公开(公告)号：US20070160262A1

公开(公告)日：2007-07-12

申请号：US11544643

申请日：2006-10-10

申请人： Junmo Kim ,  Gyu-tae Park ,  Jong-ha Lee ,  Seok-cheol Kee

发明人： Junmo Kim ,  Gyu-tae Park ,  Jong-ha Lee ,  Seok-cheol Kee

IPC分类号： G06K9/00

CPC分类号： G06K9/6293

摘要： A score fusion method and apparatus. The score fusion method includes receiving a plurality of scores respectively obtained by a plurality of classifiers, and fusing the received scores using a likelihood ratio. The score fusion apparatus includes a fusion unit which receives a plurality of scores respectively obtained by a plurality of classifiers and fuses the received scores using a likelihood ratio, and a parameter providing unit which provides the fusion unit with a plurality of parameters needed for fusing the received scores.

摘要翻译： 分数融合方法和装置。 所述分数融合方法包括接收由多个分类器分别获得的多个分数，并且使用似然比来融合所接收的分数。 分数融合装置包括：融合单元，其接收由多个分类器分别获得的多个分数，并使用似然比对所接收的分数进行融合;以及参数提供单元，为融合单元提供融合所需的多个参数 收到分数

公开(公告)号：US20070160296A1

公开(公告)日：2007-07-12

申请号：US11529350

申请日：2006-09-29

申请人： Jong-ha Lee ,  Gyu-tae Park ,  Seok-cheol Kee

发明人： Jong-ha Lee ,  Gyu-tae Park ,  Seok-cheol Kee

IPC分类号： G06K9/62

CPC分类号： G06K9/00281 ,  G06K9/4619

摘要： A face recognition method and apparatus. The face recognition apparatus includes a Gabor filter unit which obtains a plurality of response values by applying a plurality of Gabor filters having different properties to a plurality of fiducial points extracted from an input face image, a linear discriminant analysis (LDA) unit which obtains first LDA results by performing LDA on each of a plurality of response value groups into which the response values of the plurality of response values are classified, a similarity calculation unit which calculates similarities between the first LDA results and second LDA results obtained by performing LDA on a face image other than the input face image, and a determination unit which classifies the input face image according to the similarities.

摘要翻译： 人脸识别方法和装置。 人脸识别装置包括：Gabor滤波器单元，其通过对从输入面部图像提取的多个基准点应用具有不同性质的多个Gabor滤波器来获得多个响应值;线性判别分析（LDA）单元，其获得第一 通过在对多个响应值的响应值进行分类的多个响应值组中的每个响应值组上执行LDA而得到LDA结果;相似度计算单元，计算第一LDA结果与通过对LDA执行LDA获得的第二LDA结果之间的相似度 除了输入面部图像之外的脸部图像，以及根据相似性对输入面部图像进行分类的确定单元。

公开(公告)号：US20070172099A1

公开(公告)日：2007-07-26

申请号：US11581491

申请日：2006-10-17

申请人： Gyu-tae Park ,  Jong-ha Lee ,  Seok-cheol Kee ,  Won-jun Hwang

发明人： Gyu-tae Park ,  Jong-ha Lee ,  Seok-cheol Kee ,  Won-jun Hwang

IPC分类号： G06K9/00 ,  G06K9/62 ,  G06K9/68

CPC分类号： G06K9/00281 ,  G06K9/00288 ,  G06K9/6234 ,  G06K2009/4666

摘要： A scalable face recognition method and apparatus using complementary features. The scalable face recognition apparatus includes a multi-analysis unit which analyzes a plurality of features of an input face image using a plurality of feature analysis techniques separately, compares the features of the input face image with a plurality of features of a reference image; and provides similarities as the results of the comparison, a fusion unit which fuses the similarities, and a determination unit which classifies the input face image according to a result of the fusion performed by the fusion unit.

摘要翻译： 一种可扩展的人脸识别方法和使用互补功能的装置。 可扩展人脸识别装置包括多分析单元，其使用多个特征分析技术分别分析输入面部图像的多个特征，将输入面部图像的特征与参考图像的多个特征进行比较; 并且提供与比较结果相似的相似性，融合单元，其融合相似性;以及确定单元，其根据由融合单元进行的融合的结果对输入的面部图像进行分类。

公开(公告)号：US07254257B2

公开(公告)日：2007-08-07

申请号：US10377748

申请日：2003-03-04

申请人： Hyun-woo Kim ,  Tae-kyun Kim ,  Seok-cheol Kee ,  Jong-ha Lee ,  Won-jun Hwang

发明人： Hyun-woo Kim ,  Tae-kyun Kim ,  Seok-cheol Kee ,  Jong-ha Lee ,  Won-jun Hwang

IPC分类号： G06K9/00

CPC分类号： G06K9/00281 ,  G06K9/6242 ,  G06K9/6247

摘要： A method and apparatus for recognizing and searching for a face using 2nd-order independent component analysis (ICA) are provided. The method for describing feature points uses 2nd-order ICA d to describe a facial image space and improve recognition performance in various illumination conditions. According to the method and apparatus, use of pose or illumination invariant face descriptor enables retrieval of human faces and authentication of a specific individual.

摘要翻译： 提供了使用二阶独立分量分析（ICA）识别和搜索面部的方法和装置。 描述特征点的方法使用二阶ICA d来描述面部图像空间，并提高各种照明条件下的识别性能。 根据该方法和装置，使用姿态或照明不变面部描述符能够检索人脸和特定个体的认证。

公开(公告)号：US07164781B2

公开(公告)日：2007-01-16

申请号：US10377752

申请日：2003-03-04

申请人： Hyun-woo Kim ,  Tae-kyun Kim ,  Seok-cheol Kee ,  Jong-ha Lee ,  Won-jun Hwang ,  Chang-kyu Choi

发明人： Hyun-woo Kim ,  Tae-kyun Kim ,  Seok-cheol Kee ,  Jong-ha Lee ,  Won-jun Hwang ,  Chang-kyu Choi

IPC分类号： G06K9/00

CPC分类号： G06K9/6247 ,  G06F19/00 ,  G06K9/00275 ,  G06K9/6242

摘要： A method and apparatus for recognizing and searching for a face using 2nd-order independent component analysis (ICA) are provided. The method includes performing PCA on an input original image and generating a low-pass filtered image by removing high-frequency component from the original image, subtracting the low-pass filtered image from the original image and obtaining residual image having only frequency-components, and performing ICA on the residual image and generating feature information corresponding to the original image. While an original ICA subtracts independent components (i.e., independent basis components) from gray scale images, the proposed 2nd-order ICA is robust to illumination variation since it is applied to make the remaining images correspond to high pass frequency components.

摘要翻译： 提供了使用二阶独立分量分析（ICA）识别和搜索面部的方法和装置。 该方法包括在输入原始图像上执行PCA，并通过从原始图像中去除高频分量并从原始图像中减去低通滤波图像并获得仅具有频率分量的残差图像来生成低通滤波图像， 对剩余图像执行ICA并产生与原始图像相对应的特征信息。 虽然原始ICA从灰度图像中减去独立分量（即独立基础分量），但是所提出的二阶ICA对照明变化是鲁棒的，因为它被应用于使剩余的图像对应于高通频率分量。

公开(公告)号：US08111880B2

公开(公告)日：2012-02-07

申请号：US11896300

申请日：2007-08-30

申请人： Jong-ha Lee ,  Jung-bae Kim ,  Young-su Moon ,  Gyu-tae Park ,  Won-jun Hwang

发明人： Jong-ha Lee ,  Jung-bae Kim ,  Young-su Moon ,  Gyu-tae Park ,  Won-jun Hwang

IPC分类号： G06K9/00 ,  G06K9/46 ,  G06K9/40

CPC分类号： G06K9/00281 ,  G06K9/4619

摘要： Provided are a method and apparatus for extracting facial features from an image containing a face. The method and apparatus filter an input image using a filter set for face recognition at each of predetermined locations in the input image, merge values obtained by filtering the input image at locations, which are horizontally symmetrical to each other with respect to the center of the face, and synthesize values obtained by filtering the input image at locations which are not symmetrical to each other with respect to the center of the face with the merged values. Therefore, the time, feature values, and storage space required to extract or compare facial features can be significantly reduced. In addition, a face recognition system that runs well on low specification hardware can be implemented.

摘要翻译： 提供了一种从包含脸部的图像中提取面部特征的方法和装置。 该方法和装置使用输入图像中的每个预定位置处的用于人脸识别的滤波器对输入图像进行滤波，将通过对输入图像进行滤波而获得的合并值相对于 并且合成通过以合并的值相对于面部的中心彼此不对称的位置对输入图像进行滤波而获得的值。 因此，可以显着减少提取或比较面部特征所需的时间，特征值和存储空间。 另外，可以实现在低规格硬件上运行良好的人脸识别系统。

公开(公告)号：US20090034953A1

公开(公告)日：2009-02-05

申请号：US12004429

申请日：2007-12-21

申请人： Young-kyoo Hwang ,  Jung-bae Kim ,  Seong-deok Lee ,  Gyu-tae Park ,  Jong-ha Lee

发明人： Young-kyoo Hwang ,  Jung-bae Kim ,  Seong-deok Lee ,  Gyu-tae Park ,  Jong-ha Lee

IPC分类号： G03B13/00 ,  H04N5/235

CPC分类号： H04N5/23212 ,  H04N5/23219 ,  H04N5/235

摘要： An object-oriented photographing control method, medium, and apparatus. The object-oriented photographing control method includes detecting an interesting object registered in advance from an input image, estimating photographic information on the detected interesting object, and generating control information for capturing the input image by using the estimated photographing information, and capturing the input image according to the control information. Accordingly, states of a position and illuminance of the object are perceived in real-time, a high-quality image can be captured, and the user does not need to control the focus and the exposure of the input image.

摘要翻译： 面向对象拍摄控制方法，介质和装置。 面向对象拍摄控制方法包括：从输入图像中预先登记的感兴趣对象，对所检测到的感兴趣对象进行摄影信息的估计，以及利用所估计的拍摄信息生成拍摄输入图像的控制信息，拍摄输入图像 根据控制信息。 因此，实时地感知对象的位置和照度的状态，可以捕获高质量的图像，并且用户不需要控制输入图像的焦点和曝光。

公开(公告)号：US20080199055A1

公开(公告)日：2008-08-21

申请号：US11896300

申请日：2007-08-30

申请人： Jong-ha Lee ,  Jung-bae Kim ,  Young-su Moon ,  Gyu-tae Park ,  Won-jun Hwang

发明人： Jong-ha Lee ,  Jung-bae Kim ,  Young-su Moon ,  Gyu-tae Park ,  Won-jun Hwang

IPC分类号： G06K9/00

CPC分类号： G06K9/00281 ,  G06K9/4619

摘要： Provided are a method and apparatus for extracting facial features from an image containing a face. The method and apparatus filter an input image using a filter set for face recognition at each of predetermined locations in the input image, merge values obtained by filtering the input image at locations, which are horizontally symmetrical to each other with respect to the center of the face, and synthesize values obtained by filtering the input image at locations which are not symmetrical to each other with respect to the center of the face with the merged values. Therefore, the time, feature values, and storage space required to extract or compare facial features can be significantly reduced. In addition, a face recognition system that runs well on low specification hardware can be implemented.

摘要翻译： 提供了一种从包含脸部的图像中提取面部特征的方法和装置。 该方法和装置使用输入图像中的每个预定位置处的用于人脸识别的滤波器对输入图像进行滤波，将通过对输入图像进行滤波而获得的合并值相对于 并且合成通过以合并的值相对于面部的中心彼此不对称的位置对输入图像进行滤波而获得的值。 因此，可以显着减少提取或比较面部特征所需的时间，特征值和存储空间。 另外，可以实现在低规格硬件上运行良好的人脸识别系统。

公开(公告)号：US08908955B2

公开(公告)日：2014-12-09

申请号：US13482972

申请日：2012-05-29

申请人： Kang-eui Lee ,  Myung-jin Chung ,  Young-hun Sung ,  Jong-ha Lee ,  Kwang-eun Jang

发明人： Kang-eui Lee ,  Myung-jin Chung ,  Young-hun Sung ,  Jong-ha Lee ,  Kwang-eun Jang

IPC分类号： G06K9/00 ,  A61B6/02 ,  G06T11/00 ,  A61B6/00 ,  H04N13/02

CPC分类号： A61B6/022 ,  A61B6/486 ,  G06T11/006 ,  G06T2211/436 ,  H04N13/221

摘要： A method of providing a stereoscopic X-ray image is provided. The method includes acquiring X-ray images captured at respective rotation angles with respect to a part of a patient to be examined while rotating around the part to be examined, and in response to information regarding a viewpoint with respect to the part to be examined being input, using X-ray images at respective rotation angles corresponding to the viewpoint from among the acquired X-ray images to generate a three-dimensional (3D) X-ray image.

摘要翻译： 提供了提供立体X射线图像的方法。 所述方法包括获取相对于要被检查的患者的一部分以相应的旋转角捕获的X射线图像，同时围绕待检查的部分旋转，并且响应于关于待检查部分的视点的信息为 输入，使用从所获取的X射线图像中的与视点相对应的各旋转角度的X射线图像生成三维（3D）X射线图像。

公开(公告)号：US08666175B2

公开(公告)日：2014-03-04

申请号：US12078737

申请日：2008-04-03

申请人： Jung-bae Kim ,  Seong-deok Lee ,  Jong-ha Lee

发明人： Jung-bae Kim ,  Seong-deok Lee ,  Jong-ha Lee

IPC分类号： G06K9/62

CPC分类号： G06K9/00228 ,  G06K9/6256

摘要： A method and apparatus for detecting an object are provided. The method calculates a feature value based on features extracted from an input image by using a classifier of an ith stage, compares the calculated feature value with a first threshold value of the ith stage, compares the feature value with a second threshold value of the ith stage according to a result of the comparison between the feature value and the first threshold value of the ith stage, and jumps to a classifier of an i+2th stage according to a result of the comparison between the feature value and the second threshold value of the ith stage. By doing so, the method can avoid repeated calculations and can rapidly detect the object in the input image.

摘要翻译： 提供了一种用于检测物体的方法和装置。 该方法基于通过使用第i级的分类器从输入图像提取的特征来计算特征值，将计算出的特征值与第i级的第一阈值进行比较，将特征值与​​第i级的第二阈值进行比较 根据特征值与第i阶段的第一阈值的比较结果，根据特征值和第二阈值的比较结果，跳到第i + 2级的分类器 第i阶段 通过这样做，该方法可以避免重复计算，并可以快速检测输入图像中的对象。