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

US20060221341A1 Systems and methods for compensating for temperature induced spectral emission variations in LED based color parameter measuring devices 有权
标题翻译：用于补偿基于LED的颜色参数测量装置中的温度感应光谱发射变化的系统和方法
公开(公告)号：US20060221341A1
公开(公告)日：2006-10-05
申请号：US11092674
申请日：2005-03-30
申请人： Peter Paul , Lalit Mestha , Claude Fillion , R. Viturro
发明人： Peter Paul , Lalit Mestha , Claude Fillion , R. Viturro
IPC分类号： G01N21/25 , G01J3/50
CPC分类号： G01J3/50 , G01J3/501 , G01J3/524 , G01J2003/466 , G01N21/255
摘要： Systems and method provide compensation for temperature induced peak wavelength shift of LEDs is color parameter measuring systems that use a model to reconstruct target color parameter values from the reflectance values measured when the target is illuminated by LEDs. Several models may be constructed, with each model being trained at a unique temperature, resulting in a set of models that span the temperature range of interest. In real-time, the LED based color parameter measuring system measures the temperature and interpolates between the models to estimate the appropriate model to use at the temperature of interest. The estimated model is then used to perform the color parameter value estimation.
摘要翻译：系统和方法为温度引起的LED的峰值波长偏移提供补偿是使用模型从由LED照射目标时测量的反射率值重建目标颜色参数值的颜色参数测量系统。可以构建几个模型，每个模型在独特的温度下进行训练，得到一组跨越感兴趣的温度范围的模型。基于LED的颜色参数测量系统实时测量模型之间的温度和内插，以估计在感兴趣的温度下使用的适当模型。然后使用估计的模型来执行颜色参数值估计。

2. 发明申请

US20070046941A1 Spectrophotometer target distance variation compensation 有权
公开(公告)号：US20070046941A1
公开(公告)日：2007-03-01
申请号：US11210957
申请日：2005-08-24
申请人： Lalit Mestha , Tonya Love , Peter Paul , Claude Fillion
发明人： Lalit Mestha , Tonya Love , Peter Paul , Claude Fillion
IPC分类号： G01J3/46
CPC分类号： G01J3/50 , G01J3/02 , G01J3/0256 , G01J3/0278 , G01J3/501 , G01J3/524
摘要： Spectrophotometer color measurement with a target illumination system and a reflected illumination sensing system where the target surface is variably spaced from said spectrophotometer. Color correction calibration information corresponding to color measurements for known different spacings of a test target surface from the spectrophotometer are obtained and stored. In use, the spacing of the actual target surface from the spectrophotometer is measured to provide a target spacing information signal. That signal is automatically combined with the stored color correction calibration information for the corresponding distances to provide at least partial correction of color measurement errors of the spectrophotometer for variable spacing of the target surface relative to the spectrophotometer even with low cost fixed focus optics. The spectrophotometer output can be so corrected by changing the target illumination, such as by LED pulse width changes, and/or by corrective adjustment of the measured reflectances.

3. 发明授权

US08934676B2 Robust character segmentation for license plate images 有权
标题翻译：车牌图像的强大字符分割
公开(公告)号：US08934676B2
公开(公告)日：2015-01-13
申请号：US13539739
申请日：2012-07-02
申请人： Aaron Michael Burry , Claude Fillion , Vladimir Kozitsky
发明人： Aaron Michael Burry , Claude Fillion , Vladimir Kozitsky
IPC分类号： G06K9/00 , G06K9/48 , G06K9/03 , G06K7/10
CPC分类号： G06K9/34 , G06K9/325 , G06K2209/01 , G06K2209/15
摘要： A method and system for achieving accurate segmentation of characters with respect to a license plate image within a tight bounding box image. A vehicle image can be captured by an image capturing unit and processed utilizing an ALPR unit. A vertical projection histogram can be calculated to produce an initial character boundary (cuts) and local statistical information can be employed to split a large cut and insert a missing character. The cut can be classified as a valid and/or a suspect character and the suspect character can be analyzed. The suspect character can be normalized and passed to an OCR module for decoding and generating a confidence quote with every conclusion. The non-character images can be rejected at the OCR level by enforcing a confidence threshold. An adjoining suspect narrow character can be combined and the OCR confidence of the combined character can be assessed.
摘要翻译：一种用于在紧密的边界框图像内实现相对于车牌图像的字符的精确分割的方法和系统。车辆图像可以由图像捕获单元捕获并且利用ALPR单元进行处理。可以计算垂直投影直方图以产生初始字符边界（切割），并且可以采用局部统计信息来分割大剪切并插入缺失的字符。切割可以分为有效的和/或可疑的角色，并且可以分析可疑的角色。可疑的角色可以被归一化并传递给OCR模块进行解码，并产生每个结论的置信度。非字符图像可以通过强制置信阈值在OCR级别被拒绝。可以组合相邻的可疑小角色，可以评估组合角色的OCR置信度。

4. 发明申请

US20130279758A1 METHOD AND SYSTEM FOR ROBUST TILT ADJUSTMENT AND CROPPING OF LICENSE PLATE IMAGES 审中-公开
标题翻译：用于稳定倾斜调整的方法和系统和许可证板图像的合并
公开(公告)号：US20130279758A1
公开(公告)日：2013-10-24
申请号：US13453144
申请日：2012-04-23
申请人： Aaron Michael Burry , Claude Fillion , Vladimir Kozitsky , Zhigang Fan
发明人： Aaron Michael Burry , Claude Fillion , Vladimir Kozitsky , Zhigang Fan
IPC分类号： G06K9/46 , G06K9/00
CPC分类号： G06K9/3258 , G06K9/3275 , G06K9/342 , G06K2209/01
摘要： Methods, systems and processor-readable media for robust tilt adjustment and cropping of a license plate image. A vehicle image can be captured by an image-capturing unit and converted to a binary image utilizing a binarization approach. A long run within the binary image can then be removed and a morphological filtering can be applied to break an unwanted connection between characters due to a license plate frame and an image noise. A connected component (CC) within the image can be identified and screened based on a number of key metrics to remove a most likely candidate character connected component. A line-fit based iterative search process can then be performed for robust tilt removal and vertical cropping of the license plate image to obtain a tight bounding box on the license plate characters if sufficient candidate characters remain after the search process. Otherwise, the region of interest can be rejected.
摘要翻译：方法，系统和处理器可读介质，用于强大的倾斜调整和车牌图像的裁剪。车辆图像可以由图像捕获单元捕获并且使用二值化方法被转换成二值图像。然后可以去除二进制图像中的长时间，并且可以应用形态滤波来打破由于牌照框架和图像噪声引起的字符之间的不期望的连接。可以基于多个关键指标来识别和屏蔽图像内的连接分量（CC），以消除最可能的候选字符连接分量。然后可以执行基于线拟合的迭代搜索过程，用于强制倾斜移除和车牌图像的垂直裁剪，以便在搜索过程之后剩余足够的候选人物时，在车牌字符上获得紧密的边界框。否则，可以拒绝感兴趣的区域。

5. 发明申请

US20130272579A1 ROBUST CROPPING OF LICENSE PLATE IMAGES 有权
标题翻译：许可证板图像的稳健修剪
公开(公告)号：US20130272579A1
公开(公告)日：2013-10-17
申请号：US13448976
申请日：2012-04-17
申请人： Aaron Michael Burry , Claude Fillion , Vladimir Kozitsky , Raja Bala , Zhigang Fan
发明人： Aaron Michael Burry , Claude Fillion , Vladimir Kozitsky , Raja Bala , Zhigang Fan
IPC分类号： G06K9/46 , G06K9/34 , G06K9/54
CPC分类号： G06K9/3258 , G06K2209/15
摘要： A method, system, and computer-usable tangible storage device for robustly cropping and accurately recognizing license plates to account for noise sources and interfering artifacts are disclosed. License plate images and sub-images can be tightly cropped utilizing an image-based classifier and gradient-based cropping. An image-based classifier can identify the location of valid characters within the image. Because of a number of noise sources, such as, for example, residual plate rotation and shear in the characters within the image, the image-based classifier performs a “rough” identification of the image boundaries. An additional processing step utilizing gradient-based cropping is performed to fine-tune the license plate image boundaries. Gradient-based cropping eliminates unwanted border artifacts that could substantially impact the segmentation and license plate character recognition results.
摘要翻译：公开了一种方法，系统和计算机可用的有形存储设备，用于强力裁剪和准确识别牌照以考虑噪声源和干扰伪像。可以使用基于图像的分类器和基于梯度的裁剪来严格裁剪牌照图像和子图像。基于图像的分类器可以识别图像中有效字符的位置。由于许多噪声源，例如图像中的字符中的残余板旋转和剪切，基于图像的分类器对图像边界执行“粗略”识别。执行利用基于梯度的裁剪的附加处理步骤来微调车牌图像边界。基于梯度的裁剪消除了不必要的边界伪影，可能会对分割和车牌字符识别结果产生重大影响。

6. 发明申请

US20050004974A1 Device model agent 失效
标题翻译：设备型号代理
公开(公告)号：US20050004974A1
公开(公告)日：2005-01-06
申请号：US10687244
申请日：2003-10-16
申请人： Naveen Sharma , Michael Furst , Claude Fillion , Weixia Huang , Michael Kehoe , Arturo Lorenzo , Mary McCorkindale , Robert St. Jacques , Tracy Thieret , John Austin , Marc Daniels , Michael Cavanaugh
发明人： Naveen Sharma , Michael Furst , Claude Fillion , Weixia Huang , Michael Kehoe , Arturo Lorenzo , Mary McCorkindale , Robert St. Jacques , Tracy Thieret , John Austin , Marc Daniels , Michael Cavanaugh
IPC分类号： G06F9/44 , G06F9/445 , G06F9/46 , G06F15/00 , G06F15/16 , G06F15/173 , G06F15/177 , G06Q10/08 , H04L29/06 , H04L29/08 , H04N1/00
CPC分类号： G06Q10/0875 , H04L29/06 , H04L67/10
摘要： The Device Model Agent (DMA), the device side technology module in Device Centric Services (DCS) system, is the main focus of this invention. DMA is a thin, efficient applications/services execution environment. DMA provides an embedded services platform for enabling system management applications and services. This allows a flexible, extensible, dynamic services management module allowing networked services to be designed, added, and managed within the system without modifications to devices, DCS system, or DMA itself. While this invention specifically describes the integration of benefits from DMA into document system devices, the concepts are equally applicable in other domains. The DMA runtime environment is a thin software interface layer that resides on a document system device between the Java runtime environment and embedded web server.
摘要翻译：设备型号代理（DMA）是设备中心服务（DCS）系统中的设备侧技术模块，是本发明的主要重点。 DMA是一种薄型，高效的应用程序/服务执行环境。 DMA提供了一个用于启用系统管理应用程序和服务的嵌入式服务平台。这允许灵活的，可扩展的，动态的服务管理模块，允许在系统内设计，添加和管理网络服务，而无需修改设备，DCS系统或DMA本身。虽然本发明具体描述了从DMA到文档系统设备的益处的集成，但是这些概念同样适用于其他领域。 DMA运行时环境是位于Java运行时环境和嵌入式Web服务器之间的文档系统设备上的瘦软件接口层。

7. 发明授权

US09760789B2 Robust cropping of license plate images 有权
公开(公告)号：US09760789B2
公开(公告)日：2017-09-12
申请号：US13448976
申请日：2012-04-17
申请人： Aaron Michael Burry , Claude Fillion , Vladimir Kozitsky , Raja Bala , Zhigang Fan
发明人： Aaron Michael Burry , Claude Fillion , Vladimir Kozitsky , Raja Bala , Zhigang Fan
IPC分类号： G06K9/32
CPC分类号： G06K9/3258 , G06K2209/15
摘要： A method, system, and computer-usable tangible storage device for robustly cropping and accurately recognizing license plates to account for noise sources and interfering artifacts are disclosed. License plate images and sub-images can be tightly cropped utilizing an image-based classifier and gradient-based cropping. An image-based classifier can identify the location of valid characters within the image. Because of a number of noise sources, such as, for example, residual plate rotation and shear in the characters within the image, the image-based classifier performs a “rough” identification of the image boundaries. An additional processing step utilizing gradient-based cropping is performed to fine-tune the license plate image boundaries. Gradient-based cropping eliminates unwanted border artifacts that could substantially impact the segmentation and license plate character recognition results.

8. 发明申请

US20130294654A1 ROBUST CHARACTER SEGMENTATION FOR LICENSE PLATE IMAGES 有权
标题翻译：许可证板图像的强大字符分段
公开(公告)号：US20130294654A1
公开(公告)日：2013-11-07
申请号：US13539739
申请日：2012-07-02
申请人： Aaron Michael Burry , Claude Fillion , Vladimir Kozitsky
发明人： Aaron Michael Burry , Claude Fillion , Vladimir Kozitsky
IPC分类号： G06K9/34
CPC分类号： G06K9/34 , G06K9/325 , G06K2209/01 , G06K2209/15
摘要： A method and system for achieving accurate segmentation of characters with respect to a license plate image within a tight bounding box image. A vehicle image can be captured by an image capturing unit and processed utilizing an ALPR unit. A vertical projection histogram can be calculated to produce an initial character boundary (cuts) and local statistical information can be employed to split a large cut and insert a missing character. The cut can be classified as a valid and/or a suspect character and the suspect character can be analyzed. The suspect character can be normalized and passed to an OCR module for decoding and generating a confidence quote with every conclusion. The non-character images can be rejected at the OCR level by enforcing a confidence threshold. An adjoining suspect narrow character can be combined and the OCR confidence of the combined character can be assessed.
摘要翻译：一种用于在紧密的边界框图像内实现相对于车牌图像的字符的精确分割的方法和系统。车辆图像可以由图像捕获单元捕获并且利用ALPR单元进行处理。可以计算垂直投影直方图以产生初始字符边界（切割），并且可以采用局部统计信息来分割大剪切并插入缺失的字符。切割可以分为有效的和/或可疑的角色，并且可以分析可疑的角色。可疑人物可以归一化并传递给OCR模块进行解码，并产生每个结论的置信度。非字符图像可以通过强制置信阈值在OCR级别被拒绝。可以组合相邻的可疑小角色，可以评估组合角色的OCR置信度。

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