公开(公告)号：US08411171B2

公开(公告)日：2013-04-02

申请号：US12833481

申请日：2010-07-09

申请人： Chang-Han Kim ,  Tae-Hwa Hong ,  Chung-Hoon Kim ,  Sung-Dae Cho

发明人： Chang-Han Kim ,  Tae-Hwa Hong ,  Chung-Hoon Kim ,  Sung-Dae Cho

IPC分类号： H04N5/225

CPC分类号： H04N5/265 ,  G06K9/00228 ,  G06K9/03 ,  H04N5/232 ,  H04N5/23219 ,  H04N5/23293

摘要： Provided is an apparatus and a method for generating an image including multiple people, in which images are photographed, face images are detected from each of the photographed images, a face score for each of the face images detected from the photographed images is calculated, it is determined whether each of the face scores calculated for each of the face images is at least equal to a predetermined threshold, and each of face images having a highest face score for each of the face images is synthesized, to output the synthesized image as a final image, in order to generate a most satisfactory photographed image for a user.

公开(公告)号：US08279288B2

公开(公告)日：2012-10-02

申请号：US12336766

申请日：2008-12-17

申请人： Byung-Jun Son ,  Soo-Kyun Kim ,  Tae-Hwa Hong ,  Sung-Dae Cho ,  Sang-Wook Oh

发明人： Byung-Jun Son ,  Soo-Kyun Kim ,  Tae-Hwa Hong ,  Sung-Dae Cho ,  Sang-Wook Oh

IPC分类号： H04N5/228

CPC分类号： H04N5/23216 ,  H04N5/232 ,  H04N5/23238

摘要： A method for photographing a panoramic picture, and for identifying motion of a photographing apparatus to automatically photograph respective images of a panoramic picture. The method steps include: (a) obtaining a first image in response to a request for a panoramic picture photography; (b) identifying motion of a photographing apparatus having obtained the first image, by applying a motion estimation technique to currently input images; (c) automatically determining a photographing direction based on the identified motion of the photographing apparatus; (d) selectively applying a motion estimation technique for estimating motion in a horizontal direction or a vertical direction, according to the determined photographing direction, and identifying motion of the photographing apparatus; (e) judging photographing time points of respective images by identifying that the identified motion of the photographing apparatus has reached a preset threshold value for decision of the photographing time point; and (f) photographing images at the photographing time point of the respective images.

摘要翻译： 一种用于拍摄全景图像并用于识别拍摄设备的运动以自动拍摄全景图像的各个图像的方法。 方法步骤包括：（a）响应于全景图像摄影的请求获得第一图像; （b）通过对当前输入的图像应用运动估计技术来识别获得了第一图像的拍摄装置的运动; （c）基于所识别的拍摄装置的动作来自动确定拍摄方向; （d）根据确定的拍摄方向选择性地应用用于估计水平方向或垂直方向上的运动的运动估计技术，以及识别拍摄装置的运动; （e）通过识别所识别出的拍摄装置的动作已经达到预设的阈值以判定拍摄时间点来判断各图像的拍摄时间点; 和（f）在各图像的拍摄时间点拍摄图像。

公开(公告)号：US20120027193A1

公开(公告)日：2012-02-02

申请号：US13193217

申请日：2011-07-28

申请人： Chang-Han KIM ,  Joo-Young Son ,  Tae-Hwa Hong ,  Sung-Dae Cho

发明人： Chang-Han KIM ,  Joo-Young Son ,  Tae-Hwa Hong ,  Sung-Dae Cho

IPC分类号： H04M3/44

CPC分类号： H04M1/72583 ,  H04M1/00 ,  H04M1/27455 ,  H04M1/274583 ,  H04M1/72586 ,  H04M2250/22 ,  H04M2250/60

摘要： An apparatus and method for creating a call transmission screen using a collage technique is provided. The method includes analyzing user condition information, calculating priorities for terminal transmission/reception information corresponding to the analyzed user condition information according to predetermined priority conditions, selecting available transmission/reception information, used to create a call transmission screen, from the prioritized terminal transmission/reception information, and creating the call transmission screen using the collage technique by arranging images corresponding to the available transmission/reception information according to a predetermined pattern.

摘要翻译： 提供了一种使用拼贴技术创建呼叫发送屏幕的装置和方法。 该方法包括：根据预定的优先级条件分析用户状态信息，根据预定的优先级条件计算与分析的用户状态信息相对应的终端发送/接收信息的优先级，从优先化终端发送/接收信息中选择用于创建呼叫发送屏幕的可用发送/接收信息， 接收信息，并且使用拼贴技术通过根据预定模式布置与可用发送/接收信息相对应的图像来创建呼叫发送屏幕。

公开(公告)号：US20110075933A1

公开(公告)日：2011-03-31

申请号：US12962309

申请日：2010-12-07

申请人： Tae-Hwa HONG ,  Young-Min Jeong ,  Joo-Young Son ,  Chang-Han Kim ,  Sung-Dae Cho

发明人： Tae-Hwa HONG ,  Young-Min Jeong ,  Joo-Young Son ,  Chang-Han Kim ,  Sung-Dae Cho

IPC分类号： G06K9/46

CPC分类号： G06K9/00228

摘要： A method for determining a frontal face pose by using the symmetry of a face including detecting a face region in an image, detecting an eye region in the detected face region, normalizing the face region, analyzing the symmetry in the normalized face region, and determining whether a face pose is a frontal face pose based on an analysis of the symmetry.

摘要翻译： 一种用于通过使用面部对称性来确定正面面部姿势的方法，包括检测图像中的面部区域，检测检测到的面部区域中的眼睛区域，归一化脸部区域，分析归一化脸部区域中的对称性，以及确定 基于对称性的分析，面部姿势是否是正面姿势。

公开(公告)号：US20080186313A1

公开(公告)日：2008-08-07

申请号：US12012697

申请日：2008-02-05

申请人： Seok-Jin Won ,  Yun-Je Oh ,  Sung-Dae Cho ,  Tae-Hwa Hong ,  Soo-Kyun Kim ,  Min-Woo Lee ,  In-Kyu Park ,  Man-Hee Lee

发明人： Seok-Jin Won ,  Yun-Je Oh ,  Sung-Dae Cho ,  Tae-Hwa Hong ,  Soo-Kyun Kim ,  Min-Woo Lee ,  In-Kyu Park ,  Man-Hee Lee

IPC分类号： G06T15/10

CPC分类号： G06T15/005 ,  H04N19/42 ,  H04N19/423 ,  H04N19/436 ,  H04N19/63

摘要： A method for high-speed image processing based on graphic processing unit includes processing an input image for the image processing in a texture format of a 32 bit floating point, and performing a predetermined algorithm for the image processing on the input image through at least one or more Framebuffer Object (FOB) and outputting the result as texture data.

摘要翻译： 一种基于图形处理单元的高速图像处理方法包括以32位浮点的纹理格式处理用于图像处理的输入图像，并且通过至少一个对输入图像执行图像处理的预定算法 或更多的帧缓冲对象（FOB），并将结果输出为纹理数据。

公开(公告)号：US08437567B2

公开(公告)日：2013-05-07

申请号：US12915993

申请日：2010-10-29

申请人： Young-Min Jeong ,  Sung-Dae Cho ,  Tae-Hwa Hong

发明人： Young-Min Jeong ,  Sung-Dae Cho ,  Tae-Hwa Hong

IPC分类号： G06T5/00

CPC分类号： G06T5/005 ,  G06T11/001 ,  G06T2207/20192

摘要： Disclosed is an image inpainting apparatus and method using a restricted search region. The image inpainting apparatus sets a target image region to be inpainted in response to an image inpainting request, sets a surrounding image region, which has a preset size and includes the set target image region, sets a plurality of similar image regions by grouping similar pixels in the surrounding image region, divides the surrounding image region into the plurality of set similar image regions, divides the target image region according to the similar image regions, sets a search region of each divided target image region, and detects an image of an image region most similar to each divided target image region from the set search region of each divided target image region, thereby performing image inpainting. Accordingly, image inpainting is performed using a search region, which has been determined to include a similar image most similar to an image to inpaint, so that it is possible to increase the probability of searching for an image most similar to the inpainting image region.

摘要翻译： 公开了使用限制搜索区域的图像修复装置和方法。 图像修像装置响应于图像修像请求设置要被修补的目标图像区域，设置具有预设尺寸并且包括设定的目标图像区域的周围图像区域，通过对相似的像素进行分组来设置多个相似的图像区域 在周围图像区域中，将周围图像区域划分为多个组合的相似图像区域，根据相似的图像区域划分目标图像区域，设置每个划分的目标图像区域的搜索区域，并检测图像的图像 区域与每个划分的目标图像区域的设置搜索区域最相似的区域，从而执行图像修复。 因此，使用已被确定为包括与图像最近似乎相似的图像的搜索区域的搜索区域执行图像修复，使得可以增加搜索与修复图像区域最相似的图像的概率。

公开(公告)号：US08217989B2

公开(公告)日：2012-07-10

申请号：US12199007

申请日：2008-08-27

申请人： Soo-Kyun Kim ,  Jae-Won Moon ,  Sung-Dae Cho ,  Sang-Wook Oh ,  Byung-Jun Son ,  Tae-Hwa Hong ,  Hee-Won Jung ,  Nam-Ik Cho ,  Sang-Hwa Lee ,  Seong-Jong Ha

发明人： Soo-Kyun Kim ,  Jae-Won Moon ,  Sung-Dae Cho ,  Sang-Wook Oh ,  Byung-Jun Son ,  Tae-Hwa Hong ,  Hee-Won Jung ,  Nam-Ik Cho ,  Sang-Hwa Lee ,  Seong-Jong Ha

IPC分类号： H04N7/00

CPC分类号： G06T7/20 ,  G03B37/04 ,  H04N5/232 ,  H04N5/23238 ,  H04N5/2624

摘要： A panoramic picture photographing method permits more accurate photographing of an image, particularly a panoramic image of a subject, without additional equipment, or separate devices and hardware. The method includes projecting an image, which is successively inputted in every predetermined unit of time, to an imaginary surface having a same focal distance in photographing each image constituting a panoramic picture to obtain a projected image; confirming movement of a corresponding photographing apparatus so that the projected image is compared with a previous image in real time by using a motion estimation technique, to which exposure correction has been applied; determining a photographing time point of each image by confirming the confirmed movement of the corresponding photographing apparatus according to a photographing direction has reached a predetermined critical value; and photographing each image at the photographing time point of each image according to a passive input or automatically.

摘要翻译： 全景图像拍摄方法允许更精确地拍摄图像，特别是对象的全景图像，而无需附加的设备，或单独的设备和硬件。 该方法包括：在拍摄构成全景图像的每个图像时，将在每个预定时间单位连续输入的图像投影到具有相同焦距的虚拟表面以获得投影图像; 通过使用已应用曝光校正的运动估计技术来确认对应的拍摄装置的运动，使得投影图像与先前图像实时比较; 通过根据拍摄方向确认对应的拍摄装置的确定的移动来确定每个图像的拍摄时间点已经达到预定的临界值; 并且根据被动输入或自动地在每个图像的拍摄时间点拍摄每个图像。

公开(公告)号：US20090202106A1

公开(公告)日：2009-08-13

申请号：US12369113

申请日：2009-02-11

申请人： Tae-Hwa HONG ,  Byung-Jun Son ,  Soo-Kyun Kim ,  Sung-Dae Cho ,  Guee-Sang Lee ,  Sung-Ryul Oh ,  Kun-Hee Park

发明人： Tae-Hwa HONG ,  Byung-Jun Son ,  Soo-Kyun Kim ,  Sung-Dae Cho ,  Guee-Sang Lee ,  Sung-Ryul Oh ,  Kun-Hee Park

IPC分类号： G06K9/00 ,  G06K9/46

CPC分类号： G06K9/38 ,  G06K9/00449 ,  G06K9/346

摘要： A method for recognizing a music score included in an image and various information included in the music score, which may be obtained through a camera provided in a mobile terminal without requiring a separate editing program. The method includes detecting a region with staff lines from the image including the music score; detecting a region with an accompaniment chord from the image by taking the region with the staff lines and a region with a musical note into consideration; extracting and removing the staff lines from the music score included in the image; recognizing the musical note by extracting the musical note from the image, from which the staff lines have been removed; recognizing the accompaniment chord by extracting the accompaniment chord from the image, from which the staff lines have been removed; and generating data for reproducing a sound source corresponding to the musical note and accompaniment chord.

摘要翻译： 用于识别包括在图像中的乐谱的方法以及可以通过设置在移动终端中的相机获得的各种信息，其可以通过不需要单独的编辑程序来获得。 该方法包括从包括乐谱的图像检测具有人员线的区域; 通过考虑具有工作人员线的区域和具有音符的区域来检测来自图像的伴奏和弦的区域; 从图像中包含的乐谱中提取和删除人员线; 通过从图像中提取音符来识别音符，人员线从该图像中移除; 通过从图像中提取伴奏和声来识别伴奏和弦，从中删除人员线; 并产生用于再现对应于音符和伴奏和弦的声源的数据。

公开(公告)号：US08811744B2

公开(公告)日：2014-08-19

申请号：US12962309

申请日：2010-12-07

申请人： Tae-Hwa Hong ,  Young-Min Jeong ,  Joo-Young Son ,  Chang-Han Kim ,  Sung-Dae Cho

发明人： Tae-Hwa Hong ,  Young-Min Jeong ,  Joo-Young Son ,  Chang-Han Kim ,  Sung-Dae Cho

IPC分类号： G06K9/00 ,  G06K9/46 ,  G06K9/66

CPC分类号： G06K9/00228

摘要： A method for determining a frontal face pose by using the symmetry of a face including detecting a face region in an image, detecting an eye region in the detected face region, normalizing the face region, analyzing the symmetry in the normalized face region, and determining whether a face pose is a frontal face pose based on an analysis of the symmetry.

摘要翻译： 一种用于通过使用面部对称性来确定正面面部姿势的方法，包括检测图像中的面部区域，检测检测到的面部区域中的眼睛区域，归一化脸部区域，分析归一化脸部区域中的对称性，以及确定 基于对称性的分析，面部姿势是否是正面姿势。

公开(公告)号：US20110103706A1

公开(公告)日：2011-05-05

申请号：US12915993

申请日：2010-10-29

申请人： Young-Min JEONG ,  Sung-Dae Cho ,  Tae-Hwa Hong

发明人： Young-Min JEONG ,  Sung-Dae Cho ,  Tae-Hwa Hong

IPC分类号： G06K9/40

CPC分类号： G06T5/005 ,  G06T11/001 ,  G06T2207/20192

摘要： Disclosed is an image inpainting apparatus and method using a restricted search region. The image inpainting apparatus sets a target image region to be inpainted in response to an image inpainting request, sets a surrounding image region, which has a preset size and includes the set target image region, sets a plurality of similar image regions by grouping similar pixels in the surrounding image region, divides the surrounding image region into the plurality of set similar image regions, divides the target image region according to the similar image regions, sets a search region of each divided target image region, and detects an image of an image region most similar to each divided target image region from the set search region of each divided target image region, thereby performing image inpainting. Accordingly, image inpainting is performed using a search region, which has been determined to include a similar image most similar to an image to inpaint, so that it is possible to increase the probability of searching for an image most similar to the inpainting image region.

摘要翻译： 公开了使用限制搜索区域的图像修复装置和方法。 图像修像装置响应于图像修像请求设置要被修补的目标图像区域，设置具有预设尺寸并且包括设定的目标图像区域的周围图像区域，通过对相似的像素进行分组来设置多个相似的图像区域 在周围图像区域中，将周围图像区域划分为多个组合的相似图像区域，根据相似的图像区域划分目标图像区域，设置每个划分的目标图像区域的搜索区域，并检测图像的图像 区域与每个划分的目标图像区域的设置搜索区域最相似的区域，从而执行图像修复。 因此，使用已被确定为包括与图像最近似乎相似的图像的搜索区域的搜索区域执行图像修复，使得可以增加搜索与修复图像区域最相似的图像的概率。