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
    • 1. 发明申请
    • Asymmetric subspace watermarking
    • 不对称子空间水印
    • US20070025590A1
    • 2007-02-01
    • US11355013
    • 2006-02-16
    • Wen-Liang HwangJeng-Nan TzengI-Liang Chern
    • Wen-Liang HwangJeng-Nan TzengI-Liang Chern
    • G06K9/00
    • G06T1/005G06T2201/0052H04K1/00
    • The present invention discloses an asymmetric watermarking technology, which is particularly resistant to projection attack. The asymmetric watermark embedding technology of this invention comprises the following steps: Analyze an original image φo to obtain its watermarking space W. Divide said watermarking space W to obtain two orthogonal subspaces g and h. Select an embedding key G, which is a matrix and which columns form bases of subspace g. Calculate a matrix H, HTG=0. Columns of matrix H form bases of subspace h. Calculate detecting key D: D=GT+BHT; wherein B is a matrix. Obtain a watermark w and embed said watermark w into said original image φo to obtain a watermarked image φw, as follows: φw=φo+Gw wherein D φo=mo is not a 0 vector.
    • 本发明公开了一种非对称水印技术,特别适用于投射攻击。 本发明的非对称水印嵌入技术包括以下步骤:分析原始图像文件以获得其水印空间W.将所述水印空间W除以获得两个正交子空间g和h。 选择一个嵌入密钥G,它是一个矩阵,哪个列以子空间g为基础。 计算矩阵H,H T G = 0。 矩阵H的列形成子空间h的基础。 计算检测键D:<?in-line-formula description =“In-line Formulas”end =“lead”?> D = G + BH <?in-line-formula description =“In-line Formulas”end =“tail”?>其中B是一个矩阵。 获取水印w并将所述水印w嵌入到所述原始图像文件中以获得水印图像文件,如下所示:<?in-line-formula description =“ 在线公式“end =”lead“?> phi > Gw <?in-line-formula description =”In-line Formulas“end = “尾”?>其中D phi不是0矢量。
    • 7. 发明授权
    • Iris recognition method utilizing matching pursuit algorithm
    • 虹膜识别方法利用匹配追踪算法
    • US07920724B2
    • 2011-04-05
    • US11603031
    • 2006-11-22
    • Wen-Gang CheJian-Liang LinWen-Liang HwangChung-Ling Huang
    • Wen-Gang CheJian-Liang LinWen-Liang HwangChung-Ling Huang
    • G06K9/00
    • G06K9/0061
    • The present invention disclose an iris recognition method, which utilizes a matching pursuit algorithm to simplify the extraction and reconstruction of iris features and reduce the memory space required by each iris feature vector without the penalty of recognition accuracy. The iris recognition method of the present invention comprises an iris-localization component and a pattern matching component. The iris-localization component locates the iris region via the color difference between different portions of the eyeball. The primary iris features are extracted from iris information and transformed into a sequence of iris feature vectors by a matching pursuit algorithm. Thus, the iris image can be represented by a sequence of atoms, and each atom contains base, amplitude and location. Then, the comparison between the feature vectors of two irises is performed to determine whether the two irises match.
    • 本发明公开了一种虹膜识别方法,其利用匹配追踪算法来简化虹膜特征的提取和重建,并减少每个虹膜特征向量所需的存储空间,而不会损失识别精度。 本发明的虹膜识别方法包括虹膜定位部件和图案匹配部件。 虹膜定位组件经由眼球的不同部分之间的色差定位虹膜区域。 主要虹膜特征从虹膜信息中提取,并通过匹配追踪算法转换成虹膜特征向量序列。 因此,虹膜图像可以由原子序列表示,并且每个原子包含碱基,幅度和位置。 然后,执行两个虹膜的特征向量之间的比较,以确定两个虹膜是否匹配。
    • 8. 发明申请
    • Iris recognition method
    • 虹膜识别方法
    • US20080095411A1
    • 2008-04-24
    • US11603031
    • 2006-11-22
    • Wen-Liang HwangJian-Liang LinChung-Lin HuangWei-Gang Che
    • Wen-Liang HwangJian-Liang LinChung-Lin HuangWei-Gang Che
    • G06K9/00
    • G06K9/0061
    • The present invention disclose an iris recognition method, which utilizes a matching pursuit algorithm to simplify the extraction and reconstruction of iris features and reduce the memory space required by each iris feature vector without the penalty of recognition accuracy. The iris recognition method of the present invention comprises an iris-localization component and a pattern matching component. The iris-localization component locates the iris region via the color difference between different portions of the eyeball. The primary iris features are extracted from iris information and transformed into a sequence of iris feature vectors by a matching pursuit algorithm. Thus, the iris image can be represented by a sequence of atoms, and each atom contains base, amplitude and location. Then, the comparison between the feature vectors of two irises is performed to determine whether the two irises match.
    • 本发明公开了一种虹膜识别方法,其利用匹配追踪算法来简化虹膜特征的提取和重建,并减少每个虹膜特征向量所需的存储空间,而不会损失识别精度。 本发明的虹膜识别方法包括虹膜定位部件和图案匹配部件。 虹膜定位组件经由眼球的不同部分之间的色差定位虹膜区域。 主要虹膜特征从虹膜信息中提取,并通过匹配追踪算法转换成虹膜特征向量序列。 因此,虹膜图像可以由原子序列表示,并且每个原子包含基底,幅度和位置。 然后,执行两个虹膜的特征向量之间的比较,以确定两个虹膜是否匹配。