公开(公告)号：US09202281B2

公开(公告)日：2015-12-01

申请号：US13423209

申请日：2012-03-17

申请人： Su Wang ,  Shengyang Dai ,  Xun Xu ,  Akira Nakamura ,  Takeshi Ohashi ,  Jun Yokono

发明人： Su Wang ,  Shengyang Dai ,  Xun Xu ,  Akira Nakamura ,  Takeshi Ohashi ,  Jun Yokono

IPC分类号： G06K9/00 ,  G06T7/00

CPC分类号： G06T7/0081 ,  G06K9/00 ,  G06T7/11 ,  G06T7/143 ,  G06T7/162 ,  G06T7/194 ,  G06T2207/20081

摘要： An integrated interactive segmentation with spatial constraint method utilizes a combination of several of the most popular online learning algorithms into one and implements a spatial constraint which defines a valid mask local to the user's given marks. Additionally, both supervised learning and statistical analysis are integrated, which are able to compensate each other. Once prediction and activation are obtained, pixel-wised multiplication is conducted to fully indicate how likely each pixel belongs to the foreground or background.

摘要翻译： 具有空间约束方法的集成交互式分割将几种最流行的在线学习算法的组合应用于一种，并实现了定义用户给定标记本地的有效掩码的空间约束。 此外，监督学习和统计分析都是综合的，可以相互补偿。 一旦获得了预测和激活，就进行像素增益乘法以完全指示每个像素属于前景或背景的可能性。

公开(公告)号：US20130243308A1

公开(公告)日：2013-09-19

申请号：US13423209

申请日：2012-03-17

申请人： Su Wang ,  Shengyang Dai ,  Xun Xu ,  Akira Nakamura ,  Takeshi Ohashi ,  Jun Yokono

发明人： Su Wang ,  Shengyang Dai ,  Xun Xu ,  Akira Nakamura ,  Takeshi Ohashi ,  Jun Yokono

IPC分类号： G06K9/62

CPC分类号： G06T7/0081 ,  G06K9/00 ,  G06T7/11 ,  G06T7/143 ,  G06T7/162 ,  G06T7/194 ,  G06T2207/20081

摘要： An integrated interactive segmentation with spatial constraint method utilizes a combination of several of the most popular online learning algorithms into one and implements a spatial constraint which defines a valid mask local to the user's given marks. Additionally, both supervised learning and statistical analysis are integrated, which are able to compensate each other. Once prediction and activation are obtained, pixel-wised multiplication is conducted to fully indicate how likely each pixel belongs to the foreground or background.

摘要翻译： 具有空间约束方法的集成交互式分割将几种最流行的在线学习算法的组合应用于一种，并实现了定义用户给定标记本地的有效掩码的空间约束。 此外，监督学习和统计分析都是综合的，可以相互补偿。 一旦获得了预测和激活，就进行像素增益乘法以完全指示每个像素属于前景或背景的可能性。

公开(公告)号：US08345976B2

公开(公告)日：2013-01-01

申请号：US12852096

申请日：2010-08-06

申请人： Su Wang ,  Shengyang Dai ,  Akira Nakamura ,  Takeshi Ohashi ,  Jun Yokono

发明人： Su Wang ,  Shengyang Dai ,  Akira Nakamura ,  Takeshi Ohashi ,  Jun Yokono

IPC分类号： G06K9/34

CPC分类号： G06K9/6256 ,  G06K9/0014 ,  G06T7/0012 ,  G06T7/11 ,  G06T7/136 ,  G06T7/187 ,  G06T2207/30024

摘要： Methods and systems disclosed herein provide the capability to automatically process digital pathology images quickly and accurately. According to one embodiment, an digital pathology image segmentation task may be divided into at least two parts. An image segmentation task may be carried out utilizing both bottom-up analysis to capture local definition of features and top-down analysis to use global information to eliminate false positives. In some embodiments, an image segmentation task is carried out using a “pseudo-bootstrapping” iterative technique to produce superior segmentation results. In some embodiments, the superior segmentation results produced by the pseudo-bootstrapping method are used as input in a second segmentation task that uses a combination of bottom-up and top-down analysis.

摘要翻译： 本文公开的方法和系统提供了快速且准确地自动处理数字病理图像的能力。 根据一个实施例，数字病理图像分割任务可以被划分为至少两部分。 图像分割任务可以利用自下而上的分析来捕获特征的局部定义和自上而下的分析，以使用全局信息来消除假阳性。 在一些实施例中，使用伪自举迭代技术来执行图像分割任务以产生优异的分割结果。 在一些实施例中，通过伪自举方法产生的优越分割结果被用作使用自下而上和自顶向下分析的组合的第二分段任务中的输入。

公开(公告)号：US08351676B2

公开(公告)日：2013-01-08

申请号：US12902321

申请日：2010-10-12

申请人： Shengyang Dai ,  Su Wang ,  Akira Nakamura ,  Takeshi Ohashi ,  Jun Yokono

发明人： Shengyang Dai ,  Su Wang ,  Akira Nakamura ,  Takeshi Ohashi ,  Jun Yokono

IPC分类号： G06K9/00 ,  G06K9/34

CPC分类号： G06K9/0014 ,  G06K9/00147 ,  G06K9/6282

摘要： Systems and methods for implementing a multi-step image recognition framework for classifying digital images are provided. The provided multi-step image recognition framework utilizes a gradual approach to model training and image classification tasks requiring multi-dimensional ground truths. A first step of the multi-step image recognition framework differentiates a first image region from a remainder image region. Each subsequent step operates on a remainder image region from the previous step. The provided multi-step image recognition framework permits model training and image classification tasks to be performed more accurately and in a less resource intensive fashion than conventional single-step image recognition frameworks.

摘要翻译： 提供了用于实现用于分类数字图像的多步图像识别框架的系统和方法。 提供的多步图像识别框架利用逐步的方法来模拟需要多维地面真实的训练和图像分类任务。 多步图像识别框架的第一步骤将第一图像区域与剩余图像区域区分开。 每个后续步骤对前一步骤的余数图像区域进行操作。 提供的多步图像识别框架允许模型训练和图像分类任务以比传统的单步图像识别框架更精确和更少资源密集的方式执行。

公开(公告)号：US09208405B2

公开(公告)日：2015-12-08

申请号：US12851818

申请日：2010-08-06

申请人： Shengyang Dai ,  Su Wang ,  Akira Nakamura ,  Takeshi Ohashi ,  Jun Yokono

发明人： Shengyang Dai ,  Su Wang ,  Akira Nakamura ,  Takeshi Ohashi ,  Jun Yokono

IPC分类号： G06K9/00 ,  G06K9/62

CPC分类号： G06K9/6292 ,  G06K9/6254

摘要： Systems and methods for implementing a hierarchical image recognition framework for classifying digital images are provided. The provided hierarchical image recognition framework utilizes a multi-layer approach to model training and image classification tasks. A first layer of the hierarchical image recognition framework generates first layer confidence scores, which are utilized by the second layer to produce a final recognition score. The provided hierarchical image recognition framework permits model training and image classification tasks to be performed more accurately and in a less resource intensive fashion than conventional single-layer image recognition frameworks. In some embodiments real-time operator guidance is provided for an image classification task.

摘要翻译： 提供了用于实现用于分类数字图像的分层图像识别框架的系统和方法。 所提供的分层图像识别框架利用多层方法对训练和图像分类任务进行建模。 分层图像识别框架的第一层产生第一层置信度得分，其由第二层利用以产生最终识别分数。 所提供的分层图像识别框架允许模型训练和图像分类任务以比常规单层图像识别框架更精确和更少资源密集的方式执行。 在一些实施例中，为图像分类任务提供了实时操作者指导。

公开(公告)号：US20120033861A1

公开(公告)日：2012-02-09

申请号：US12851818

申请日：2010-08-06

申请人： Shengyang Dai ,  Su Wang ,  Akira Nakamura ,  Takeshi Ohashi ,  Jun Yokono

发明人： Shengyang Dai ,  Su Wang ,  Akira Nakamura ,  Takeshi Ohashi ,  Jun Yokono

IPC分类号： G06K9/00

CPC分类号： G06K9/6292 ,  G06K9/6254

摘要： Systems and methods for implementing a hierarchical image recognition framework for classifying digital images are provided. The provided hierarchical image recognition framework utilizes a multi-layer approach to model training and image classification tasks. A first layer of the hierarchical image recognition framework generates first layer confidence scores, which are utilized by the second layer to produce a final recognition score. The provided hierarchical image recognition framework permits model training and image classification tasks to be performed more accurately and in a less resource intensive fashion than conventional single-layer image recognition frameworks. In some embodiments real-time operator guidance is provided for an image classification task.

摘要翻译： 提供了用于实现用于分类数字图像的分层图像识别框架的系统和方法。 所提供的分层图像识别框架利用多层方法对训练和图像分类任务进行建模。 分层图像识别框架的第一层产生第一层置信度得分，其由第二层利用以产生最终识别分数。 所提供的分层图像识别框架允许模型训练和图像分类任务以比常规单层图像识别框架更精确和更少资源密集的方式执行。 在一些实施例中，为图像分类任务提供了实时操作者指导。

公开(公告)号：US08588518B2

公开(公告)日：2013-11-19

申请号：US12951702

申请日：2010-11-22

申请人： Su Wang ,  Shengyang Dai ,  Akira Nakamura ,  Takeshi Ohashi ,  Jun Yokono

发明人： Su Wang ,  Shengyang Dai ,  Akira Nakamura ,  Takeshi Ohashi ,  Jun Yokono

IPC分类号： G06K9/62

CPC分类号： G06K9/4671 ,  G06K9/468 ,  G06T7/12 ,  G06T2207/20076

摘要： Systems and methods for implementing a superpixel boosted top-down image recognition framework are provided. The framework utilizes superpixels comprising contiguous pixel regions sharing similar characteristics. Feature extraction methods described herein provide non-redundant image feature vectors for classification model building. The provided framework differentiates a digitized image into a plurality of superpixels. The digitized image is characterized through image feature extraction methods based on the plurality of superpixels. Image classification models are generated from the extracted image features and ground truth labels and may then be used to classify other digitized images.

摘要翻译： 提供了用于实现超像素增强自顶向下图像识别框架的系统和方法。 框架利用包含具有相似特征的相邻像素区域的超像素。 本文描述的特征提取方法提供用于分类模型构建的非冗余图像特征向量。 所提供的框架将数字化图像区分为多个超像素。 数字化图像的特征在于基于多个超像素的图像特征提取方法。 图像分类模型从提取的图像特征和地面真值标签生成，然后可以用于对其他数字化图像进行分类。

公开(公告)号：US08379994B2

公开(公告)日：2013-02-19

申请号：US12904138

申请日：2010-10-13

申请人： Shengyang Dai ,  Su Wang ,  Akira Nakamura ,  Takeshi Ohashi ,  Jun Yokono

发明人： Shengyang Dai ,  Su Wang ,  Akira Nakamura ,  Takeshi Ohashi ,  Jun Yokono

IPC分类号： G06K9/62

CPC分类号： G06K9/6262 ,  G06K9/6232

摘要： Systems and methods for implementing a multi-label image recognition framework for classifying digital images are provided. The provided multi-label image recognition framework utilizes an iterative, multiple analysis path approach to model training and image classification tasks. A first iteration of the multi-label image recognition framework generates confidence maps for each label, which are shared by the multiple analysis paths to update the confidence maps in subsequent iterations. The provided multi-label image recognition framework permits model training and image classification tasks to be performed more accurately than conventional single-label image recognition frameworks.

摘要翻译： 提供了用于实现用于分类数字图像的多标签图像识别框架的系统和方法。 提供的多标签图像识别框架利用迭代的多分析路径方法来对训练和图像分类任务进行建模。 多标签图像识别框架的第一迭代生成每个标签的置信图，其由多个分析路径共享以在后续迭代中更新置信度图。 提供的多标签图像识别框架允许模型训练和图像分类任务比传统的单标签图像识别框架更准确地执行。

公开(公告)号：US20120128237A1

公开(公告)日：2012-05-24

申请号：US12951702

申请日：2010-11-22

申请人： Su Wang ,  Shengyang Dai ,  Akira Nakamura ,  Takeshi Ohashi ,  Jun Yokono

发明人： Su Wang ,  Shengyang Dai ,  Akira Nakamura ,  Takeshi Ohashi ,  Jun Yokono

IPC分类号： G06K9/62 ,  G06K9/46

CPC分类号： G06K9/4671 ,  G06K9/468 ,  G06T7/12 ,  G06T2207/20076

摘要： Systems and methods for implementing a superpixel boosted top-down image recognition framework are provided. The framework utilizes superpixels comprising contiguous pixel regions sharing similar characteristics. Feature extraction methods described herein provide non-redundant image feature vectors for classification model building. The provided framework differentiates a digitized image into a plurality of superpixels. The digitized image is characterized through image feature extraction methods based on the plurality of superpixels. Image classification models are generated from the extracted image features and ground truth labels and may then be used to classify other digitized images.

摘要翻译： 提供了用于实现超像素增强自顶向下图像识别框架的系统和方法。 框架利用包含具有相似特征的相邻像素区域的超像素。 本文描述的特征提取方法提供用于分类模型构建的非冗余图像特征向量。 所提供的框架将数字化图像区分为多个超像素。 数字化图像的特征在于基于多个超像素的图像特征提取方法。 图像分类模型从提取的图像特征和地面真值标签生成，然后可以用于对其他数字化图像进行分类。

公开(公告)号：US20120093396A1

公开(公告)日：2012-04-19

申请号：US12904138

申请日：2010-10-13

申请人： Shengyang Dai ,  Su Wang ,  Akira Nakamura ,  Takeshi Ohashi ,  Jun Yokono

发明人： Shengyang Dai ,  Su Wang ,  Akira Nakamura ,  Takeshi Ohashi ,  Jun Yokono

IPC分类号： G06K9/62

CPC分类号： G06K9/6262 ,  G06K9/6232

摘要： Systems and methods for implementing a multi-label image recognition framework for classifying digital images are provided. The provided multi-label image recognition framework utilizes an iterative, multiple analysis path approach to model training and image classification tasks. A first iteration of the multi-label image recognition framework generates confidence maps for each label, which are shared by the multiple analysis paths to update the confidence maps in subsequent iterations. The provided multi-label image recognition framework permits model training and image classification tasks to be performed more accurately than conventional single-label image recognition frameworks.

摘要翻译： 提供了用于实现用于分类数字图像的多标签图像识别框架的系统和方法。 提供的多标签图像识别框架利用迭代的多分析路径方法来对训练和图像分类任务进行建模。 多标签图像识别框架的第一迭代生成每个标签的置信图，其由多个分析路径共享以在后续迭代中更新置信度图。 提供的多标签图像识别框架允许模型训练和图像分类任务比传统的单标签图像识别框架更准确地执行。