 ,  김동주 ,  김병민 ,  김현덕

IPC: G06K9/46 ,  G06K9/20

CPC classification number: G06K9/00228 ,  G06K9/00281 ,  G06K9/6274 ,  G06T7/11

Abstract: PURPOSE: A face recognition system robust to changes in lighting based on differential components is provided to recognize the face based on D2D-PCA considering differential components, thereby recognizing exactly the face regardless of a change of lighting. CONSTITUTION: A face recognition system divides a face image obtained from a camera into right and left images (120). The system obtains a left image characteristic matrix by using differential two-dimensional principal component analysis (D2D-PCA) considering differential components based on the left image (130). The system calculates a left image distance value showing a distance value of the left image characteristic matrix based on the left image characteristic matrix (140). The system obtains a right image characteristic matrix by using D2D-PCA considering differential components based on the right image (150). The system calculates a right image distance value showing a distance value of the right image characteristic matrix based on the right image characteristic matrix (160). The system recognizes the face based on an integrated value combining the right and left image distance values (180). [Reference numerals] (110) Obtain a face image; (120) Divide the face image into right and left images; (130) Obtain s a left image characteristic matrix by using a two-dimensional principal component analysis based on the left image considering differential components; (140) Calculate a left image distance value; (150) Obtain a right image characteristic matrix by using a two-dimensional principal component analysis based on the left image considering differential components; (160) Calculate a right image distance value; (170) Calculate an integration value; (180) Perform face recognition; (AA) Start; (BB) End

Abstract translation: 目的：提供基于差分组件对照明变化稳健的人脸识别系统，以识别基于D2D-PCA的面部差分组件，从而可以准确地识别面部，而不管照明的变化如何。 构成：脸部识别系统将从相机获得的脸部图像分成左右图像（120）。 该系统通过使用基于左图像的差分分量（130），通过使用微分二维主分量分析（D2D-PCA）来获得左图像特征矩阵。 系统基于左图像特征矩阵（140）计算表示左图像特征矩阵的距离值的左图像距离值。 系统通过使用基于正确图像的差分分量的D2D-PCA获得右图像特征矩阵（150）。 该系统基于右图像特征矩阵计算表示右图像特征矩阵的距离值的右图像距离值（160）。 系统基于组合右图像距离值和左图像距离值的积分值来识别面部（180）。 （附图标记）（110）获取脸部图像; （120）将脸部图像分为左右图像; （130）通过使用考虑到差分分量的基于左图像的二维主分量分析获得左图像特征矩阵; （140）计算左图像距离值; （150）通过使用考虑到差分分量的基于左图像的二维主分量分析来获得右图像特征矩阵; （160）计算右图像距离值; （170）计算积分值; （180）执行面部识别; （AA）开始; （BB）结束

公开(公告)号：KR101269107B1

公开(公告)日：2013-05-29

申请号：KR1020110115872

申请日：2011-11-08

Applicant: 재단법인대구경북과학기술원

Inventor： 손명규 ,  이상헌 ,  김병민 ,  이장우

IPC: G06T7/20

Abstract: 본발명은카메라를이용한손동작인식방법및 장치에관한것이다. 본발명에따르면, 카메라를통해촬영된손의기준점을검출하는단계와, 상기기준점이검출된손으로부터움직임이감지되면, 상기감지된움직임에대응되는손의궤적정보를저장하는단계와, 상기움직임이감지된손의현재위치와상기기준점사이의차이값을연산하여기 설정된제1 임계치와비교하는단계와, 상기차이값이상기제1 임계치이상인경우, 상기감지된움직임에대응되는손의궤적정보와기 저장된손동작별 궤적 DB를비교하는단계, 및상기궤적 DB로부터상기손의궤적정보와일치하는손동작을판별하는단계를포함하는카메라를이용한손동작인식방법및 장치를제공한다. 상기카메라를이용한손동작인식방법및 장치에따르면, 손이기준점으로부터멀어진정도를일차적으로판단한다음, 손이움직인궤적정보와기 저장된손동작별 궤적 DB를재차비교하여검증함에따라손동작의인식률을높일수 있는이점이있다.

公开(公告)号：KR1020130050672A

公开(公告)日：2013-05-16

申请号：KR1020110115874

申请日：2011-11-08

Applicant: 재단법인대구경북과학기술원

Inventor： 손명규 ,  이상헌 ,  김병민 ,  이장우

IPC: G06F3/03 ,  G06F3/041 ,  G06T7/00

CPC classification number: G06F3/011 ,  G06F3/017 ,  G06F3/0416 ,  G06F2203/011 ,  G06T7/00

Abstract: PURPOSE: A virtual touch method using a 3D camera and a device thereof are provided to implement a virtual touch mode without a special touch recognition device or touch display by using the 3D camera which recognizes a touch motion. CONSTITUTION: A first area detecting unit(110) detects a screen area differentiated from surrounding areas of a screen unit from an image of the screen unit. When a shape of a touch performer is sensed on the screen area is sensed, a second area detecting unit(120) detects a part of a body of the touch performer differentiated from the screen area from an image of a 3D camera. A touch determining unit(130) compares a depth value of the screen area with a depth value of the part of the body to determine a touch to the part of the body. [Reference numerals] (110) First area detecting unit; (120) Second area detecting unit; (130) Touch determining unit; (140) Operation control unit; (150) DB unit

Abstract translation: 目的：提供使用3D相机及其装置的虚拟触摸方法，以通过使用识别触摸运动的3D相机来实现无特殊触摸识别装置或触摸显示的虚拟触摸模式。 构成：第一区域检测单元（110）从屏幕单元的图像中检测与屏幕单元的周围区域不同的屏幕区域。 当检测到在屏幕区域上感测到触摸表演者的形状时，第二区域检测单元（120）从与3D相机的图像相区别的屏幕区域检测触摸执行者的身体的一部分。 触摸确定单元（130）将屏幕区域的深度值与身体的一部分的深度值进行比较，以确定对身体的一部分的触摸。 （附图标记）（110）第一区域检测单元; （120）第二区域检测单元; （130）触摸确定单元; （140）操作控制单元; （150）DB单元