公开(公告)号：US07263243B2

公开(公告)日：2007-08-28

申请号：US10747594

申请日：2003-12-29

申请人： Shoupu Chen ,  Lawrence A. Ray ,  Nathan D. Cahill ,  Marvin M. Goodgame ,  Cranos M. Williams

发明人： Shoupu Chen ,  Lawrence A. Ray ,  Nathan D. Cahill ,  Marvin M. Goodgame ,  Cranos M. Williams

IPC分类号： G06K9/32 ,  G06K9/00

CPC分类号： G06K9/6212

摘要： A digital image processing method for image registration, that acquires a reference intensity image and a floating intensity image that is to be registered; and preprocesses the reference and the floating images, before converting the preprocessed reference image to a vectorized reference image. Subsequently, the vectorized reference image is converted to a reference index image. Additional image processing includes spatially transforming the preprocessed floating image using a transformation matrix; converting the transformed floating image to a vectorized floating image; converting the vectorized floating image to a floating index image; and obtaining joint statistics of the index images. Other steps include, computing a cost function due to misalignment of the two images using the joint statistics; and updating the transformation matrix and repeating several aforementioned steps, if the cost function does not satisfy a predefined criterion, otherwise, applying the transformation matrix to an acquired floating intensity image.

摘要翻译： 一种用于图像配准的数字图像处理方法，其获取要登记的参考强度图像和浮动强度图像; 并在将预处理参考图像转换为矢量化参考图像之前，预处理参考和浮动图像。 随后，将矢量化参考图像转换为参考索引图像。 附加图像处理包括使用变换矩阵对预处理的浮动图像进行空间变换; 将变换的浮动图像转换为矢量化的浮动图像; 将矢量化浮动图像转换为浮动索引图像; 并获得索引图像的联合统计。 其他步骤包括：使用联合统计计算两个图像的未对准的成本函数; 并且如果所述成本函数不满足预定标准，则更新所述变换矩阵并重复若干上述步骤，否则，将所述变换矩阵应用于所获取的浮动强度图像。

公开(公告)号：US07120279B2

公开(公告)日：2006-10-10

申请号：US10354837

申请日：2003-01-30

申请人： Shoupu Chen ,  Lawrence A. Ray

发明人： Shoupu Chen ,  Lawrence A. Ray

IPC分类号： G06K9/00

CPC分类号： G06K9/00234 ,  G06K9/00248

摘要： A digital image processing method for determining an orientation of a face in a digital color image generates a mean grid pattern element image from a plurality of sample face images and an integral image from the digital color image. A face is located in the color digital image by using the integral image to perform a correlation test between the mean grid pattern element image and the digital color image at a plurality of effective resolutions by reducing the digital color image to a plurality of grid pattern element images at different effective resolutions and correlating the mean grid pattern element image with the plurality of grid pattern element images, whereby either the mean grid pattern element image or the grid pattern element images are provided at a plurality of different orientations. Accordingly, an orientation of the face in the color digital image is determined by using the images with different orientations in the correlation test.

摘要翻译： 用于确定数字彩色图像中的面部的取向的数字图像处理方法从多个样本面部图像和来自数字彩色图像的整体图像生成平均网格图案单元图像。 通过使用积分图像将面部位于彩色数字图像中，通过将数字彩色图像减少到多个网格图案元素来以多个有效分辨率执行平均网格图案元素图像和数字彩色图像之间的相关性测试 图像以不同的有效分辨率并且将平均网格图案元素图像与多个网格图案元素图像相关联，由此平均网格图案元素图像或网格图案元素图像以多个不同的取向提供。 因此，通过在相关性测试中使用具有不同取向的图像来确定彩色数字图像中的面部的取向。

公开(公告)号：US06856382B2

公开(公告)日：2005-02-15

申请号：US10360380

申请日：2003-02-06

申请人： Nathan D. Cahill ,  Lawrence A. Ray

发明人： Nathan D. Cahill ,  Lawrence A. Ray

IPC分类号： G06T1/00 ,  G01C3/08 ,  G06T7/00 ,  H04N20060101 ,  H04N5/225

CPC分类号： G06T7/521

摘要： A method for generating a range image sequence from a scannerless range imaging system of the type comprising an illuminator for illuminating a scene with modulated illumination; an image modulating component for receiving and modulating the modulated illumination reflected from the scene; an image capture element for capturing images output by the image modulating component, including an image bundle of at least three phase offset images each incorporating a phase delay corresponding to the distance of objects in the scene from the illuminator, wherein each phase offset image of an image bundle also incorporates a phase offset distinct for each image. According to the method, a sequence of three or more phase offset images are acquired that correspond to the modulated illumination reflected from the scene, whereby the sequence contains overlapping subsequences of successive phase offset images, each subsequence forming an image bundle. A range image is then computed using the phase offset images from each corresponding image bundle, thereby forming a range image sequence.

摘要翻译： 一种用于从包括用调制照明照明场景的照明器的类型的无扫描仪范围成像系统产生范围图像序列的方法; 用于接收和调制从场景反射的调制照明的图像调制组件; 用于捕获由图像调制部件输出的图像的图像捕获元件，包括至少三个相位偏移图像的图像束，每个相位偏移图像包含与场景中的物体距离照明器相对应的相位延迟，其中每个相位偏移图像 图像束还包含每个图像不同的相位偏移。 根据该方法，获取与从场景反射的调制照明相对应的三个或更多个相位偏移图像的序列，由此该序列包含连续相位偏移图像的重叠子序列，每个子序列形成图像束。 然后使用来自每个对应图像束的相位偏移图像来计算范围图像，从而形成范围图像序列。

公开(公告)号：US06690822B1

公开(公告)日：2004-02-10

申请号：US09692930

申请日：2000-10-20

申请人： Shoupu Chen ,  Lawrence A. Ray

发明人： Shoupu Chen ,  Lawrence A. Ray

IPC分类号： G06K900

CPC分类号： G06K9/00234 ,  G06K9/4652 ,  G06T7/11 ,  G06T2207/30201

摘要： A method for detecting skin color in a digital image having pixels in an RGB color space generally includes the steps of performing statistical analysis of the digital color image to determine the mean RGB color values; then, if the mean value of any one of the colors is below a predetermined threshold, applying a transformation to the digital image to move skin colors in the image toward a predetermined region of the color space; and employing the transformed space to locate the skin color pixels in the digital color image. More specifically, if the mean value of any one of the colors is below a predetermined threshold, a non-linear transformation is applied to the digital image to move skin colors in the image toward a predetermined region of the color space. Then, depending on the preceding step, either the digital image or the transformed digital image is converted from the RGB space to a generalized RGB space to produce a gRGB digital image; skin color pixels are detected within the gRGB digital image; a first skin color image mask is formed based on the detected skin color pixels; a masked gRGB image is generated using the first skin color image mask; and finally the skin color image mask is employed to locate the skin color pixels in the digital color image.

摘要翻译： 用于检测具有RGB颜色空间中的像素的数字图像中的肤色的方法通常包括执行数字彩色图像的统计分析以确定平均RGB颜色值的步骤; 然后，如果任意一种颜色的平均值低于预定阈值，则向数字图像应用变换以使图像中的皮肤颜色朝着颜色空间的预定区域移动; 并且使用变换的空间来定位数字彩色图像中的肤色像素。 更具体地说，如果任何一种颜色的平均值低于预定阈值，则将非线性变换应用于数字图像，以使图像中的皮肤颜色朝着颜色空间的预定区域移动。 然后，根据上述步骤，将数字图像或经变换的数字图像从RGB空间转换为广义RGB空间以产生gRGB数字图像; 在gRGB数字图像内检测肤色像素; 基于检测到的肤色像素形成第一皮肤彩色图像掩模; 使用第一皮肤彩色图像掩模生成蒙版的gRGB图像; 最后使用肤色图像掩模来定位数字彩色图像中的肤色像素。

公开(公告)号：US06677982B1

公开(公告)日：2004-01-13

申请号：US09686610

申请日：2000-10-11

申请人： Shoupu Chen ,  Lawrence A. Ray

发明人： Shoupu Chen ,  Lawrence A. Ray

IPC分类号： H04N700

CPC分类号： H04N5/23238 ,  G06T3/4038 ,  G06T2200/04 ,  G06T2200/32 ,  G06T2207/10012 ,  G06T2207/10028 ,  H04N13/106

摘要： A method, a system, and a computer program product for deriving a three-dimensional panorama from a plurality of stereo image pairs of a scene generated from a plurality of cameras, that includes acquiring a plurality of stereo image pairs of the scene, wherein there is an intra-overlap region between vertically aligned stereo image pairs; acquiring a plurality of stereo image pairs of the scene by rotating the plurality of cameras about a Y-axis, wherein there is an inter-overlap region between adjacent stereo image pairs; providing displacement data for capturing scene depth from a local XYZ image with non-distorted depth information; generating (X,Y,Z) values for each of the stereo image pairs with respect to a local three-dimensional coordinate system wherein the intra-stereo image pair is taken; selecting a reference three-dimensional world coordinate system against which spatial information of the scene can be correctly presented; transforming the generated (X,Y,Z) values from each of the local three-dimensional coordinate systems to the selected reference three-dimensional world coordinate system; warping the transformed (X,Y,Z) images onto a cylindrical surface, and forming a plurality of warped (X,Y,Z) images; registering adjacent warped (X,Y,Z) images; and forming a three-dimensional panorama, i.e., a (X,Y,Z) panorama using the warped (X,Y,Z) images.

摘要翻译： 一种用于从多个相机生成的场景的多个立体图像对中导出三维全景图的方法，系统和计算机程序产品，其包括获取场景的多个立体图像对，其中， 是垂直对齐的立体图像对之间的重叠内区域; 通过围绕Y轴旋转所述多个照相机来获取所述场景的多个立体图像对，其中在相邻的立体图像对之间存在相互重叠的区域; 提供用于从具有非失真深度信息的本地XYZ图像捕获场景深度的位移数据; 针对立体图像对采用的局部三维坐标系生成每个立体图像对的（X，Y，Z）值; 选择可以正确呈现场景的空间信息的参考三维世界坐标系; 将生成的（X，Y，Z）值从局部三维坐标系中的每一个变换为所选择的参考三维世界坐标系; 将变形的（X，Y，Z）图像翘曲在圆柱形表面上，并形成多个翘曲（X，Y，Z）图像; 记录相邻的扭曲（X，Y，Z）图像; 以及使用扭曲（X，Y，Z）图像形成三维全景图，即（X，Y，Z）全景图。

公开(公告)号：US06410930B1

公开(公告)日：2002-06-25

申请号：US09645752

申请日：2000-08-24

申请人： Joseph F. Revelli, Jr. ,  Lawrence A. Ray

发明人： Joseph F. Revelli, Jr. ,  Lawrence A. Ray

IPC分类号： G01J350

CPC分类号： G01S7/481 ,  G01S17/89

摘要： An alignment method is provided for a color scannerless range imaging system whereby the separate optical paths of colored texture and monochromatic range images may be precisely aligned. The range imaging system includes an illumination system for illuminating a scene with modulated infrared illumination, image forming optics for forming an image of the scene, optical means for forming first and second optical paths between the image forming optics and an image sensor, a transponder subject to modulation located in the first optical path for amplifying and converting infrared light to visible light to form a range image on the image sensor. The alignment method includes the steps of providing a target having alignment indicia that can be imaged in both infrared and visible regions of the spectrum, capturing an infrared image of the target using the first optical path, capturing a color image of the target using the second optical path, and adjusting at least one of the optical paths so that the captured images are coincident.

摘要翻译： 提供了一种用于彩色无扫描范围成像系统的对准方法，由此可以精确对准彩色纹理和单色范围图像的单独光路。 范围成像系统包括用调制红外照明照明场景的照明系统，用于形成场景图像的图像形成光学器件，用于在成像光学器件和图像传感器之间形成第一和第二光路的光学装置，应答器对象 到位于第一光路中的调制，用于将红外光放大并转换成可见光，以在图像传感器上形成范围图像。 对准方法包括以下步骤：提供具有可以在光谱的红外和可见区域中成像的对准标记的目标，使用第一光路捕获目标的红外图像，使用第二光学捕获目标的彩色图像 光路，并且调整光路中的至少一个，使得所捕获的图像一致。

公开(公告)号：US5754311A

公开(公告)日：1998-05-19

申请号：US848779

申请日：1992-03-10

申请人： Lawrence A. Ray

发明人： Lawrence A. Ray

IPC分类号： G06T5/00 ,  H04N1/405 ,  H04N1/40

CPC分类号： H04N1/4051

摘要： Method and apparatus for generating a halftone image. An ensemble of correlated minimum visual modulation two-dimensional binary patterns are provided. Each pattern corresponds to one density level of a digital input signal. The set of patterns is generated simultaneously to minimize an ensemble cost function which is the variance of non-zero spatial frequencies weighted by a human visual system modulation transfer function. The patterns are then modularly addressed to select bits to form halftone pattern.

摘要翻译： 用于产生半色调图像的方法和装置。 提供了相关的最小视觉调制二维二进制模式的集合。 每个图案对应于数字输入信号的一个密度级。 同时产生一组模式以最小化作为由人类视觉系统调制传递函数加权的非零空间频率的方差的整体成本函数。 然后将模式模块化地寻址以选择位以形成半色调图案。

公开(公告)号：US5586203A

公开(公告)日：1996-12-17

申请号：US331246

申请日：1994-10-28

申请人： Kevin E. Spaulding ,  Lawrence A. Ray

发明人： Kevin E. Spaulding ,  Lawrence A. Ray

IPC分类号： G06T5/00 ,  G09G5/02 ,  H04N1/40 ,  H04N1/405 ,  G06K9/38

CPC分类号： H04N1/40087 ,  H04N1/4051

摘要： Method and apparatus for generating a halftone image for a multi-level output device employing a dither matrix generated by minimizing a visual cost function. The dither matrix is addressed by the least significant bits of a pixel address and the value supplied by the dither matrix is added to the pixel value. The resulting sum is quantized in a quantizer to produce the multi-level halftone value.

摘要翻译： 用于生成用于通过最小化视觉成本函数产生的抖动矩阵的多级输出装置的半色调图像的方法和装置。 抖动矩阵由像素地址的最低有效位寻址，并且由抖动矩阵提供的值被添加到像素值。 所得到的和在量化器中量化以产生多级半色调值。

公开(公告)号：US5574573A

公开(公告)日：1996-11-12

申请号：US145284

申请日：1993-10-29

申请人： Lawrence A. Ray ,  Richard N. Ellson

发明人： Lawrence A. Ray ,  Richard N. Ellson

IPC分类号： H04N7/26 ,  G06T9/00 ,  G07C9/00 ,  H03M7/30 ,  H04N1/41 ,  H04N1/387 ,  G06K9/00 ,  H04N1/00 ,  H04N7/18

CPC分类号： G07C9/00071 ,  G06T9/008

摘要： A technique involving the standardization of the subject matter of an image and the compression of the image using features of the standardization can provide for a high compression ratio. This technique can be used to improve the quality of a restored image for a predetermined amount of storage space.

摘要翻译： 涉及图像标题化和使用标准化特征压缩图像的技术可提供高压缩率。 该技术可以用于提高恢复的图像的质量以达到预定量的存储空间。

公开(公告)号：US5436970A

公开(公告)日：1995-07-25

申请号：US142781

申请日：1993-10-26

申请人： Lawrence A. Ray ,  Richard N. Ellson

发明人： Lawrence A. Ray ,  Richard N. Ellson

IPC分类号： G06Q20/34 ,  G06Q20/36 ,  G06Q20/40 ,  G07C9/00 ,  G07F7/10 ,  H04K1/00 ,  H04L9/00

CPC分类号： G07F7/1008 ,  G06Q20/341 ,  G06Q20/3674 ,  G06Q20/40145 ,  G07C9/00079 ,  G07F7/10

摘要： Techniques for multiple verification of transaction cards incorporating digital image information and authorization data onto a transaction card to assist in the card verification process. This technique requires the authorized card holder to have a picture identification accompany the application for the card. Picture information is converted to a digital image that is stored and used in one or a plurality of means for verifying that the presenter of the card, at the point of the transaction, is the authorized user. Such means include visual comparison of card presenter and extracted digital image information and verification that the data has not been altered. Encryption of the data, as it is read from the card, at the point of origin is used to formulate encoded authorization data that is then compared against like encoded authorized card holder data stored at a centrally located data base.

摘要翻译： 将数字图像信息和授权数据合并到交易卡上以便协助卡验证过程的交易卡的多次验证技术。 这种技术要求授权持卡人在卡片的应用程序中附上图片标识。 图像信息被转换为以一种或多种装置存储和使用的数字图像，用于验证在交易点处卡的呈现者是授权用户。 这样的方法包括卡片呈现者的视觉比较和提取的数字图像信息，以及数据未被改变的验证。 数据在从原始位置读取时的加密用于制定编码的授权数据，然后与存储在位于中心位置的数据库中的相同编码的授权持卡人数据进行比较。