公开(公告)号：US20130236072A1

公开(公告)日：2013-09-12

申请号：US13868698

申请日：2013-04-23

Applicant: SONY CORPORATION

Inventor： Yun SUN ,  Tamaki Kojima ,  Tomohiko Gotoh ,  Makoto Murata ,  Masatomo Kurata

IPC: G06K9/00

CPC classification number: G06K9/00288 ,  G06K9/00248 ,  G06K9/00281 ,  G06K9/00295 ,  G06K9/00308

Abstract: An image processing apparatus includes a face detector detecting face images from still-image frames successively extracted from a moving-image stream in accordance with image information items regarding the still-image frames, a face-feature-value calculation unit calculating face feature values of the face images in accordance with image information items regarding the face images, an identity determination unit determining whether a first face image in a current frame and a second face image in a previous frame represent an identical person in accordance with at least face feature values of the first and second face images, and a merging processor which stores one of the first and second face images when the first face image and the second face image represent an identical person, and which stores the first and second face images when the first face image and the second face image do not represent an identical person.

Abstract translation: 图像处理装置包括面部检测器，根据关于静止图像帧的图像信息，从运动图像流连续提取的静止图像帧中检测面部图像，面部特征值计算单元，计算脸部特征值 根据关于脸部图像的图像信息项的脸部图像，身份确定单元，确定当前帧中的第一面部图像和前一帧中的第二面部图像是否根据至少面部特征值表示相同的人物 第一和第二面部图像以及当第一面部图像和第二面部图像表示相同的人时存储第一和第二面部图像之一的合并处理器，并且当第一面部图像存储时存储第一和第二面部图像 并且第二张脸部图像不代表相同的人物。

公开(公告)号：US20130300748A1

公开(公告)日：2013-11-14

申请号：US13666423

申请日：2012-11-01

Applicant: SONY CORPORATION

Inventor： Takeshi YAEDA ,  Yuki OKAMURA ,  Tomohiko GOTOH ,  Tatsuhito SATO ,  Yun SUN ,  Shunsuke MOCHIZUKI ,  Daisuke MOCHIZUKI

IPC: G06T11/00

CPC classification number: G06T11/00 ,  G06F16/583 ,  G06T11/60

Abstract: An image related information obtaining unit that obtains information relating to a predetermined image as image related information, a keyword generating unit that generates a keyword based on the image related information obtained by the image related information obtaining unit, and a display text string candidate generating unit that generates, as a display text string candidate, a text string serving as a candidate for display, using one or more of the keywords generated by the keyword generating unit.

Abstract translation: 获取与预定图像有关的信息作为图像相关信息的图像相关信息获取单元，基于由图像相关信息获得单元获得的图像相关信息生成关键字的关键词生成单元和显示文本串候选生成单元 其使用由关键字生成单元生成的一个或多个关键字来生成用作显示候选的文本串作为显示文本字符串候选。