知搜-全球专利检索

  1. 登录
  2. 注册

搜索结果

400 条记录 (耗时 0.024 秒)

    System for identifying materials by NIR spectrometry
    71.
    发明授权
    System for identifying materials by NIR spectrometry 失效
    通过NIR光谱法识别材料的系统

    公开(公告)号：US5822219A

    公开(公告)日：1998-10-13

    申请号：US645104

    申请日：1996-05-13

    申请人： Xiaolin Chen ,  Stephen L Monfre

    发明人： Xiaolin Chen ,  Stephen L Monfre

    IPC分类号： G01N21/35 ,  G06K9/62 ,  G06F19/00

    CPC分类号： G06K9/6247 ,  G01N21/359 ,  G06K9/6219

    摘要： In a method for identifying an unknown product a library of absorbance spectra of known products is measured and stored in a library. A quick search using clustering techniques is conducted to narrow the search to a few products, followed by an exhaustive search of the spectra of the few products. More specifically, principal component analysis is applied to the absorbance spectra to generate product score vectors extending into principal component inside model space which are divided into clusters and subclusters in accordance with their relative proximity. Hyperspheres are constructed around each vector and an envelope is constructed to enclose each cluster surrounding the hyperspheres within the cluster. The absorbance spectrum of the unknown product to be identified is measured and an unknown product score vector is determined from the unknown product spectrum projecting in principal component inside model space of the clusters. It is determined whether or not the unknown product score vector falls within one of the envelopes and if so the product score vector is projected into the principal component inside model space of that cluster and it is determined whether or not the unknown product score vector falls within any of the subclusters divided from the cluster. This process is repeated until the unknown product score vector is found to lie in a cluster which is not further subdivided. In this manner, the search is narrowed to a few products. An exhaustive search is then carried out to match the spectrum of the unknown product with the spectra of the known products corresponding to the undivided subcluster.

    摘要翻译： 在识别未知产物的方法中，测量已知产品的吸收光谱图并将其存储在文库中。 进行使用聚类技术的快速搜索，将搜索缩小到几个产品，然后详细搜索少数产品的光谱。 更具体地，将主成分分析应用于吸收光谱，以生成延伸到模型空间内的主成分的产物分数向量，其根据它们的相对接近度被分成簇和子簇。 围绕每个向量构建超球体，并且构造包围以围绕簇内的超球体周围的每个簇。 测量待鉴定的未知产物的吸收光谱，并从在簇的模型空间内的主成分中突出的未知产物光谱确定未知产物得分矢量。 确定未知产品评分向量是否落入一个包络内，如果是，则将该产品分数向量投影到该群集的模型空间内的主成分中，并且确定未知商品分数向量是否落入 任何子集群从集群中分离出来。 重复该过程，直到发现未知产品分数向量位于不进一步细分的簇中。 以这种方式，搜索被缩小到几个产品。 然后进行详尽的搜索以将未知产物的光谱与对应于未分解的亚簇的已知产物的光谱相匹配。

    Unsupervised speaker clustering for automatic speaker indexing of recorded audio data
    72.
    发明授权
    Unsupervised speaker clustering for automatic speaker indexing of recorded audio data 失效
    无监督扬声器群集，用于录制音频数据的自动扬声器索引

    公开(公告)号：US5659662A

    公开(公告)日：1997-08-19

    申请号：US710013

    申请日：1996-09-09

    申请人： Lynn D. Wilcox ,  Donald G. Kimber

    发明人： Lynn D. Wilcox ,  Donald G. Kimber

    IPC分类号： G10L15/06 ,  G10L15/10 ,  G10L15/14 ,  G10L17/00 ,  H04R3/00 ,  G10L9/00

    CPC分类号： G06K9/6219 ,  G10L17/00 ,  G10L17/04 ,  G11B27/28 ,  G10L15/142

    摘要： A system and method for unsupervised clustering of audio data segments in an audio data recording containing speech from multiple speakers including the steps of: 1) providing a portion of the audio data containing speech from all of the speakers; 2) forming initial clusters by dividing the portion of the audio data into segments, each of which includes an ordered data set; 3) computing the pairwise distance between each pair of clusters using a likelihood ration independent of the order of data within the segments; and 4) combining into a new cluster the two clusters with a minimum pairwise distance. These steps are repeated until a number of clusters equal to the number of speakers is obtained.

    摘要翻译： 一种用于在包含来自多个扬声器的语音的音频数据记录中的音频数据段的无监督聚类的系统和方法，包括以下步骤：1）从所有扬声器提供包含语音的音频数据的一部分; 2）通过将音频数据的部分划分成段，形成初始簇，每个段包括有序数据集; 3）使用独立于段内的数据顺序的似然比计算每对群集之间的成对距离; 并且4）将具有最小成对距离的两个群集合成新群集。 重复这些步骤，直到获得等于扬声器数量的多个簇。

    DATA MANAGEMENT SYSTEM AND STORAGE MEDIUM
    73.
    发明申请
    DATA MANAGEMENT SYSTEM AND STORAGE MEDIUM 审中-公开

    公开(公告)号：US20190205316A1

    公开(公告)日：2019-07-04

    申请号：US16232017

    申请日：2018-12-25

    申请人： KYOCERA Document Solutions Inc.

    发明人： Rie KASAI

    IPC分类号： G06F16/28 ,  G06K9/62 ,  G06F9/54

    CPC分类号： G06F16/282 ,  G06F9/542 ,  G06K9/6219

    摘要： To provide a data management system and a data management program enabling a person not having reference authority of a display name of a node of an ordinary hierarchical structure to refer to data associated with a node in an ordinary hierarchical structure, a data management system which, when one of the nodes of a hierarchical structure constituted by a plurality of nodes is specified, notifies at least some values of purchased product data associated with the specified node notifies the ordinary hierarchical structure to a person having reference authority of a display name of a node of the ordinary hierarchical structure, and notifies, to a person not having reference authority of the display name of the node of the ordinary hierarchical structure, a substitute hierarchical structure constituted by nodes of which value of at least one item of the purchased product data is the display name and with which purchased product data including this value is associated.

    Learning device and learning method for object detection
    80.
    发明授权
    Learning device and learning method for object detection 有权

    公开(公告)号：US10002290B2

    公开(公告)日：2018-06-19

    申请号：US14704696

    申请日：2015-05-05

    申请人： SONY CORPORATION

    发明人： Jun Yokono

    IPC分类号： G06K9/00 ,  G06K9/62 ,  G06K9/46

    CPC分类号： G06K9/00389 ,  G06K9/4604 ,  G06K9/6219 ,  G06K9/6257 ,  G06K9/627

    摘要： Disclosed is a learning device. A feature-quantity calculation unit extracts a feature quantity from each feature point of a learning image. An acquisition unit acquires a classifier already obtained by learning as a transfer classifier. A classifier generation unit substitutes feature quantities into weak classifiers constituting the transfer classifier, calculates error rates of the weak classifiers on the basis of classification results of the weak classifiers and a weight of the learning image, and iterates a process of selecting a weak classifier of which the error rate is minimized a plurality of times. In addition, the classifier generation unit generates a classifier for detecting a detection target by linearly coupling a plurality of selected weak classifiers.