公开(公告)号：US20130004077A1

公开(公告)日：2013-01-03

申请号：US13472790

申请日：2012-05-16

申请人： Jun SUN ,  Satoshi Naoi

发明人： Jun SUN ,  Satoshi Naoi

IPC分类号： G06K9/18

CPC分类号： G06K9/3208 ,  G06K9/342 ,  G06K2209/01

摘要： The present embodiments disclose a method of and device for identifying the direction of characters in an image block. The method includes: performing optical character recognition processing on the image block by assuming various directions as assumed character directions to obtain sub image blocks, recognized characters corresponding to the sub image blocks and correctness measures thereof in each assumed character directions; in sub image blocks in the assumed character directions with 180° mutual relation, searching for a minimum matching pair of the sub image blocks; adjusting the sub image blocks in the searched minimum matching pair to eliminate the effect, on an identification result, of different numbers of sub image blocks in various assumed character directions; calculating an accumulative correctness measure in each assumed character directions based on the adjusted sub image blocks; and identifying the direction of characters in the image block according to the accumulative correctness measures.

摘要翻译： 本实施例公开了用于识别图像块中的字符的方向的方法和装置。 该方法包括：通过假设各种方向作为假定的字符方向，对每个假定的字符方向进行图像块的识别处理，对应于子图像块的识别字符及其正确性度量，对图像块执行光学字符识别处理; 在具有180°相互关系的假定字符方向的子图像块中，搜索子图像块的最小匹配对; 调整搜索到的最小匹配对中的子图像块以消除识别结果对各种假定字符方向的不同数量的子图像块的影响; 基于经调整的子图像块计算每个假设字符方向上的累积正确性度量; 并根据累积的正确性度量来识别图像块中的字符的方向。

公开(公告)号：US20120063687A1

公开(公告)日：2012-03-15

申请号：US13156688

申请日：2011-06-09

申请人： Jun SUN ,  Hao Yu ,  Satoshi Naoi

发明人： Jun SUN ,  Hao Yu ,  Satoshi Naoi

IPC分类号： G06K9/46

CPC分类号： G06K9/6814 ,  G06K9/6224

摘要： Method and apparatus for processing an image including a character are disclosed. The method may include: searching in a set of characters one or more characters having highest similarities of shape to a character in the set of characters, hereinafter the character being referred to as a first character, the one or more searched characters forming a similar character list of the first character; searching in the set of characters one or more characters having highest similarities of shape to each character in the similar character list of the first character, to form a similar character list of each character in the similar character list of the first character; and selecting in the similar character lists one or more characters having a high mutual similarity between each other, as a character cluster.

摘要翻译： 公开了用于处理包括字符的图像的方法和装置。 该方法可以包括：在一组字符中搜索具有与该组文字中的字符具有最高相似度的一个或多个字符，此后字符被称为第一个字符，该一个或多个搜索到的字符形成相似的字符 第一个字符的列表; 在所述一组字符中搜索与所述第一字符的相似字符列表中的每个字符具有最高相似度形状的一个或多个字符，以形成所述第一字符的相似字符列表中每个字符的相似字符列表; 并且在相似的字符中选择一个或多个彼此之间具有高相互相似性的字符作为字符簇。

公开(公告)号：US07480409B2

公开(公告)日：2009-01-20

申请号：US11200202

申请日：2005-08-10

申请人： Sun Jun ,  Yutaka Katsuyama ,  Satoshi Naoi

发明人： Sun Jun ,  Yutaka Katsuyama ,  Satoshi Naoi

IPC分类号： G06K9/34 ,  G06K9/32 ,  G06K9/62

CPC分类号： G06K9/036 ,  G06K9/3266 ,  G06K9/6255 ,  G06K2209/01

摘要： A method and apparatus for generating a degraded character image at various levels of degradation automatically is presented in this invention. The method comprises rendering the character image on a scene plane; translating and rotating the scene plane according to various parameters; determining a projection region of the character image on an image plane according to various parameters; generating a pixel region mask; and generating a final degraded image by super-sampling. Thus various degraded character images are generated on various conditions of degradation. The generated synthetic characters can be used for performance evaluation and training data augmentation in optical character recognition (OCR).

摘要翻译： 本发明提供了一种用于在自动降级的各种劣化级别生成降级字符图像的方法和装置。 该方法包括：将场景平面上的人物图像渲染; 根据各种参数平移和旋转场景平面; 根据各种参数确定图像平面上的字符图像的投影区域; 生成像素区域掩模; 并通过超采样生成最终退化图像。 因此，在各种劣化条件下产生各种退化的字符图像。 所生成的合成字符可用于光学字符识别（OCR）中的性能评估和训练数据增加。

公开(公告)号：US20090016608A1

公开(公告)日：2009-01-15

申请号：US12168370

申请日：2008-07-07

申请人： Katsuhito Fujimoto ,  Misako Suwa ,  Satoshi Naoi

发明人： Katsuhito Fujimoto ,  Misako Suwa ,  Satoshi Naoi

IPC分类号： G06K9/00

CPC分类号： G06K9/6205 ,  G06K9/00463

摘要： According to an aspect of an embodiment, a method of character recognition out of an image having a frame and a plurality of characters in an area, comprises the steps of: dividing the area into a plurality of partial areas having a plurality of partial images, respectively; providing a template image having a reference frame image; calculating differences between the partial images and the reference frame image of the template image, respectively; calculating misalignment of the image from the template image based on the average of the differences of the partial images and the reference frame image; and recognizing the characters out of the image upon correction of the misalignment.

摘要翻译： 根据实施例的一个方面，一种在区域中具有帧和多个字符的图像中的字符识别方法包括以下步骤：将该区域划分为具有多个部分图像的多个部分区域， 分别; 提供具有参考帧图像的模板图像; 分别计算模板图像的部分图像和参考帧图像之间的差异; 基于所述部分图像和所述参考帧图像的差的平均值计算所述图像与所述模板图像的未对准; 并且在校正不对准时识别图像中的字符。

公开(公告)号：US07167281B1

公开(公告)日：2007-01-23

申请号：US09669663

申请日：2000-09-26

申请人： Katsuhito Fujimoto ,  Atsuko Ohara ,  Satoshi Naoi

发明人： Katsuhito Fujimoto ,  Atsuko Ohara ,  Satoshi Naoi

IPC分类号： H04N1/38 ,  H04N1/40 ,  H04N1/00 ,  H04N1/04

CPC分类号： H04N1/403 ,  G06K9/38 ,  G06K2209/01

摘要： It is judged for each pixel in an inputted multilevel image whether the pixel is a background pixel, and the pixel is locally binarized if it is judged not to be a background pixel. Then, it is judged whether the pixel belongs to a background or a stroke, such as of a character, ruled line, etc., and a binary image is generated.

摘要翻译： 判断输入的多值图像中的各像素是否为背景像素，如果判断为不是背景像素，则对像素进行局部二值化处理。 然后，判断像素是否属于诸如字符，划线等的背景或笔画，并且生成二进制图像。

公开(公告)号：US07146047B2

公开(公告)日：2006-12-05

申请号：US09956933

申请日：2001-09-21

申请人： Katsuhito Fujimoto ,  Atsuko Ohara ,  Satoshi Naoi

发明人： Katsuhito Fujimoto ,  Atsuko Ohara ,  Satoshi Naoi

IPC分类号： G06K9/46

CPC分类号： G06K9/346 ,  G06K2209/01

摘要： An information processing apparatus extracts a plurality of strokes from a multilevel image, and generates a stroke binary image. Next, the image processing apparatus extracts feature amounts indicating the thickness and the smoothed graylevel of a stroke in a neighboring region of a target pixel by using each pixel belonging to each of the strokes as the target pixel. Then, the apparatus generates a target stroke binary image from the stroke binary image based on the distribution of the extracted feature amounts.

摘要翻译： 信息处理装置从多级图像提取多个笔画，并生成笔画二进制图像。 接下来，图像处理装置通过使用属于每个笔画的每个像素作为目标像素，提取指示目标像素的相邻区域中的笔画的厚度和平滑灰度的特征量。 然后，该装置基于提取的特征量的分布从笔划二进制图像生成目标笔划二进制图像。

公开(公告)号：US07133558B1

公开(公告)日：2006-11-07

申请号：US09410626

申请日：1999-10-01

申请人： Atsuko Ohara ,  Satoshi Naoi

发明人： Atsuko Ohara ,  Satoshi Naoi

IPC分类号： G06K9/48 ,  G06K9/34

CPC分类号： G06K9/00449

摘要： A table image processing device processes a table image and a memory medium stores a processing program. The table image processing device processes precisely a table image containing a round corner and includes a device extracting a line extracting a longitudinal line and lateral line out of an input image, a device finding a potential match of a round corner region extracting an oblique line which commences from a terminal of a line found by the line extracting device, and finding the potential match of the round corner region, a device extracting a cell containing the potential match of the round corner found by the potential match of the round corner region finding device, and a device deciding the round corner part deciding the round corner from the cells found by the device extracting the cells.

摘要翻译： 表格图像处理装置处理表格图像，存储介质存储处理程序。 表格图像处理装置精确地处理包含圆角的表格图像，并且包括提取从输入图像提取纵向线和横向线的线的装置，找到提取斜线的圆角区域的潜在匹配的装置， 从线提取装置找到的线的终端开始，并找到圆角区域的潜在匹配，提取包含通过圆角区域查找装置的电位匹配发现的圆角的可能匹配的单元的装置 以及确定从提取单元的设备发现的小区决定圆角的圆角部分的设备。

公开(公告)号：US20060078204A1

公开(公告)日：2006-04-13

申请号：US09956933

申请日：2001-09-21

申请人： Katsuhito Fujimoto ,  Atsuko Ohara ,  Satoshi Naoi

发明人： Katsuhito Fujimoto ,  Atsuko Ohara ,  Satoshi Naoi

IPC分类号： G06K9/46

CPC分类号： G06K9/346 ,  G06K2209/01

摘要： An information processing apparatus extracts a plurality of strokes from a multilevel image, and generates a stroke binary image. Next, the image processing apparatus extracts feature amounts indicating the thickness and the smoothed graylevel of a stroke in a neighboring region of a target pixel by using each pixel belonging to each of the strokes as the target pixel. Then, the apparatus generates a target stroke binary image from the stroke binary image based on the distribution of the extracted feature amounts.

公开(公告)号：US20060056696A1

公开(公告)日：2006-03-16

申请号：US11200194

申请日：2005-08-10

申请人： Sun Jun ,  Yutaka Katsuyama ,  Satoshi Naoi

发明人： Sun Jun ,  Yutaka Katsuyama ,  Satoshi Naoi

IPC分类号： G06K9/18

CPC分类号： G06K9/6255

摘要： A method and apparatus for generating a degraded dictionary automatically is presented in this invention. Herein, a degraded pattern generating means generates a plurality of degraded patterns from an original character image, based on a plurality of degradation parameters. A degraded dictionary generating means generates a plurality of degraded dictionaries corresponding to the plurality of degradation parameters, based on the plurality of degradation patterns. Finally, a dictionary matching means selects one of the plurality of dictionaries which matches the degradation level of a test sample set best, as the final degraded dictionary. In this invention, various degraded patterns can be generated by means of simple scaling and blurring process for establishing degraded dictionaries. Therefore, the invention can be implemented simply and easily. The method and apparatus of the invention can not only be used in character recognition field, but also can be used in other fields such as speech recognition and face recognition.

公开(公告)号：US6141435A

公开(公告)日：2000-10-31

申请号：US681485

申请日：1996-07-23

申请人： Satoshi Naoi ,  Hiroichi Egawa ,  Morito Shiohara

发明人： Satoshi Naoi ,  Hiroichi Egawa ,  Morito Shiohara

IPC分类号： G01P3/36 ,  G01B11/00 ,  G01P13/00 ,  G06T1/00 ,  G06T7/20 ,  G06K9/00

CPC分类号： G06K9/3216 ,  G06T7/2053 ,  G06K2009/3225

摘要： An image processing apparatus for extracting the specified objects has a background image extract unit for extracting a background; a first average background extract unit which extracts an image that includes a plurality of stationary and moving objects each having a speed not higher than a predetermined first speed and also the background; a second average background extract unit which extracts an image that includes the stationary and moving objects each having a speed not higher than a predetermined second speed and also the background; a first difference-calculation processing unit which calculates a difference between an output from the background image extract unit and an output from the first average background extract unit as a first speed image; a second difference-calculation processing unit which calculates a difference value between two outputs from the first and second average background extract units as a second speed image; and a third difference-calculation processing unit which calculates a difference value between an original image and either one of outputs from the first and second average background extract units as a third speed image.