专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

US20060088194A1 Apparatus for online signature verification using pattern transform technique and method therefor 失效
标题翻译：使用模式变换技术进行在线签名验证的装置及其方法
公开(公告)号：US20060088194A1
公开(公告)日：2006-04-27
申请号：US10532301
申请日：2003-03-18
申请人： Jae Lee , Yun Chung , Jung Soh , Byung Chun , Ho Yoon , Kyu Han , Do-Hyung Kim , Yongwha Chung
发明人： Jae Lee , Yun Chung , Jung Soh , Byung Chun , Ho Yoon , Kyu Han , Do-Hyung Kim , Yongwha Chung
IPC分类号： G06K9/00
CPC分类号： G06K9/00154
摘要： In an apparatus for online signature verification, a signature data input unit digitalizes a locus of a user signature and reads the locus as a sequence of points. A first and a second pattern transform unit performs a speed equalization and a velocity transform on the signature sequence and generates a first and a second transformed pattern sequence, respectively. A characteristics extraction unit extracts three characteristics vectors from the signature sequence, the first and the second transformed pattern sequence, respectively, to thereby generate the three characteristics vectors. A difference vector estimation unit generates a difference vector. A determination unit determines whether an input signature and the reference signature are signed by a single person.
摘要翻译：在用于在线签名验证的装置中，签名数据输入单元将用户签名的轨迹数字化，并将该轨迹读取为点序列。第一和第二图案变换单元对签名序列执行速度均衡和速度变换，并分别产生第一和第二变换图案序列。特征提取单元从签名序列，第一和第二变换图案序列分别提取三个特征向量，从而生成三个特征向量。差矢量估计单元产生差矢量。确定单元确定输入签名和参考签名是否由单个人签名。

2. 发明申请

US20060104358A1 Method and apparatus for motion estimation using adaptive search pattern for video sequence compression 有权
标题翻译：用于视频序列压缩的自适应搜索模式的运动估计方法和装置
公开(公告)号：US20060104358A1
公开(公告)日：2006-05-18
申请号：US10532219
申请日：2003-10-13
申请人： Hyu Han , Byung Chun , Jae Lee , Yun Chung , Chieleuk Ahn
发明人： Hyu Han , Byung Chun , Jae Lee , Yun Chung , Chieleuk Ahn
IPC分类号： H04N11/02 , H04N7/12 , H04N11/04 , H04B1/66
CPC分类号： H04N5/145 , H04N19/533 , H04N19/57
摘要： In a method for motion estimation using adaptive patterns in a video sequence compression system, an initial search pattern located at a center of a search window in a block of a video frame is determined. A location of a minimum block distortion measure (BDM) is searched in the initial search pattern. A horizontal search pattern for functioning on the search window is determined in the horizontal direction to search a location of a minimum BDM in the horizontal search pattern. A vertical search pattern for operating on the search window is determined in the vertical direction to search a location of a minimum BDM in the vertical search pattern. The location of the minimum BDM in each pattern is designated to be a motion vector. A search pattern to be used in a subsequent searching stage is determined based on the location of the minimum BDM in each pattern.
摘要翻译：在使用视频序列压缩系统中的自适应模式的运动估计方法中，确定位于视频帧块中搜索窗口中心的初始搜索模式。在初始搜索模式中搜索最小块失真度量（BDM）的位置。在水平方向上确定在搜索窗口上起作用的水平搜索模式，以搜索水平搜索模式中最小BDM的位置。在垂直方向上确定用于在搜索窗口上操作的垂直搜索模式，以搜索垂直搜索模式中最小BDM的位置。每个图案中最小BDM的位置被指定为运动矢量。基于每个图案中最小BDM的位置来确定在随后的搜索阶段中使用的搜索模式。

3. 发明申请

US20070174280A1 Texture-based image database browsing and sorting method 审中-公开
标题翻译：基于纹理的图像数据库浏览和排序方法
公开(公告)号：US20070174280A1
公开(公告)日：2007-07-26
申请号：US11710395
申请日：2007-02-26
申请人： Kyu Kim , Se Jeong , Jae Lee , Young Bae , Byung Chun
发明人： Kyu Kim , Se Jeong , Jae Lee , Young Bae , Byung Chun
IPC分类号： G06F7/00
CPC分类号： G06F16/5862 , Y10S707/915 , Y10S707/99933 , Y10S707/99937 , Y10S707/99942 , Y10S707/99943
摘要： A texture-based image database browsing and sorting method computes the number of edge pixels of objects in static images, measures textures of the static images by numerating the number of edge pixels thereof and measures a texture of a query image by numerating the number of edge pixels of an object in the query image. Then, the method sorts the measured textures according to a sorting order and searches a texture close to the texture of the query image among the sorted textures.
摘要翻译：基于纹理的图像数据库浏览和排序方法计算静态图像中对象的边缘像素数，通过计算其边缘像素的数量来测量静态图像的纹理，并通过计算边缘数量来测量查询图像的纹理查询图像中的对象的像素。然后，该方法根据排序顺序对测量的纹理进行排序，并在排序纹理中搜索靠近查询图像的纹理的纹理。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式