利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

43 条记录 (耗时 0.024 秒)

    A COMPUTER-IMPLEMENTED METHOD OF CONVERTING AN INPUT IMAGE INTO AN OUTPUT IMAGE BASED ON A REFERENCE IMAGE
    1.
    发明公开
    A COMPUTER-IMPLEMENTED METHOD OF CONVERTING AN INPUT IMAGE INTO AN OUTPUT IMAGE BASED ON A REFERENCE IMAGE 审中-公开

    公开(公告)号：EP3836090A1

    公开(公告)日：2021-06-16

    申请号：EP19215606.5

    申请日：2019-12-12

    申请人： Koninklijke Philips N.V.

    发明人： VLUTTERS, Ruud ,  VAN LEEUWEN, Marinus Bastiaan

    IPC分类号： G06T11/00

    摘要： A process for converting an arbitrary input digital pathology image into an output digital pathology image that shares statistical information with a reference image. The input digital pathology image is separated into two or more image sections. Each image section is encoded, using a first convolutional neural network, into one or more feature maps. The one or more feature maps of each image section are modified based on statistical information derived from a reference image. The modified feature map(s) of each image section is/are then decoded to construct a respective image section for an output image. The constructed image sections for an output image then form the output image.

    SYSTEM AND METHOD FOR ANALYSIS OF MICROSCOPIC IMAGE DATA AND FOR GENERATING AN ANNOTATED DATA SET FOR CLASSIFIER TRAINING
    3.
    发明公开
    SYSTEM AND METHOD FOR ANALYSIS OF MICROSCOPIC IMAGE DATA AND FOR GENERATING AN ANNOTATED DATA SET FOR CLASSIFIER TRAINING 审中-公开

    公开(公告)号：EP3611654A1

    公开(公告)日：2020-02-19

    申请号：EP18189091.4

    申请日：2018-08-15

    申请人： Koninklijke Philips N.V.

    发明人： VAN LEEUWEN, Marinus Bastiaan ,  VLUTTERS, Ruud

    IPC分类号： G06K9/00 ,  G06K9/62 ,  G06N3/08

    摘要： Disclosed is a system for analysis of microscopic image data which includes a data processing system. Pixel classification data for each of a plurality of pixels of the microscopic image data are read. The pixel classification data include for each of the pixels of the microscopic image data, binary or probabilistic classification data for classifying the pixel of the microscopic image data into one or more object classes of pre-defined objects which are shown by the image. At least a portion of the pixels of the microscopic image data are grouped to form one or more pixels groups. For each of the pixel groups, probabilistic group classification data are calculated depending on the pixel classification data of the pixels of the respective group. The probabilistic group classification data are indicative of a probability that the group shows at least a portion of an object of the respective object class.

    METHOD AND DEVICE FOR ESTIMATING ABSOLUTE SIZE DIMENSIONS OF A TEST OBJECT
    4.
    发明公开
    METHOD AND DEVICE FOR ESTIMATING ABSOLUTE SIZE DIMENSIONS OF A TEST OBJECT 审中-公开

    公开(公告)号：EP3378038A1

    公开(公告)日：2018-09-26

    申请号：EP16798686.8

    申请日：2016-11-15

    申请人： Koninklijke Philips N.V.

    发明人： ZNAMENSKIY, Dmitry, Nikolayevich ,  VLUTTERS, Ruud

    IPC分类号： G06T7/00 ,  G06T7/60 ,  G06T7/50

    摘要： The present invention relates to a method for estimating absolute size dimensions of a test object (32) based on image data of the test object (32), the test object (32) being a face or part of a face of a test person, the method comprising the steps of: —receiving (S101) image data of the test object (32); —determining (S102) a first model (30) of the test object (32) based on the received image data, wherein the first model (30) has an unknown scale; —aligning and scaling the first model (30) of the test object (32) to a first average model, wherein the first average model includes an average of a plurality of first models of reference objects being faces or parts of faces of reference persons, wherein said first models of the reference objects are of a same type as the first model (30) of the test object (32) and have an unknown scale; —determining a shape difference between the test object (32) and an average of the reference objects by determining a difference between the aligned and scaled first model of the test object (32) and the first average model; —determining a second model (34) of the test object (32) with an estimated scale based on (i) the determined shape difference, (ii) a statistical operator that is indicative of a statistical correlation between shape and size dimensions of the reference objects, and (iii) a second average model, wherein the second average model includes an average of a plurality of second models of the reference objects, wherein said second models of the reference objects are of a same type as the second model of the test object and have a known scale; and —determining the size dimensions of the test object (32) based on the second model (34) of the test object (32).

    LIGHT DETECTION SYSTEM
    7.
    发明公开
    LIGHT DETECTION SYSTEM 有权
    LICHTDETEKTIONSSYSTEM

    公开(公告)号：EP3107356A1

    公开(公告)日：2016-12-21

    申请号：EP16174686.2

    申请日：2012-03-22

    申请人： Koninklijke Philips N.V.

    发明人： DE BRUIJN, Frederik Jan ,  VLUTTERS, Ruud ,  FERI, Lorenzo ,  SCHENK, Tim Corneel Wilhelmus ,  RIETMAN, Ronal

    IPC分类号： H05B37/02

    CPC分类号： H04B10/116 ,  H04B10/54 ,  H04B10/548 ,  H04B10/69 ,  H04N5/225 ,  H04N5/2256 ,  H04N5/235 ,  H04N5/3532 ,  H05B37/02 ,  H05B37/0272 ,  H05B37/029

    摘要： There is provided a light detection system which is capable of determining in light embedded codes by detecting light in a scene which is illuminated by an illumination system (110) comprising one or more light sources (111,112,113) each providing a light contribution (I 111 , I 112 , I 113 ) comprising an embedded code (ID#1, ID#2, ID#3) emitted as a temporal sequence of modulations in a characteristics of the light emitted and wherein the embedded code is repeated periodically. The light detection system comprises light detection means (220), which are arranged for acquiring a plurality of images of the scene, where the images are acquired at a plurality of temporal shifted line instances. Each line of the acquired images comprise an instance of the temporal sequence of modulations of the first embedded code where the light footprint is imaged. The light detection system further comprises means (230) for determining embedded codes from the spatial pattern of modulations from the plurality of images, by determining bits of the first embedded code from the respective ones of the plurality of images until each bit of the first embedded code has been determined.

    摘要翻译： 提供了一种光检测系统，其能够通过检测由包括一个或多个光源（111,112,113）的照明系统（110）照明的场景中的光来确定光嵌入代码，每个光源（111,112,113）提供光贡献（I 111， I 112，I 113）包括作为发射的光的特性的调制的时间序列发射的嵌入码（ID＃1，ID＃2，ID＃3），并且其中嵌入码被周期性地重复。 光检测系统包括光检测装置（220），其被设置用于获取场景的多个图像，其中在多个时间偏移线实例处获取图像。 所获取的图像的每一行包括第一嵌入代码的调制的时间序列的实例，其中对光足迹进行成像。 光检测系统还包括用于通过从多个图像中的相应图像确定第一嵌入代码的位来确定来自多个图像的调制的空间模式的嵌入代码的装置（230），直到第一嵌入的每个位 代码已经确定。