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. 发明申请

US20130044123A1 USER-SPECIFIED IMAGE COLORIZATION FOR APPLICATION USER INTERFACE 审中-公开
标题翻译：用户指定的应用用户界面的图像分类
公开(公告)号：US20130044123A1
公开(公告)日：2013-02-21
申请号：US13210381
申请日：2011-08-16
申请人： Harshit Shah , Erik Daniel Anderson , Veljko Miljanic , Fei Xiong , Paul Stephen Gildea , Kevin Welton , Markus Mielke , Sebastian Poulose
发明人： Harshit Shah , Erik Daniel Anderson , Veljko Miljanic , Fei Xiong , Paul Stephen Gildea , Kevin Welton , Markus Mielke , Sebastian Poulose
IPC分类号： G06T11/40
CPC分类号： G06F8/38 , G06T11/001
摘要： Techniques involving dynamic colorization of graphical user interfaces. One representative technique includes enabling a user to specify colors in which user interface elements will be colored in an application. An application colorization service is initiated in response to the user specification of the colors, which is used at least to obtain the colors specified by the user, and to create bitmap images of the application's user interface elements using the user-specified colors. A bitmap image output location is made accessible to the application to enable the application to retrieve the created bitmap images, and present the application using the application user interface elements having the user-specified colors.
摘要翻译：涉及图形用户界面动态着色的技术。一种代表性的技术包括使用户能够指定用户界面元素将在应用中被着色的颜色。响应于颜色的用户指定启动应用程序着色服务，该颜色至少用于获得用户指定的颜色，并且使用用户指定的颜色来创建应用程序的用户界面元素的位图图像。应用程序使位图图像输出位置可访问，以使应用程序能够检索创建的位图图像，并使用具有用户指定颜色的应用程序用户界面元素呈现应用程序。

2. 发明授权

US08881002B2 Trial based multi-column balancing 有权
标题翻译：基于试用的多列平衡
公开(公告)号：US08881002B2
公开(公告)日：2014-11-04
申请号：US13233408
申请日：2011-09-15
申请人： Evgeny N. Veselov , Peter G. Salas , Phillip F. Cupp , Michael Jacob Jolson , Markus W. Mielke , Veljko Miljanic
发明人： Evgeny N. Veselov , Peter G. Salas , Phillip F. Cupp , Michael Jacob Jolson , Markus W. Mielke , Veljko Miljanic
IPC分类号： G06F17/00 , G06F17/21
CPC分类号： G06F17/212
摘要： A trial based layout builder generates multiple trial multi-column layouts for content until a multi-column layout that satisfies particular criteria for multi-column balancing is generated. Multiple trial multi-column layouts can be generated in parallel based on different boundaries until a layout that does satisfy the criteria is identified. Different elements of the content laid out in different trial multi-column layouts can be reused in subsequently generated trial multi-column layouts. The content can also optionally be separated into multiple different portions at various break points, and trial multi-column layouts for the different portions can be generated in parallel. Additionally, if a trial multi-column layout for one of the portions that satisfies the particular criteria is identified, the content in that portion can be displayed while continuing to attempt to identify a layout for the content of the other portion that satisfies the one or more criteria.
摘要翻译：基于试用的布局构建器为内容生成多个试用多列布局，直到生成满足多列平衡特定标准的多列布局。可以基于不同的边界并行生成多个试验多列布局，直到确定满足标准的布局。在不同的试验多列布局中布置的内容的不同元素可以在随后生成的试验多列布局中重复使用。该内容还可以在各种断点处可选地分成多个不同的部分，并且可以并行地生成不同部分的试验多列布局。此外，如果识别满足特定标准的部分之一的试用多列布局，则可以显示该部分中的内容，同时继续尝试识别满足一个或另一个部分的另一部分的内容的布局更多的标准。

3. 发明申请

US20100080462A1 Letter Model and Character Bigram based Language Model for Handwriting Recognition 有权
标题翻译：字母模型和字符基于Bigram的手写识别语言模型
公开(公告)号：US20100080462A1
公开(公告)日：2010-04-01
申请号：US12239850
申请日：2008-09-29
申请人： Veljko Miljanic , Dave Stevens
发明人： Veljko Miljanic , Dave Stevens
IPC分类号： G06K9/18 , G06F17/27 , G09G5/00
CPC分类号： G06K9/00429 , G06K9/723 , G06K2209/01
摘要： A handwriting recognition system is described that includes a language model with scoring to improve recognition accuracy, such as for words outside of a selected language model. The handwriting recognition system increases the accuracy of handwriting recognizers that perform segmentation of ink into atomic elements (segments) and then classify each ink segment separately. After segmentation, a shape classifier estimates the class (letter) probabilities for each segment of ink by producing a corresponding score. The system applies the language model scoring to the shape classification results and typically selects the class with the highest score as the recognition result. Because the language model is not too restrictive, it works well for recognizing any word, even those that would not be in a dictionary for the current language. Thus, the handwriting recognition system produces better recognition results and can often recognize words that dictionary-based language models would not recognize correctly.
摘要翻译：描述了一种手写识别系统，其包括具有评分的语言模型以提高识别精度，例如对于所选语言模型之外的字。手写识别系统提高了执行墨水分解为原子元素（段）的手写识别器的准确度，然后分别对每个墨迹进行分类。分割后，形状分类器通过产生相应的分数来估计每段油墨的类（字母）概率。系统将语言模型评分应用于形状分类结果，通常选择具有最高分数的类作为识别结果。因为语言模型不是太限制性，它对于识别任何单词都是有效的，即使是那些不会在当前语言的字典中的单词。因此，手写识别系统产生更好的识别结果，并且可以经常识别基于字典的语言模型不能正确识别的单词。

4. 发明授权

US08559723B2 Letter model and character bigram based language model for handwriting recognition 有权
标题翻译：字母模型和字符双语语言模型的手写识别
公开(公告)号：US08559723B2
公开(公告)日：2013-10-15
申请号：US12239850
申请日：2008-09-29
申请人： Veljko Miljanic , Dave Stevens
发明人： Veljko Miljanic , Dave Stevens
IPC分类号： G06K9/18 , G06K9/34 , G06K7/10
CPC分类号： G06K9/00429 , G06K9/723 , G06K2209/01
摘要： A handwriting recognition system is described that includes a language model with scoring to improve recognition accuracy, such as for words outside of a selected language model. The handwriting recognition system increases the accuracy of handwriting recognizers that perform segmentation of ink into atomic elements (segments) and then classify each ink segment separately. After segmentation, a shape classifier estimates the class (letter) probabilities for each segment of ink by producing a corresponding score. The system applies the language model scoring to the shape classification results and typically selects the class with the highest score as the recognition result. Because the language model is not too restrictive, it works well for recognizing any word, even those that would not be in a dictionary for the current language. Thus, the handwriting recognition system produces better recognition results and can often recognize words that dictionary-based language models would not recognize correctly.
摘要翻译：描述了一种手写识别系统，其包括具有评分的语言模型以提高识别精度，例如对于所选语言模型之外的字。手写识别系统提高了执行墨水分解为原子元素（段）的手写识别器的准确度，然后分别对每个墨迹进行分类。分割后，形状分类器通过产生相应的分数来估计每段油墨的类（字母）概率。系统将语言模型评分应用于形状分类结果，通常选择具有最高分数的类作为识别结果。因为语言模型不是太限制性，它对于识别任何单词都是有效的，即使是那些不会在当前语言的字典中的单词。因此，手写识别系统产生更好的识别结果，并且可以经常识别基于字典的语言模型不能正确识别的单词。

5. 发明申请

US20130073943A1 TRIAL BASED MULTI-COLUMN BALANCING 有权
标题翻译：基于试验的多柱平衡
公开(公告)号：US20130073943A1
公开(公告)日：2013-03-21
申请号：US13233408
申请日：2011-09-15
申请人： Evgeny N. Veselov , Peter G. Salas , Phillip F. Cupp , Michael Jacob Jolson , Markus W. Mielke , Veljko Miljanic
发明人： Evgeny N. Veselov , Peter G. Salas , Phillip F. Cupp , Michael Jacob Jolson , Markus W. Mielke , Veljko Miljanic
IPC分类号： G06F17/20
CPC分类号： G06F17/212
摘要： A trial based layout builder generates multiple trial multi-column layouts for content until a multi-column layout that satisfies particular criteria for multi-column balancing is generated. Multiple trial multi-column layouts can be generated in parallel based on different boundaries until a layout that does satisfy the criteria is identified. Different elements of the content laid out in different trial multi-column layouts can be reused in subsequently generated trial multi-column layouts. The content can also optionally be separated into multiple different portions at various break points, and trial multi-column layouts for the different portions can be generated in parallel. Additionally, if a trial multi-column layout for one of the portions that satisfies the particular criteria is identified, the content in that portion can be displayed while continuing to attempt to identify a layout for the content of the other portion that satisfies the one or more criteria.
摘要翻译：基于试用的布局构建器为内容生成多个试用多列布局，直到生成满足多列平衡特定标准的多列布局。可以基于不同的边界并行生成多个试验多列布局，直到确定满足标准的布局。在不同的试验多列布局中布置的内容的不同元素可以在随后生成的试验多列布局中重复使用。该内容还可以在各种断点处可选地分成多个不同的部分，并且可以并行地生成不同部分的试验多列布局。此外，如果识别满足特定标准的部分之一的试用多列布局，则可以显示该部分中的内容，同时继续尝试识别满足一个或另一个部分的另一部分的内容的布局更多的标准。

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