公开(公告)号：US6067366A

公开(公告)日：2000-05-23

申请号：US22204

申请日：1998-02-11

申请人： Sergey Simanovsky ,  Ibrahim M. Bechwati ,  Muzaffer Hiraoglu ,  Carl R. Crawford

发明人： Sergey Simanovsky ,  Ibrahim M. Bechwati ,  Muzaffer Hiraoglu ,  Carl R. Crawford

IPC分类号： A61B6/00 ,  G06K9/00 ,  G06K9/42 ,  G06T7/00

CPC分类号： G06T7/0004 ,  G06K9/00771 ,  G06K2209/09

摘要： A method and apparatus for detecting objects in computed tomography (CT) data are disclosed. Erosion of the data can be performed by identifying a neighborhood of voxels surrounding a voxel of interest. If the number of voxels having densities below a predetermined threshold exceeds a predetermined number, then it is assumed that the voxel of interest is a surface voxel of an object and is removed from the object. A connectivity process is then applied to remaining voxels to combine them into objects. A dilation function can then be performed on the eroded object to replace surface voxels removed by erosion. This morphological connected components labeling (CCL) approach separates adjacent objects in the data such that they can be individually labeled and analyzed.

摘要翻译： 公开了一种用于检测计算机断层摄影（CT）数据中的物体的方法和装置。 可以通过识别感兴趣的体素周围的体素的邻域来执行数据的侵蚀。 如果具有低于预定阈值的密度的体素的数量超过预定数量，则假设感兴趣的体素是对象的表面体素并且从对象中移除。 然后将连接过程应用于剩余的体素以将它们组合成对象。 然后可以对侵蚀的物体执行扩张功能，以取代被侵蚀除去的表面体素。 这种形态连通的组件标记（CCL）方法将数据中的相邻对象分开，使得它们可以被单独标记和分析。

公开(公告)号：US6035014A

公开(公告)日：2000-03-07

申请号：US22164

申请日：1998-02-11

申请人： Muzaffer Hiraoglu ,  Ibrahim M. Bechwati ,  Sergey Simanovsky ,  Carl R. Crawford

发明人： Muzaffer Hiraoglu ,  Ibrahim M. Bechwati ,  Sergey Simanovsky ,  Carl R. Crawford

IPC分类号： G01N23/04

CPC分类号： G06K9/00771 ,  G06K2209/09 ,  Y10S378/901

摘要： A method and apparatus for detecting objects in computed tomography (CT) data are disclosed. Sheet-shaped objects such as sheet explosives can be detected by analyzing a neighborhood of voxels surrounding a test voxel. If the density of the test voxel is sufficiently different from the mean density of the neighboring voxels, then it is concluded that the test voxel is associated with a sheet object. Sheet objects can also be detected by eroding the CT data so as to eliminate voxels associated with thin objects. Remaining objects are then subtracted from the original data, leaving only thin sheet-shaped objects. Bulk objects can be detected by a modified morphological connected components labeling (CCL) approach which performs a series of erosion and dilation steps to separate adjacent objects in the data such that they can be individually labeled and analyzed. The process of the invention can be carried out in multiple paths. That is, for example, a sheet object detection process and a bulk object detection process can be implemented separately and in parallel. During the sheet object detection process, the data can be analyzed to identify bulk objects. Those objects can then be removed from the data and the remaining data can then be analyzed to identify any remaining sheets. Redundant analysis of data is eliminated.

摘要翻译： 公开了一种用于检测计算机断层摄影（CT）数据中的物体的方法和装置。 可以通过分析围绕测试体素的体素周围来检测片状物体，例如片状炸药。 如果测试体素的密度与相邻体元的平均密度有很大的不同，则可以得出结论，测试体素与片材物体相关联。 也可以通过侵蚀CT数据来检测片材物体，以消除与薄物体相关联的体素。 然后从原始数据中减去剩余对象，只留下薄片状物体。 大量物体可以通过修改后的形态连接分量标记（CCL）方法进行检测，该方法执行一系列侵蚀和扩张步骤以分离数据中的相邻物体，使得它们可以被单独标记和分析。 本发明的方法可以在多条路径中进行。 也就是说，例如，可以单独地并行地实现片材对象检测处理和批量对象检测处理。 在纸张对象检测过程中，可以分析数据以识别批量对象。 然后可以从数据中删除那些对象，然后可以分析剩余的数据以识别任何剩余的纸张。 数据的冗余分析被消除。

公开(公告)号：US6026143A

公开(公告)日：2000-02-15

申请号：US22165

申请日：1998-02-11

申请人： Sergey Simanovsky ,  Ibrahim M. Bechwati ,  Muzaffer Hiraoglu ,  Carl R. Crawford

发明人： Sergey Simanovsky ,  Ibrahim M. Bechwati ,  Muzaffer Hiraoglu ,  Carl R. Crawford

IPC分类号： G01N23/04

CPC分类号： G06K9/00771 ,  G06K2209/09 ,  Y10S378/901

摘要： Sheet-shaped objects can be detected by analyzing voxels surrounding a test voxel. If the density different from the mean density then the test voxel is associated with a sheet object. Sheet objects can also be detected by eroding the CT data. Remaining objects are then subtracted from the original data removing with surface voxels, being removed. A connectivity process combines voxels into objects after sheets are detected A dilation function replaces surface voxels removed by erosion. A corrected mass can be compared to mass thresholds to classify the object. Multiple mass thresholds can be used, each of which is associated with a particular density range based on the density of an expected threat object. Bulk objects can be detected by a modified morphological connected components labeling (CCL) approach. A merging process can be used to reconnect related items, The system can also identify objects that contain liquids. The overall system performance, including overall object detection rate and false alarm rate, can be adjusted by adjusting individual object detection rates and/or false alarm rates.

摘要翻译： 可以通过分析测试体素周围的体素来检测片状物体。 如果密度与平均密度不同，则测试体素与片材物体相关联。 也可以通过侵蚀CT数据来检测纸张对象。 然后从原始数据中删除剩余的对象，删除表面体素。 连接过程在检测到纸张之后将体素组合到对象中扩张功能取代了被侵蚀消除的表面体素。 可以将校正的质量与质量阈值进行比较以对对象进行分类。 可以使用多个质量阈值，每个质量阈值基于预期威胁对象的密度与特定密度范围相关联。 大量物体可以通过修改后的形态连接元件标记（CCL）方法进行检测。 合并过程可用于重新连接相关项目，系统还可以识别含有液体的物体。 可以通过调整个别物体检测率和/或误报率来调整整体系统性能，包括总体物体检测率和误报率。

公开(公告)号：US20050238232A1

公开(公告)日：2005-10-27

申请号：US10831909

申请日：2004-04-26

申请人： Zhengrong Ying ,  Sergey Simanovsky ,  Carl Crawford

发明人： Zhengrong Ying ,  Sergey Simanovsky ,  Carl Crawford

IPC分类号： G06K9/00 ,  G06K9/48

CPC分类号： G06K9/00201 ,  G06K9/00771 ,  G06K9/48 ,  G06K2209/09

摘要： A method of and system for detecting threat objects represented in 3D CT data uses knowledge of one or more predefined shapes of the threat objects. An object represented by CT data for a region is identified. A two-dimensional projection of the object along a principal axis of the object is generated. A contour of the object boundary in the projection image is computed. A shape histogram is computed from the extracted contour. A difference measure between the extracted shape histogram and a set of pre-computed threat shape histograms is computed. A declaration of a threat object is made if the difference measure is less than a pre-defined threshold.

摘要翻译： 用于检测在3D CT数据中表示的威胁对象的方法和系统使用威胁对象的一个​​或多个预定义形状的知识。 识别由区域的CT数据表示的对象。 产生物体沿物体主轴的二维投影。 计算投影图像中物体边界的轮廓。 从提取的轮廓计算形状直方图。 计算提取的形状直方图和一组预先计算的威胁形状直方图之间的差异度量。 如果差异度量小于预定义的阈值，则作出威胁对象的声明。

公开(公告)号：US06813374B1

公开(公告)日：2004-11-02

申请号：US09842075

申请日：2001-04-25

申请人： Seemeen S. Karimi ,  David Rozas ,  Sergey Simanovsky ,  Ibrahim Bechwati ,  Carl R. Crawford

发明人： Seemeen S. Karimi ,  David Rozas ,  Sergey Simanovsky ,  Ibrahim Bechwati ,  Carl R. Crawford

IPC分类号： G06K900

CPC分类号： G06K9/00771 ,  A61B6/482 ,  A61B6/583 ,  G01V5/0008 ,  G06K2209/09

摘要： A method of and apparatus for assessing the image quality of a CT scanner is described in which assessment can be made manually or automatically. No special image quality mode of CT scanner operation is necessary, and no precise alignment of the phantom is necessary. In general, performance of the scanner comprises: using the scanner (a) to scan a phantom in one or more of its normal modes of operation while translating said phantom along the scanner axis of rotation and (b) to produce scanned data of the phantom, and assessing the performance of the scanner from the scanned data. In accordance with another aspect, the assessment is performed by (a) using the scanner to scan a phantom in one or more of its normal modes of operation; (b) reconstructing a three-dimensional volume CT image for a region containing at least a portion of the phantom; (c) calculating properties of the CT image; and (d) using the calculated properties of the CT image to assess CT scanner performance.

摘要翻译： 描述了用于评估CT扫描仪的图像质量的方法和装置，其中可以手动或自动地进行评估。 不需要CT扫描仪操作的特殊图像质量模式，并且不需要精确对准幻像。 通常，扫描仪的性能包括：使用扫描仪（a）在其一般或多种操作模式中扫描幻影，同时沿着扫描仪旋转轴旋转所述幻影，并且（b）产生幻影的扫描数据 并从扫描数据评估扫描仪的性能。 根据另一方面，评估通过以下步骤来执行：（a）使用扫描仪扫描其一种或多种正常操作模式中的体模; （b）为包含至少一部分体模的区域重建三维体积CT图像; （c）计算CT图像的性质; 和（d）使用CT图像的计算性能来评估CT扫描仪性能。

公开(公告)号：US06272230B1

公开(公告)日：2001-08-07

申请号：US09022062

申请日：1998-02-11

申请人： Muzaffer Hiraoglu ,  Ibrahim M. Bechwati ,  Sergey Simanovsky ,  Carl R. Crawford

发明人： Muzaffer Hiraoglu ,  Ibrahim M. Bechwati ,  Sergey Simanovsky ,  Carl R. Crawford

IPC分类号： G06K900

CPC分类号： G01V5/005 ,  G01N33/22 ,  G06K9/00771 ,  G06K2209/09

摘要： A method of and apparatus for detecting objects in computed tomography (CT) data includes the ability to define the types of objects to be detected, and at least one algorithm related to the detection of each type of object. Multiple types of objects can be detected and distinguished from one another. Each type of object exhibits an object detection rate related to the probability of the system detecting the corresponding object type, and a false detection rate related to the false identification of objects, different from the target objects, as the target objects. An overall system detection rate is related to a combination of the object detection rates. Each type of object can also be associated with a unique object false alarm rate, with a overall false detection rate being related to the combination of object false alarm rates. The overall system and/or object detection rate, and/or the false alarm rate and/or the overall false detection rate can be optimized by modifying at least one algorithm so as to adjust at least one of the object detection rates or object false alarm rate.

摘要翻译： 用于在计算机断层摄影（CT）数据中检测物体的方法和装置包括定义要检测的对象的类型的能力以及与每种类型的对象的检测有关的至少一种算法。 可以检测和区分多种类型的对象。 每种类型的对象表现出与系统检测相应对象类型的概率相关的对象检测率，以及与目标对象不同的对象的虚假识别相关的错误检测率作为目标对象。 整体系统检测率与对象检测率的组合有关。 每种类型的对象也可以与唯一对象的误报率相关联，其中总体错误检测率与对象误报率的组合相关。 可以通过修改至少一个算法来优化整个系统和/或物体检测率，和/或虚假警报率和/或总体错误检测率，以便调整目标检测率或物体假警报中的至少一个 率。

公开(公告)号：US06195444B1

公开(公告)日：2001-02-27

申请号：US09228380

申请日：1999-01-12

申请人： Sergey Simanovsky ,  Ibrahim M. Bechwati ,  Muzzafer Hiraoglu ,  Carl R. Crawford

发明人： Sergey Simanovsky ,  Ibrahim M. Bechwati ,  Muzzafer Hiraoglu ,  Carl R. Crawford

IPC分类号： G06K900

CPC分类号： G06K9/00771 ,  G06K2209/09

摘要： A method and apparatus for detecting concealed objects in computed tomography data are disclosed. Sheet-shaped objects such as sheet explosives can be detected by a CT scanning system, in particular, a CT baggage scanning system. The invention analyzes CT voxels in a subregion in proximity to the sheet object to determine if the sheet object is concealed in an electronic device or is “sandwiched” within an item such as a book or magazine. To detect electronic concealment, the number of voxels in a subregion that contains the object having a density above a predetermined threshold is counted and the ratio of that number of voxels to the number of object voxels is computed. If the ratio exceeds a threshold, then it is concluded that the object is concealed in electronics. In response, the CT scanning system can alter discrimination parameters to allow the object to be classified as a threat. For “sandwich” concealment, layers on opposite sides of a sheet object are examined. The mean and standard deviation of density values for the voxels are computed. Where the mean density exceeds a predetermined threshold and the standard deviation is below a different threshold, for at least one of the layers, then it is concluded that the sheet object is sandwiched within an innocuous object such as a magazine or a book.

摘要翻译： 公开了一种用于检测计算机断层摄影数据中的隐藏对象的方法和装置。 CT扫描系统，特别是CT行李扫描系统可以检测片状物体，如片状炸药。 本发明分析在片材对象附近的子区域中的CT体素，以确定片材物体是否被隐藏在电子设备中，或者被“夹在”诸如书籍或杂志的物品内。 为了检测电子隐藏，对包含密度高于预定阈值的对象的子区域中的体素数进行计数，并计算该体素数与对象体素数之比。 如果比值超过阈值，则得出结论，该物体被隐藏在电子设备中。 作为响应，CT扫描系统可以改变辨别参数以允许对象被分类为威胁。 对于“三明治”隐蔽，检查片材对象的相对侧上的层。 计算体素密度值的平均值和标准偏差。 在平均密度超过预定阈值并且标准偏差低于不同阈值的情况下，对于至少一个层，则得出结论，片材物体被夹在诸如杂志或书籍的无害物体内。

公开(公告)号：US6128365A

公开(公告)日：2000-10-03

申请号：US22060

申请日：1998-02-11

申请人： Ibrahim M. Bechwati ,  Sergey Simanovsky ,  Muzaffer Hiraoglu ,  Carl R. Crawford

发明人： Ibrahim M. Bechwati ,  Sergey Simanovsky ,  Muzaffer Hiraoglu ,  Carl R. Crawford

IPC分类号： G01N23/04

CPC分类号： G06K9/00771 ,  G06K2209/09 ,  Y10S378/901

摘要： Sheet-shaped objects can be detected by analyzing a neighborhood of voxels surrounding a test voxel. If the density is sufficiently different, then the voxel is associated with a sheet object. Sheet objects can also be detected by eroding the CT data so as to eliminate voxels associated with thin objects. Remaining objects are then subtracted from the original data, leaving only thin sheet-shaped objects. If the number of voxels having densities below a predetermined threshold exceeds a predetermined number, then it is assumed that the test voxel is a surface voxel and is removed from the object. A connectivity process can be applied to voxels to combine them into objects after sheets are detected. A dilation function can then be performed to replace surface voxels. A corrected mass can be compared to mass thresholds. Bulk objects can be detected by a modified morphological connected components labeling (CCL) approach. A merging process can be used to reconnect related items. The system can also identify objects that contain liquids. The object detection rate and false alarm rate can be adjusted by adjusting individual object detection rates and/or false alarm rates.

摘要翻译： 可以通过分析围绕测试体素的体素的邻域来检测片状物体。 如果密度充分不同，则体素与片材物体相关联。 也可以通过侵蚀CT数据来检测片材物体，以消除与薄物体相关联的体素。 然后从原始数据中减去剩余对象，只留下薄片状物体。 如果具有低于预定阈值的密度的体素的数量超过预定数量，则假设测试体素是表面体素并且从对象中移除。 可以将连接过程应用于体素，以便在检测到床单后将它们组合到对象中。 然后可以执行扩张功能来代替表面体素。 可以将校正的质量与质量阈值进行比较。 大量物体可以通过修改后的形态连接元件标记（CCL）方法进行检测。 合并过程可用于重新连接相关项目。 系统还可以识别含有液体的物体。 可以通过调整个别物体检测率和/或误报率来调整物体检测率和误报率。

公开(公告)号：US6078642A

公开(公告)日：2000-06-20

申请号：US21889

申请日：1998-02-11

申请人： Sergey Simanovsky ,  Ibrahim M. Bechwati ,  Muzaffer Hiraoglu ,  Carl R. Crawford

发明人： Sergey Simanovsky ,  Ibrahim M. Bechwati ,  Muzaffer Hiraoglu ,  Carl R. Crawford

IPC分类号： G01N23/04

CPC分类号： G06K9/00771 ,  G06K2209/09

摘要： A method and apparatus for detecting and classifying objects in computed tomography (CT) data are disclosed. A connectivity process can be applied to voxels in the data to combine them into objects. A dilation function can then be performed on the eroded object to replace surface voxels removed by erosion. A corrected mass using the mean eroded density of the object can be computed and compared to mass thresholds to classify the object as to whether it poses a threat. Multiple mass thresholds can be used, each of which is associated with a particular density range based on the density of an expected threat object.

摘要翻译： 公开了一种用于在计算机断层摄影（CT）数据中检测和分类对象的方法和装置。 连接过程可以应用于数据中的体素，以将它们组合成对象。 然后可以对侵蚀的物体执行扩张功能，以取代被侵蚀除去的表面体素。 可以计算使用对象的平均侵蚀密度的校正质量，并将其与质量阈值进行比较，以对对象是否构成威胁进行分类。 可以使用多个质量阈值，每个质量阈值基于预期威胁对象的密度与特定密度范围相关联。

公开(公告)号：US6076400A

公开(公告)日：2000-06-20

申请号：US21782

申请日：1998-02-11

申请人： Ibrahim M. Bechwati ,  Sergey Simanovsky ,  Muzaffer Hiraoglu ,  Carl R. Crawford

发明人： Ibrahim M. Bechwati ,  Sergey Simanovsky ,  Muzaffer Hiraoglu ,  Carl R. Crawford

IPC分类号： G01N9/02

CPC分类号： G06K9/00771 ,  G06K2209/09

摘要： A method and apparatus for detecting objects in computed tomography (CT) data are disclosed. Sheet-shaped objects such as sheet explosives can be detected by analyzing a neighborhood of voxels surrounding a test voxel. If the density of the test voxel is sufficiently different from the mean density of the neighboring voxels, then it is concluded that the test voxel is associated with a sheet object. Sheet objects can also be detected by eroding the CT data so as to eliminate voxels associated with thin objects. Remaining objects are then subtracted from the original data, leaving only thin sheet-shaped objects. Erosion of the data can be performed by identifying a neighborhood of voxels surrounding a voxel of interest. If the number of voxels having densities below a predetermined threshold exceeds a predetermined number, then it is assumed that the test voxel is a surface voxel and is removed from the object. A connectivity process can be applied to voxels to combine them into objects after sheets are detected to prevent sheets from being inadvertently removed from the data by erosion. A dilation function can then be performed on the eroded object to replace surface voxels removed by erosion. A corrected mass using the mean eroded density of the object can be computed and compared to mass thresholds to classify the object as to whether it poses a threat. Multiple mass thresholds can be used, each of which is associated with a particular density range based on the density of an expected threat object. Bulk objects can be detected by a modified morphological connected components labeling (CCL) approach which performs a series of erosion and dilation steps to separate adjacent objects in the data such that they can be individually labeled and analyzed. A merging process can be used to reconnect related items, such as multiple sticks, that were separated during an erosion step. The merging process allows multiple objects that would individually pass as non-threat items to be combined into a single item that is correctly classified as a threat. The system can also identify objects that contain liquids, if desired. The process of the invention can be carried out in multiple stages. The overall system performance, including overall object detection rate and false alarm rate, can be adjusted by adjusting individual object detection rates and/or false alarm rates.