-
公开(公告)号：US20130301913A1
公开(公告)日：2013-11-14
申请号：US13466170
申请日：2012-05-08
IPC分类号： G06K9/62
CPC分类号： G06K9/00577
摘要： Methods for selecting metrics for substrate classification, and apparatus to perform such methods. The methods include determining a value of a metric from an image of a substrate sample for each substrate sample of a plurality of substrate samples, wherein the metric is indicative of a surface texture of each substrate sample and iteratively assigning substrate samples of the plurality of substrate samples to an aggregate of a particular number of aggregates in response to a value of the metric for each substrate sample until a convergence of clustering is deemed achieved, then determining an indication of cluster tightness of the particular number of aggregates. The methods further include selecting or ignoring the metric for substrate classification in response to the indication of cluster tightness of the particular number of aggregates.
摘要翻译： 用于选择底物分类的度量的方法以及执行这些方法的装置。 所述方法包括从多个衬底样品的每个衬底样品的衬底样品的图像中确定度量的值，其中度量指示每个衬底样品的表面纹理并迭代地分配多个衬底的衬底样品 响应于每个底物样品的度量的值而将样品聚集到特定数量的聚集体，直到聚类的收敛被认为实现，然后确定特定数目的聚集体的聚类紧密度的指示。 所述方法还包括响应于特定数量的聚集体的簇紧密度的指示来选择或忽略用于底物分类的度量。
-
公开(公告)号：US20140333969A1
公开(公告)日：2014-11-13
申请号：US14347316
申请日：2012-01-31
IPC分类号： G06K15/02
CPC分类号： G06K15/1881 , H04N1/32144 , H04N1/40062 , H04N1/405 , H04N2201/3271
摘要： A system can comprise a memory to store machine readable instructions and a processing unit to access the memory and execute the machine readable instructions. The machine readable instructions can comprise a feature set extractor to extract a feature set from each of a plurality of digital images of print samples. The feature set can be a filtered feature set that includes a feature set characterizing a printer that printed a given print sample of the print samples. The machine readable instructions can also comprise a cluster component to determine clusters of the print samples based on the feature set of each of the plurality of scanned images of the print samples. The machine readable instructions can further comprise a printer identifier to identify the printer of the print samples based on the clusters of the print samples.
摘要翻译： 系统可以包括用于存储机器可读指令的存储器和用于访问存储器并执行机器可读指令的处理单元。 机器可读指令可以包括特征集提取器，以从打印样本的多个数字图像中的每一个提取特征集。 该功能集可以是一个过滤的功能集，其中包含一个功能集，表征打印机打印样本的给定打印样本的打印机。 机器可读指令还可以包括基于打印样本的多个扫描图像中的每一个的特征集来确定打印样本的群集的群集组件。 机器可读指令还可以包括打印机标识符，以基于打印样本的聚类来识别打印样本的打印机。
-
公开(公告)号：US08818018B2
公开(公告)日：2014-08-26
申请号：US13145321
申请日：2009-01-24
CPC分类号： G06K9/00442 , G06T1/0028
摘要： A system for enhancing security printing includes a segmentation system, a secure database in operative communication with the segmentation system, a secure registry in selective operative communication with the segmentation system, and an analysis system in operative communication with the segmentation system and the secure database, and in selective operative communication with the secure registry. The segmentation system performs zoning analysis on a scanned image to identifying a list of regions in the image. The secure database stores at least one of i) a template, or ii) prior zoning output specification. The secure registry stores region of interest information and information pertaining to strategies for identifying a region of interest. The analysis system identifies the region of interest utilizing at least one of the secure database or the secure registry.
摘要翻译： 一种用于增强安全打印的系统包括分割系统，与分割系统操作性通信的安全数据库，与分割系统的选择性操作通信中的安全注册表，以及与分割系统和安全数据库操作通信的分析系统， 并与安全注册表进行有选择的操作性沟通。 分割系统对扫描图像执行分区分析以识别图像中的区域列表。 安全数据库存储i）模板中的至少一个，或ii）先前的分区输出规范。 安全注册表存储感兴趣的区域信息和与用于识别感兴趣区域的策略有关的信息。 分析系统使用安全数据库或安全注册表中的至少一个来识别兴趣区域。
-
公开(公告)号：US20140185943A1
公开(公告)日：2014-07-03
申请号：US14235867
申请日：2011-09-12
IPC分类号： G06K9/62
CPC分类号： G06K9/6267 , G06K9/036 , G06K9/6202 , G06K9/6218
摘要： An image analyzer (120) aggregates image samples (140) into a cluster (170) based on the image samples (140) being classified from a subset of image metrics applied to a reference sample (130). The image analyzer (120) generates an image quality output (150) by analyzing a distance (180) from the cluster (180) relative to another cluster.
摘要翻译： 基于从施加到参考样本（130）的图像度量的子集分类的图像样本（140），图像分析器（120）将图像样本（140）聚集成群集（170）。 图像分析器（120）通过分析与集群（180）相对于另一个集群的距离（180）来生成图像质量输出（150）。
-
公开(公告)号：US20100188512A1
公开(公告)日：2010-07-29
申请号：US12359267
申请日：2009-01-23
IPC分类号： H04N17/00
CPC分类号： H04N17/00
摘要： A method for testing image pipelines includes transforming an untransformed captured image multiple times using a plurality of pipelines, thereby generating a plurality of transformed images, and comparing a functional set of metrics associated with each of the plurality of transformed images with a functional set of metrics associated with each image in a ground truth set. From the comparison, a determination is made as to which of the plurality of pipelines generates a transformed image that is functionally closest to an image in the ground truth set.
摘要翻译： 一种用于测试图像管线的方法包括使用多个管线多次转换未变换的捕获图像，从而生成多个变换图像，以及将与多个变换图像中的每一个相关联的度量的功能集合与功能的一组度量 与地面真相集中的每个图像相关联。 从比较中，确定多个管道中的哪个管道产生功能上最靠近地面真值集中的图像的变换图像。
-
公开(公告)号：US09977987B2
公开(公告)日：2018-05-22
申请号：US14347254
申请日：2011-10-03
申请人： Steven J. Simske , Malgorzata M. Sturgill , Matthew D. Gaubatz , Masoud Zavarehi , Paul S. Everest
发明人： Steven J. Simske , Malgorzata M. Sturgill , Matthew D. Gaubatz , Masoud Zavarehi , Paul S. Everest
CPC分类号： G06K9/4671 , G06K9/6231 , G06T7/11 , G06T2207/10004
摘要： A method and apparatus to select from an image (30) of a first sample (28), at least one region (44) digitally captured at a first resolution based upon how a counterfeit identification performance attribute of each region (44) digitally captured at the first resolution correlate to the counterfeit identification performance attribute of the region (44) digitally captured at a second resolution higher than the first resolution. The selected region (44) is used to determine whether the image (30) on a second sample is a counterfeit.
-
公开(公告)号：US08269849B2
公开(公告)日：2012-09-18
申请号：US12359267
申请日：2009-01-23
CPC分类号： H04N17/00
摘要： A method for testing image pipelines includes transforming an untransformed captured image multiple times using a plurality of pipelines, thereby generating a plurality of transformed images, and comparing a functional set of metrics associated with each of the plurality of transformed images with a functional set of metrics associated with each image in a ground truth set. From the comparison, a determination is made as to which of the plurality of pipelines generates a transformed image that is functionally closest to an image in the ground truth set.
摘要翻译： 一种用于测试图像管线的方法包括使用多个管线多次转换未变换的捕获图像，从而生成多个变换图像，以及将与多个变换图像中的每一个相关联的度量的功能集合与功能的一组度量 与地面真相集中的每个图像相关联。 从比较中，确定多个管道中的哪个管道产生功能上最靠近地面真值集中的图像的变换图像。
-
公开(公告)号：US09367888B2
公开(公告)日：2016-06-14
申请号：US14347307
申请日：2012-01-20
CPC分类号： G06T1/0028 , G06T2201/0201
摘要： A counterfeit identification performance attribute (CIPA) sensitivity to changes in resolution of the image for features of an image is determined (102). The CIPA sensitivity for the features is used to choose at least one feature to determine whether the image on a sample is a counterfeit (106).
摘要翻译： 确定对图像特征的分辨率变化的伪造识别性能属性（CIPA）灵敏度（102）。 功能的CIPA灵敏度用于选择至少一个功能来确定样品上的图像是否为假冒（106）。
-
公开(公告)号：US20140376811A1
公开(公告)日：2014-12-25
申请号：US14364729
申请日：2012-03-16
申请人： Steven J. Simske , Malgorzata M. Sturgill , Matthew D. Gaubatz , Masoud Zavarehi , Paul S. Everest
发明人： Steven J. Simske , Malgorzata M. Sturgill , Matthew D. Gaubatz , Masoud Zavarehi , Paul S. Everest
CPC分类号： G06K9/00577 , G06K9/00536 , G06K9/46 , G06K2009/0059 , G06Q50/184
摘要： Methods, and apparatus for performing methods, for classifying an image. Methods include determining a corresponding set of metrics for each region of two or more regions of a pattern of regions of an image, and classifying the image in response to at least the corresponding set of metrics for each of the two or more regions of the pattern of regions.
摘要翻译： 用于执行方法的方法和装置，用于对图像进行分类。 方法包括确定图像区域的图案的图案的两个或更多个区域的每个区域的对应的度量集合，并且响应于该图案的两个或更多个区域中的每一个的至少对应的一组度量来对图像进行分类 的地区。
-
公开(公告)号：US20110280480A1
公开(公告)日：2011-11-17
申请号：US13145321
申请日：2009-01-24
IPC分类号： G06K9/34
CPC分类号： G06K9/00442 , G06T1/0028
摘要： A system for enhancing security printing includes a segmentation system, a secure database in operative communication with the segmentation system, a secure registry in selective operative communication with the segmentation system, and an analysis system in operative communication with the segmentation system and the secure database, and in selective operative communication with the secure registry. The segmentation system performs zoning analysis on a scanned image to identifying a list of regions in the image. The secure database stores at least one of i) a template, or ii) prior zoning output specification. The secure registry stores region of interest information and information pertaining to strategies for identifying a region of interest. The analysis system identifies the region of interest utilizing at least one of the secure database or the secure registry.
摘要翻译： 一种用于增强安全打印的系统包括分割系统，与分割系统操作性通信的安全数据库，与分割系统的选择性操作通信中的安全注册表，以及与分割系统和安全数据库操作通信的分析系统， 并与安全注册表进行有选择的操作性沟通。 分割系统对扫描图像执行分区分析以识别图像中的区域列表。 安全数据库存储i）模板中的至少一个，或ii）先前的分区输出规范。 安全注册表存储感兴趣的区域信息和与用于识别感兴趣区域的策略有关的信息。 分析系统使用安全数据库或安全注册表中的至少一个来识别兴趣区域。
-
-
-
-
-
-
-
-
-
搜索结果
20 条记录 (耗时 0.021 秒)