-
公开(公告)号：US06141431A
公开(公告)日：2000-10-31
申请号：US595224
申请日：1996-02-01
CPC分类号： G06T7/0042 , G06K9/00281 , G06T15/00 , G06T19/00 , H04N2005/2726
摘要： An image processing apparatus has a hair region selecting part 11 for selecting hair and shade of the hair in a front face image 13, as a removal region 15, on the basis of each pixel value of the front face image 13 which is a front image of a face, and a face surface model 14 showing structural information relative to a surface of the face in the front face image 13, and a removal region changing part 12 for changing each pixel value in whole or part of the removal region 15, on the basis of the structural information in the face surface model 14, and at least one pixel value in the front image.
摘要翻译： 图像处理装置具有：基于作为前方图像的正面图像13的每个像素值，具有用于选择前脸图像13中的头发和阴影作为移除区域15的头发区域选择部分11 面部表面模型14和显示相对于正面图像13中的脸部的表面的结构信息的面部表面模型14以及用于改变去除区域15的全部或一部分中的每个像素值的去除区域改变部分12， 面部表面模型14中的结构信息的基础，以及前方图像中的至少一个像素值。
-
公开(公告)号：US5905807A
公开(公告)日：1999-05-18
申请号：US708873
申请日：1996-09-05
CPC分类号： A61B5/1176 , G06K9/00268 , H04N19/20
摘要： A facial image picture data is processed by an edge extraction part, which performs edge extraction on the inputted image picture. The processed data is then converted by a binary level conversion part for each preestimated point of facial elements. An image picture arithmetic processing part performs time-to-time arithmetic computation of correlation values between the data of the binary-leveled edged-image picture and the data having been previously stored in the shape data-base part, and issues an output including extracted data of feature points of the facial image picture.
摘要翻译： 面部图像图像数据由对所输入的图像图像进行边缘提取的边缘提取部进行处理。 然后，处理后的数据由面部元素的每个预测点的二进制水平转换部分转换。 图像图像算术处理部分执行二进制等级边缘图像图像的数据与先前存储在形状数据库部分中的数据之间的相关值的时间运算，并发出包括提取的输出 面部图像图像的特征点数据。
-
公开(公告)号：US5410609A
公开(公告)日：1995-04-25
申请号：US926914
申请日：1992-08-07
CPC分类号： G06K9/00288 , G06K9/00315
摘要： In an apparatus for identification of individuals, a facial image of an individual to be identified is inputted into a visual image input unit and characteristic points of the inputted facial image are extracted by a characteristics extracting unit. Characteristic points of expressionless facial images of individuals to be identified are stored in a data base. The difference between the characteristic points from the data base of individuals and the characteristic points from the inputted facial image is detected by a difference detecting unit. Further, the apparatus is equipped with a database of expression muscles wherein expression muscle movement vectors to form facial expressions are described. The apparatus is also equipped with an information processing unit whereby the difference information obtained from the difference detecting unit and the information as described in the data base of expression muscles are processed. By this processed information, coupled with the facial image inputted from the visual image input unit, the subject in question is identified.
摘要翻译： 在用于识别个体的装置中，要识别的个体的面部图像被输入到视觉图像输入单元，并且通过特征提取单元提取输入的面部图像的特征点。 要识别的个体的无表情面部图像的特征点存储在数据库中。 来自个人数据库的特征点与来自输入的面部图像的特征点之间的差异由差异检测单元检测。 此外，该装置配备有表达肌肉的数据库，其中描述了形成面部表情的表达肌肉运动向量。 该装置还配备有信息处理单元，由此处理从差异检测单元获得的差异信息和表达肌肉的数据库中描述的信息。 通过该处理的信息，与从视觉图像输入单元输入的面部图像相结合，识别出所讨论的被摄体。
-
公开(公告)号：US6166746A
公开(公告)日：2000-12-26
申请号：US505607
申请日：1995-07-21
CPC分类号： G06T13/40
摘要： An image processing apparatus has a three-dimensional joint position storing circuit for storing a three-dimensional coordinate position for each of available joints of an object at each frame for a standard action; a geometric data storing circuit for storing geometric data for at least a portion of the object based on unique coordinate systems for each of the available joints; a unique coordinate system determining circuit for determining the unique coordinate system for each of the available joints based on the stored three-dimensional coordinate positions; a three-dimensional joint angle computing circuit for computing a three-dimensional joint angle for at least one of the available joints based on a desired mode of action modification and the determined unique coordinate systems; a joint angle displacing circuit for displacing the three-dimensional joint angle for at least one of the available joints; a unique coordinate system generating circuit for generating the unique coordinate system for at least one of the available joints; and an action synthesizing circuit for assigning the geometric data corresponding to each of the available joints.
摘要翻译： 一种图像处理装置具有三维关节位置存储电路，用于存储用于标准动作的每个帧处的对象的每个可用关节的三维坐标位置; 几何数据存储电路，用于基于每个可用关节的唯一坐标系存储用于至少一部分对象的几何数据; 一个独特的坐标系确定电路，用于基于存储的三维坐标位置确定每个可用关节的唯一坐标系; 三维关节角度计算电路，用于基于期望的作用修改模式和确定的唯一坐标系统计算至少一个可用关节的三维关节角度; 关节角位移电路，用于移位用于至少一个可用接头的三维关节角; 唯一的坐标系生成电路，用于为至少一个可用关节产生独特的坐标系; 以及动作合成电路，用于分配对应于每个可用关节的几何数据。
-
5.发明申请Digest video specification system, digest video providing system, digest video specifying method, digest video providing method, and medium and program therefor 审中-公开摘要视频指定系统，摘要视频提供系统，摘要视频指定方法，摘要视频提供方法及其媒体和程序公开(公告)号：US20050105002A1
公开(公告)日：2005-05-19
申请号：US10501998
申请日：2003-01-09
申请人： Fumio Maehara
发明人： Fumio Maehara
IPC分类号： H04N5/91 , H04N7/173 , H04N21/472 , H04N21/8549 , H04N7/00
CPC分类号： H04N21/47202 , H04N5/2627 , H04N7/173 , H04N21/2543 , H04N21/84 , H04N21/8549
摘要： Producing digest video from AV data which includes retrieval means of retrieving multi-angle video from AV data having multi-angle video; digest video specification means of defining the retrieved multi-angle video as digest video; and digest video providing means of providing digest video, and an information terminal which includes receiving means of receiving digest video.
摘要翻译： 从AV数据生成摘要视频，其包括从具有多角度视频的AV数据中检索多角度视频的检索装置; 将所检索的多角度视频定义为摘要视频的摘要视频指定装置; 以及提供摘要视频的摘要视频提供装置，以及包括接收摘要视频的接收装置的信息终端。
-
公开(公告)号：US5317508A
公开(公告)日：1994-05-31
申请号：US966879
申请日：1992-10-26
申请人： Shusaku Okamoto , Toshiyuki Maeda , Fumio Maehara
发明人： Shusaku Okamoto , Toshiyuki Maeda , Fumio Maehara
CPC分类号： G06F17/274 , G06F17/30265
摘要： There is provided an image editing apparatus, which comprises language image uniting dictionary storing informations on words, on relation between meanings of the words, and on image, a grammer dictionary storing grammer, image editing rule and, a language parsing means to parse a linguistic sentence, an image retrieving means to retrieve image information and an image editing means to edit image, and, being input information on an intended image in natural language, parses the input sentence, retrieves images for expressing the meaning thereof, processes and snystesizes the retrieved images, all automatically, so that, an intended image can be obtained by simple operation.
摘要翻译： 提供了一种图像编辑装置，其包括存储关于单词的信息的语言图像组合字典，单词的含义之间的关系以及图像，存储语法的语法词典，图像编辑规则和解析语言的语言解析装置 句子，检索图像信息的图像检索装置和用于编辑图像的图像编辑装置，并且以自然语言输入关于预期图像的信息，解析输入的句子，检索用于表达其含义的图像，处理和跟踪检索到的 图像，全部自动，使得通过简单的操作可以获得预期的图像。
-
公开(公告)号：US4303988A
公开(公告)日：1981-12-01
申请号：US45676
申请日：1979-06-05
申请人： Eiichi Tsuboka , Fumio Maehara , Hiroshi Fujita , Yoshiteru Izura, deceased , by Keiko Izura, heir
发明人： Eiichi Tsuboka , Fumio Maehara , Hiroshi Fujita , Yoshiteru Izura, deceased , by Keiko Izura, heir
CPC分类号： G06F3/0601 , G11B5/012 , G06F2003/0691
摘要： The present invention is a random accessible signal filing system containing magnetic discs, at least two buffer memories and a circuit for controlling the buffer memories in such a way that the write-in and read-out of at least two of the buffer memories may be alternately performed, whereby through random access, the required signals are selected and read out so as to be outputted as a series of signals.In this system, during the outputting of the signals, the signals coming from the magnetic discs are written into one of the buffer memories sector by sector at the read-out speed of the magnetic discs, and thereafter, are read out at the demodulating speed of the demodulator. The two buffer memories are so controlled that while the signals are written into one of them; the signals are read out from the other.
摘要翻译： 本发明是一种包含磁盘，至少两个缓冲存储器和用于控制缓冲存储器的电路的随机可访问信号归档系统，使得至少两个缓冲存储器的写入和读出可以是 交替执行，由此通过随机存取，选择和读出所需的信号，以便作为一系列信号被输出。 在该系统中，在输出信号期间，来自磁盘的信号以磁盘的读出速度扇区逐扇区地写入缓冲存储器之一，然后以解调速度读出 的解调器。 两个缓冲存储器被如此控制，当信号被写入其中之一时; 信号从另一个读出。
-
-
-
-
-
-
搜索结果
7 条记录 (耗时 0.021 秒)
