公开(公告)号：EP2779089B1

公开(公告)日：2018-11-14

申请号：EP14160371.2

申请日：2011-08-01

申请人： Fundação D. Anna Sommer Champalimaud E Dr. Carlos Montez Champalimaud

发明人： Ajemba, Peter ,  Scott, Richard ,  Ramachandran, Janakiramanan ,  Zeineh, Jack ,  Donovan, Michael ,  Fernandez, Gerardo ,  Liu, Qiuhua ,  Khan, Faisal

IPC分类号： G06T5/30 ,  G06T7/00

CPC分类号： G06K9/00147 ,  G06T5/008 ,  G06T7/0012 ,  G06T7/11 ,  G06T7/155 ,  G06T7/45 ,  G06T2207/10056 ,  G06T2207/20041 ,  G06T2207/20212 ,  G06T2207/30024

摘要： Apparatus, methods, and computer-readable media are provided for segmentation, processing (e.g., preprocessing and/or postprocessing), and/or feature extraction from tissue images such as, for example, images of nuclei and/or cytoplasm. Tissue images processed by various embodiments described herein may be generated by Hematoxylin and Eosin (H&E) staining, immunofluorescence (IF) detection, immunohistochemistry (IHC), similar and/or related staining processes, and/or other processes. Predictive features described herein may be provided for use in, for example, one or more predictive models for treating, diagnosing, and/or predicting the occurrence (e.g., recurrence) of one or more medical conditions such as, for example, cancer or other types of disease.

公开(公告)号：EP3249603A1

公开(公告)日：2017-11-29

申请号：EP16171267.4

申请日：2016-05-25

申请人： IMINT Image Intelligence AB

发明人： PIUVA, David

IPC分类号： G06T3/00 ,  G06T7/20 ,  G06T5/30 ,  G06T7/00

CPC分类号： G06T3/0093 ,  G06T5/30 ,  G06T7/254 ,  G06T7/30 ,  G06T2210/52

摘要： A method for detecting motion in a video, the method comprising the steps of:
Getting (1) self-rotation from frame to frame; storing (1.2) a history of old images and projective transforms; accumulating (1.3) transforms from the oldest image to the newest image; detecting (2) motion for each point in a lower resolution image; eroding (3) the motion image; applying (4) regional analysis on the motion image to make it very small.
Only gray-scale is used in this method because colors have less quality if they even exist at all.

摘要翻译： 一种用于检测视频中的运动的方法，所述方法包括以下步骤：获得（1）帧间自转; 存储（1.2）旧图像的历史和投影变换; 累积（1.3）从最早的图像变换到最新的图像; 检测（2）较低分辨率图像中的每个点的运动; 腐蚀（3）运动图像; 对运动图像应用（4）区域分析以使其非常小。 这种方法只使用灰度，因为即使颜色完全存在，颜色的质量也会降低。

公开(公告)号：EP3182896A1

公开(公告)日：2017-06-28

申请号：EP15797947.7

申请日：2015-11-16

申请人： Koninklijke Philips N.V.

发明人： BERGNER, Frank ,  HOMANN, Hanno Heyke ,  GOOSSEN, André ,  MAACK, Hanns-Ingo

IPC分类号： A61B6/00 ,  G06T5/30 ,  G06T7/00

CPC分类号： A61B6/5211 ,  A61B6/0414 ,  A61B6/502 ,  G06T5/008 ,  G06T7/0012 ,  G06T7/12 ,  G06T2207/10116 ,  G06T2207/30068

摘要： The invention relates to peripheral equalization during a mammography X-ray examination. High contrast tissue pixel values are removed from the background estimate by finding the minimum intensity values of the pixel located in the neighbourhood, which have approximately the same distance to the skin line. Thus, high attenuating pixel values may be removed from the estimate and replaced by lower attenuating tissue pixel values. After a minimum filtration, a conventional peripheral equalization is performed. This may result in less overshoots and intensity values for higher attenuating structures in the peripheral region may become more consistent with intensity values for higher attenuating structures in the fully compressed region.

摘要翻译： 本发明涉及乳房摄影X射线检查期间的外周均衡。 通过找到位于邻近区域的像素的最小强度值（它们具有与皮肤线大致相同的距离），从背景估计中去除高对比度组织像素值。 因此，可以从估计中去除高衰减像素值并用较低衰减的组织像素值替换。 在最小滤波之后，执行常规的外围均衡。 这可能导致对于较高衰减结构在周边区域中的过冲和强度值更小可能与完全压缩区域中较高衰减结构的强度值更加一致。

公开(公告)号：EP2827588A3

公开(公告)日：2015-02-18

申请号：EP14187659.9

申请日：2011-05-06

申请人： CANON KABUSHIKI KAISHA

发明人： Kawaguchi, Zenya ,  Hara, Takayuki ,  Kunieda, Shutaro

IPC分类号： H04N9/07 ,  G06T5/00 ,  G06T5/20 ,  H04N5/213 ,  H04N5/232 ,  G06T5/30 ,  H04N9/04

CPC分类号： H04N9/045 ,  H04N5/213 ,  H04N5/23229

摘要： An image processing apparatus can execute appropriate image processing while preventing increase in a capacity of a memory for storing a plurality of pieces of image data of different frequency bands. The image processing apparatus stores first image data having the highest frequency among the plurality of pieces of image data of different frequency bands in a state in which each pixel of the first image data includes a color component signal of any of a plurality of colors, on the memory, and further stores second image data whose frequency band is lower than that of the first image data on the memory, in a state in which a part of or all pixels of the second image data have color component signals of a plurality of colors.

摘要翻译： 图像处理装置可以在防止存储多个不同频带的图像数据的存储器的容量的增加的同时执行适当的图像处理。 图像处理装置在第一图像数据的每个像素包括多种颜色中的任何一种的颜色分量信号的状态下存储多个不同频带的多个图像数据中具有最高频率的第一图像数据， 存储器，并且在第二图像数据的一部分或全部像素具有多种颜色的分量信号的状态下，将存储器中的频带低于第一图像数据的第二图像数据的存储器存储在存储器中 。

公开(公告)号：EP2790150A1

公开(公告)日：2014-10-15

申请号：EP14162878.4

申请日：2014-03-31

申请人： Sony Corporation

发明人： Watanabe, Keisuke ,  Shimizu, Akira

IPC分类号： G06T5/20 ,  G06T5/30 ,  H04N5/262 ,  H04N5/278 ,  H04N13/00

CPC分类号： H04N13/122 ,  H04N13/156 ,  H04N13/183 ,  H04N13/341

摘要： An image processing device includes: a sub-image generation section, the sub-image generation section configured to generate a third sub-image by providing a peripheral image including at least a first region that is a transparent region around a first sub-image and to perform a filtering process on the entire or a part of a second sub-image including the first sub-image and the peripheral image; and a composition section configured to composite together a frame image and the third sub-image.

摘要翻译： 一种图像处理装置，包括：子图像生成部，所述子图像生成部被配置为通过提供至少包括作为第一子图像周围的透明区域的第一区域的周边图像来生成第三子图像，以及 对包括第一子图像和周边图像的第二子图像的全部或一部分进行滤波处理; 以及构造成将帧图像和第三子图像复合在一起的合成部。

公开(公告)号：EP2698114A4

公开(公告)日：2014-10-01

申请号：EP12772003

申请日：2012-04-05

申请人： HITACHI ALOKA MEDICAL LTD

发明人： NAGASE YUKO ,  MATSUSHITA NORIYOSHI

IPC分类号： A61B8/00 ,  A61B8/08 ,  A61B8/13 ,  G06T5/30 ,  G06T7/00 ,  G06T7/60 ,  G06T19/20

CPC分类号： A61B8/5207 ,  A61B8/13 ,  A61B8/466 ,  A61B8/483 ,  G01S7/52073 ,  G01S7/52074 ,  G06T7/11 ,  G06T7/155 ,  G06T7/60 ,  G06T7/73 ,  G06T19/20 ,  G06T2207/10136 ,  G06T2207/20036 ,  G06T2207/30004 ,  G06T2210/41 ,  G06T2219/028 ,  G06T2219/2016

公开(公告)号：EP2569948A4

公开(公告)日：2014-05-28

申请号：EP11780364

申请日：2011-05-06

申请人： CANON KK

发明人： KAWAGUCHI ZENYA ,  HARA TAKAYUKI ,  KUNIEDA SHUTARO

IPC分类号： H04N9/07 ,  G06T5/00 ,  G06T5/20 ,  G06T5/30 ,  H04N5/213 ,  H04N5/232 ,  H04N9/04

CPC分类号： H04N9/045 ,  H04N5/213 ,  H04N5/23229

公开(公告)号：EP2700052A1

公开(公告)日：2014-02-26

申请号：EP12710921.3

申请日：2012-03-21

申请人： MICHELIN Recherche et Technique S.A. ,  Compagnie Générale des Etablissements Michelin

发明人： ZANELLA, Jean-Paul ,  MOREAU, Claire ,  NOYEL, Guillaume ,  SHEN, Yusi

IPC分类号： G06T5/00 ,  G06T5/30

CPC分类号： G06T7/408 ,  G06T5/005 ,  G06T5/30 ,  G06T2207/10028

摘要： The invention relates to a method for processing the three-dimensional digital image of the surface of a tyre, in which: the three-dimensional image of the surface is captured and each point of the acquired image is assigned a grey scale value corresponding to the elevation thereof; a first closing-type transformation of the image of the surface is performed with the aid of a first morphological operator using a rectangular structuring element; a second opening-type transformation of the surface is performed with the aid of a second morphological operator using a rectangular structuring element; and each point of the image is assigned a grey scale value equal to the minimum value between the grey scale value at this point in the image obtained in the preceding step and the grey scale value at this point in the acquired image, such as to eliminate false measurement points.

公开(公告)号：EP2191414A4

公开(公告)日：2010-10-06

申请号：EP08827961

申请日：2008-08-18

申请人： ORAL CANCER PREVENTION INTERNA

IPC分类号： G06T5/30 ,  G06K9/00 ,  G06T5/50

CPC分类号： G06T5/50 ,  G06T5/30 ,  G06T2207/10056 ,  G06T2207/30024

摘要： A method and system for constructing a digital image of a three-dimensional biological specimen that displays diagnostically important information—substantially to the exclusion of unimportant information. The system de-enhances features in a cellular specimen which are not diagnostically important and enhances those which are. The system selects the sharpest pixel for each pixel location from among a stack of image slices and copies them into a composite image.

公开(公告)号：EP2230855A2

公开(公告)日：2010-09-22

申请号：EP10002459.5

申请日：2010-03-09

申请人： Mitsubishi Electric Corporation

发明人： Yea, Sehoon ,  Oh, Kwan-Jung ,  Vetro, Anthony

IPC分类号： H04N13/00 ,  G06T5/00 ,  G06T5/20 ,  G06T5/30 ,  G06T5/40 ,  G06T5/50 ,  G06T15/20 ,  G06T3/00

CPC分类号： G06T3/0093 ,  G06T5/009 ,  G06T5/30 ,  G06T5/40 ,  G06T5/50 ,  G06T15/205 ,  G06T2207/10016 ,  G06T2207/10028 ,  G06T2207/20028 ,  G06T2207/20036 ,  H04N13/261 ,  H04N19/597

摘要： A method synthesizes virtual images from a sequence of texture images and a sequence of corresponding depth images, wherein each depth images stores depths d at pixel locations I ( x , y ). Each depth image, is preprocessed to produce a corresponding preprocessed depth image. A first reference image and a second reference image are selected from the sequence of texture images. Then, depth-based 3D warping, depth-based histogram matching, base plus assistant image blending, and depth-based in-painting are applied in order to synthesize a virtual image.

摘要翻译： 一种方法从纹理图像序列和相应深度图像的序列合成虚拟图像，其中每个深度图像存储像素位置I（x，y）处的深度d。 每个深度图像被预处理以产生相应的预处理深度图像。 从纹理图像序列中选择第一参考图像和第二参考图像。 然后，应用基于深度的3D翘曲，基于深度的直方图匹配，基础加辅助图像混合和基于深度的绘画，以便合成虚拟图像。