公开(公告)号：US20070058870A1

公开(公告)日：2007-03-15

申请号：US11516213

申请日：2006-09-06

申请人： Jianming Liang ,  Zhiyun Xue ,  Marcos Salganicoff ,  Matthias Wolf

发明人： Jianming Liang ,  Zhiyun Xue ,  Marcos Salganicoff ,  Matthias Wolf

IPC分类号： G06K9/46 ,  G06K9/34

CPC分类号： G06T7/0012

摘要： A computer-implemented method for identifying an object of interest includes providing input data including an image and a candidate for the object of interest in the image, extracting a boundary of the candidate, and extracting a segment of a region of interest containing the candidate. The method further includes determining a plurality of features of an extracted segment of the region of interest containing the candidate, and outputting the object of interest, wherein the object of interest is characterized by the plurality of features, wherein the object of interest and the plurality of features are stored as computer-readable code.

摘要翻译： 用于识别感兴趣对象的计算机实现的方法包括提供包括图像中的图像和感兴趣对象的候选者的输入数据，提取候选者的边界，以及提取包含候选的感兴趣区域的片段。 该方法还包括确定包含该候选者的所述感兴趣区域的提取段的多个特征，并输出所述感兴趣对象，其中所述感兴趣对象由所述多个特征表征，其中所述感兴趣对象和所述多个特征 功能存储为计算机可读代码。

公开(公告)号：US08160336B2

公开(公告)日：2012-04-17

申请号：US11516213

申请日：2006-09-06

申请人： Jianming Liang ,  Zhiyun Xue ,  Marcos Salganicoff ,  Matthias Wolf

发明人： Jianming Liang ,  Zhiyun Xue ,  Marcos Salganicoff ,  Matthias Wolf

IPC分类号： G06K9/00

CPC分类号： G06T7/0012

摘要： A computer-implemented method for identifying an object of interest includes providing input data including an image and a candidate for the object of interest in the image, extracting a boundary of the candidate, and extracting a segment of a region of interest containing the candidate. The method further includes determining a plurality of features of an extracted segment of the region of interest containing the candidate, and outputting the object of interest, wherein the object of interest is characterized by the plurality of features, wherein the object of interest and the plurality of features are stored as computer-readable code.

摘要翻译： 用于识别感兴趣对象的计算机实现的方法包括提供包括图像中的图像和感兴趣对象的候选者的输入数据，提取候选者的边界，以及提取包含候选的感兴趣区域的片段。 该方法还包括确定包含该候选者的所述感兴趣区域的提取段的多个特征，并输出所述感兴趣对象，其中所述感兴趣对象由所述多个特征表征，其中所述感兴趣对象和所述多个特征 功能存储为计算机可读代码。

公开(公告)号：US20060209063A1

公开(公告)日：2006-09-21

申请号：US11247609

申请日：2005-10-11

申请人： Jianming Liang ,  Matthias Wolf ,  Marcos Salganicoff

发明人： Jianming Liang ,  Matthias Wolf ,  Marcos Salganicoff

IPC分类号： G06T15/00

CPC分类号： G06K9/342 ,  G06K2209/05 ,  G06T7/11 ,  G06T7/155 ,  G06T2207/10081 ,  G06T2207/20152 ,  G06T2207/30032 ,  G06T2207/30064 ,  G06T2207/30101

摘要： An exemplary method of detecting one or more objects in image data is provided. The image data includes a plurality of pixels/voxels. The method includes sliding pixels/voxels that meet sliding criteria; and collecting the slid pixels/voxels that satisfy collecting criteria. An exemplary method of segmenting an object in image data is also provided. The method includes receiving an initial pixel/voxel in the image data; and forming a segmentation of the object based on the initial pixel/voxel.

摘要翻译： 提供了检测图像数据中的一个或多个对象的示例性方法。 图像数据包括多个像素/体素。 该方法包括符合滑动标准的滑动像素/体元; 并收集满足收集标准的滑动像素/体素。 还提供了分割图像数据中的对象的示例性方法。 该方法包括在图像数据中接收初始像素/体元; 并基于初始像素/体元形成对象的分割。

公开(公告)号：US10861151B2

公开(公告)日：2020-12-08

申请号：US15750989

申请日：2016-08-08

申请人： Jianming Liang ,  Nima Tajbakhsh

发明人： Jianming Liang ,  Nima Tajbakhsh

IPC分类号： G06T7/00 ,  G06K9/62 ,  G16H50/20 ,  G16H30/40 ,  G06T7/12

摘要： Mechanisms for simultaneously monitoring colonoscopic video quality and detecting polyps in colonoscopy are provided. In some embodiments, the mechanisms can include a quality monitoring system that uses a first trained classifier to monitor image frames from a colonoscopic video to determine which image frames are informative frames and which image frames are non-informative frames. The informative image frames can be passed to an automatic polyp detection system that uses a second trained classifier to localize and identify whether a polyp or any other suitable object is present in one or more of the informative image frames.

公开(公告)号：US20190332896A1

公开(公告)日：2019-10-31

申请号：US16397990

申请日：2019-04-29

申请人： Jianming Liang ,  Zongwei Zhou ,  Jae Shin

发明人： Jianming Liang ,  Zongwei Zhou ,  Jae Shin

IPC分类号： G06K9/62

摘要： Methods, systems, and media for selecting candidates for annotation for use in training classifiers are provided. In some embodiments, the method comprises: identifying, for a trained Convolutional Neural Network (CNN), a group of candidate training samples, wherein each candidate training sample includes a plurality of patches; for each patch of the plurality of patches, determining a plurality of probabilities, each probability being a probability that the patch corresponds to a label of a plurality of labels; identifying a subset of the patches in the plurality of patches; for each patch in the subset of the patches, calculating a metric that indicates a variance of the probabilities assigned to each patch; selecting a subset of the candidate training samples based on the metric; labeling candidate training samples in the subset of the candidate training samples by querying an external source; and re-training the CNN using the labeled candidate training samples.

公开(公告)号：US20090060307A1

公开(公告)日：2009-03-05

申请号：US12198251

申请日：2008-08-26

申请人： Bernard S. Ghanem ,  Jianming Liang

发明人： Bernard S. Ghanem ,  Jianming Liang

IPC分类号： G06K9/00

CPC分类号： G06T7/0012 ,  G06T7/11 ,  G06T2207/30028 ,  G06T2207/30061

摘要： Described herein is a method and system for facilitating a tensor voting scheme. The tensor voting scheme includes determining at least one voter point and at least one receiver point from input data and determining a tensor vote directed from the receiver point to the voter point.

摘要翻译： 这里描述了一种用于促进张量投票方案的方法和系统。 张量投票方案包括从输入数据确定至少一个选民点和至少一个接收点，并确定从接收者点指向选民点的张量投票。

公开(公告)号：US07391893B2

公开(公告)日：2008-06-24

申请号：US10858270

申请日：2004-06-01

申请人： Jianming Liang ,  Luca Bogoni ,  Alok Gupta

发明人： Jianming Liang ,  Luca Bogoni ,  Alok Gupta

IPC分类号： G06K9/00

CPC分类号： G06K9/48

摘要： A system and method for detecting a shape in an image are provided. The method comprises: constructing a deformable model from an image; deforming the deformable model to remove an undesired shape in a portion of the image; computing properties of the deformed model to enable detection of a desired shape in the portion of the image; and detecting the desired shape based on the computed properties.

摘要翻译： 提供了用于检测图像中的形状的系统和方法。 该方法包括：从图像构建可变形模型; 使可变形模型变形以去除图像的一部分中的不期望的形状; 计算变形模型的属性，以便能够检测图像部分中期望的形状; 并基于所计算的特性来检测所需的形状。

公开(公告)号：US20070036406A1

公开(公告)日：2007-02-15

申请号：US11440780

申请日：2006-05-25

申请人： Luca Bogoni ,  Jianming Liang ,  Pascal Cathier

发明人： Luca Bogoni ,  Jianming Liang ,  Pascal Cathier

IPC分类号： G06K9/00

CPC分类号： G06T7/0012 ,  G06T7/11 ,  G06T7/155

摘要： A system and method for toboggan-based object detection in cutting planes are provided. A method for detecting an object in an image includes: determining a region of interest (ROI) in the image; determining a toboggan potential for each image element in the ROI; extracting a plurality of cutting planes from the ROI; and performing a tobogganing in the cutting planes to form a toboggan cluster to determine a location of the object, wherein image elements inside the toboggan cluster are stored in a cluster-member list, image elements on an outer-border of the toboggan cluster are stored in an outer-border list and image elements on an inner-border of the toboggan cluster are stored in an inner-border list.

摘要翻译： 提供了一种用于切割平面中基于雪橇的物体检测的系统和方法。 用于检测图像中的对象的方法包括：确定图像中的感兴趣区域（ROI）; 确定ROI中每个图像元素的雪橇潜力; 从ROI提取多个切割平面; 并且在所述切割平面中执行雪橇形成以形成所述物体的位置以确定所述物体的位置，其中，所述滑降簇内的图像元素被存储在群集成员列表中，存储所述滑降簇的外部边界上的图像元素 在外部边界列表中，并且滑冰群集的内部边界上的图像元素存储在内部边界列表中。

公开(公告)号：US20050271278A1

公开(公告)日：2005-12-08

申请号：US11145887

申请日：2005-06-06

申请人： Jianming Liang ,  Luca Bogoni

发明人： Jianming Liang ,  Luca Bogoni

IPC分类号： G06K9/46 ,  G06T5/00

CPC分类号： G06K9/342 ,  G06T7/11 ,  G06T7/155 ,  G06T2207/10081 ,  G06T2207/20152 ,  G06T2207/20164 ,  G06T2207/30032

摘要： A method of identifying an object in a digital image includes finding a point in a digital image that is a concentration location, initializing a cluster with said concentration location, adding the neighboring points of the concentration location to a list, selecting a neighbor point with an extremal potential value from said list, determining a slide direction of all neighbors of said selected point and identifying those neighbors that slide to the selected point, adding those neighbor points not already in the list to the list, adding the selected point to the cluster, and repeating the steps of selecting a neighbor point with an extremal potential value, determining a slide direction, adding points to the list, and adding the selected point to the cluster, until the list is empty.

摘要翻译： 识别数字图像中的对象的方法包括找到作为浓度位置的数字图像中的点，利用所述浓度位置初始化聚类，将浓度位置的相邻点添加到列表中，选择具有 确定所述选定点的所有邻居的滑动方向并识别滑动到所选择的点的那些邻居，将尚未在列表中的相邻点添加到列表中，将所选择的点添加到群集中， 并重复选择具有极值电位值的相邻点的步骤，确定滑动方向，向列表添加点，并将所选择的点添加到集群中，直到列表为空。

公开(公告)号：US20180314943A1

公开(公告)日：2018-11-01

申请号：US15965691

申请日：2018-04-27

申请人： Jianming Liang ,  Zongwei Zhou ,  Jae Shin

发明人： Jianming Liang ,  Zongwei Zhou ,  Jae Shin

IPC分类号： G06N3/08 ,  G06N3/04 ,  G06K9/62

摘要： Systems for selecting candidates for labelling and use in training a convolutional neural network (CNN) are provided, the systems comprising: a memory device; and at least one hardware processor configured to: receive a plurality of input candidates, wherein each candidate includes a plurality of identically labelled patches; and for each of the plurality of candidates: determine a plurality of probabilities, each of the plurality of probabilities being a probability that a unique patch of the plurality of identically labelled patches of the candidate corresponds to a label using a pre-trained CNN; identify a subset of candidates of the plurality of input candidates, wherein the subset does not include all of the plurality of candidates, based on the determined probabilities; query an external source to label the subset of candidates to produce labelled candidates; and train the pre-trained CNN using the labelled candidates.