公开(公告)号：US20120148101A1

公开(公告)日：2012-06-14

申请号：US13325035

申请日：2011-12-13

申请人： Young Woo YOON ,  Ho Sub Yoon ,  Kyu Dae Ban ,  Jae Yeon Lee ,  Do Hyung Kim ,  Su Young Chi ,  Jae Hong Kim ,  Joo Chan Sohn

发明人： Young Woo YOON ,  Ho Sub Yoon ,  Kyu Dae Ban ,  Jae Yeon Lee ,  Do Hyung Kim ,  Su Young Chi ,  Jae Hong Kim ,  Joo Chan Sohn

IPC分类号： G06K9/18

CPC分类号： G06K9/325 ,  G06K2209/15

摘要： Disclosed is a method of extracting a text area, the method including generating a text area prediction value within an input second image based on a plurality of text area data stored in a database including geometric information about a text area of a first image, generating a text recognition result value by determining whether a text is recognized with respect to a probable text area within the input second image, and selecting a text area within the second image by combining the generated text area prediction value and text recognition result value.

摘要翻译： 公开了一种提取文本区域的方法，所述方法包括：基于存储在数据库中的多个文本区域数据，生成输入的第二图像内的文本区域预测值，所述文本区域数据包括关于第一图像的文本区域的几何信息， 通过确定文本是否相对于所输入的第二图像内的可能的文本区域被识别，以及通过组合生成的文本区域预测值和文本识别结果值来选择第二图像内的文本区域来选择文本识别结果值。

公开(公告)号：US08548201B2

公开(公告)日：2013-10-01

申请号：US13224178

申请日：2011-09-01

申请人： Ho Sub Yoon ,  Kyu Dae Ban ,  Young Woo Yoon ,  Woo Han Yun ,  Do Hyung Kim ,  Jae Yeon Lee ,  Jae Hong Kim ,  Su Young Chi ,  Joo Chan Sohn

发明人： Ho Sub Yoon ,  Kyu Dae Ban ,  Young Woo Yoon ,  Woo Han Yun ,  Do Hyung Kim ,  Jae Yeon Lee ,  Jae Hong Kim ,  Su Young Chi ,  Joo Chan Sohn

IPC分类号： G06K9/00

CPC分类号： G06K9/6256 ,  G06K9/3258

摘要： The present invention detects a candidate ROI group associated with character strings/figure strings on the basis of a result acquired through prior learning of various types of license plates, verifies the interested region candidate group detected by using at least one condition of five predetermined conditions, and determines an MBR region in the selected ROI region from the verified interested region candidate group by considering a ratio between the height and width of the ROI region to recognize the license plate for the automobile. According to the present invention, it is possible to automatically detect the location of the license plate regardless of various types of license plate specifications defined for each of countries.

摘要翻译： 本发明基于通过先前学习各种类型的车牌而获得的结果检测与字符串/图形串相关联的候选ROI组，通过使用五个预定条件的至少一个条件来检验感兴趣区域候选组， 并且通过考虑ROI区域的高度和宽度之间的比率来识别汽车的车牌，从所验证的感兴趣区域候选组中确定所选择的ROI区域中的MBR区域。 根据本发明，无论为每个国家定义的各种类型的车牌规格如何，都可以自动检测车牌的位置。

公开(公告)号：US08705814B2

公开(公告)日：2014-04-22

申请号：US13332879

申请日：2011-12-21

申请人： Woo Han Yun ,  Do Hyung Kim ,  Jae Yeon Lee ,  Kyu Dae Ban ,  Dae Ha Lee ,  Mun Sung Han ,  Ho Sub Yoon ,  Su Young Chi ,  Yun Koo Chung ,  Joo Chan Sohn ,  Hye Jin Kim ,  Young Woo Yoon ,  Jae Hong Kim ,  Jae Il Cho

发明人： Woo Han Yun ,  Do Hyung Kim ,  Jae Yeon Lee ,  Kyu Dae Ban ,  Dae Ha Lee ,  Mun Sung Han ,  Ho Sub Yoon ,  Su Young Chi ,  Yun Koo Chung ,  Joo Chan Sohn ,  Hye Jin Kim ,  Young Woo Yoon ,  Jae Hong Kim ,  Jae Il Cho

IPC分类号： G06K9/00

CPC分类号： G06K9/00362

摘要： Disclosed is a method of detecting an upper body. The method includes detecting an omega candidate area including a shape formed of a face and a shoulder line of a human from a target image, cutting the target image into the upper body candidate area including the omega candidate area, detecting a human face from the upper body candidate area, and judging whether the upper body of the human is included in the target image according to the result of detecting the human face.

摘要翻译： 公开了一种检测上身的方法。 该方法包括从目标图像中检测包括人脸的形状和肩部线的形状的欧米茄候选区域，将目标图像切割成包括欧米茄候选区域的上身候选区域，从上层检测人脸 根据检测人脸的结果来判断人的上半身是否包含在目标图像中。

公开(公告)号：US08934716B2

公开(公告)日：2015-01-13

申请号：US13599111

申请日：2012-08-30

申请人： Ho Sub Yoon ,  Ji Eun Kim ,  Kyu Dae Ban ,  Dong Jin Lee ,  Jae Hong Kim ,  Joo Chan Sohn

发明人： Ho Sub Yoon ,  Ji Eun Kim ,  Kyu Dae Ban ,  Dong Jin Lee ,  Jae Hong Kim ,  Joo Chan Sohn

IPC分类号： G06K9/34 ,  G06K9/46

CPC分类号： G06K9/00865 ,  G06K9/3258 ,  G06K9/348 ,  G06K2209/01

摘要： Disclosed is a method of sequencing character information in order to increase precision of character recognition. The method includes: a pre-processing that extracts character information from an image to binarize the extracted character information through a predetermined threshold and extracts and thins a center line of the binarized character information; normalizing the pre-processed character information to character information according to a predetermined criteria; and sequencing the normalized character information using structural features including an end point or a divergence point of the character information. The present invention suggests an angle normalization method of input character information, a structural feature position determining method, and a structural feature numeral string generating method to strongly recognize characters configured by various fonts obtained from a natural scene regardless of an angle or a size of the characters.

摘要翻译： 公开了一种对字符信息进行排序以提高字符识别精度的方法。 该方法包括：预处理，其从图像提取字符信息，以将所提取的字符信息二值化为预定阈值，并提取并清除二值化字符信息的中心线; 根据预定标准将预处理字符信息规范化为字符信息; 以及使用包括字符信息的终点或发散点的结构特征对归一化字符信息进行排序。 本发明提出一种输入字符信息的角度归一化方法，结构特征位置确定方法和结构特征数字串生成方法，用于强烈地识别从自然场景获得的各种字体配置的字符，而不管角度或尺寸如何 人物。