-
公开(公告)号：KR1020140037464A
公开(公告)日：2014-03-27
申请号：KR1020120103599
申请日：2012-09-18
Applicant: 재단법인대구경북과학기술원
CPC classification number: G06F3/011 , G06F3/012 , G06F3/013 , G06F3/017 , G06F3/0304 , G06F3/0346 , G06F3/042 , G06T7/20
Abstract: The present invention relates to a user interface apparatus and a user interface method. The present invention provides a configuration including a detection unit for detecting at least one of a face direction and an eye direction of a user located at the front of a camera, a first area specifying unit for specifying a portion of a whole area of a screen to be manipulated by a user based on a direction information of the detection unit, a second area specifying unit for tracking the location of a hand input through the camera, estimating an area, in which the motion of the user is possible, from the whole area of a camera image, and specifying the area as a camera area, a location specifying unit for mapping the motion of the hand displayed in the screen area and the motion of the hand displayed in the camera area based on a moving distance information or a moving speed information, so that an icon is located at a target coordinate on the screen, and a recognition unit for recognizing the shape of the hand of the user input through the camera, and an executing unit for performing a command corresponding to the recognized shape of the hand in the part indicated by the icon. As described above, according to the present invention, even if the difference is made in resolution between the camera and the screen, the user can exactly move the icon to the location required by the user on the screen. [Reference numerals] (302) Face direction recognizing unit; (304) Eye direction recognizing unit; (310) Screen area specifying unit; (320) Camera area specifying unit; (330) Location specifying unit; (340) Recognition unit; (350) Executing unit; (360) Storage unit; (AA) Screen size/resolution; (BB) Camera resolution; (CC) Distance between camera and user; (DD) Hand movement distance informationi; (EE) Hand movement speed information
Abstract translation: 本发明涉及用户界面装置和用户界面方法。 本发明提供了一种配置，其包括用于检测位于相机前部的用户的脸部方向和眼睛方向中的至少一个的检测单元，用于指定屏幕的整个区域的一部分的第一区域指定单元 由用户基于检测单元的方向信息来操作;第二区域指定单元，用于跟踪通过照相机的手输入的位置，估计可能的用户的运动的区域 相机图像的区域，以及将该区域指定为相机区域，基于移动距离信息或位置指定单元，用于映射在屏幕区域中显示的手的运动和显示在相机区域中的手的运动的位置指定单元 移动速度信息，使得图标位于屏幕上的目标坐标上，以及识别单元，用于识别通过照相机输入的用户的手的形状，以及用于每个的执行单元 在由图标指示的部分中形成与所识别的手的形状相对应的命令。 如上所述，根据本发明，即使在相机和屏幕之间的分辨率上存在差异，用户可以将图标精确地移动到屏幕上用户所需的位置。 （附图标记）（302）面部方向识别单元; （304）眼睛识别单元; （310）屏幕区域指定单元; （320）相机区域指定单元; （330）位置指定单元; （340）识别单位; （350）执行单位; （360）存储单元; （AA）屏幕尺寸/分辨率; （BB）相机分辨率; （CC）相机与用户之间的距离; （DD）手动距离信息; （EE）手动速度信息
-
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
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：KR101880522B1
公开(公告)日：2018-07-23
申请号：KR1020160182280
申请日：2016-12-29
Applicant: 재단법인대구경북과학기술원
Abstract: 본발명은영상분석기반의트레드밀감시장치및 그것을이용한위험상황감지방법에관한것이다. 본발명에따르면, 트레드밀감시장치를이용한위험상황감지방법에있어서, 위험상황감지방법은트레트밀을이용하여운동중인사용자를촬영한 RGB 영상및 깊이영상을수신하는단계, 상기 RGB 영상으로부터사용자얼굴영역을추출하고, 현재시점에서의사용자얼굴영역과이전시점에서의사용자얼굴영역의픽셀변위값에대응하는얼굴위치변화량을산출하는단계, 상기깊이영상으로부터사용자신체중심축을추출하고, 상기깊이영상의수직축과상기사용자신체중심축이형성하는각도에대응하는신체중심축기울기량을산출하는단계, 상기얼굴위치변화량및 신체중심축기울기량을이용하여위험상황스코어를산출하는단계, 그리고상기위험상황스코어를기 설정된위험임계치를비교하고, 비교결과에대응하여사용자의위험상황을외부로알리는단계를포함한다. 이와같이본 발명에따르면, 사용자의트레드밀운동시응급상황을자동으로판단하여알람을울려줌과동시에보호자및 트레이너에게메시지를전송함으로써편리하고안전한트레드밀운동을수행할수 있는장점이있다.
-
24.发明公开
公开(公告)号：KR1020180037419A
公开(公告)日：2018-04-12
申请号：KR1020160127534
申请日：2016-10-04
Applicant: 재단법인대구경북과학기술원
CPC classification number: G06K9/00288 , G06K9/00281 , G06K9/481 , G06K9/6267
Abstract: 본발명은 Region-SIFT와 Discriminant SVM 분류기를이용한나이및 성별인식장치및 그방법에대한것이다. 본발명에따른 Region-SIFT와 Discriminant SVM 분류기를이용한나이및 성별인식장치는영상내 얼굴영역과눈, 코및 입을포함하는특징점을검출하고, 상기얼굴영역을정규화하는얼굴정규화부; 상기검출된특징점을이용하여상기얼굴영역을다수의구역으로구분하고, Dense-SIFT(Dense Scale Invariant Feature Transform) 알고리즘을이용하여각 구역에서특징벡터를추출하는특징벡터추출부; 상기각 구역에서추출된특징벡터를합쳐서성별및 나이인식을위한하나의 Region-SIFT(Region Scale Invariant Feature Transform) 특징벡터를생성하는특징벡터생성부; 및상기생성된 Region-SIFT 특징벡터를 SVM(Support Vector Machine) 학습하여 Discriminant SVM 분류기를생성하고, 상기생성된 Discriminant SVM 분류기를이용하여성별및 나이를인식하는인식부를포함한다. 이와같이본 발명에따르면, 수행시간이단축되고인식률이향상되어빠르고정확하게나이및 성별을인식할수 있는효과가있다.
Abstract translation: 本发明涉及一种使用地区-SIFT和判别SVM分类年龄和性别识别装置和方法。 年龄和性别读者使用根据用于检测包括所述脸部区域和眼睛，鼻子和嘴，以及归一化所述面部区域内的图像的特征点的脸部发明归一化单元的区域-SIFT和判别SVM分类; 使用密集-SIFT（密集尺度不变特征变换）算法在每个区域中通过使用检测到的特征点辨别面部区域分割成多个区域的特征向量提取单元，并且提取的特征向量; 用于从每个区域中提取的特征向量的组合特征矢量发生器创建一个地区-SIFT（地区尺度不变特征变换）性别和年龄识别特征向量; 和该研究的识别单元，将所得地区-SIFT特征矢量SVM（支持向量机）生成判别SVM分类，识别使用所生成的判别式SVM的性别和年龄组的分类。 如上所述，根据本发明，缩短了执行时间并提高了识别率，从而可以快速而准确地识别年龄和性别。
-
公开(公告)号：KR101827168B1
公开(公告)日：2018-02-08
申请号：KR1020160146852
申请日：2016-11-04
Applicant: 재단법인대구경북과학기술원
CPC classification number: G06T11/60 , G06K9/00268 , G06K9/00288 , G06K2009/00322 , G06T3/0093 , G06T2207/20221
Abstract: 본발명은얼굴합성콘텐츠를출력하는장치및 얼굴합성콘텐츠를출력하는방법에관한것이다. 본발명에따른장치는, 얼굴합성콘텐츠를출력하는장치는, 이미지에대한인식수단을결정하는결정부, 상기인식수단에따라, 상기이미지로부터인식영역을추출하는추출부, 상기인식영역에대하여인식정보를생성하는처리부, 및상기인식정보를분석하여, 상기이미지에합성하는콘텐츠를출력하는출력부를포함할수 있다.
-
Patent Agency Ranking
公开(公告)号：KR1020170014050A
公开(公告)日：2017-02-08
申请号：KR1020150106576
申请日：2015-07-28
Applicant: 재단법인대구경북과학기술원
IPC: A61M21/00 , G06F3/01 , G06F17/30 , A61B5/0476
Abstract: 본발명은가상현실기반의개인맞춤용캡슐형힐링장치및 제공방법에관한것이다. 가상현실을제공하는 VR 기기를포함하는개인맞춤용캡슐형힐링장치에있어서, 2D 또는 3D 카메라를이용하여상기사용자의얼굴또는제스쳐를인식하는사용자인식부, 뇌파전극이부착된상기 VR 기기로부터측정된사용자의뇌파를수신하여뇌파종류및 형태에따라상기사용자의두뇌활동상태를판단하는뇌파인식부, 상기사용자의두뇌활동상태에따라컨텐츠를선택하여상기사용자에게추천하고, 상기사용자로부터제스쳐를통해입력신호를받으면, 그에따른제어신호를생성하는제어부및 상기제어신호에따라, 해당컨텐츠를 2D 또는 3D 영상, 입체사운드, 향기, 산소공급, 좌석의움직임중에서적어도하나의형태로상기사용자에게제공하는출력부를포함한다. 이와같이본 발명에따르면, 측정한사용자의뇌파를분석하여보다정확하게사용자의현재상태를측정하고그에따른컨텐츠를제공하며, 사용기록을저장및 관리하여개인맞춤형서비스를제공할수 있다. 또한, 가상현실기반의다차원감각을자극하는컨텐츠를제공함으로컨텐츠에대한몰입도를높여좀 더효율적으로스트레스해소및 완화에도움을줄 수있다.
-
公开(公告)号：KR101647969B1
公开(公告)日：2016-08-12
申请号：KR1020140120825
申请日：2014-09-12
Applicant: 재단법인대구디지털산업진흥원 , 재단법인대구경북과학기술원
IPC: G06T7/20
Abstract: 사용자시선검출방법이개시된다. 본방법은, 뎁스카메라로촬영을수행하여뎁스맵을획득하는단계, 뎁스맵 내에서인물영역을제외한배경영역을제거하는단계, 인물영역내에서얼굴의위치및 자세를추정하는단계, 추정된위치및 자세를이용하여, 3차원실좌표계에서의사용자시선위치를산출하고, 사용자시선위치를 2차원픽셀좌표계에서의사용자시선위치로변환하는변환단계, 디스플레이패널의해상도및 2차원픽셀좌표계에서의사용자시선위치를이용하여, 디스플레이패널상에서사용자시선이위치하는포인트를산출하는시선검출단계를포함한다. 이에따라, 조명의영향없이사용자의시선포인트를산출할수 있다.
-
公开(公告)号：KR1020140040322A
公开(公告)日：2014-04-03
申请号：KR1020120105926
申请日：2012-09-24
Applicant: 재단법인대구경북과학기술원
IPC: G06T5/00
CPC classification number: G06T5/20 , G06T3/4053
Abstract: Provided is a method for reconstructing a super resolution image. The method of the present invention is a method for reconstructing a super resolution image from a low resolution image using sparse representation and edge reinforcement. Learning-based sparse representation and restoration-based repetitive reverse projection are used for reconstructing a super resolution image in the method. [Reference numerals] (AA) Start; (BB) End; (S10) Input a low resolution image; (S20) Reconstruct the image using a sparse representation; (S30) Preprocess; (S40) Reconstruct the image using repetitive reverse projection; (S50) Output a super resolution image
Abstract translation: 提供了一种用于重建超分辨率图像的方法。 本发明的方法是使用稀疏表示和边缘加强从低分辨率图像重建超分辨率图像的方法。 基于学习的稀疏表示和基于恢复的重复反向投影用于重建该方法中的超分辨率图像。 （附图标记）（AA）开始; （BB）结束; （S10）输入低分辨率图像; （S20）使用稀疏表示重建图像; （S30）预处理; （S40）使用重复反投影重建图像; （S50）输出超分辨率图像
-
公开(公告)号：KR101314293B1
公开(公告)日：2013-10-02
申请号：KR1020120093895
申请日：2012-08-27
Applicant: 재단법인대구경북과학기술원
CPC classification number: G06K9/4661 , G06F17/16 , G06F17/30244 , G06K9/00228
Abstract: PURPOSE: A face recognition system is provided to control misrecognition rates generated in an illumination change environment by applying a characteristic extracting technology based on image covariance. CONSTITUTION: A face database (DB) (150) stores face images and identification information for the face image. A face area detecting unit (110) extracts the face image from the inputted image, and a pre-processing unit (120) changes the pixel values of pixels constructing the face area into a binary pattern. A characteristic extraction unit (130) extracts characteristic information from the face image changed into the binary pattern. A face recognition unit (140) recognizes a face by using the characteristic information for the face images stored in the characteristic information and the face DB. [Reference numerals] (100) Image input unit; (110) Face area detecting unit; (120) Face area pre-processing unit; (130) Characteristic extraction unit; (140) Face recognition unit; (150) Face database
Abstract translation: 目的：提供一种面部识别系统，通过应用基于图像协方差的特征提取技术来控制在照明变化环境中产生的误识别率。 构成：面部数据库（DB）（150）存储面部图像和面部图像的识别信息。 脸部区域检测部（110）从输入图像中提取脸部图像，预处理部（120）将构成脸部区域的像素的像素值变更为二进制图案。 特征提取单元（130）从改变为二进制图案的面部图像提取特征信息。 面部识别单元（140）通过使用存储在特征信息和面部DB中的面部图像的特征信息来识别脸部。 （附图标记）（100）图像输入单元; （110）面部区域检测单元; （120）面部预处理单元; （130）特征提取单元; （140）面部识别单元; （150）脸部数据库
-
公开(公告)号：KR1020180077683A
公开(公告)日：2018-07-09
申请号：KR1020160182280
申请日：2016-12-29
Applicant: 재단법인대구경북과학기술원
CPC classification number: G06T7/248 , A63B24/0087 , G06T7/11 , G06T7/269 , G06T7/579 , G06T2207/10028 , G06T2207/30201 , G08B21/182
Abstract: 본발명은영상분석기반의트레드밀감시장치및 그것을이용한위험상황감지방법에관한것이다. 본발명에따르면, 트레드밀감시장치를이용한위험상황감지방법에있어서, 위험상황감지방법은트레트밀을이용하여운동중인사용자를촬영한 RGB 영상및 깊이영상을수신하는단계, 상기 RGB 영상으로부터사용자얼굴영역을추출하고, 현재시점에서의사용자얼굴영역과이전시점에서의사용자얼굴영역의픽셀변위값에대응하는얼굴위치변화량을산출하는단계, 상기깊이영상으로부터사용자신체중심축을추출하고, 상기깊이영상의수직축과상기사용자신체중심축이형성하는각도에대응하는신체중심축기울기량을산출하는단계, 상기얼굴위치변화량및 신체중심축기울기량을이용하여위험상황스코어를산출하는단계, 그리고상기위험상황스코어를기 설정된위험임계치를비교하고, 비교결과에대응하여사용자의위험상황을외부로알리는단계를포함한다. 이와같이본 발명에따르면, 사용자의트레드밀운동시응급상황을자동으로판단하여알람을울려줌과동시에보호자및 트레이너에게메시지를전송함으로써편리하고안전한트레드밀운동을수행할수 있는장점이있다.
-
-
-
-
-
-
-
-
-
Search Results
50
records
(took 0.026 seconds)
