专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US08526732B2 Text enhancement of a textual image undergoing optical character recognition 有权
标题翻译：正在进行光学字符识别的文字图像的文本增强
公开(公告)号：US08526732B2
公开(公告)日：2013-09-03
申请号：US12720732
申请日：2010-03-10
申请人： Sasa Galic , Djordje Nijemcevic , Bodin Dresevic
发明人： Sasa Galic , Djordje Nijemcevic , Bodin Dresevic
IPC分类号： G06K9/00
CPC分类号： G06K9/4638 , G06K9/38 , G06K2209/01 , G06K2209/015
摘要： A method for enhancing a textual image for undergoing optical character recognition begins by receiving an image that includes native lines of text. A background line profile is determined which represents an average background intensity along the native lines in the image. Likewise, a foreground line profile is determined which represents an average foreground background intensity along the native lines in the image. The pixels in the image are assigned to either a background or foreground portion of the image based at least in part on the background line profile and the foreground line profile. The intensity of the pixels designated to the background portion of the image is adjusted to a maximum brightness so as to represent a portion of the image that does not include text.
摘要翻译：用于增强用于进行光学字符识别的文本图像的方法通过接收包括原生文本行的图像开始。确定背景线轮廓，其表示沿着图像中的原生线的平均背景强度。同样，确定前景线轮廓，其表示沿着图像中的本机线的平均前景背景强度。至少部分地基于背景线轮廓和前景线轮廓，将图像中的像素分配给图像的背景或前景部分。将指定给图像的背景部分的像素的强度调整到最大亮度，以便表示不包括文本的图像的一部分。

2. 发明申请

US20110222768A1 TEXT ENHANCEMENT OF A TEXTUAL IMAGE UNDERGOING OPTICAL CHARACTER RECOGNITION 有权
标题翻译：纹理识别的文字图像的文本增强
公开(公告)号：US20110222768A1
公开(公告)日：2011-09-15
申请号：US12720732
申请日：2010-03-10
申请人： Sasa Galic , Djordje Nijemcevic , Bodin Dresevic
发明人： Sasa Galic , Djordje Nijemcevic , Bodin Dresevic
IPC分类号： G06K9/46 , G06K9/00
CPC分类号： G06K9/4638 , G06K9/38 , G06K2209/01 , G06K2209/015
摘要： A method for enhancing a textual image for undergoing optical character recognition begins by receiving an image that includes native lines of text. A background line profile is determined which represents an average background intensity along the native lines in the image. Likewise, a foreground line profile is determined which represents an average foreground background intensity along the native lines in the image. The pixels in the image are assigned to either a background or foreground portion of the image based at least in part on the background line profile and the foreground line profile. The intensity of the pixels designated to the background portion of the image is adjusted to a maximum brightness so as to represent a portion of the image that does not include text.
摘要翻译：用于增强用于进行光学字符识别的文本图像的方法通过接收包括原生文本行的图像开始。确定背景线轮廓，其表示沿着图像中的原生线的平均背景强度。同样，确定前景线轮廓，其表示沿着图像中的本机线的平均前景背景强度。至少部分地基于背景线轮廓和前景线轮廓，将图像中的像素分配给图像的背景或前景部分。将指定给图像的背景部分的像素的强度调整到最大亮度，以便表示不包括文本的图像的一部分。

3. 发明申请

US20110069180A1 CAMERA-BASED SCANNING 有权
标题翻译：摄像机扫描
公开(公告)号：US20110069180A1
公开(公告)日：2011-03-24
申请号：US12578445
申请日：2009-10-13
申请人： Djordje Nijemcevic , Magdalena Vukosavljevic , Milan Vugdelija , Ana Mitrovic , Georg F. Petschnigg , Bodin Dresevic
发明人： Djordje Nijemcevic , Magdalena Vukosavljevic , Milan Vugdelija , Ana Mitrovic , Georg F. Petschnigg , Bodin Dresevic
IPC分类号： H04N5/225 , H04N5/262
CPC分类号： H04N5/23293 , G06K9/3216 , H04N1/00251 , H04N1/00307
摘要： Embodiments of camera-based scanning are described. In various embodiments, scanned documents can be created using images captured by a camera associated with a device. An image captured by the camera is processed to identify portions within the image that correspond to rectangular objects such as paper, business cards, whiteboards, screens, and so forth. One or more of these portions can be selected for scanning automatically based on a scoring scheme and/or semi-automatically with the aid of input from a user. One or more scanned documents are created from the selected portions by un-warping the selected portions to remove effects of perspective (e.g., rectify the portions to rectangles) and applying various image enhancements to improve appearance.
摘要翻译：描述基于相机的扫描的实施例。在各种实施例中，可以使用与设备相关联的摄像机捕获的图像来创建扫描的文档。处理由相机拍摄的图像以识别图像中对应于矩形对象（例如纸张，名片，白板，屏幕等）的部分。可以选择这些部分中的一个或多个，以便借助于来自用户的输入，基于评分方案和/或半自动地自动扫描。通过使所选择的部分变形来去除所选部分中的一个或多个扫描文档，以去除透视效果（例如，将部分整理为矩形）并应用各种图像增强以改善外观。

4. 发明授权

US08345106B2 Camera-based scanning 有权
标题翻译：基于相机的扫描
公开(公告)号：US08345106B2
公开(公告)日：2013-01-01
申请号：US12578445
申请日：2009-10-13
申请人： Djordje Nijemcevic , Magdalena Vukosavljevic , Milan Vugdelija , Ana Mitrovic , Georg F. Petschnigg , Bodin Dresevic
发明人： Djordje Nijemcevic , Magdalena Vukosavljevic , Milan Vugdelija , Ana Mitrovic , Georg F. Petschnigg , Bodin Dresevic
IPC分类号： H04N5/225 , H04N5/228 , H04N5/222 , G06K9/20
CPC分类号： H04N5/23293 , G06K9/3216 , H04N1/00251 , H04N1/00307
摘要： Embodiments of camera-based scanning are described. In various embodiments, scanned documents can be created using images captured by a camera associated with a device. An image captured by the camera is processed to identify portions within the image that correspond to rectangular objects such as paper, business cards, whiteboards, screens, and so forth. One or more of these portions can be selected for scanning automatically based on a scoring scheme and/or semi-automatically with the aid of input from a user. One or more scanned documents are created from the selected portions by un-warping the selected portions to remove effects of perspective (e.g., rectify the portions to rectangles) and applying various image enhancements to improve appearance.
摘要翻译：描述基于相机的扫描的实施例。在各种实施例中，可以使用与设备相关联的摄像机捕获的图像来创建扫描的文档。处理由相机拍摄的图像以识别图像中对应于矩形对象（例如纸张，名片，白板，屏幕等）的部分。可以选择这些部分中的一个或多个，以便借助于来自用户的输入，基于评分方案和/或半自动地自动扫描。通过使所选择的部分变形来去除所选部分中的一个或多个扫描文档，以去除透视效果（例如，将部分整理为矩形）并应用各种图像增强以改善外观。

5. 发明授权

US08311331B2 Resolution adjustment of an image that includes text undergoing an OCR process 有权
标题翻译：包含正在进行OCR过程的文本的图像的分辨率调整
公开(公告)号：US08311331B2
公开(公告)日：2012-11-13
申请号：US12719894
申请日：2010-03-09
申请人： Djordje Nijemcevic , Milan Vugdelija , Bodin Dresevic
发明人： Djordje Nijemcevic , Milan Vugdelija , Bodin Dresevic
IPC分类号： G06K9/34
CPC分类号： G06K9/3283 , G06K9/00463 , G06K2209/01
摘要： An optical character recognition process characterizes text lines in a textual image by their base-line, mean-line and x-height. The base-line for at least one text line in the image is determined by finding a parametric curve that maximizes a first fitness function that depends on the values of pixels through which the parametric curve passes and pixels below the parametric curve. The base-line corresponds to the parametric curve for which the first fitness function is maximized. The first fitness function is designed so that it increases with increasing lightless or brightness of pixels immediately below the parametric curve while also increasing with decreasing lightness of pixels through which the parametric curve passes. The mean-line is determined by incrementally shifting the base-line upward by predetermined amounts (e.g., a single pixel) until a second fitness function for the shifted base-line is maximized. The second fitness function is essentially the inverse of the first fitness function. Specifically, the second fitness function increases with increasing lightless of pixels immediately above the shifted base-line while also increasing with decreasing lightness of pixels through which the shifted base-line passes. The x-height is equal to the sum of the predetermined amounts by which the base-line is shifted upward in order to maximize the second fitness function. In some cases different groups of text-lines in the textual image may be characterized differently from one another. For example, each group may be characterized by a most probable x-height for that group.
摘要翻译：光学字符识别过程通过其基线，平均线和x高度来表征文本图像中的文本行。通过找到最大化第一适应度函数的参数曲线来确定图像中至少一条文本行的基线，该参数曲线取决于参数曲线通过的像素的值和参数曲线下方的像素。基线对应于第一适应度函数最大化的参数曲线。第一适应度功能被设计成随着参数曲线正下方的像素的无光或亮度的增加而增加，同时随着参数曲线通过的像素的亮度的减小而增加。通过将基线向上逐渐地移动预定量（例如，单个像素）直到用于移位的基线的第二适应度函数最大化来确定平均线。第二适应度函数本质上是第一适应度函数的倒数。具体地，第二适应度函数随着位于移动基线上方的像素的无光增加而增加，同时随着偏移的基线通过的像素的亮度的减小而增加。 x高度等于基线向上移位的预定量的总和，以便使第二适应度函数最大化。在某些情况下，文本图像中不同的文本行组可能具有彼此不同的特征。例如，每个组的特征可以是该组的最可能的x-高度。

6. 发明申请

US20110222772A1 RESOLUTION ADJUSTMENT OF AN IMAGE THAT INCLUDES TEXT UNDERGOING AN OCR PROCESS 有权
标题翻译：分辨率调整包含OCR过程文本的图像
公开(公告)号：US20110222772A1
公开(公告)日：2011-09-15
申请号：US12719894
申请日：2010-03-09
申请人： Djordje Nijemcevic , Milan Vugdelija , Bodin Dresevic
发明人： Djordje Nijemcevic , Milan Vugdelija , Bodin Dresevic
IPC分类号： G06K9/18
CPC分类号： G06K9/3283 , G06K9/00463 , G06K2209/01
摘要： An optical character recognition process characterizes text lines in a textual image by their base-line, mean-line and x-height. The base-line for at least one text line in the image is determined by finding a parametric curve that maximizes a first fitness function that depends on the values of pixels through which the parametric curve passes and pixels below the parametric curve. The base-line corresponds to the parametric curve for which the first fitness function is maximized. The first fitness function is designed so that it increases with increasing lightless or brightness of pixels immediately below the parametric curve while also increasing with decreasing lightness of pixels through which the parametric curve passes. The mean-line is determined by incrementally shifting the base-line upward by predetermined amounts (e.g., a single pixel) until a second fitness function for the shifted base-line is maximized. The second fitness function is essentially the inverse of the first fitness function. Specifically, the second fitness function increases with increasing lightless of pixels immediately above the shifted base-line while also increasing with decreasing lightness of pixels through which the shifted base-line passes. The x-height is equal to the sum of the predetermined amounts by which the base-line is shifted upward in order to maximize the second fitness function. In some cases different groups of text-lines in the textual image may be characterized differently from one another. For example, each group may be characterized by a most probable x-height for that group.
摘要翻译：光学字符识别过程通过其基线，平均线和x高度来表征文本图像中的文本行。通过找到最大化第一适应度函数的参数曲线来确定图像中至少一条文本行的基线，该参数曲线取决于参数曲线通过的像素的值和参数曲线下方的像素。基线对应于第一适应度函数最大化的参数曲线。第一适应度功能被设计成随着参数曲线正下方的像素的无光或亮度的增加而增加，同时随着参数曲线通过的像素的亮度的减小而增加。通过将基线向上逐渐地移动预定量（例如，单个像素）直到用于移位的基线的第二适应度函数最大化来确定平均线。第二适应度函数本质上是第一适应度函数的倒数。具体地，第二适应度函数随着位于移动基线上方的像素的无光增加而增加，同时随着偏移的基线通过的像素的亮度的减小而增加。 x高度等于基线向上移位的预定量的总和，以便使第二适应度函数最大化。在某些情况下，文本图像中不同的文本行组可能具有彼此不同的特征。例如，每个组的特征可以是该组的最可能的x-高度。

7. 发明申请

US20110243445A1 DETECTING POSITION OF WORD BREAKS IN A TEXTUAL LINE IMAGE 有权
标题翻译：检测文字线图像中的字符位置
公开(公告)号：US20110243445A1
公开(公告)日：2011-10-06
申请号：US12749599
申请日：2010-03-30
申请人： Aleksandar Uzelac , Bodin Dresevic , Sasa Galic , Bogdan Radakovic
发明人： Aleksandar Uzelac , Bodin Dresevic , Sasa Galic , Bogdan Radakovic
IPC分类号： G06K9/34 , G06K9/18
CPC分类号： G06K9/344 , G06K9/342 , G06K2209/01
摘要： Line segmentation in an OCR process is performed to detect the positions of words within an input textual line image by extracting features from the input to locate breaks and then classifying the breaks into one of two break classes which include inter-word breaks and inter-character breaks. An output including the bounding boxes of the detected words and a probability that a given break belongs to the identified class can then be provided to downstream OCR or other components for post-processing. Advantageously, by reducing line segmentation to the extraction of features, including the position of each break and the number of break features, and break classification, the task of line segmentation is made less complex but with no loss of generality.
摘要翻译：执行OCR处理中的线分割以通过从输入中提取特征来定位分组，然后将分组分类成包括字间间隔和字符间的两个断点类之一来检测输入文本行图像内的单词的位置休息然后可以将包括检测到的单词的边界框和给定中断属于所识别的类别的概率的输出提供给下游OCR或用于后处理的其他组件。有利的是，通过将行分割减少到特征的提取，包括每个断点的位置和断裂特征的数量以及断裂分类，线分割的任务变得不那么复杂，但不失一般性。

8. 发明授权

US08345978B2 Detecting position of word breaks in a textual line image 有权
标题翻译：检测文字行图像中的分词位置
公开(公告)号：US08345978B2
公开(公告)日：2013-01-01
申请号：US12749599
申请日：2010-03-30
申请人： Aleksandar Uzelac , Bodin Dresevic , Sasa Galic , Bogdan Radakovic
发明人： Aleksandar Uzelac , Bodin Dresevic , Sasa Galic , Bogdan Radakovic
IPC分类号： G06K9/00
CPC分类号： G06K9/344 , G06K9/342 , G06K2209/01
摘要： Line segmentation in an OCR process is performed to detect the positions of words within an input textual line image by extracting features from the input to locate breaks and then classifying the breaks into one of two break classes which include inter-word breaks and inter-character breaks. An output including the bounding boxes of the detected words and a probability that a given break belongs to the identified class can then be provided to downstream OCR or other components for post-processing. Advantageously, by reducing line segmentation to the extraction of features, including the position of each break and the number of break features, and break classification, the task of line segmentation is made less complex but with no loss of generality.
摘要翻译：执行OCR处理中的线分割以通过从输入中提取特征来定位分组，然后将分组分类成包括字间间隔和字符间的两个断点类之一来检测输入文本行图像内的单词的位置休息然后可以将包括检测到的单词的边界框和给定中断属于所识别的类别的概率的输出提供给下游OCR或用于后处理的其他组件。有利的是，通过将行分割减少到特征的提取，包括每个断点的位置和断裂特征的数量以及断裂分类，线分割的任务变得不那么复杂，但不失一般性。

9. 发明授权

US08250469B2 Document layout extraction 有权
标题翻译：文件布局提取
公开(公告)号：US08250469B2
公开(公告)日：2012-08-21
申请号：US11949537
申请日：2007-12-03
申请人： Bodin Dresevic , Oren Trutner , Sasa Tomasevic , Aleksandar Uzelac , Dejan Lukacevic
发明人： Bodin Dresevic , Oren Trutner , Sasa Tomasevic , Aleksandar Uzelac , Dejan Lukacevic
IPC分类号： G06F17/00
CPC分类号： G06F17/2241 , G06F17/2205 , G06F17/2264 , G06F17/30011
摘要： Computer-readable media, systems, and methods for document layout extraction are described. In embodiments, textual data in an electronic format is received and the textual data is converted from the electronic format to an independent interface format, the independent interface format including coordinates to one or more structural elements of the textual data. Further, in embodiments, a structure and layout analysis of the textual data is performed to generate a set of structure and layout information. Still further, in embodiments, the textual data and the set of structure and layout information is stored in an enriched interface format, the enriched interface format providing for search and navigation of the textual data.
摘要翻译：描述了用于文档布局提取的计算机可读介质，系统和方法。在实施例中，接收电子格式的文本数据，并将文本数据从电子格式转换为独立接口格式，独立接口格式包括对文本数据的一个或多个结构元素的坐标。此外，在实施例中，执行文本数据的结构和布局分析以生成一组结构和布局信息。此外，在实施例中，文本数据和结构和布局信息集合以丰富的界面格式存储，提供用于文本数据的搜索和导航的丰富的界面格式。

10. 发明授权

US07870501B2 Method for hollow selection feedback 有权
标题翻译：中空选择反馈方法
公开(公告)号：US07870501B2
公开(公告)日：2011-01-11
申请号：US11067949
申请日：2005-03-01
申请人： Marieke Iwema , Shawna Davis , Robert J. Jarrett , F. David Jones , Guy Barker , Bodin Dresevic
发明人： Marieke Iwema , Shawna Davis , Robert J. Jarrett , F. David Jones , Guy Barker , Bodin Dresevic
IPC分类号： G06F3/048
CPC分类号： G06F3/0488 , G06F3/0481 , G06T11/203
摘要： An improved approach to highlighting a graphical object in a graphical user interface is disclosed. A body of a highlighted graphical object may, upon selection or highlighting, be changed to a transparent color, and a graphical outline, or “halo,” is added surrounding the original graphical object's body. The halo may be in the same color as the graphical object originally was, preserving any meaning attributed to the color of the graphical object and simplifying the user's ability to identify the selected object(s), as well as the ability to select the highlighted object for further processing. The highlighted graphical object may also be displayed with a bounding box to further identify the selected object(s). A moving version of the highlighted graphical object may be drawn during a moving process, in which the moving version has an appearance distinct from the original object.
摘要翻译：公开了一种在图形用户界面中突出显示图形对象的改进方法。突出显示的图形对象的主体可以在选择或突出显示时被改变为透明颜色，并且围绕原始图形对象的主体添加图形轮廓或“晕”。光晕可能与原始图形对象的颜色相同，保留了归因于图形对象的颜色的任何意义，并简化了用户识别所选对象的能力，以及选择突出显示的对象的能力进一步处理。突出显示的图形对象也可以用边界框显示以进一步标识所选择的对象。在移动过程中可绘制突出显示的图形对象的移动版本，其中移动版本具有与原始对象不同的外观。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式