公开(公告)号：US20110200257A1

公开(公告)日：2011-08-18

申请号：US13029845

申请日：2011-02-17

申请人： Sang-Wook Oh ,  Sang-Hoon Sull ,  Myung-Hoon Kim ,  Hoon-Jae Lee ,  Soon-Hong Jung ,  Jun-Sic Youn

发明人： Sang-Wook Oh ,  Sang-Hoon Sull ,  Myung-Hoon Kim ,  Hoon-Jae Lee ,  Soon-Hong Jung ,  Jun-Sic Youn

IPC分类号： G06K9/46

CPC分类号： G06K9/325 ,  G06K2209/01

摘要： A character region extracting apparatus and method which extract a character region through the calculation of character stroke widths are provided. The method includes producing a binary image including a candidate character region from an original image; extracting a character outline from the candidate character region; acquires character outline information for the extracted outline; setting a representative character stroke width and a representative character angle in each of the pixels forming the outline, based on the character outline information; and determining a character existing region in the candidate character region by confirming the ratio of effective representative stroke widths and effective angles as compared to the entire length of the outline. Accordingly, it is possible to efficiently determine whether one or more characters exist in the candidate character region.

摘要翻译： 提供了一种通过字符笔划宽度的计算提取字符区域的字符区域提取装置和方法。 该方法包括从原始图像生成包括候选字符区域的二进制图像; 从候选字符区域提取字符轮廓; 获取提取的轮廓的字符轮廓信息; 基于所述字符轮廓信息，在形成轮廓的每个像素中设置代表性的字符行程宽度和代表性角色; 以及通过确认与轮廓的整个长度相比有效的代表性行程宽度和有效角度的比率来确定候选字符区域中的字符存在区域。 因此，可以有效地确定候选字符区域中是否存在一个或多个字符。

公开(公告)号：US08744189B2

公开(公告)日：2014-06-03

申请号：US13029845

申请日：2011-02-17

申请人： Sang-Wook Oh ,  Sang-Hoon Sull ,  Myung-Hoon Kim ,  Hoon-Jae Lee ,  Soon-Hong Jung ,  Jun-Sic Youn

发明人： Sang-Wook Oh ,  Sang-Hoon Sull ,  Myung-Hoon Kim ,  Hoon-Jae Lee ,  Soon-Hong Jung ,  Jun-Sic Youn

IPC分类号： G06K9/00

CPC分类号： G06K9/325 ,  G06K2209/01

摘要： A character region extracting apparatus and method which extract a character region through the calculation of character stroke widths are provided. The method includes producing a binary image including a candidate character region from an original image; extracting a character outline from the candidate character region; acquires character outline information for the extracted outline; setting a representative character stroke width and a representative character angle in each of the pixels forming the outline, based on the character outline information; and determining a character existing region in the candidate character region by confirming the ratio of effective representative stroke widths and effective angles as compared to the entire length of the outline. Accordingly, it is possible to efficiently determine whether one or more characters exist in the candidate character region.

摘要翻译： 提供了一种通过字符笔划宽度的计算提取字符区域的字符区域提取装置和方法。 该方法包括从原始图像生成包括候选字符区域的二进制图像; 从候选字符区域提取字符轮廓; 获取提取的轮廓的字符轮廓信息; 基于所述字符轮廓信息，在形成轮廓的每个像素中设置代表性的字符行程宽度和代表性角色; 以及通过确认与轮廓的整个长度相比有效的代表性行程宽度和有效角度的比率来确定候选字符区域中的字符存在区域。 因此，可以有效地确定候选字符区域中是否存在一个或多个字符。

公开(公告)号：US08355571B2

公开(公告)日：2013-01-15

申请号：US13015194

申请日：2011-01-27

申请人： Sang-Wook Oh ,  Sang-Hoon Sull ,  Hoon-Jae Lee ,  Soon-Hong Jung ,  Jun-Sic Youn

发明人： Sang-Wook Oh ,  Sang-Hoon Sull ,  Hoon-Jae Lee ,  Soon-Hong Jung ,  Jun-Sic Youn

IPC分类号： G06K9/00 ,  G06K9/46 ,  G06K9/34

CPC分类号： G06K9/3258 ,  G06K9/38 ,  G06K2209/01

摘要： Provided is an apparatus and method for generating an image for character region extraction. Upon input of an original image, a candidate character image is generated from the original image and a plurality of binarization maps for similar colors are generated from the generated candidate character image. A binarization map including a background region is selected from among the plurality of generated binarization maps, and the background region of the selected binarization map is expanded. The expanded background region is inverted to generate an image including a character region, thereby generating an image for accurately extracting the character region without missing a boundary portion of a character.

摘要翻译： 提供了一种用于生成用于字符区域提取的图像的装置和方法。 在输入原始图像时，从原始图像生成候选字符图像，并且从生成的候选字符图像生成用于类似颜色的多个二值化图。 从多个生成的二值化图中选择包括背景区域的二值化图，并且扩大所选择的二值化图的背景区域。 扩展背景区域被反转以产生包括字符区域的图像，从而生成用于精确地提取字符区域而不丢失字符的边界部分的图像。

公开(公告)号：US20110200250A1

公开(公告)日：2011-08-18

申请号：US13015194

申请日：2011-01-27

申请人： Sang-Wook OH ,  Sang-Hoon Sull ,  Hoon-Jae Lee ,  Soon-Hoog Jung ,  Jun-Sic Youn

发明人： Sang-Wook OH ,  Sang-Hoon Sull ,  Hoon-Jae Lee ,  Soon-Hoog Jung ,  Jun-Sic Youn

IPC分类号： G06K9/34

CPC分类号： G06K9/3258 ,  G06K9/38 ,  G06K2209/01

摘要： Provided is an apparatus and method for generating an image for character region extraction. Upon input of an original image, a candidate character image is generated from the original image and a plurality of binarization maps for similar colors are generated from the generated candidate character image. A binarization map including a background region is selected from among the plurality of generated binarization maps, and the background region of the selected binarization map is expanded. The expanded background region is inverted to generate an image including a character region, thereby generating an image for accurately extracting the character region without missing a boundary portion of a character.

摘要翻译： 提供了一种用于生成用于字符区域提取的图像的装置和方法。 在输入原始图像时，从原始图像生成候选字符图像，并且从生成的候选字符图像生成用于类似颜色的多个二值化图。 从多个生成的二值化图中选择包括背景区域的二值化图，并且扩大所选择的二值化图的背景区域。 扩展背景区域被反转以产生包括字符区域的图像，从而生成用于精确地提取字符区域而不丢失字符的边界部分的图像。

公开(公告)号：US20120051633A1

公开(公告)日：2012-03-01

申请号：US13222648

申请日：2011-08-31

申请人： Jung-Rim KIM ,  Sang-Hoon Sull ,  Soon-Hong Jung ,  Eun-Heui Cho

发明人： Jung-Rim KIM ,  Sang-Hoon Sull ,  Soon-Hong Jung ,  Eun-Heui Cho

IPC分类号： G06K9/34

CPC分类号： G06T11/00

摘要： A method and apparatus are provided for generating a character collage message. A character is recognized from an image. A region is extracted from the image to create a character image. The region includes the recognized character. The created character image is stored in a memory. At least the character image is output to an output unit as the character collage message in accordance with input of one or more characters through an input unit. At least one of the one or more characters corresponds to the character image, and the character image is output to the output unit as a substitute for the at least one of the one or more characters.

摘要翻译： 提供了一种用于生成角色拼贴消息的方法和装置。 从图像中识别出一个角色。 从图像中提取区域以创建字符图像。 该地区包括公认的角色。 创建的字符图像存储在存储器中。 根据通过输入单元的一个或多个字符的输入，至少将字符图像作为字符拼接消息输出到输出单元。 所述一个或多个字符中的至少一个对应于所述字符图像，并且所述字符图像作为所述一个或多个字符中的至少一个字符的替换被输出到所述输出单元。

公开(公告)号：US09159143B2

公开(公告)日：2015-10-13

申请号：US13222648

申请日：2011-08-31

申请人： Jung-Rim Kim ,  Sang-Hoon Sull ,  Soon-Hong Jung ,  Eun-Heui Cho

发明人： Jung-Rim Kim ,  Sang-Hoon Sull ,  Soon-Hong Jung ,  Eun-Heui Cho

IPC分类号： G06K9/18 ,  G06T11/00

CPC分类号： G06T11/00

摘要： A method and apparatus are provided for generating a character collage message. A character is recognized from an image. A region is extracted from the image to create a character image. The region includes the recognized character. The created character image is stored in a memory. At least the character image is output to an output unit as the character collage message in accordance with input of one or more characters through an input unit. At least one of the one or more characters corresponds to the character image, and the character image is output to the output unit as a substitute for the at least one of the one or more characters.

摘要翻译： 提供了一种用于生成角色拼贴消息的方法和装置。 从图像中识别出一个角色。 从图像中提取区域以创建字符图像。 该地区包括公认的角色。 创建的字符图像存储在存储器中。 根据通过输入单元的一个或多个字符的输入，至少将字符图像作为字符拼接消息输出到输出单元。 所述一个或多个字符中的至少一个对应于所述字符图像，并且所述字符图像作为所述一个或多个字符中的至少一个字符的替换被输出到所述输出单元。

公开(公告)号：US06609134B1

公开(公告)日：2003-08-19

申请号：US09496306

申请日：2000-02-01

申请人： Hyun-Sung Chang ,  Sang-Hoon Sull ,  Sang-Uk Lee ,  Nam-Kyu Kim

发明人： Hyun-Sung Chang ,  Sang-Hoon Sull ,  Sang-Uk Lee ,  Nam-Kyu Kim

IPC分类号： G06F1730

CPC分类号： G06K9/00711 ,  G06F17/30858 ,  Y10S707/913 ,  Y10S707/914 ,  Y10S707/99945

摘要： An apparatus and method for retrieving a moving picture using a descriptor of a tree-structured moving picture index. If the user starts a query for the retrieval of information, a decoder sends an in-index highest-order key frame number, in-index edge information and an intra-layer threshold value list of a tree-structured moving picture index descriptor stored therein to a server environment. Then, the server environment reads a key frame number and sends it to the decoder. The decoder sends a feature vector designated by the key frame number to the server environment. Subsequently, the server environment first compares the designated feature vector with a query feature vector and, thereafter, the compared result with a threshold value and retrieval precision desired by the user to determine whether the key frame number is concerned with a query picture. If the key frame number is concerned with the query picture, the server environment transfers the retrieved result to a user environment. This processing is sequentially carried out by key frame numbers.

摘要翻译： 一种用于使用树结构的运动图像索引的描述符来检索运动图像的装置和方法。 如果用户开始查询信息，则解码器发送索引中最高阶的关键帧号码，索引内边缘信息和存储在其中的树结构的运动图像索引描述符的层内阈值列表 到服务器环境。 然后，服务器环境读取一个关键帧号并将其发送到解码器。 解码器将由关键帧号指定的特征向量发送到服务器环境。 随后，服务器环境首先将指定的特征向量与查询特征向量进行比较，然后比较具有用户所期望的阈值和检索精度的比较结果，以确定关键帧号是否与查询图片有关。 如果关键帧编号与查询图片有关，则服务器环境将检索结果传送到用户环境。 该处理依次由关键帧号执行。