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. 发明专利

JP2010279038A Method and system for electronic image real-time personalization 有权
标题翻译：电子图像实时个性化的方法和系统
公开(公告)号：JP2010279038A
公开(公告)日：2010-12-09
申请号：JP2010121194
申请日：2010-05-27
申请人： Xerox Corp , ゼロックスコーポレイションXerox Corporation
发明人： CHAPMAN EDWARD , DING HENGZHOU , ESCHBACH REINER , BALA RAJA
IPC分类号： H04N1/387 , B41J29/38 , G06F3/12 , G06T1/00
CPC分类号： G06T11/60
摘要： PROBLEM TO BE SOLVED: To perform personalization of electronic images on real time. SOLUTION: A system 10 has a processor 14 which executes a group of instructions executable by a computer stored on a memory 16. The group of instructions includes the steps of receiving input coordinates of each peak of a quadrilateral 28 considered to exist on a certain plane in electronic images; reading one or more variable text strings 32 from a database; performing affine transformation 30 so that each variable text string matches a rectangular text box; performing nonlinear projection conversion 24 to the rectangular text box so that the peaks of the rectangular text box are moved to respective peaks of the quadrilateral; and rendering converted variable text strings into quadrilaterals on each version of the electronic images, respectively. The system 10 has a printer 22 which prints electronic images, such that the variable text string has been located in the quadrilateral. COPYRIGHT: (C)2011,JPO&INPIT
摘要翻译：要解决的问题：实时地执行电子图像的个性化。解决方案：系统10具有处理器14，处理器14执行可由存储在存储器16上的计算机执行的指令组。指令组包括以下步骤：接收被认为存在于存储器16上的四边形28的每个峰值的输入坐标电子图像中的某一平面; 从数据库读取一个或多个可变文本串32; 执行仿射变换30，使得每个可变文本字符串匹配矩形文本框; 对矩形文本框执行非线性投影转换24，使矩形文本框的峰移动到四边形的各个峰; 并分别在每个版本的电子图像上将转换的可变文本字符串渲染成四边形。系统10具有打印电子图像的打印机22，使得可变文本串已经位于四边形中。版权所有（C）2011，JPO＆INPIT

2. 发明专利

JP2014071900A Visibility improvement in bad weather using enhanced reality 审中-公开
标题翻译：使用增强现实的天气中的可见性改进
公开(公告)号：JP2014071900A
公开(公告)日：2014-04-21
申请号：JP2013197292
申请日：2013-09-24
申请人： Xerox Corp , ゼロックスコーポレイションXerox Corporation
发明人： ZIGAN WANG , DING HENGZHOU
IPC分类号： G08G1/16 , G01C21/36 , G06T19/00
CPC分类号： G06K9/00671 , G06F17/30241 , G06T11/00 , Y02A90/15
摘要： PROBLEM TO BE SOLVED: To provide methods and systems for improving driver visibility during bad weather and/or poor lighting for objects such as road signs, road lines, and road markings.SOLUTION: The disclosed approach can enhance captured images by exploiting priori knowledge about the scene and the objects that are stored in a database. In general, the orientation and location of a vehicle can be determined, and data can be retrieved which is indicative of stationary objects that are anticipated to be detectable at a current orientation and location of the vehicle. A captured scene is compared to data retrieved from the database by using the information regarding the orientation and location of the vehicle so that a matching scene indicates where objects are expected to appear in the captured scene and improve driver visibility with respect to the vehicle during poor driving conditions.
摘要翻译：要解决的问题：提供在恶劣天气和/或恶劣照明下提高驾驶员可视性的方法和系统，如道路标志，路线和道路标记等。解决方案：所公开的方法可以通过利用先前的知识来增强捕获的图像场景和存储在数据库中的对象。通常，可以确定车辆的方向和位置，并且可以检索指示预定在车辆的当前方向和位置处可检测的静止物体的数据。将捕获的场景与通过使用关于车辆的取向和位置的信息从数据库检索的数据进行比较，使得匹配场景指示预期在被捕获的场景中出现物体的位置，并且在差的时候提高驾驶员相对于车辆的可视性驾驶条件。

3. 发明专利

JP2013257866A Discovery of text in natural scenery 有权
标题翻译：发现自然景观中的文字
公开(公告)号：JP2013257866A
公开(公告)日：2013-12-26
申请号：JP2013111587
申请日：2013-05-28
申请人： Xerox Corp , ゼロックスコーポレイションXerox Corporation
发明人： RAJA BALA , ZIGAN WANG , DING HENGZHOU , JAN P ALLEBACH , BOUMAN CHARLES A
IPC分类号： G06T7/40 , G06K9/20
CPC分类号： G06K9/4604 , G06K9/3258 , G06K9/4638 , G06K2209/01 , G06T7/13 , G06T7/181 , G06T2207/10004
摘要： PROBLEM TO BE SOLVED: To simplify the providing of a method based on efficient edge detection and a closed curve in order to find text in natural scenery of a photographic image, a digital image, and/or an electronic image or the like.SOLUTION: Edge information (for example, edges of a structure or an object in an image) is acquired through an edge detection technology. A closed curve is formed by edges from a text character even though noise of some level exists. A link of the closed curve and the formation of a candidate text line are two additional features. A classifier of the candidate text line is applied, and text specification of false recognition is further removed. A candidate text region in which text is arranged in natural scenery of an electronic image is highlighted and presented to a user.
摘要翻译：要解决的问题：为了简化基于有效边缘检测和闭合曲线的方法的提供，以便在摄影图像，数字图像和/或电子图像等的自然风景中找到文本。解决方案：通过边缘检测技术获取边缘信息（例如，图像中的结构或对象的边缘）。即使存在一些级别的噪声，也可以从文本字符的边缘形成闭合曲线。闭合曲线的链接和候选文本行的形成是两个附加特征。应用候选文本行的分类器，进一步消除虚假识别的文本规范。将文本排列在电子图像的自然风景中的候选文本区域被突出显示并呈现给用户。

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