Method and system for improving pattern recognition system performance
    11.
    发明授权
    Method and system for improving pattern recognition system performance 失效
    改进模式识别系统性能的方法和系统

    公开(公告)号:US06847731B1

    公开(公告)日:2005-01-25

    申请号:US09633330

    申请日:2000-08-07

    申请人: H. John Caulfield

    发明人: H. John Caulfield

    IPC分类号: G06K9/62 G06K9/74

    CPC分类号: G06K9/741 G06K9/6256

    摘要: Stand-alone or assistive pattern recognition system and process enabling error free classification of all objects in a training set and application to unclassified objects. Parameters and/or features of the data objects in a training set are selected and measured, from which discriminants are computed. The measured data is plotted in discriminant space and decision boundaries or thresholds determined, preferably such that at least one object from one class is isolated from the remaining objects, removed from the training set, and the process repeated until an acceptable number of unclassified objects remain. The system can be applied sequentially to classify all the members of the training set belonging to one class and then applied to objects in other classes. Fuzzy quantifiable determinations of an object's likelihood of class membership can be made. Objects' positions and classifications are obtainable in an optical system using Fourier techniques without limitation to linearly discriminable problems.

    摘要翻译: 独立或辅助模式识别系统和过程使训练集中的所有对象和未分类对象的应用程序无误差分类。 选择和测量训练集中的数据对象的参数和/或特征,从中计算歧视。 将测量数据绘制在判别空间和确定的判定边界或阈值中,优选地使得来自一个类的至少一个对象与剩余对象隔离,从训练集中移除,并且重复该过程直到可接受数量的未分类对象保持 。 该系统可以顺序应用,对属于一个类的训练集的所有成员进行分类,然后应用于其他类中的对象。 可以对对象的类成员可能性进行模糊量化确定。 对象的位置和分类可以在使用傅立叶技术的光学系统中获得,而不限于线性可区分的问题。

    Real-time three dimensional acoustoelectronic imaging and characterization of objects
    12.
    发明授权
    Real-time three dimensional acoustoelectronic imaging and characterization of objects 有权
    实时三维声光电子成像和物体表征

    公开(公告)号:US06672165B2

    公开(公告)日:2004-01-06

    申请号:US10082656

    申请日:2002-02-25

    IPC分类号: G01N2906

    摘要: An acoustoelectronic method and apparatus for generating real-time three-dimensional images of an object and characterizing such object are provided. The object is insonified with an incident acoustic signal derived from an electrical signal. Acoustic signals scattered from the object are collected by an acoustic receiver, which generates analog electrical signals that are subsequently converted to digital electronic signals. The digital electronic signals are used in both direct-imaging and holographic methods to produce a three-dimensional representation of the object from which images and characterizations can be generated.

    摘要翻译: 提供了一种用于产生对象的实时三维图像并表征该对象的声电子方法和装置。 该物体用来自电信号的入射声信号进行声化。 从物体散射的声学信号由声学接收器收集,声学接收器产生随后转换成数字电子信号的模拟电信号。 数字电子信号用于直接成像和全息方法中以产生可以从其生成图像和表征的对象的三维表示。

    Hologram writer and method
    14.
    发明授权
    Hologram writer and method 失效
    全息作家和方法

    公开(公告)号:US4498740A

    公开(公告)日:1985-02-12

    申请号:US485828

    申请日:1983-04-18

    申请人: H. John Caulfield

    发明人: H. John Caulfield

    IPC分类号: G03H1/08 G03H1/26 G03H1/30

    摘要: A hologram is written from x, y, z data by presenting an information beam at a holographic medium with x and y coordinates represented by x and y position on the medium and z coordinates represented by distance between the holographic medium and a point position of the beam close to the medium, while simultaneously presenting a reference beam in interference with the information beam and of a size comparable with the size of the information beam at the holographic medium. The area of the information beam and the reference beam at any position on the holographic medium is a small fraction of the total area of the hologram.

    摘要翻译: 通过在全息介质上呈现信息光,通过在介质上由x和y位置表示的x和y坐标以及由全息介质和点状态之间的距离表示的z坐标,从x,y,z数据写入全息图 光束靠近介质,同时呈现与信息光束干涉的参考光束以及与全息介质上的信息光束尺寸相当的尺寸。 信息光束和参考光束在全息介质上的任何位置的面积是全息图总面积的一小部分。

    Side illuminated multimode waveguide
    17.
    发明授权
    Side illuminated multimode waveguide 失效
    侧面照明多模波导

    公开(公告)号:US5465311A

    公开(公告)日:1995-11-07

    申请号:US179209

    申请日:1994-01-10

    IPC分类号: G02B6/34 G02B6/43

    CPC分类号: G02B6/43 G02B6/34 G03H1/0408

    摘要: A multimode waveguide having a small thickness has light coupled to the side of the waveguide in order to provide a multimode operation of the waveguide for providing a continuous pattern of totally internally reflected light which is utilized to reconstruct holographic images from a holographic emulsion placed on a surface of the waveguide. This waveguide structure for reconstructuring a hologram has the capability of providing highly efficient hologram reconstruction while using ordinary light sources and is able to use beam diameters greater than the thickness of the waveguide.

    摘要翻译: 具有小厚度的多模波导具有耦合到波导侧的光,以便提供波导的多模操作,以提供全内反射光的连续图案,其被用于从放置在所述波导上的全息乳状液重建全息图像 波导表面。 用于重建全息图的波导结构具有在使用普通光源时提供高效全息图重建的能力,并且能够使用大于波导厚度的光束直径。

    Neural processor with holographic optical paths and nonlinear operating
means
    18.
    发明授权
    Neural processor with holographic optical paths and nonlinear operating means 失效
    具有全息光路和非线性运算装置的神经处理器

    公开(公告)号:US5132813A

    公开(公告)日:1992-07-21

    申请号:US631104

    申请日:1990-12-19

    IPC分类号: G06N3/067

    CPC分类号: G06N3/067 G06N3/0675

    摘要: An optical apparatus for simulating a highly interconnected neural network is disclosed as including a spatial light modulator (SLM), an inputting device, a laser, a detecting device, and a page-oriented holographic component. The inputting device applies input signals to the SLM. The holographic component optically interconnects N.sup.2 pixels defined on the spatial light modulator to N.sup.2 pixels defined on a detecting surface of the detecting device. The interconnections are made by N.sup.2 patterns of up to N.sup.2 interconnection weight encoded beams projected by N.sup.2 planar, or essentially two-dimensional, holograms arranged in a spatially localized array within the holographic component. The SLM modulates the encoded beams and directs them onto the detecting surface wherein a parameter of the beams is evaluated at each pixel thereof. The evaluated parameter is transformed according to a nonlinear threshold function to provide transformed signals which can be fed back to the SLM for further iterations.

    摘要翻译: 公开了一种用于模拟高度互连的神经网络的光学装置,包括空间光调制器(SLM),输入装置,激光,检测装置和面向页的全息成分。 输入设备将输入信号应用于SLM。 全息成分将定义在空间光调制器上的N2个像素光学地互连到在检测装置的检测表面上限定的N2个像素。 互连通过由N 2平面或基本上二维的全息图投影的多达N2个互连重量编码光束的N 2图案来制成,该全息图排列在全息组件内的空间定位阵列中。 SLM调制编码的光束并将其引导到检测表面上,其中在其每个像素处评估光束的参数。 评估参数根据非线性阈值函数进行变换,以提供可以反馈到SLM进行进一步迭代的变换信号。

    Hologram writing apparatus and method
    19.
    发明授权
    Hologram writing apparatus and method 失效
    全息书写设备及方法

    公开(公告)号:US4655539A

    公开(公告)日:1987-04-07

    申请号:US664392

    申请日:1984-10-23

    IPC分类号: G03H1/08 G03H1/10

    CPC分类号: G03H1/08 G03H2210/46

    摘要: An improved hologram writer writes a halogram from a three dimensional data stream or signal such as a signal corresponding to a scene, a picture, drawing or the like. A reference beam and an object or information beam are directed to a holographic recording member, and the information beam is focused through a point near the holographic recording member. A diverger means such as a diffuser, a lens array, a holographic element or the like adapted to form an expanding beam from a point image or spot receives a focused modulated information beam and directs it to the holographic recording member as a divergent beam. The beam may be sent directly to the recording member or it may be optically or otherwise relayed to the member. The point source may be in front of, behind or within the holographic recording member.

    摘要翻译: 改进的全息图写入器从三维数据流或诸如对应于场景,图片,绘图等的信号的信号写入晕圈。 参考光束和物体或信息光束被引导到全息记录部件,信息光束通过全息记录部件附近的点聚焦。 适于从点图像或点形成扩展光束的扩散器,透镜阵列,全息元件等分散器装置接收聚焦的调制信息光束,并将其引导到全息记录部件作为发散光束。 光束可以被直接发送到记录部件,或者可以光学地或以其他方式中继到该部件。 点源可以在全息记录元件的前方,后面或内部。

    Image enhancement
    20.
    发明授权
    Image enhancement 失效
    图像增强

    公开(公告)号:US4416538A

    公开(公告)日:1983-11-22

    申请号:US328021

    申请日:1981-12-07

    IPC分类号: G03B27/54

    CPC分类号: G03B27/542

    摘要: Image enhancement is achieved to increase the ability to distinguish details otherwise difficult to discern in bright and dark areas of a photorecord by reflecting light off surface perturbations on the record and displaying the reflected light by means of schlieren optics.

    摘要翻译: 实现图像增强以增加区分细节的能力,否则在光记录的明暗区域难以辨别,通过反射光在记录上的表面扰动并通过色彩光学显示反射光。