公开(公告)号：EP3216008A4

公开(公告)日：2018-06-27

申请号：EP14905549

申请日：2014-11-05

申请人： INTEL CORP

发明人： DU YANGZHOU ,  LI WENLONG ,  LI QIANG ,  TONG XIAOFENG ,  KIM TAE-HOON ,  PARK MINJE

IPC分类号： G06K9/00 ,  G06T13/20 ,  G06T13/40

CPC分类号： G06T13/40 ,  G06F17/2785 ,  G06K9/00248 ,  G06K9/00281 ,  G06K9/00308 ,  G06T13/205 ,  G10L25/48

摘要： Apparatuses, methods and storage medium associated with creating an avatar video are disclosed herein. In embodiments, the apparatus may one or more facial expression engines, an animation-rendering engine, and a video generator. The one or more facial expression engines may be configured to receive video, voice and/or text inputs, and, in response, generate a plurality of animation messages having facial expression parameters that depict facial expressions for a plurality of avatars based at least in part on the video, voice and/or text inputs received. The animation-rendering engine may be configured to receive the one or more animation messages, and drive a plurality of avatar models, to animate and render the plurality of avatars with the facial expression depicted. The video generator may be configured to capture the animation and rendering of the plurality of avatars, to generate a video. Other embodiments may be described and/or claimed.

公开(公告)号：EP2657908A4

公开(公告)日：2018-01-17

申请号：EP11850862

申请日：2011-03-18

申请人： OMRON TATEISI ELECTRONICS CO

发明人： IRIE ATSUSHI ,  SAKAI SHUN ,  MURAKAMI TATSUYA

IPC分类号： G06K9/00

CPC分类号： G06K9/00295 ,  G06K9/00288 ,  G06K9/00308 ,  G06K2009/00328

摘要： To achieve an objective of implementing authentication with high precision, even when image-capturing conditions differ among registered images, an image authentication apparatus (1) of the present invention has registered images (R) obtained by capturing images of people, and image-capturing conditions pertaining to the faces of the people in the registered images (R) registered in association with each other in a registered image database (21), and is provided with: a face-information data estimation unit (33) for estimating face-information data of an inputted image (A1); a weighting determination unit (34) for determining weighting in accordance with the similarities between face-information data of registered images (R) and the face-information data of the inputted image (A1); an authentication score calculation unit (35) for calculating authentication scores between the inputted image (A1) and the registered images (R); a weighted authentication-score calculation unit (36) for applying, to the authentication scores, weighting determined for the corresponding registered images (R); and an authentication result output unit (37) for verifying the inputted image (A1) on the basis of the weighted authentication scores.

公开(公告)号：EP3216008A1

公开(公告)日：2017-09-13

申请号：EP14905549.3

申请日：2014-11-05

申请人： Intel Corporation

发明人： DU, Yangzhou ,  LI, Wenlong ,  LI, Qiang ,  TONG, Xiaofeng ,  KIM, Tae-Hoon ,  PARK, Minje

IPC分类号： G06T13/40

CPC分类号： G06T13/40 ,  G06F17/2785 ,  G06K9/00248 ,  G06K9/00281 ,  G06K9/00308 ,  G06T13/205 ,  G10L25/48

摘要： Apparatuses, methods and storage medium associated with creating an avatar video are disclosed herein. In embodiments, the apparatus may one or more facial expression engines, an animation-rendering engine, and a video generator. The one or more facial expression engines may be configured to receive video, voice and/or text inputs, and, in response, generate a plurality of animation messages having facial expression parameters that depict facial expressions for a plurality of avatars based at least in part on the video, voice and/or text inputs received. The animation-rendering engine may be configured to receive the one or more animation messages, and drive a plurality of avatar models, to animate and render the plurality of avatars with the facial expression depicted. The video generator may be configured to capture the animation and rendering of the plurality of avatars, to generate a video. Other embodiments may be described and/or claimed.

摘要翻译： 这里公开了与创建化身视频相关联的设备，方法和存储介质。 在实施例中，该装置可以是一个或多个面部表情引擎，动画呈现引擎和视频生成器。 所述一个或多个面部表情引擎可以被配置为接收视频，语音和/或文本输入，并且作为响应，至少部分地基于所述多个动画消息生成具有面部表情参数的多个动画消息，所述面部表情参数描绘多个化身的面部表情 在收到的视频，语音和/或文字输入上。 动画呈现引擎可以被配置为接收一个或多个动画消息，并且驱动多个化身模型，以用所描绘的面部表情来动画和呈现多个化身。 视频生成器可以被配置成捕捉动画和渲染多个化身以生成视频。 其他实施例可以被描述和/或要求保护。

公开(公告)号：EP1986128A3

公开(公告)日：2013-11-27

申请号：EP08154951.1

申请日：2008-04-22

申请人： Sony Corporation

发明人： Fukushima, Seigo ,  Kashiwagi, Shigeru

IPC分类号： G06K9/00 ,  G06F17/30

CPC分类号： G06K9/00228 ,  G06F16/5854 ,  G06K9/00308 ,  G06K9/00751

摘要： Disclosed herein is an image processing apparatus (100), including a representative face extraction unit (114) configured to detect face images in an image frame that forms part of video image data, and select, from the detected face images, a face image to be used as index information. The representative face extraction unit (114) is configured to calculate a score of each of the face images detected in the image frame based on characteristics of the face image, and select a detected face image whose score is high as an index-use face image.

公开(公告)号：EP2161678A3

公开(公告)日：2013-08-14

申请号：EP09169351.5

申请日：2009-09-03

申请人： Sony Corporation

发明人： Okada, Miyuki

IPC分类号： G06K9/00 ,  G06K9/68

CPC分类号： G06K9/6814 ,  G06K9/00308

摘要： An image processing apparatus includes: a subject information storage unit configured to store feature quantities and attributes relating to a plurality of subjects; a subject detecting unit configured to detect a subject included in an image; an attribute determining unit configured to determine the attributes of the detected subject; a feature quantity extracting unit configured to extract a feature quantity relating to the detected subject; and a similarity calculating unit configured to select one or a plurality of feature quantities from feature quantities relating to a plurality of subjects stored in the subject information storage unit based on the determined attributes to calculate similarity between a subject according to the selected feature quantities, and the detected subject, based on the selected feature quantities and the extracted feature quantity.

摘要翻译： 一种图像处理装置，包括：被摄体信息存储单元，被配置为存储与多个被摄体有关的特征量和属性; 对象检测单元，被配置为检测包括在图像中的被摄体; 属性确定单元，被配置为确定所检测到的被摄体的属性; 特征量提取单元，被配置为提取与所检测的被摄体有关的特征量; 以及相似度计算单元，被配置为基于所确定的属性来从存储在所述对象信息存储单元中的与多个主题相关的特征量中选择一个或多个特征量，以根据所选择的特征量计算被摄体之间的相似度;以及 基于所选择的特征量和提取的特征量来检测被检体。

公开(公告)号：EP2616993A1

公开(公告)日：2013-07-24

申请号：EP10857368.4

申请日：2010-09-13

申请人： Hewlett-Packard Development Company, L.P.

发明人： DALTON, Dan L. ,  BLOOM, Daniel ,  STAUDACHER, David

IPC分类号： G06K9/52 ,  G06T7/60

CPC分类号： G06K9/00302 ,  G06K9/00308

摘要： Systems and methods of smile detection are disclosed. An exemplary method comprises generating a search map for a subset of an image. The method also comprises identifying a plurality of candidates representing mouth corners. The method also comprises generating parabolas between each pair of candidates representing mouth corners. The method also comprises analyzing contour of at least one of the parabolas to determine whether the mouth curves substantially upward to form a smile or curves substantially downward to form a frown.

摘要翻译： 公开了微笑检测的系统和方法。 一种示例性方法包括生成用于图像（300）的子集的搜索图（400）。 该方法还包括识别表示嘴角的多个候选（400a-f）。 该方法还包括在代表嘴角的每对候选者之间产生抛物线（410）。 该方法还包括分析至少一个抛物线的轮廓，以确定嘴是否基本上向上弯曲以形成微笑或基本向下弯曲以形成皱眉。

公开(公告)号：EP2309723A4

公开(公告)日：2011-08-31

申请号：EP09797793

申请日：2009-06-25

申请人： NEC CORP

发明人： KATOH SATOSHI

IPC分类号： H04N5/232 ,  G03B15/00 ,  G06T1/00 ,  H04N101/00

CPC分类号： H04N5/232 ,  G03B15/00 ,  G06K9/00308 ,  H04N1/00328 ,  H04N1/00336 ,  H04N1/2145 ,  H04N5/23219 ,  H04N5/772 ,  H04N5/781 ,  H04N5/85 ,  H04N2101/00 ,  H04N2201/0084

公开(公告)号：EP2161678A2

公开(公告)日：2010-03-10

申请号：EP09169351.5

申请日：2009-09-03

申请人： Sony Corporation

发明人： Okada, Miyuki

IPC分类号： G06K9/00 ,  G06K9/68

CPC分类号： G06K9/6814 ,  G06K9/00308

摘要： An image processing apparatus includes: a subject information storage unit configured to store feature quantities and attributes relating to a plurality of subjects; a subject detecting unit configured to detect a subject included in an image; an attribute determining unit configured to determine the attributes of the detected subject; a feature quantity extracting unit configured to extract a feature quantity relating to the detected subject; and a similarity calculating unit configured to select one or a plurality of feature quantities from feature quantities relating to a plurality of subjects stored in the subject information storage unit based on the determined attributes to calculate similarity between a subject according to the selected feature quantities, and the detected subject, based on the selected feature quantities and the extracted feature quantity.

摘要翻译： 一种图像处理设备，包括：被摄体信息存储单元，被配置为存储与多个被摄体有关的特征量和属性; 被摄体检测单元，被配置为检测包括在图像中的被摄体; 属性确定单元，被配置为确定检测到的对象的属性; 特征量提取单元，被配置为提取与检测到的被摄体有关的特征量; 以及相似度计算单元，被配置为基于所确定的属性从存储在所述对象信息存储单元中的与多个对象有关的特征量中选择一个或多个特征量，以根据所选择的特征量计算对象之间的相似度，以及 基于所选择的特征量和提取的特征量来检测所检测到的对象。

公开(公告)号：EP0620529A1

公开(公告)日：1994-10-19

申请号：EP94104104.8

申请日：1994-03-16

申请人： CASIO COMPUTER CO., LTD.

发明人： Yoshino, Hiroyuki, c/o Casio Computer Co., Ltd. ,  Kojo, Takashi, c/o Casio Computer Co., Ltd.

IPC分类号： G06F15/72

CPC分类号： G06T11/00 ,  A61B5/1176 ,  G06F15/025 ,  G06K9/00308

摘要： A montage image creating apparatus which selectively designates one of the patterns of each of a plurality of parts which constitutes a face, and combines the respective designated part patterns into a montage image. It selectively designates a pattern of at least one of a plurality of parts on the basis of a character designated by a character designating unit.

摘要翻译： 一种蒙太奇图像创建装置，其选择性地指定构成面部的多个部分中的每一个的图案中的一个，并将各个指定部位图案组合成蒙太奇图像。 它基于由字符指定单元指定的字符来选择性地指定多个部分中的至少一个的图案。

公开(公告)号：EP2293221B1

公开(公告)日：2018-11-28

申请号：EP10173731.0

申请日：2010-08-23

申请人： Sony Corporation

发明人： Onoe, Naoyuki ,  Yamashita, Junichi ,  Mochizuki, Daisuke ,  Kobayashi, Naoki ,  Kaino, Akihiko

IPC分类号： G06K9/00 ,  G06T11/60

CPC分类号： G06K9/00268 ,  G06K9/00308 ,  G06T11/00 ,  G06T11/60

摘要： An image processing apparatus includes a face detector for detecting a face region from an image including a face of a user, a part detector for detecting a positional layout of a part of the face included in the face region detected by the face detector, a determiner for determining an attribute of the face on the basis of the positional layout of the part detected by the part detector and calculating a score indicating attribute determination results, a model selector for selecting, on the basis of the score calculated by the determiner, a model that is to be displayed in place of the face of the user in the image, and an image generator for generating an image of a face of the model selected by the model selector and synthesizing the image of the face of the model with the face of the user within the face region.