公开(公告)号：US06804416B1

公开(公告)日：2004-10-12

申请号：US09809026

申请日：2001-03-16

申请人： Ivan Bachelder ,  Lowell Jacobson ,  Jay Negro ,  Leonid Segal

发明人： Ivan Bachelder ,  Lowell Jacobson ,  Jay Negro ,  Leonid Segal

IPC分类号： G06K932

CPC分类号： G06K9/6253

摘要： A method and system is provided for aligning a geometric object model with a pixel image. A geometric object model representing an object is obtained first. Using the geometric object model of the object, a revised geometric object model is created. An alignment tool is then trained based on the revised geometric object model. The alignment model can be applied to a pixel image of the object so that the pose of the object can be computed by aligning the revised geometric object model with the image.

摘要翻译： 提供了一种用于将几何对象模型与像素图像对准的方法和系统。 首先获得表示对象的几何对象模型。 使用对象的几何对象模型，创建修改后的几何对象模型。 然后基于修改后的几何对象模型训练对准工具。 对准模型可以应用于对象的像素图像，使得可以通过将修改后的几何对象模型与图像对准来计算对象的姿态。

公开(公告)号：US06795590B1

公开(公告)日：2004-09-21

申请号：US09668657

申请日：2000-09-22

申请人： Yang Chen

发明人： Yang Chen

IPC分类号： G06K932

CPC分类号： G06K9/6205 ,  G06T7/33 ,  G06T7/37

摘要： There is disclosed herein, a method used to associate or correspond synthetic aperture radar (SAR) and forward looking infrared (FLIR) images. Based on feature points detectable from both images, a two stage approach is taken to address the issue of SAR and FLIR image registration: an initial registration stage where feature points detected from the FLIR image are transformed into the SAR image coordinates; and a residual registration stage where the SAR and FLIR feature points undergo a “Generalized Hough Transform” from which a maximal subset of matching feature points is obtained and the registration transformation can be derived. These two stages are separated into five steps which comprise the SAR and FLIR Image Registration Method: (1) extracting feature points from said SAR and FLIR images; (2) creating an initial registration of the FLIR image; (3) creating a two-dimensional residual registration utilizing a generalized Hough transform; (4) estimating the registration transformation; and, (5) verifying the registration. This method allows the residual registration to be done in a two-dimensional (rather than six) Hough transform, which results in fast and robust implementation as well as reduce the possibility of false registration.

摘要翻译： 这里公开了一种用于关联或对应合成孔径雷达（SAR）和前视红外（FLIR）图像的方法。 基于从两个图像可检测的特征点，采用两阶段方法来解决SAR和FLIR图像配准的问题：其中从FLIR图像检测到的特征点被转换成SAR图像坐标的初始注册阶段; 以及SAR和FLIR特征点经历“广义霍夫变换”的残留登记阶段，从该特征点获得匹配特征点的最大子集，并且可以导出注册变换。 这两个阶段分为五个步骤，包括SAR和FLIR图像注册方法：（1）从SAR和FLIR图像中提取特征点; （2）创建FLIR图像的初始注册; （3）使用广义霍夫变换创建二维残差配准; （4）估算登记变更; 和（5）验证注册。 这种方法允许在二维（而不是六个）霍夫变换中进行剩余注册，这导致快速和可靠的实现，并且减少虚假注册的可能性。

公开(公告)号：US06768821B2

公开(公告)日：2004-07-27

申请号：US10291560

申请日：2002-11-12

申请人： Kia Silverbrook ,  Paul Lapstun ,  Simon Robert Walmsley

发明人： Kia Silverbrook ,  Paul Lapstun ,  Simon Robert Walmsley

IPC分类号： G06K932

CPC分类号： B41J2/17556 ,  B41J2/17503 ,  B41J2/17513 ,  B41J2/1752 ,  B41J2/17523 ,  B41J2/17546 ,  B41J2/17553 ,  B41J2/17563 ,  B41J2/2114 ,  B41J13/103 ,  B41J13/106 ,  B42C9/0006 ,  B42C9/0081 ,  B42C19/02 ,  B65H29/34 ,  B65H37/04 ,  G06F3/016 ,  G06F3/0321 ,  G06F3/03545 ,  G06K9/2054 ,  G06K9/2063 ,  G06K9/22 ,  G06K9/222 ,  G06K2009/226 ,  G06K2209/01 ,  H04N1/00127 ,  H04N1/00204 ,  H04N1/00244 ,  H04N1/00326 ,  H04N1/00358 ,  H04N1/00376 ,  H04N1/00567 ,  H04N1/00968 ,  H04N1/32101 ,  H04N1/32122 ,  H04N1/32128 ,  H04N1/32771 ,  H04N1/32778 ,  H04N2201/0082 ,  H04N2201/3243 ,  H04N2201/3269 ,  H04N2201/327

摘要： A sensing device for sensing region identity data and generating movement data when the sensing device is moved relative to a region of a surface, the region identity data being indicative of an identity of the region, the movement data being indicative of the movement of the sensing device relative to the region, the surface having disposed upon it coded data indicative of at least one region associated with the surface, the sensing device including: region identity sensing means configured to sense the region identity data using at least some of the coded data; motion sensing means configured to generate the movement data; and communications means configured to communicate the region identity data and the movement data to a computer system.

摘要翻译： 一种感测装置，用于在感测装置相对于表面的区域移动时感测区域识别数据并产生移动数据，该区域识别数据指示区域的身份，移动数据表示感测的移动 所述表面具有指示与所述表面相关联的至少一个区域的编码数据，所述感测装置包括：区域标识感测装置，被配置为使用所述编码数据中的至少一些来感测所述区域标识数据; 运动检测装置，被配置为产生移动数据; 以及通信装置，被配置为将区域标识数据和移动数据传送到计算机系统。

公开(公告)号：US06766067B2

公开(公告)日：2004-07-20

申请号：US09838811

申请日：2001-04-20

申请人： William T. Freeman ,  Thouis R. Jones

发明人： William T. Freeman ,  Thouis R. Jones

IPC分类号： G06K932

CPC分类号： G06T3/4053

摘要： A super-resolution image is generated from a pixel image by first performing an initial image interpolation, creating an interpolated low resolution image. The interpolated low resolution image is then partitioned into overlapping low resolution patches. The low resolution patches are then processed in a raster scan order. For each low-resolution patch, a scaled mid band patch is generated. A search vector is constructed from pixels in the scaled mid band input patch, and pixels in an overlap region of adjacent previously predicted high band patches. A nearest index vector to the search vector is located in a training database, the nearest index vector has an associated high band output patch. The high band output patch is then combined with the interpolated low resolution patch to predict pixel values for the corresponding high resolution patch of the super-resolution image.

摘要翻译： 通过首先执行初始图像插值，创建内插低分辨率图像，从像素图像生成超分辨率图像。 然后将内插的低分辨率图像分割成重叠的低分辨率补丁。 然后以光栅扫描顺序处理低分辨率补丁。 对于每个低分辨率补丁，生成缩放的中间带补丁。 搜索向量由缩放的中频带输入音调中的像素和相邻的预先预测的高频带的重叠区域中的像素构成。 搜索向量的最近的索引向量位于训练数据库中，最近的索引向量具有相关联的高带输出补丁。 然后将高频带输出贴片与内插的低分辨率贴片组合以预测超分辨率图像的相应高分辨率图像的像素值。

公开(公告)号：US06754402B2

公开(公告)日：2004-06-22

申请号：US09779745

申请日：2001-02-09

申请人： Toru Matama

发明人： Toru Matama

IPC分类号： G06K932

CPC分类号： H04N1/1951 ,  H04N1/19505 ,  H04N1/19515 ,  H04N1/19568 ,  H04N1/40068

摘要： An interpolation arithmetic method and an image reader are provided which, in reading a film image using an area CCD sensor in which reading elements are arranged in a hound's tooth check form, is capable of making full use of excellent characteristics of the area CCD sensor. The interpolation arithmetic method and the image reader can be realized by interpolating first image signals of the neighboring two or more reading elements to allocate the second image signals and outputting the interpolated second image signals or the first and second image signals in a square check form, and by providing a light source section; an area image sensor; an imaging optical system; and at least one of pixel shifting device of the area image sensor, and an interpolation arithmetic section for rearranging the second image signals of pixels in the square check form by performing interpolation arithmetic of first image signals outputted from respective reading elements of the area image sensor.

摘要翻译： 提供一种内插算术方法和图像读取器，其中使用其中读取元件以猎犬牙齿检查形式布置的区域CCD传感器读取胶片图像，能够充分利用区域CCD传感器的优异特性。 可以通过对相邻的两个或更多个读取元件的第一图像信号进行内插来分配第二图像信号并以平方检查形式输出插值的第二图像信号或第一和第二图像信号来实现插值算术方法和图像读取器， 并通过提供光源部分; 区域图像传感器; 成像光学系统; 以及区域图像传感器的像素移位装置中的至少一个以及用于通过对从区域图像传感器的各个读取单元输出的第一图像信号进行插值运算来重新排列方形检查体的像素的第二图像信号的插值运算部 。

公开(公告)号：US06741757B1

公开(公告)日：2004-05-25

申请号：US09519794

申请日：2000-03-07

申请人： Philip H. S. Torr ,  Colin Davidson

发明人： Philip H. S. Torr ,  Colin Davidson

IPC分类号： G06K932

CPC分类号： G06K9/00154 ,  G06K9/6857

摘要： Feature correspondence between images using an image pyramid is disclosed. In one embodiment, a fundamental matrix between a first and a second image is generated from the image pyramid. The image pyramid is first generated, and has a predetermined number of fineness levels, from a coarsest to a finest level. Each of the images has significant features at each pyramid level. A plurality of hypotheses, or particles, is generated for the fundamental matrix at the coarsest level, based on matching significant features of the images at the coarsest level. In an iterative procession through the levels of the image pyramid, starting at a present level initially set to the coarsest level and then subsequently advanced by one fineness level upon each iteration, an importance sampling function is first formulated from the hypotheses. The plurality of hypotheses is then generated at the next pyramid level based on the function, and on the significant features of the images at this next level. The iteration is complete when the next level has reached the finest pyramid level. The hypotheses generated at the finest level encapsulate the fundamental matrix together with its uncertainty.

摘要翻译： 公开了使用图像金字塔的图像之间的特征对应。 在一个实施例中，从图像金字塔生成第一和第二图像之间的基本矩阵。 首先产生图像金字塔，并且具有预定数量的细度水平，从最粗糙到最高水平。 每个图像在每个金字塔级别都有显着的特征。 基于在最粗糙级别的图像的匹配显着特征，为最粗糙级别的基本矩阵生成多个假设或粒子。 在通过图像金字塔的层次的迭代游行中，从最初设置为最粗糙级别的当前级别开始，然后在每次迭代上随后提前一个细度级别，首先从假设来制定重要性抽样函数。 然后在下一个金字塔级别基于该功能以及在下一级的图像的显着特征上生成多个假设。 当下一级达到最好的金字塔级别时，迭代完成。 最高层次产生的假设包含了基本矩阵及其不确定性。

公开(公告)号：US06738534B2

公开(公告)日：2004-05-18

申请号：US10066501

申请日：2002-01-31

申请人： Justin Ridge ,  Stephane Coulombe

发明人： Justin Ridge ,  Stephane Coulombe

IPC分类号： G06K932

CPC分类号： G06T3/4084 ,  G06T3/40

摘要： Apparatus, and an associated method, for reducing the resolution of a digital image, such as a JPEG image. The digital image is pre-scaled by a pre-scaling factor that is selected such that a matrix multiplication is performed upon the digital image once pre-scaled, to reduce the resolution of the image. The matrix multiplication utilizes a multiplier that exhibits symmetry, thereby to reduce the number of calculations required to reduce the resolution of the image. Resolution reduction is performed, for instance, prior to communicating the digital image to a mobile station operable in a mobile communication system.

摘要翻译： 用于降低诸如JPEG图像的数字图像的分辨率的装置和相关联的方法。 数字图像通过预定尺寸因子进行预缩放，所述预缩放因子被选择为使得一旦预缩放就对数字图像执行矩阵乘法，以降低图像的分辨率。 矩阵乘法利用显示对称性的乘法器，从而减少降低图像分辨率所需的计算次数。 例如，在将数字图像传送到在移动通信系统中可操作的移动台之前执行分辨率降低。

公开(公告)号：US06707954B1

公开(公告)日：2004-03-16

申请号：US09414956

申请日：1999-10-12

申请人： Manabu Akamatsu ,  Yoshinori Awata ,  Kenichi Takahashi ,  Kazumi Fukazawa

发明人： Manabu Akamatsu ,  Yoshinori Awata ,  Kenichi Takahashi ,  Kazumi Fukazawa

IPC分类号： G06K932

CPC分类号： G06T3/40 ,  G06K9/46

摘要： There are provided an image processing apparatus and an image processing method which are capable of correctly determining the scaling factor of an input image containing a specific image composed of a predetermined number of partial images. When an input image is inputted, the partial image detection unit 1 detects information about partial images. As information about partial images, information indicating whether partial images exist, the size of the partial images, and the like are outputted. The information about partial images is outputted for each pixel of an input image and a pattern composed of the information about partial images is obtained. The scaling factor estimation unit 2 uses a pattern composed of the information about partial images outputted from the partial image detection unit 1 to detect an area where a predetermined number of partial images exist, and determines the scaling factor of the input image from information of the area.

摘要翻译： 提供了能够正确地确定包含由预定数量的部分图像组成的特定图像的输入图像的缩放因子的图像处理装置和图像处理方法。 当输入图像被输入时，部分图像检测单元1检测关于部分图像的信息。 作为关于部分图像的信息，指示是否存在部分图像的信息，部分图像的尺寸等。 对于输入图像的每个像素输出关于部分图像的信息，并且获得由关于部分图像的信息组成的图案。 缩放因子估计单元2使用由从部分图像检测单元1输出的关于部分图像的信息组成的图案来检测存在预定数量的部分图像的区域，并且根据该图像信息确定输入图像的缩放因子 区。

公开(公告)号：US06678426B1

公开(公告)日：2004-01-13

申请号：US09047315

申请日：1998-03-24

申请人： James G. Bearss ,  Eugene A. Roylance ,  Wayne E. Bradburn ,  Arlin R. Jones

发明人： James G. Bearss ,  Eugene A. Roylance ,  Wayne E. Bradburn ,  Arlin R. Jones

IPC分类号： G06K932

CPC分类号： G06K15/02 ,  G06K15/1874 ,  G06K2215/0071

摘要： Lower resolution source data is synthesized to a higher resolution format for subsequent rendering on a lower resolution output device. Synthesis occurs by selecting or generating and using a synthesis template that represents a configuration of a plurality of pixel data in the higher resolution format into which the lower resolution source data is to be synthesized. A working or active pixel is identified from the lower resolution source data, a synthesis template is selected, and then the synthesis template pixel data is substituted for the working pixel for rendering on the output device. The synthesized higher resolution data is rendered in a manner such that dots represented by the synthesized data are formed interstitially relative to scan lines of the given lower raster/resolution capability of the output device. The working pixel is identified in the lower resolution data by recognizing a configuration of a plurality of pixel data adjacent the working pixel. The synthesis template comprises at least a two by two cell matrix for pixel placement in the higher resolution format. The synthesis template pixel placement is formed to provide an apparent merge of the pixel data in the higher resolution format with the adjacent pixel data of the lower resolution format data.

摘要翻译： 较低分辨率的源数据被合成为较高分辨率的格式，用于在较低分辨率的输出设备上进行后续渲染。 通过选择或生成和使用表示要合成较低分辨率源数据的较高分辨率格式的多个像素数据的配置的合成模板进行合成。 从较低分辨率源数据识别工作或活动像素，选择合成模板，然后将合成模板像素数据替换为用于在输出设备上呈现的工作像素。 合成的较高分辨率数据以使得由合成数据表示的点相对于输出装置的给定较低光栅/分辨能力的扫描线在间隙形成的方式呈现。 通过识别与工作像素相邻的多个像素数据的配置，在较低分辨率数据中识别工作像素。 合成模板包括至少两个两个单元矩阵，用于以较高分辨率格式放置像素。 形成合成模板像素布置以提供较高分辨率格式的像素数据与较低分辨率格式数据的相邻像素数据的明显合并。

公开(公告)号：US06668101B2

公开(公告)日：2003-12-23

申请号：US09329202

申请日：1999-06-10

申请人： Kitahiro Kaneda

发明人： Kitahiro Kaneda

IPC分类号： G06K932

CPC分类号： G06K9/6857

摘要： An input image is converted into an image in a predetermined format. An optimal character recognition resolution determination unit determines, using the converted image, an optimal resolution to be used upon executing character recognition of the input image. A character recognition circuit executes character recognition of the input image on the basis of the determination result. An output circuit outputs the recognition result.

摘要翻译： 将输入图像转换为预定格式的图像。 最佳字符识别分辨率确定单元使用转换的图像确定在执行输入图像的字符识别时要使用的最佳分辨率。 字符识别电路基于确定结果执行输入图像的字符识别。 输出电路输出识别结果。