公开(公告)号：US09025865B2

公开(公告)日：2015-05-05

申请号：US13746412

申请日：2013-01-22

Applicant: Xerox Corporation

Inventor： Vladimir Kozitsky ,  Aaron Michael Burry ,  Peter Paul

IPC: G06K9/62 ,  A47C7/14 ,  B60N2/44 ,  B60N2/02 ,  B60N2/18

CPC classification number: A47C7/14 ,  B60N2/02 ,  B60N2/1803 ,  B60N2/1835 ,  B60N2/1864 ,  B60N2002/0236 ,  G06K9/3258 ,  G06K9/623 ,  G06K9/6267 ,  G06K2009/4666 ,  G06K2209/01 ,  G06K2209/15

Abstract: Methods and systems for reducing the required footprint of SNoW-based classifiers via optimization of classifier features. A compression technique involves two training cycles. The first cycle proceeds normally and the classifier weights from this cycle are used to rank the Successive Mean Quantization Transform (SMQT) features using several criteria. The top N (out of 512 features) are then chosen and the training cycle is repeated using only the top N features. It has been found that OCR accuracy is maintained using only 60 out of 512 features leading to an 88% reduction in RAM utilization at runtime. This coupled with a packing of the weights from doubles to single byte integers added a further 8× reduction in RAM footprint or a reduction of 68× over the baseline SNoW method.

Abstract translation: 通过优化分类器功能来减少基于SNoW的分类器所需占用面积的方法和系统。 压缩技术涉及两个训练周期。 第一个周期正常进行，并且使用来自该周期的分类器权重使用几个标准对连续平均量化变换（SMQT）特征进行排序。 然后选择顶部N（512个特征之​​一），并且仅使用前N个特征重复训练周期。 已经发现，使用仅512个特征中的60个来维持OCR精度，导致运行时RAM利用率降低88％。 这加上权重从双精度到单字节整数的加载，增加了RAM占用的8倍减少或基线SNoW方法减少了68倍。

公开(公告)号：US20140355836A1

公开(公告)日：2014-12-04

申请号：US13904559

申请日：2013-05-29

Applicant: Xerox Corporation

Inventor： Vladimir Kozitsky ,  Aaron Michael Burry

IPC: G06K9/32

CPC classification number: G06K9/3258 ,  G06K9/685 ,  G06K2209/15

Abstract: Methods and systems for improving automated license plate recognition performance. One or more images of a vehicle can be captured via an automated license plate recognition engine. Vehicle class information associated with the vehicle can be obtained using the automated license place recognition engine. Such vehicle class information can be analyzed with respect to the vehicle. Finally, data can be dynamically adjusted with respect to the vehicle based on a per image basis to enhance recognition of the vehicle via the automated license plate recognition engine.

Abstract translation: 提高自动牌照识别性能的方法和系统。 可以通过自动车牌识别引擎捕获车辆的一个或多个图像。 与车辆相关的车辆类别信息可以使用自动许可证位置识别引擎获得。 可以相对于车辆分析这样的车辆类别信息。 最后，基于每个图像可以相对于车辆动态地调整数据，以通过自动车牌识别引擎增强对车辆的识别。

公开(公告)号：US08774462B2

公开(公告)日：2014-07-08

申请号：US13768883

申请日：2013-02-15

Applicant: Xerox Corporation

Inventor： Vladimir Kozitsky ,  Aaron Michael Burry ,  Zhigang Fan ,  Frank Bradley Mayberry ,  John Deppen

IPC: G06K9/00 ,  H04N7/18

CPC classification number: H04N7/18 ,  G06Q10/087 ,  G06Q30/06

Abstract: Images with respect to an object at an ordering, payment, and delivery locations can be captured utilizing an image capturing system. Capture can be after detecting the presence of the object at each location utilizing an object presence sensor. The captured image can be processed to associate it with a signature and can also be processed in order to extract a small region of interest (e.g., license plate) and can be reduced to a unique signature. Signature can be stored into a database together with the corresponding order and images. Signatures can be matched. The order associated with the object matched by the system together with at least one of the images captured at the delivery point and the order point can be displayed at a user interface located at the payment/delivery point to ensure that the right order is delivered to the right customer associated with the object.

Abstract translation: 可以使用图像捕获系统捕获在订购，付款和传送位置处的对象的图像。 在使用对象存在传感器检测每个位置处的对象的存在之后，可以进行捕获。 捕获的图像可以被处理以将其与签名相关联，并且还可以被处理以便提取感兴趣的小区域（例如，牌照），并且可以将其缩小为唯一的签名。 签名可以与相应的订单和图像一起存储到数据库中。 签名可以匹配。 与由系统匹配的对象相关联的订单与在传送点和订单点捕获的至少一个图像可以显示在位于支付/传送点的用户界面上，以确保正确的订单被传送到 与对象关联的正确客户。

公开(公告)号：US20180012101A1

公开(公告)日：2018-01-11

申请号：US15205146

申请日：2016-07-08

Applicant: Xerox Corporation

Inventor： Howard Mizes ,  Vladimir Kozitsky

IPC: G06K9/34 ,  G06K9/00 ,  G06T7/00 ,  G06T5/00

CPC classification number: G06K9/346 ,  G06K9/00771 ,  G06K2209/01 ,  G06K2209/15 ,  G06T5/008 ,  G06T7/0002 ,  G06T2207/20104

Abstract: A method, system, and apparatus for license plate relighting comprises collecting an image of a license plate, performing license plate recognition on the image of the license plate; calculating a confidence metric for the license plate recognition; and performing a shadow detection and relighting method if the confidence metric is below a predetermined threshold, comprising identifying a shaded region of said license plate, determining if the shaded region is actually shaded, and relighting the actually shaded region.

公开(公告)号：US09501707B2

公开(公告)日：2016-11-22

申请号：US14688255

申请日：2015-04-16

Applicant: Xerox Corporation

Inventor： Orhan Bulan ,  Claude Fillion ,  Aaron M. Burry ,  Vladimir Kozitsky

IPC: G06K9/18 ,  G06K9/32 ,  G06K9/62 ,  G06K9/00

CPC classification number: G06K9/6256 ,  G06K2209/01 ,  G06K2209/15

Abstract: Methods and systems for bootstrapping an OCR engine for license plate recognition. One or more OCR engines can be trained utilizing purely synthetically generated characters. A subset of classifiers, which require augmentation with real examples, along how many real examples are required for each, can be identified. The OCR engine can then be deployed to the field with constraints on automation based on this analysis to operate in a “bootstrapping” period wherein some characters are automatically recognized while others are sent for human review. The previously determined number of real examples required for augmenting the subset of classifiers can be collected. Each subset of identified classifiers can then be retrained as the number of real examples required becomes available.

Abstract translation: 引导OCR引擎进行车牌识别的方法和系统。 可以使用纯合成生成的字符来训练一个或多个OCR引擎。 可以识别分类器的一个子集，它们需要通过实例增加，每个需要多少个实例。 然后，可以将OCR引擎部署到具有基于该分析的自动化约束的现场，以在“自举”期间操作，其中一些字符被自动识别，而其他人被发送供人审查。 可以收集先前确定的用于增加分类器子集所需的实例的数量。 随着所需实际数量的可用数量的增加，识别的分类器的每个子集可以被重新训练。

公开(公告)号：US09405985B1

公开(公告)日：2016-08-02

申请号：US14660255

申请日：2015-03-17

Applicant: Xerox Corporation

Inventor： Aaron M. Burry ,  Vladimir Kozitsky

IPC: G06K9/00 ,  G06K9/18 ,  G06K9/78 ,  G06K9/32 ,  H04N7/18 ,  G06K9/03

CPC classification number: H04N7/18 ,  G06K9/3258 ,  G06K9/6828 ,  G06K2209/01 ,  G06K2209/15

Abstract: Methods and systems for enhancing the accuracy of license plate state identification in an ALPR (Automated License Plate Recognition) system. This is accomplished through use of individual character-by-character image-based classifiers that are trained to distinguish between the fonts for different states. At runtime, the OCR result for the license plate code can be used to determine which character in the plate would provide the highest discriminatory power for arbitrating between candidate state results. This classifier is then applied to the individual character image to provide a final selection of the estimated state/jurisdiction for the plate.

Abstract translation: 在ALPR（自动牌照识别）系统中提高车牌状态识别准确性的方法和系统。 这是通过使用单独的逐个字符的基于图像的分类器来完成的，该分类器被训练以区分不同状态的字体。 在运行时，车牌代码的OCR结果可用于确定板中的哪个字符将提供用于候选状态结果之间仲裁的最高辨别力。 然后将此分类器应用于个人字符图像，以提供板的估计状态/管辖权的最终选择。

公开(公告)号：US20160171328A1

公开(公告)日：2016-06-16

申请号：US14567000

申请日：2014-12-11

Applicant: Xerox Corporation

Inventor： Orhan Bulan ,  Howard Mizes ,  Vladimir Kozitsky ,  Aaron M. Burry

IPC: G06K9/32 ,  G06T7/00

CPC classification number: G06K9/3241 ,  G06K9/3258 ,  G06K9/723 ,  G06K2209/01 ,  G06K2209/15

Abstract: Methods and systems for tag recognition in captured images. A candidate region can be localized from regions of interest with respect to a tag and a tag number shown in the regions of interest within a side image of a vehicle. A number of confidence levels can then be calculated with respect to each digit recognized as a result of an optical character recognition operation performed with respect to the tag number. Optimal candidates within the candidate region can be determined for the tag number based on individual character confidence levels among the confidence levels. Optimal candidates from a pool of valid tag numbers can then be validated using prior appearance probabilities and data returned, which is indicative of the most probable tag to be detected to improve image recognition accuracy.

Abstract translation: 捕获图像中标签识别的方法和系统。 候选区域可以相对于标签和感兴趣区域中所示的在车辆侧面图像内的标签号进行定位。 然后可以相对于作为对标签号执行的光学字符识别操作的结果识别的每个数字来计算多个置信水平。 可以基于置信水平中的个人字符置信水平来确定候选区域内的最佳候选人的标签号码。 然后可以使用先前出现的概率和返回的数据来验证来自有效标签号码池的最佳候选者，这表示要检测的最可能标签以提高图像识别精度。

公开(公告)号：US09224058B2

公开(公告)日：2015-12-29

申请号：US13857657

申请日：2013-04-05

Applicant: Xerox Corporation

Inventor： Peter Paul ,  Vladimir Kozitsky ,  Aaron Michael Burry ,  Martin Edward Hoover ,  Mark Cantelli

IPC: G06K9/00 ,  G06K9/20 ,  G06K9/32

CPC classification number: G06K9/2027 ,  G06K9/3258 ,  G06K2209/15

Abstract: Methods, systems, and processor-readable media for data augmentation utilized in an automatic license plate recognition engine. A machine-readable code can be associated with an automatic license plate recognition engine. The machine-readable code can be configured to define parameters that drive processing within the automatic license plate recognition engine to produce recognition results thereof and enhance a machine readability of a license plate recognized and analyzed via the automatic license plate recognition engine.

Abstract translation: 用于在自动车牌识别引擎中使用的用于数据增加的方法，系统和处理器可读介质。 机器可读代码可以与自动车牌识别引擎相关联。 机器可读代码可以被配置为定义驱动自动车牌识别引擎内的处理以产生其识别结果的参数，并提高通过自动车牌识别引擎识别和分析的牌照的机器可读性。

公开(公告)号：US09195908B2

公开(公告)日：2015-11-24

申请号：US13899705

申请日：2013-05-22

Applicant: Xerox Corporation

Inventor： Stuart Schweid ,  Aaron Michael Burry ,  Vladimir Kozitsky

IPC: G06K9/62

CPC classification number: G06K9/623

Abstract: Methods, systems and processor-readable media for determining, post training, which locations of a classifier window are most significant in discriminating between class and non-class objects. The important locations can be determined by calculating the mean and standard deviation of every pixel location in the classifier context for both the positive and negative samples of the classifier. Using a combination of t-scores and mean differences, the importance of all pixel locations in the classifier score can be rank ordered. A sufficient number of pixel locations can then be selected to achieve a detection rate close enough to the full classifier for a particular application.

Abstract translation: 用于确定后期训练的方法，系统和处理器可读介质，分类器窗口的哪些位置在区分类和非类对象之间最显着。 可以通过计算分类器的正和负样本的分类器上下文中每个像素位置的平均值和标准偏差来确定重要位置。 使用t分和平均差的组合，分类器得分中所有像素位置的重要性可以是排序的。 然后可以选择足够数量的像素位置，以实现足够接近特定应用的全分类器的检测率。

公开(公告)号：US09042647B2

公开(公告)日：2015-05-26

申请号：US13911448

申请日：2013-06-06

Applicant: Xerox Corporation

Inventor： Vladimir Kozitsky ,  Aaron Burry ,  Claude Fillion

IPC: G06K9/00

CPC classification number: G06K9/00624 ,  G06K9/325 ,  G06K9/34 ,  G06K2209/15

Abstract: Methods, systems and processor-readable media for adaptive character segmentation in an automatic license plate recognition application. A region of interest can be identified in an image of a license plate acquired via an automatic license plate recognition engine. Characters in the image with respect to the region of interest can be segmented using a histogram projection associated with particular segmentation threshold parameters. The characters in the image can be iteratively validated if a minimum number of valid characters is determined based on the histogram projection and the particular segmentation threshold parameters to produce character images sufficient to identify the license plate.

Abstract translation: 用于自动车牌识别应用中的自适应角色分割的方法，系统和处理器可读介质。 可以通过自动车牌识别引擎获取的牌照的图像中识别感兴趣的区域。 可以使用与特定分割阈值参数相关联的直方图投影来分割相关于感兴趣区域的图像中的字符。 如果基于直方图投影和特定分割阈值参数来确定最小数量的有效字符，则可以迭代地验证图像中的字符，以产生足以识别牌照的字符图像。