公开(公告)号：KR101868520B1

公开(公告)日：2018-06-19

申请号：KR1020120002119

申请日：2012-01-06

Applicant: 한국전자통신연구원 ,  연세대학교 산학협력단

Inventor： 이희경 ,  차지훈 ,  변혜란 ,  조선영

IPC: G06K9/00 ,  G06K9/46

Abstract: 본발명에따른손 제스처인식방법은, 깊이카메라를이용하여손 제스처에관련된관절정보를획득하는단계, 관절정보를이용하여, 구면좌표기반의방향요소정보를도출하는단계, 방향요소정보를이용하여, 복수의방향히스토그램을생성하는단계, 복수의방향히스토그램을결합하여, 결합방향히스토그램을생성하는단계및 결합방향히스토그램에랜덤결정포레스트(forest) 분류기를적용하여, 손제스처에대한최종인식결과를도출하는단계를포함한다. 본발명에의하면, 높은인식성능이제공될수 있다.

公开(公告)号：KR100456619B1

公开(公告)日：2004-11-10

申请号：KR1020010076638

申请日：2001-12-05

Applicant: 한국전자통신연구원

Inventor： 이경희 ,  정용화 ,  박치항 ,  변혜란

IPC: G06K9/00

CPC classification number: G06K9/00288

Abstract: A system for performing face registration and authentication using face information, and a method thereof. A set of readily distinguishable features for each user is selected at a registration step and only the set of features selected at the registration step is used at a face authentication step, whereby memory use according to unnecessary information and amount of data calculation for face authentication can be reduced. Thus, the present system has an advantage in that identity authentication through face authentication can be performed even under restricted environments of a USB token or smart card with limited resources. The present system further has advantages in that authentication performance is improved, as readily distinguishable feature information is used, and the time for face authentication is reduced, as face authentication is performed using the SVM built by using the optimal set of readily distinguishable features at a training step.

Abstract translation: 一种使用脸部信息进行脸部登记和认证的系统及其方法。 在注册步骤选择每个用户容易区分的一组特征，并且在脸部认证步骤仅使用在注册步骤选择的一组特征，由此根据不必要的信息和用于脸部认证的数据计算量使用存储器 减少。 因此，本系统具有的优点在于，即使在具有有限资源的USB令牌或智能卡的受限环境下，也可以执行通过人脸认证的身份认证。 本系统进一步具有如下优点，即由于使用容易区分的特征信息而改善了认证性能，并且减少了面部认证的时间，因为面部认证是使用通过使用一组易于区分的特征 训练步骤。

公开(公告)号：KR1020130081126A

公开(公告)日：2013-07-16

申请号：KR1020120002119

申请日：2012-01-06

Applicant: 한국전자통신연구원 ,  연세대학교 산학협력단

Inventor： 이희경 ,  차지훈 ,  변혜란 ,  조선영

IPC: G06T7/20

CPC classification number: G06K9/00389 ,  G06K9/4642

Abstract: PURPOSE: A method for recognizing hand gesture and an apparatus thereof are provided to improve recognition performance of hand gesture and to process hand gesture recognition in real-time, by being strong to direction change. CONSTITUTION: A hand gesture recognition device acquires joint information of a tested person, and obtains direction element information for each direction element from the acquired joint information (S110,S120). The device generates direction histogram for each element of a vector expressing hand pose (S130). The device combines a number of direction histograms having different quantization levels (S140). The device recognizes hand gesture using the generated combined direction histogram (S150). [Reference numerals] (AA) Start; (BB) End; (S110) Acquire joint information; (S120) Draw direction element information; (S130) Generate direction histogram; (S140) Generate combined direction histogram; (S150) Recognize hand gesture using a random decision forest sorter

Abstract translation: 目的：提供一种用于识别手势的方法及其装置，以通过强烈的方向改变来提高手势的识别性能并且实时处理手势识别。 构成：手势识别装置取得被测试者的联合信息，从获取的联合信息中获取各方向要素的方向要素信息（S110，S120）。 该装置为表示手势的矢量的每个元素生成方向直方图（S130）。 该装置组合具有不同量化级别的多个方向直方图（S140）。 设备使用所生成的组合方向直方图识别手势（S150）。 （附图标记）（AA）开始; （BB）结束; （S110）收购联合资料; （S120）绘制方向要素信息; （S130）生成方向直方图; （S140）生成组合方向直方图; （S150）使用随机决策林分类器识别手势

公开(公告)号：KR1020030046181A

公开(公告)日：2003-06-12

申请号：KR1020010076638

申请日：2001-12-05

Applicant: 한국전자통신연구원

Inventor： 이경희 ,  정용화 ,  박치항 ,  변혜란

IPC: G06K9/00

CPC classification number: G06K9/00288

Abstract: PURPOSE: A system and a method for registering and certifying a face using an SVM(Support Vector Machine) are provided to realize the identification through the face certification in a limited resource environment such as a USB(Universal Serial Bus) token or a smart card by reducing the memory use due to the unnecessary information and a data computing volume for the face certification. CONSTITUTION: An image input part(105) inputs a face image of the users registered to a certification system. A face and eye region extracting part(106) extracts the face and eye region for the image inputted from the image input part(105). A controller(110) divides the face image into a learning image and a tuning image, and generates a characteristic information set in the face image representing each gene for the learning and the tuning image. An SVM classifier(108) judges the face certification by comparing a characteristic vector, which is the most suitable characteristic set repeatedly measuring the suitableness through a characteristic set selection process using a gene algorithm, with the characteristic vector selected from the face image of other user.

Abstract translation: 目的：提供使用SVM（支持向量机）注册和认证面部的系统和方法，以在有限的资源环境（例如USB（通用串行总线）令牌或智能卡）中通过面部认证实现识别 通过减少由于不必要的信息的内存使用和用于面部认证的数据计算量。 构成：图像输入部（105）输入注册到认证系统的用户的脸部图像。 面部和眼睛区域提取部分（106）从用于从图像输入部分（105）输入的图像提取面部和眼睛区域。 控制器（110）将面部图像划分为学习图像和调谐图像，并且生成表示用于学习和调整图像的每个基因的面部图像中设置的特征信息。 SVM分类器（108）通过将通过使用基因算法的特征集选择处理重复测量适合度的最合适的特征集与从其他用户的脸部图像中选择的特征向量进行比较来判断面部认证 。

公开(公告)号：KR101751417B1

公开(公告)日：2017-06-27

申请号：KR1020150180709

申请日：2015-12-17

Applicant: 연세대학교 산학협력단 ,  한국전자통신연구원

Inventor： 변혜란 ,  임광용 ,  이수웅 ,  유호영

IPC: G06K9/00 ,  G06K9/46 ,  G06K9/62

Abstract: 본발명은사용자의자세또는포스쳐를인식하는장치및 그방법에관한것이다. 본발명에따른사용자자세인식장치는복수개의프레임영상에서차분영상을생성하고, 상기생성한차분영상에기초하여상기프레임영상에서움직임이존재하는모션영역을분할하는모션영역분할부; 상기프레임영상에서사용자의피부후보영역을분할하는피부후보영역분할부; 상기프레임영상에서상기피부후보영역과상기모션영역간에대응하는영역을피부영역으로검출하는피부영역검출부; 및상기프레임영상내 상기피부영역을분석하여상기사용자의자세또는제스쳐를인식하는사용자자세인식부를포함할수 있다.