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
    • 2. 发明申请
    • Image, Video or Audio Filtering Before Biometric Recognition
    • 生物识别之前的图像,视频或音频滤波
    • US20080013801A1
    • 2008-01-17
    • US11765987
    • 2007-06-20
    • Alastair ReedBrett Bradley
    • Alastair ReedBrett Bradley
    • G06K9/00
    • G06K9/40G06K9/00885
    • The present invention relates generally to pre-processing images, audio and/or video to improve biometric analysis from such. In one implementation, a method is provided including: receiving a color digital image including a representation of a human subject; converting the color digital image into grayscale values; transforming at least one representation of the converted color image; analyzing the transformed, converted color image to identify artifacts; if artifacts are found, processing the color digital image to reduce the artifacts; and providing the processed digital image to a biometric system. Other implementations are provided as well.
    • 本发明一般涉及预处理图像,音频和/或视频以改善生物特征分析。 在一个实现中,提供了一种方法,包括:接收包括人类对象的表示的彩色数字图像; 将彩色数字图像转换为灰度值; 转换所转换的彩色图像的至少一个表示; 分析转换后的彩色图像,以识别人为因素; 如果发现伪像,则处理彩色数字图像以减少伪影; 并将经处理的数字图像提供给生物测定系统。 还提供其他实现。
    • 4. 发明申请
    • Methods For Generating Enhanced Digital Images
    • 生成增强型数字图像的方法
    • US20080036886A1
    • 2008-02-14
    • US11748851
    • 2007-05-15
    • Brett HanniganAlastair Reed
    • Brett HanniganAlastair Reed
    • H04N9/083
    • G06K9/00G06T3/4007G06T3/4015
    • Slight camera movement between capture of successive images is advantageously utilized to minimize or eliminate the need to interpolate in order to fill in the “holes” in a Bayer pattern. The captured color values from multiple appropriately positioned images are used to fill these holes. For example, instead of interpolating the value of red for the second pixel position on the first row of a Bayer pattern, an image is selected which is positioned one pixel to the right of the first image, and the red vales from this image are used for the red values of the second pixel on the first line. Values of the pixels in multiple images which are appropriately aligned to each pixel position are averaged to generate a better value for each pixel position. Information carried by a digital watermark (either alone or together with other techniques) is used to determine the alignment of the images. Images are selected which are positioned so that corresponding pixels fall within a specified tolerance from a location in a Bayer pattern. The pixel values of the images which fall within the specified tolerance of each pixel position in a Bayer pattern are selected and used for the alignment.
    • 有利地利用连续图像的拍摄之间的轻微的相机移动来最小化或消除内插的需要,以填充拜耳图案中的“孔”。 来自多个适当定位的图像的捕获的颜色值用于填充这些孔。 例如,代替内插Bayer图案的第一行上的第二像素位置的红色值,选择位于第一图像右侧一个像素的图像,并且使用来自该图像的红色值 对于第一行上第二个像素的红色值。 对与每个像素位置适当对齐的多个图像中的像素的值进行平均以为每个像素位置产生更好的值。 使用数字水印(单独或与其他技术一起)携带的信息来确定图像的对准。 被选择的图像被定位成使得相应的像素落在从拜耳图案中的位置指定的公差范围内。 落在拜耳图案中的每个像素位置的指定公差内的图像的像素值被选择并用于对准。
    • 8. 发明申请
    • Digital Watermark Detection Using Predetermined Color Projections
    • 使用预定颜色投影的数字水印检测
    • US20070147653A1
    • 2007-06-28
    • US11427265
    • 2006-06-28
    • Alastair ReedBrett Hannigan
    • Alastair ReedBrett Hannigan
    • G06K9/00
    • G06T1/0028G06T1/0042G06T2201/0051G06T2201/0065
    • The present invention relates to digital watermarking. In one implementation, a system is provided to read a digital watermark from digital imagery which includes data representing a number of pixels. Each pixel of the number of pixels is defined by a set of values representing color components of the particular pixel. The digital watermark is embedded in the digital imagery through modifications to at least some data representing the digital imagery. The system includes a filter to calculate values of pixels along a preferred projection axis, the preferred projection axis corresponds to a direction of embedding determined based on color characteristics of at least some pixels associated with the digital imagery; and a digital watermark reader which operates on values calculated by the filter. Other implementations are provided as well.
    • 本发明涉及数字水印技术。 在一个实现中,提供了一种系统,用于从数字图像读取数字水印,数字图像包括表示多个像素的数据。 像素数的每个像素由表示特定像素的颜色分量的一组值定义。 通过对代表数字图像的至少一些数据进行修改,将数字水印嵌入到数字图像中。 该系统包括用于计算沿着优选投影轴的像素值的滤光器,优选投影轴对应于基于与数字图像相关联的至少一些像素的颜色特性确定的嵌入方向; 以及对由滤波器计算的值进行操作的数字水印读取器。 还提供其他实现。
    • 9. 发明申请
    • Metadata management and generation using digital watermarks
    • 使用数字水印的元数据管理和生成
    • US20060115108A1
    • 2006-06-01
    • US11152685
    • 2005-06-13
    • Tony RodriguezSean CalhoonAlastair Reed
    • Tony RodriguezSean CalhoonAlastair Reed
    • G06K9/00G06F17/30
    • G06F17/30265G06F17/3028G06T1/0021H04N1/32149H04N1/32352
    • The present invention provides methods and systems to improve network searching for watermarked content. In some implementations we employ keyword searching to narrow the universe of possible URL candidates. A resulting URL list is searched for digital watermarking. A system is provided to allow customer input. For example, a customer enters keywords or network locations. The keywords or network locations are provided to a watermark-enabled web browser which accesses locations associated with the keywords or network locations. Some implementations of the present invention employ a plurality of distributed watermark-enabled web browsers. Other aspects of the invention provide methods and system to facilitate desktop searching and automated metadata gathering and generating. In one implementation a digital watermark is used to determine whether metadata associated with an image or audio file is current or fresh. The metadata is updated when it is out of date. Watermarks can also be used to link to or facilitate so-called on-line “blogs” (or online conversations).
    • 本发明提供了改进水印内容的网络搜索的方法和系统。 在一些实现中,我们使用关键词搜索来缩小可能的URL候选者的范围。 搜索得到的URL列表以获得数字水印。 提供了一个允许客户输入的系统。 例如,客户输入关键字或网络位置。 关键字或网络位置被提供给访问与关键字或网络位置相关联的位置的启用水印的网络浏览器。 本发明的一些实施方案采用多个分布式水印启用的网络浏览器。 本发明的其他方面提供了方便和系统以便于桌面搜索和自动元数据收集和生成。 在一个实现中,使用数字水印来确定与图像或音频文件相关联的元数据是当前还是新鲜。 元数据在过期时更新。 水印也可用于链接或促进所谓的在线“博客”(或在线对话)。
    • 10. 发明申请
    • Fragile and emerging digital watermarks
    • 脆弱和新兴的数字水印
    • US20050041835A1
    • 2005-02-24
    • US10836094
    • 2004-04-29
    • Alastair ReedTony RodriguezRavi Sharma
    • Alastair ReedTony RodriguezRavi Sharma
    • G06T1/00H04N1/00H04N1/32G06K9/00
    • G06T1/0042H04N1/00002H04N1/00005H04N1/00037
    • This disclosure describes methods for using embedded auxiliary signals in documents for copy detection. In one implementation we embed an auxiliary signal with a first color that is out of gamut with process color inks or with a particular range of printers. A process color approximation of the first color yields a relatively different contrast when, e.g., viewed with an interference filter. A copy is determined based on the relative presence or absence of the auxiliary signal. In another implementation, we provide a first auxiliary signal with a first color and a second auxiliary signal with a second color. A filter is matched according to the spectral response of the first color. The second color preferably includes a spectral response that is inversely related to the matched filter. The first signal is then detectable in a process color copy, but less so in the original. However, the second signal is detectable in the original, but less so in the copy. In still other implementations we compare relative contrast of a signal to determine an original from a copy.
    • 本公开描述了在用于复制检测的文档中使用嵌入式辅助信号的方法。 在一个实现中,我们使用具有处理颜色墨水或特定范围的打印机的第一种颜色嵌入不同色域的辅助信号。 当例如用干涉滤光片观察时,第一种颜色的处理颜色近似产生相对不同的对比度。 基于辅助信号的相对存在或不存在来确定副本。 在另一实现中,我们提供具有第一颜色的第一辅助信号和具有第二颜色的第二辅助信号。 滤光片根据第一种颜色的光谱响应进行匹配。 第二种颜色优选地包括与匹配滤波器相反的光谱响应。 然后第一个信号可以在过程颜色拷贝中检测到,但在原始信号中不太可能。 然而,第二个信号在原件中是可检测的,但在副本中较少。 在其他实施方式中,我们比较信号的相对对比度以从副本确定原件。