METHOD FOR IMAGING AN OBJECT
    2.
    发明申请
    METHOD FOR IMAGING AN OBJECT 审中-公开
    成像对象的方法

    公开(公告)号:WO2009126033A1

    公开(公告)日:2009-10-15

    申请号:PCT/NL2009/050182

    申请日:2009-04-07

    CPC classification number: G02B21/0032

    Abstract: The invention relates to a method for imaging an object, comprising the illumination of the object, and the detection of light coming from an area where the object is located and, based on the detected light, forming the image, with the illumination of the object taking place by distinguishing image elements in an imaging plane or space, and by separately illuminating the object parts corresponding with these image elements, while simultaneously registering the applied illumination dose of these object parts, and wherein the image is subsequently constructed by assembling the image elements corresponding with the illuminated object parts, subject to the light output and illumination doses pertaining to those image elements, wherein the illumination dose of each separate object part depends at least on a light output and/or illumination dose of another object part or several other object parts.

    Abstract translation: 本发明涉及一种用于对物体进行成像的方法,包括对物体的照明,以及从物体所在区域的光的检测,并且基于检测到的光,形成图像,与物体的照明 通过在成像平面或空间中区分图像元素,并且通过分别照射与这些图像元素相对应的对象部分,同时记录这些对象部分的所施加的照射剂量,并且其中通过组合图像元素来构建图像 对应于照射对象部分,受到与这些图像元素相关的光输出和照射剂量的影响,其中每个分离的物体部分的照射剂量至少依赖于另一物体部分或其它几个物体的光输出和/或照明剂量 部分。

    OPTICAL MUSIC RECOGNITION OMR : CONVERTING SHEET MUSIC TO A DIGITAL FORMAT

    公开(公告)号:WO2018194456A1

    公开(公告)日:2018-10-25

    申请号:PCT/NL2018/050250

    申请日:2018-04-20

    Abstract: The invention provides an optical music recognition (OMR) assembly for converting sheet music, representing a music part as a first temporal representation, into a machine-processable representation of said piece of music that represents at least a pitch and duration of notes that are graphically represented in said sheet music and form said music part as a second temporal representation, said assembly comprising a data processor system and software which, when running on said data processor system: - retrieves a machine-processable representation of said sheet music; - generate a series of time slices of said sheet music, by applying a sliding window on said over said machine-processable representation of at least part of said sheet music; - defines a sequence-to-sequence system, said sequence-to-sequence system comprising: provide a convolutional neural network (CNN) for converting said time slices into a sequence of third representations of said sheet music, said CNN comprising an input layer and an output layer; provide a first, encoder recurrent neural network (RNN) as an encoder on said sequence of third representations, for providing a hidden representation of said sheet music, said first RNN having an input layer that is functionally coupled to said output layer of said CNN, and an output layer; * provide a second, decoder recurrent neural network (RNN) as a decoder to said hidden representation, for converting said hidden representation into said machine- processable representation, said second RNN having an input layer that is functionally coupled to said output layer of said first RNN, and an output for providing said machine-processable representation.

    STRUCTURED ILLUMINATION SCANNING MICROSCOPY
    9.
    发明申请

    公开(公告)号:WO2018151599A1

    公开(公告)日:2018-08-23

    申请号:PCT/NL2018/050107

    申请日:2018-02-16

    Abstract: A method of forming a high-resolution image of a sample using a scanning microscope controlled by a processor is described wherein the method comprises the steps of receiving or generating control information for controlling a scanning microscope, the control information defining a plurality of different periodic patterns on the basis of one or more pattern parameters, preferably the one or more pattern parameters, including at least one of: a spatial frequency, a periodicity direction, an initial phase; using the control information to control the scanning microscope to expose the sample to multiple illumination patterns, each exposure to an illumination pattern causing one or more optical excitations in the sample, the light originating from said optical excitations forming an emission light signal; controlling an imaging system to capture multiple images, each image being associated with an emission light signal of one of the multiple exposures, and, using a structured light reconstruction algorithm for forming a high-resolution image on the basis of the one or more pattern parameters.

Patent Agency Ranking