公开(公告)号：US20050144147A1

公开(公告)日：2005-06-30

申请号：US10746169

申请日：2003-12-26

申请人： Shih-Jong Lee ,  Seho Oh ,  Donglok Kim

发明人： Shih-Jong Lee ,  Seho Oh ,  Donglok Kim

IPC分类号： G06F15/18 ,  G06N5/00

CPC分类号： G06K9/6282 ,  G06K9/6228 ,  G06N5/003 ,  G06N99/005

摘要： A feature regulation application method for hierarchical decision learning systems receives a feature regulation training data. A feature regulation method uses the feature regulation training data and invokes a plurality of the hierarchical decision learning to create feature subset information output. The feature regulation application method also receives a learning data. A feature sampling method uses the feature subset information and the learning data to create a feature subset learning data output. A hierarchical decision learning method uses the feature subset learning data to create a hierarchical decision system output. The feature regulation method also outputs feature ranking information. A feature regulated hierarchical decision learning method uses the feature subset learning data and the feature ranking information to create a hierarchical decision system output. This invention performs feature selection using a feature regulation method designed specifically for hierarchical decision learning systems such as decision tree classifiers. It provide a computationally feasible method for feature selection that considers the hierarchical decision learning systems used for decision making. It evaluates the stability of features subject to context switching and the reliability of the tree nodes by information integration. It provides the ranking of the features that can be incorporated in the creation of the hierarchical decision learning systems.

摘要翻译： 用于分层决策学习系统的特征调节应用方法接收特征调节训练数据。 特征调节方法使用特征调节训练数据并且调用多个分层决策学习来创建特征子集信息输出。 特征调节应用方法还接收学习数据。 特征采样方法使用特征子集信息和学习数据来创建特征子集学习数据输出。 分层决策学习方法使用特征子集学习数据来创建分层决策系统输出。 特征调节方法还输出特征排序信息。 特征调节分层决策学习方法使用特征子集学习数据和特征排序信息来创建分层决策系统输出。 本发明使用专门用于分层决策学习系统（例如决策树分类器）而设计的特征调节方法来执行特征选择。 它提供了一种考虑用于决策的分层决策学习系统的特征选择的计算可行方法。 它通过信息集成评估上下文切换的特征的稳定性和树节点的可靠性。 它提供了可以纳入到分级决策学习系统的创建中的功能的排名。

公开(公告)号：US20050114332A1

公开(公告)日：2005-05-26

申请号：US10723397

申请日：2003-11-26

申请人： Shih-Jong Lee ,  Seho Oh

发明人： Shih-Jong Lee ,  Seho Oh

IPC分类号： G06F17/30 ,  G06K9/68 ,  G06T7/00

CPC分类号： G06F17/30256 ,  G06F17/30277 ,  G06K9/6857 ,  G06T7/74 ,  Y10S707/99933

摘要： A fast high precision matching method receives an input image and a template. An initial search method uses the input image and the template to create an initial search result output. A high precision match uses the initial search result, the input image, and the template to create a high precision match result output. The high precision match method estimates high precision parameters by image interpolation and interpolation parameter optimization. The high precision match method also performs robust matching by limiting pixel contribution or pixel weighting. An invariant high precision match method estimates subpixel position and subsampling scale and rotation parameters by image interpolation and interpolation parameter optimization on the log-converted radial-angular transformation domain. This invention provides a fast method for high precision matching with the equivalent subpixel and subsampling interpolation in the image or template domain without actual performing the subpixel interpolation and/or subsampling. It achieves the high precision through sampling parameter optimization. Therefore, very fine sampling precision can be accomplished without the difficulty of high resolution image/template storage and expensive computation for actual matching at high resolution. This invention is generalized to include the high precision scale and rotation invariant matching through parameter optimization on log-converted radial-angular coordinate. This invention can be easily generalized to three-dimensional or higher dimensional invariant high precision pattern search and can achieve even greater speed advantage comparing to the prior art methods. Therefore, it can be used in applications such as 3D medical imaging, dynamic medical imaging, confocal microscopy, live cell assays in drug discovery, or ultrasound imaging.

摘要翻译： 快速高精度匹配方法接收输入图像和模板。 初始搜索方法使用输入图像和模板来创建初始搜索结果输出。 高精度匹配使用初始搜索结果，输入图像和模板来创建高精度匹配结果输出。 高精度匹配方法通过图像插值和插值参数优化来估计高精度参数。 高精度匹配方法还通过限制像素贡献或像素加权来执行鲁棒匹配。 不变高精度匹配方法通过对数转换的径向角变换域的图像插值和插值参数优化来估计子像素位置和子采样比例尺和旋转参数。 本发明提供了一种用于与图像或模板域中的等效子像素和子采样内插进行高精度匹配而不实际执行子像素内插和/或二次采样的快速方法。 通过采样参数优化实现了高精度。 因此，可以实现非常精细的采样精度，而不需要高分辨率图像/模板存储的难度，并且在高分辨率下实际匹配的昂贵的计算。 本发明概括为包括通过对数转换的径向角坐标的参数优化的高精度尺度和旋转不变匹配。 本发明可以容易地推广到三维或更高维度不变高精度图案搜索，并且与现有技术方法相比可以获得更大的速度优势。 因此，它可以用于3D医学成像，动态医学成像，共聚焦显微镜，药物发现中的活细胞测定或超声成像等应用。

公开(公告)号：US20060285743A1

公开(公告)日：2006-12-21

申请号：US11165561

申请日：2005-06-20

申请人： Seho Oh ,  Shih-Jong Lee

发明人： Seho Oh ,  Shih-Jong Lee

IPC分类号： G06K9/00 ,  G06K9/48

CPC分类号： G06K9/0014 ,  G06K9/34 ,  G06T7/0012 ,  G06T7/12 ,  G06T7/155 ,  G06T2207/20104 ,  G06T2207/20192 ,  G06T2207/30024

摘要： An object based boundary refinement method for object segmentation in digital images receives an image and a single initial object region of interest and performs refinement zone definition using the initial object regions of interest to generate refinement zones output. A directional edge enhancement is performed using the input image and the refinement zones to generate directional enhanced region of interest output. A radial detection is performed using the input image the refinement zones and the directional enhanced region of interest to generate radial detection mask output. In addition, a final shaping is performed using the radial detection mask having single object region output. A directional edge enhancement method determining pixel specific edge contrast enhancement direction according to the object structure direction near the pixel consists receives an image and refinement zones and performs 1D horizontal distance transform and 1D vertical distance transform using the refinement zones to generate horizontal distance map and vertical distance map outputs. A neighboring direction determination is performed using the horizontal distance map and the vertical distance map to generate neighboring image output. In addition, a directional edge contrast calculation using the neighboring image and input image having directional enhanced region of interest output.

摘要翻译： 用于数字图像中对象分割的基于对象的边界细化方法接收图像和感兴趣的单个初始对象区域，并使用感兴趣的初始对象区域执行细化区域定义，以生成细化区域输出。 使用输入图像和细化区域来执行方向边缘增强以产生方向增强的兴趣区域输出。 使用输入图像进行径向检测，该细化区域和方向增强区域用于产生径向检测掩模输出。 另外，使用具有单个物体区域输出的径向检测掩模进行最终成形。 根据像素附近的物体结构方向确定像素特征边缘对比度增强方向的方向边缘增强方法包括接收图像和细化区域，并使用细化区域进行1D水平距离变换和1D垂直距离变换，以生成水平距离图和垂直 距离图输出。 使用水平距离图和垂直距离图执行相邻方向确定以生成相邻图像输出。 另外，使用相邻图像的方向边缘对比度计算和具有方向增强感兴趣区域输出的输入图像。

公开(公告)号：US20060147105A1

公开(公告)日：2006-07-06

申请号：US11035867

申请日：2005-01-05

申请人： Shih-Jong Lee ,  Yuhui Cheng ,  Seho Oh ,  Shinichi Nakajima ,  Yuji Kokumai

发明人： Shih-Jong Lee ,  Yuhui Cheng ,  Seho Oh ,  Shinichi Nakajima ,  Yuji Kokumai

IPC分类号： G06K9/00

CPC分类号： G06T7/0006 ,  G06K9/6204 ,  G06T7/33 ,  G06T7/74 ,  G06T2207/30148 ,  H05K3/0008

摘要： An alignment template goodness qualification method receives a pattern image and a pattern based alignment template and performs template goodness measurement using the pattern image and the pattern based alignment template to generate template goodness result output. A template qualification is performed using the template goodness result to generate template qualification result output. If the template qualification result is acceptable, the pattern based alignment template is outputted as the qualified pattern based alignment template. Otherwise, an alternative template selection is performed using the pattern image, the pattern based alignment template and the template goodness result to generate alternative pattern based alignment template output. The template goodness measurements include signal content measurement, spatial discrimination measurement and pattern ambiguity measurement.

摘要翻译： 对齐模板品质鉴定方法接收图案图像和基于图案的对准模板，并使用图案图像和基于图案的对准模板进行模板优良度测量，以生成模板优良结果输出。 使用模板优化结果执行模板限定，以生成模板验证结果输出。 如果模板限定结果可以接受，则基于模式的对齐模板将作为合格模式对齐模板输出。 否则，使用模式图像，基于模式的对准模板和模板优点结果来执行替代模板选择，以生成基于替代模式的对准模板输出。 模板优点测量包括信号内容测量，空间辨别测量和模式模糊度测量。

公开(公告)号：US20060078192A1

公开(公告)日：2006-04-13

申请号：US10961663

申请日：2004-10-08

申请人： Seho Oh ,  Shih-Jong Lee ,  Shinichi Nakajima ,  Yuji Kokumai

发明人： Seho Oh ,  Shih-Jong Lee ,  Shinichi Nakajima ,  Yuji Kokumai

IPC分类号： G06K9/00

CPC分类号： G06K9/3216 ,  G06T7/001 ,  G06T2207/30148

摘要： A partition pattern template generation method for alignment receives a learning image and performs partition template generation using the learning image to generate a plurality of partition template result output. A partition template acceptance test is performed using the plurality of partition template results to generate partition templates or failure result. A partition template search method for alignment receives an alignment image and partition templates and performs a plurality of template search steps to generate a plurality of matching scores output. A partition integration method is performed using the plurality of matching scores to generate a partition template search result. A partition integration error self checking method receives a preliminary template search result position and a plurality of the matching scores. A matching score profile comparison is performed using the plurality of the matching scores and the expected matching score profile to generate the template search result.

摘要翻译： 用于对准的分割图案模板生成方法接收学习图像，并使用学习图像来执行分割模板生成，以生成多个分割模板结果输出。 使用多个分区模板结果执行分区模板验收测试，以生成分区模板或故障结果。 用于对准的分割模板搜索方法接收对准图像和分割模板，并且执行多个模板搜索步骤以生成多个匹配分数输出。 使用多个匹配分数来执行分区集成方法以生成分区模板搜索结果。 分区整合错误自检方法接收初步模板搜索结果位置和多个匹配分数。 使用多个匹配分数和预期匹配分数分布来执行匹配分数分布比较，以生成模板搜索结果。

公开(公告)号：US20070127834A1

公开(公告)日：2007-06-07

申请号：US11301292

申请日：2005-12-07

申请人： Shih-Jong Lee ,  Seho Oh

发明人： Shih-Jong Lee ,  Seho Oh

IPC分类号： G06K9/40 ,  G06K9/62 ,  G06K9/34 ,  G06K9/46

CPC分类号： G06K9/6219 ,  G06K9/38 ,  G06K9/6277

摘要： A directed pattern enhancement method receives a learning image and pattern enhancement directive. Pattern enhancement learning is performed using the learning image and the pattern enhancement directive to generate pattern enhancement recipe. An application image is received and a pattern enhancement application is performed using the application image and the pattern enhancement recipe to generate pattern enhanced image. A recognition thresholding is performed using the pattern enhanced image to generate recognition result. The pattern enhancement directive consists of background directive, patterns to enhance directive, and patterns to suppress directive. A partitioned modeling method receives an image region and performs feature extraction on the image region to generate characterization feature. A hierarchical partitioning is performed using the characterization feature to generate hierarchical partitions. A model generation is performed using the hierarchical partitions to generate partition model. The partitioned modeling further performs a partitioned matching step that matches an input point to the partition model to generate a matching score output. A partition model update method receives a partition model and input data for model update. A partition model update is performed using the partition model and the data to generate an updated partition model.

摘要翻译： 定向图案增强方法接收学习图像和图案增强指令。 使用学习图像和图案增强指令执行图案增强学习以产生图案增强配方。 接收应用图像，并且使用应用图像和图案增强配方来执行图案增强应用以生成图案增强图像。 使用图案增强图像执行识别阈值以产生识别结果。 模式增强指令包括背景指令，增强指令的模式和抑制指令的模式。 分区建模方法接收图像区域并对图像区域执行特征提取以产生表征特征。 使用表征特征来执行分层分区以生成分层分区。 使用分层分区执行模型生成以生成分区模型。 分区建模还执行将输入点与分区模型相匹配以产生匹配分数输出的分割匹配步骤。 分区模型更新方法接收分区模型并输入模型更新数据。 使用分区模型和数据执行分区模型更新，以生成更新的分区模型。

公开(公告)号：US20050232488A1

公开(公告)日：2005-10-20

申请号：US10828629

申请日：2004-04-14

申请人： Shih-Jong Lee ,  Samuel Alworth

发明人： Shih-Jong Lee ,  Samuel Alworth

IPC分类号： G06F17/00 ,  G06K9/00 ,  G06T7/00

CPC分类号： G06T7/0012 ,  G06K9/00127 ,  G06T2207/30004

摘要： A method for the detection and analysis of patterns receives an image containing object labels and performs relational feature development using the input image to create at least one pattern map. It then performs relational feature analysis using the at least one pattern map to create a relational feature analysis result. The pattern detection and analysis method further comprises a recipe for automation control and includes determination of a genetic anomaly. A relational feature development method receives an image containing object labels and performs core measurement table development using the input image to create at least one core measurement table. It then performs feature table production using the at least one core measurement table to create at least one feature table. It also performs PatternMap creation using the at least one feature table to create a PatternMap. The relational feature development method further comprises a PatternMap integration and update step to create an updated PatternMap. A boundary distance measurement receives an image containing object labels and performs structure object mask production using the input image to create structure object mask. It then performs inner distance transform using the structure object mask to create inner distance transform image and finds individual object centroid using the input image to create individual object centroid output. In addition, it finds object boundary distance using the individual object centroid and the inner distance transform image to create object boundary distance output.

摘要翻译： 用于检测和分析图案的方法接收包含对象标签的图像，并使用输入图像执行关系特征开发以创建至少一个模式图。 然后，使用至少一个模式图执行关系特征分析，以创建关系特征分析结果。 模式检测和分析方法还包括自动化控制的方案，并且包括遗传异常的确定。 关系特征开发方法接收包含对象标签的图像，并且使用输入图像执行核心测量表开发以创建至少一个核心测量表。 然后，使用至少一个核心测量表来执行特征表生成以创建至少一个特征表。 它还使用至少一个要素表创建PatternMap来创建PatternMap。 关系特征开发方法还包括PatternMap集成和更新步骤以创建更新的PatternMap。 边界距离测量接收包含对象标签的图像，并使用输入图像执行结构对象掩模生成，以创建结构对象掩码。 然后使用结构对象掩码进行内部距离变换，以创建内部距离变换图像，并使用输入图像找到单个对象中心，以创建单个对象质心输出。 此外，它使用单个对象中心和内部距离变换图像找到对象边界距离以创建对象边界距离输出。

公开(公告)号：US20070008288A1

公开(公告)日：2007-01-11

申请号：US11175952

申请日：2005-07-05

申请人： Chang-Sung Yu ,  Shih-Jong Lee

发明人： Chang-Sung Yu ,  Shih-Jong Lee

IPC分类号： G09G5/00

CPC分类号： G06F3/0237

摘要： A keypad optimization method for handheld devices with optimal multi-language entry capability and handiness for both handheld and fingertip manipulation receives application requirements containing language specification and performs application mapping using the application requirements to generate versatile keypad map output. A versatile keypad is implemented using versatile keypad map wherein the versatile keypad receives user input and generates received data output. An interactive optimization is performed using the received data having online action output. The online action is used to generate keypad output and screen display by the versatile keypad. An application mapping method receives application requirements containing language specification and performs language entry order grouping using the language specification to generate entry order groups and valid combination output. An inter-group mapping is performed using the application requirements and the entry order groups and valid combination having mapping sets output. An intra-group location mapping is performed using the application requirements and the mapping sets having key maps output. A versatile keypad interactive optimization method initializes the state value to initial input state and receives user key strike input. It performs interactive optimization using the user key strike and the state value having state update and symbol output.

摘要翻译： 具有最佳多语言输入能力的手持设备的键盘优化方法和手持和指尖操作的便利性接收包含语言规范的应用需求，并使用应用要求执行应用映射，以生成通用的键盘映射输出。 通用键盘实现多功能键盘，其中通用键盘接收用户输入并产生接收的数据输出。 使用具有在线动作输出的接收数据来执行交互式优化。 在线操作用于通过通用键盘生成键盘输出和屏幕显示。 应用映射方法接收包含语言规范的应用需求，并使用语言规范执行语言入口顺序分组，以生成入口顺序组和有效组合输出。 使用应用需求和入口顺序组以及具有映射集输出的有效组合来执行组间映射。 使用应用需求和具有键映射输出的映射集来执行组内位置映射。 通用键盘交互式优化方法将状态值初始化为初始输入状态，并接收用户键击输入。 它使用用户键击和具有状态更新和符号输出的状态值执行交互式优化。

公开(公告)号：US20060288031A1

公开(公告)日：2006-12-21

申请号：US11454277

申请日：2006-06-16

申请人： Shih-Jong Lee

发明人： Shih-Jong Lee

IPC分类号： G06F7/00

CPC分类号： G06F17/30539 ,  G06F2216/03 ,  Y10S707/99935 ,  Y10S707/99936 ,  Y10S707/99942 ,  Y10S707/99943 ,  Y10S707/99945 ,  Y10S707/99948

摘要： An integrated human and computer interactive data mining method receives an input database. A learning, modeling, and analysis method uses the database to create an initial knowledge model. A query of the initial knowledge model is performed using a query request. The initial knowledge model is processed to create a knowledge presentation output for visualization. It further comprises a feedback and update request step that updates the initial knowledge model. A multiple level integrated human and computer interactive data mining method facilitates overview interactive data mining and dynamic learning and knowledge representation by using the initial knowledge model and the database to create and update a presentable knowledge model. It facilitates zoom and filter interactive data mining and dynamic learning and knowledge representation by using the presentable knowledge model and the database to create and update the presentable knowledge model. It further facilitates details-on-demand interactive data mining and dynamic learning and knowledge representation by using the presentable knowledge model and the database to create and update the presentable knowledge model. The integrated human and computer interactive data mining method allows rule viewing by a parallel coordinate visualization technique that maps a multiple dimensional space onto two display dimensions with data items presented as polygonal lines.

公开(公告)号：US20060104516A1

公开(公告)日：2006-05-18

申请号：US10998282

申请日：2004-11-15

申请人： Shih-Jong Lee ,  Tuan Phan

发明人： Shih-Jong Lee ,  Tuan Phan

IPC分类号： G06K9/48 ,  G06K9/34

CPC分类号： G06K9/48 ,  G06K9/0014 ,  G06T7/13 ,  G06T7/149 ,  G06T7/181 ,  G06T2207/20036 ,  G06T2207/20156

摘要： A region-guided boundary refinement method for object segmentation in digital images receives an initial object regions of interest and performs directional boundary decomposition using the initial object regions of interest to generate a plurality of directional object boundaries output. A directional border search is performed using the plurality of directional object boundaries to generate base border points output. A base border integration is performed using the base border points to generate base borders output. In addition, a boundary completion is performed using the base borders having boundary refined object regions of interest output. A region-guided boundary completion method for object segmentation in digital images receives an initial object regions of interest and base borders. It performs boundary completion using the initial object regions of interest and the base borders to generate boundary refined object regions of interest output. The boundary completion method performs border growing using the base borders to generate grown borders output. A region guided connection is performed using the grown borders to generate connected borders output. A region guided merging is performed using the connected borders to generate fined object regions of interest output.

摘要翻译： 用于数字图像中的对象分割的区域引导边界细化方法接收目标的初始对象区域，并使用感兴趣的初始对象区域进行方向边界分解，以生成多个方向对象边界输出。 使用多个方向对象边界执行方向边界搜索以生成基本边界点输出。 使用基本边界点执行基本边界集成以生成基本边框输出。 此外，使用具有兴趣输出的边界精细对象区域的基本边界来执行边界完成。 用于数字图像中的对象分割的区域引导边界完成方法接收感兴趣的初始对象区域和基本边界。 它使用感兴趣的初始对象区域和基本边界来执行边界完成，以生成兴趣输出的边界细化对象区域。 边界完成方法使用基础边框执行边界生长以生成成长边界输出。 使用生成的边界执行区域引导连接以生成连接的边界输出。 使用连接的边界来执行区域引导合并，以产生感兴趣的精细对象​​区域输出。