会员体验
专利管家(专利管理)
工作空间(专利管理)
风险监控(情报监控)
数据分析(专利分析)
侵权分析(诉讼无效)
联系我们
交流群
官方交流:
QQ群: 891211   
微信请扫码    >>>
现在联系顾问~
热词
    • 7. 发明专利
    • Information processor, information processing method, program and recording medium
    • 信息处理器,信息处理方法,程序和记录介质
    • JP2014123341A
    • 2014-07-03
    • JP2013120922
    • 2013-06-07
    • Ricoh Co Ltd株式会社リコー
    • NAKAMURA SATOSHI
    • G06F17/30G06T7/00
    • G06F17/30247G06F17/3071G06K9/00684G06K9/6223G06K9/6272
    • PROBLEM TO BE SOLVED: To obtain the optimal clustering result by determining an initial value on the basis of the model parameter of an already clustered similar data group, and updating the initial value in accordance with an actual data group.SOLUTION: A similar image search part 106 searches a reference image which is similar to an input image from a recording part 109, and obtains a reference parameter recorded in association with the similar reference image. An initial parameter determination part 107 determines the initial value of a model parameter by synthesizing the reference parameters. A parameter updating part 108 updates the initial value of the model parameter in accordance with probability density distribution in the feature space of the input image, and a clustering part 104 clusters the probability density distribution in the feature space of the input image on the basis of the obtained model parameter, and a result output part 105 outputs the result.
    • 要解决的问题:通过基于已经聚类的相似数据组的模型参数确定初始值并根据实际数据组更新初始值来获得最佳聚类结果。解决方案:类似的图像搜索 部分106搜索与来自记录部分109的输入图像相似的参考图像,并且获得与相似参考图像相关联地记录的参考参数。 初始参数确定部件107通过合成参考参数来确定模型参数的初始值。 参数更新部108根据输入图像的特征空间中的概率密度分布来更新模型参数的初始值,聚类部104基于输入图像的特征空间聚类概率密度分布 所获得的模型参数和结果输出部105输出结果。
    • 10. 发明专利
    • Apparatus and method for processing image, and program
    • 用于处理图像和程序的装置和方法
    • JP2010250556A
    • 2010-11-04
    • JP2009099226
    • 2009-04-15
    • Toshiba Corp株式会社東芝
    • KAWAHARA TOMOKAZUSHIBATA SATOYUKIWAKASUGI TOMOKAZU
    • G06T7/00G06F17/30G06T1/00H04N5/76
    • G06K9/6807G06K9/00295G06K9/622G06K9/6272
    • PROBLEM TO BE SOLVED: To provide an image processing apparatus for easing the non-facilitation of threshold setting in face image clustering, and for improving face image clustering performance.
      SOLUTION: The image processing apparatus 1 includes: a sequence creating section configured to create a plurality of sequences in such a manner that one sequence includes consecutive face images of a same person in video image data; a similarity calculating section configured to calculate a first similarity of each pair in a plurality of face image dictionaries created for each sequence and a second similarity of each pair of each face image dictionary and a predetermined plurality of dictionaries; a similarity correcting section configured to correct the calculated and obtained plurality of first similarities by the second similarities; and a face clustering section configured to compare the plurality of first similarities corrected by the similarity correcting section with a predetermined threshold to cluster the plurality of face image dictionaries.
      COPYRIGHT: (C)2011,JPO&INPIT
    • 要解决的问题:提供一种图像处理装置,用于减轻面部图像聚类中的阈值设置的不便,并且用于改善面部图像聚类性能。 解决方案:图像处理装置1包括:序列创建部分,被配置为以使得一个序列包括视频图像数据中的相同人物的连续脸部图像的方式创建多个序列; 相似度计算部,被配置为计算针对每个序列创建的多个面部图像词典中的每一对的第一相似度和每对面部图像词典和预定的多个词典的第二相似度; 相似度校正部,被配置为通过第二相似度校正所计算和获得的多个第一相似度; 以及面部聚类部,被配置为将由所述相似性校正部校正的所述多个第一相似度与预定阈值进行比较,以聚集所述多个面部图像字典。 版权所有(C)2011,JPO&INPIT