公开(公告)号：US07383237B2

公开(公告)日：2008-06-03

申请号：US11349542

申请日：2006-02-06

申请人： Hong Zhang ,  Garry Carls ,  Stephen D. Barnhill

发明人： Hong Zhang ,  Garry Carls ,  Stephen D. Barnhill

IPC分类号： G06E1/00 ,  G06E3/00 ,  G06F15/18 ,  G06G7/00

CPC分类号： G06T7/0012 ,  G06F19/00 ,  G06K9/623 ,  G06K9/6269 ,  G06K9/6292 ,  G06K2209/05 ,  G06N99/005 ,  G16H30/40 ,  G16H50/70

摘要： Digitized image data are input into a processor where a detection component identifies the areas (objects) of particular interest in the image and, by segmentation, separates those objects from the background. A feature extraction component formulates numerical values relevant to the classification task from the segmented objects. Results of the preceding analysis steps are input into a trained learning machine classifier which produces an output which may consist of an index discriminating between two possible diagnoses, or some other output in the desired output format. In one embodiment, digitized image data are input into a plurality of subsystems, each subsystem having one or more support vector machines. Pre-processing may include the use of known transformations which facilitate extraction of the useful data. Each subsystem analyzes the data relevant to a different feature or characteristic found within the image. Once each subsystem completes its analysis and classification, the output for all subsystems is input into an overall support vector machine analyzer which combines the data to make a diagnosis, decision or other action which utilizes the knowledge obtained from the image.

摘要翻译： 数字化图像数据被输入到处理器中，其中检测组件识别图像中特别感兴趣的区域（对象），并且通过分割将这些对象与背景分离。 特征提取组件从分段对象中制定与分类任务相关的数值。 将前述分析步骤的结果输入到经过训练的学习机器分类器中，所述训练学习机器分类器产生输出，该输出可以由区分两种可能的诊断的指标或者期望的输出格式的一些其他输出组成。 在一个实施例中，数字化图像数据被输入到多个子系统中，每个子系统具有一个或多个支持向量机。 预处理可以包括使用有助于提取有用数据的已知变换。 每个子系统分析与图像中发现的不同特征或特征相关的数据。 一旦每个子系统完成其分析和分类，所有子系统的输出被输入到整体支持向量机分析器中，该分析器将数据组合以进行利用从图像获得的知识的诊断，决定或其他动作。

公开(公告)号：US06996549B2

公开(公告)日：2006-02-07

申请号：US10056438

申请日：2002-01-23

申请人： Hong Zhang ,  Garry Carls ,  Stephen D. Barnhill

发明人： Hong Zhang ,  Garry Carls ,  Stephen D. Barnhill

IPC分类号： G06F15/18

CPC分类号： G06T7/0012 ,  G06F19/00 ,  G06K9/623 ,  G06K9/6269 ,  G06K9/6292 ,  G06K2209/05 ,  G06N99/005 ,  G16H30/40 ,  G16H50/70

摘要： Digitized image data are input into a processor where a detection component identifies the areas (objects) of particular interest in the image and, by segmentation, separates those objects from the background. A feature extraction component formulates numerical values relevant to the classification task from the segmented objects. Results of the preceding analysis steps are input into a trained learning machine classifier which produces an output which may consist of an index discriminating between two possible diagnoses, or some other output in the desired output format. In one embodiment, digitized image data are input into a plurality of subsystems, each subsystem having one or more support vector machines. Pre-processing may include the use of known transformations which facilitate extraction of the useful data. Each subsystem analyzes the data relevant to a different feature or characteristic found within the image. Once each subsystem completes its analysis and classification, the output for all subsystems is input into an overall support vector machine analyzer which combines the data to make a diagnosis, decision or other action which utilizes the knowledge obtained from the image.

公开(公告)号：US20060224539A1

公开(公告)日：2006-10-05

申请号：US11349542

申请日：2006-02-06

申请人： Hong Zhang ,  Garry Carls ,  Stephen Barnhill

发明人： Hong Zhang ,  Garry Carls ,  Stephen Barnhill

IPC分类号： G06F15/18

CPC分类号： G06T7/0012 ,  G06F19/00 ,  G06K9/623 ,  G06K9/6269 ,  G06K9/6292 ,  G06K2209/05 ,  G06N99/005 ,  G16H30/40 ,  G16H50/70

摘要： Digitized image data are input into a processor where a detection component identifies the areas (objects) of particular interest in the image and, by segmentation, separates those objects from the background. A feature extraction component formulates numerical values relevant to the classification task from the segmented objects. Results of the preceding analysis steps are input into a trained learning machine classifier which produces an output which may consist of an index discriminating between two possible diagnoses, or some other output in the desired output format. In one embodiment, digitized image data are input into a plurality of subsystems, each subsystem having one or more support vector machines. Pre-processing may include the use of known transformations which facilitate extraction of the useful data. Each subsystem analyzes the data relevant to a different feature or characteristic found within the image. Once each subsystem completes its analysis and classification, the output for all subsystems is input into an overall support vector machine analyzer which combines the data to make a diagnosis, decision or other action which utilizes the knowledge obtained from the image.