-
公开(公告)号：US20090046931A1
公开(公告)日：2009-02-19
申请号：US11891781
申请日：2007-08-13
申请人： Jing Xiao , Anoop K. Bhattacharjya
发明人： Jing Xiao , Anoop K. Bhattacharjya
IPC分类号： G06K9/34
CPC分类号： G06K9/38 , G06K2209/01 , G06T7/11 , G06T7/194 , G06T2207/30176
摘要： Disclosed are embodiments of systems and methods for segmenting an image into at least two layers, a foreground and a background layer. An embodiment of the present invention includes rough labeling or segmenting at least a portion of the image into foreground and background pixels. The rough labeled pixels may be refined by using local classifications. In embodiments, additional processes may be performed on the image including, but not limited to, filtering, image enhancing, shape refining, image compression, etc.
摘要翻译： 公开了用于将图像分割成至少两个层，前景和背景层的系统和方法的实施例。 本发明的实施例包括将图像的至少一部分粗略标记或分割成前景和背景像素。 可以通过使用本地分类来改进粗略标记的像素。 在实施例中，可以对图像执行附加处理，包括但不限于过滤图像增强，形状精炼，图像压缩等。
-
公开(公告)号：US20080056529A1
公开(公告)日：2008-03-06
申请号：US11470479
申请日：2006-09-06
IPC分类号： G06K9/00
CPC分类号： H04N1/32203 , G06T1/005 , G06T2201/0051 , G06T2201/0061 , H04N1/32208 , H04N1/32229 , H04N1/32256 , H04N2201/327
摘要： Systems and methods for embedding data into and/or extracting data from a digital signal, such as an image, are disclosed. Embodiments described herein utilize a set of detectable small-scale structures, or tokens, together with a large-scale layout, or modulation frames, with embedding sites for the tokens to embed the data. Embodiments for extracting the embedded data use position constraints of the modulation frames to assist in identifying the embedded tokens.
摘要翻译： 公开了用于将数据嵌入数字信号（例如图像）和/或从数字信号（例如图像）中提取数据的系统和方法。 本文描述的实施例利用一组可检测的小尺度结构或令牌，以及大规模布局或调制框架，其中嵌入用于令牌的站点以嵌入数据。 用于提取嵌入数据的实施例使用调制帧的位置约束来帮助识别嵌入的令牌。
-
公开(公告)号：US20070171382A1
公开(公告)日：2007-07-26
申请号：US11623016
申请日：2007-01-12
申请人： Kar-Han Tan , Jing Xiao , Anoop K. Bhattacharjya
发明人： Kar-Han Tan , Jing Xiao , Anoop K. Bhattacharjya
CPC分类号： G03B21/26 , H04N9/3185 , H04N9/3194 , H04N17/002
摘要： An image created by a first projector is recreated using a second projector by relating the two projectors to a common point of view, preferably as viewed from a camera. A first transport matrix T1 is captured to relate the first projector to the camera. A second transport matrix T2 is then capture to relate the second projector to the camera. To have a first image p1, as projected by the first projector, reproduced by the second projector, the second projector projects a distorted image defined as (T2−1)(T1)p1. The inverse of T2, as used in this equation is an estimation defined by first creating an intermediate matrix {hacek over (T)} of equal size as T2. If a column in T2 is denoted as Tr and a corresponding column in {hacek over (T)} is denoted as {hacek over (T)}r, then the construction and population of {hacek over (T)} is defined as {hacek over (T)}r=Tr/(∥Tr∥)2, and the inverse of T2 is estimated as the transpose of {hacek over (T)}.
摘要翻译： 使用第二投影仪重新创建由第一投影仪创建的图像，该两个投影仪优选地从照相机观察到将两个投影仪相关联到共同的观点。 捕获第一传送矩阵T 1> 1以将第一投影仪与相机相关联。 然后捕获第二传输矩阵T 2 2以将第二投影仪与照相机相关联。 为了具有由第二投影仪再现的由第一投影仪投影的第一图像p 1> 1，第二投影仪投影定义为（T <2> -1）（T 1）p 1 <1>。 在该等式中使用的T 2的倒数是通过首先创建中间矩阵{hacek over（T等于T T 2> T）而定义的估计，如果列 在T 2中表示为Tr，并且{hacek over（T表示为{hacek over（Tr，则{hacek over（T）定义为{hacek over （Tr = Tr /（∥Tr‖）2），并且T 2的倒数被估计为{hacek over（T）的转置。
-
公开(公告)号：US20070171381A1
公开(公告)日：2007-07-26
申请号：US11613129
申请日：2006-12-19
申请人： Kar-Han Tan , Jing Xiao , Anoop K. Bhattacharjya
发明人： Kar-Han Tan , Jing Xiao , Anoop K. Bhattacharjya
IPC分类号： G03B21/14
CPC分类号： G03B21/26 , H04N9/3185 , H04N9/3194 , H04N17/002
摘要： Application of dual photography is simplified by reducing the number of captured images needed to generate a light transport matrix T of (p×q) projection pixel array from (p×q) images to (p+q) images. Manipulation of the light transport matrix is also simplified by replacing the use of a matrix T with an index associating each projection pixel to only non-zero light transport values. By eliminating the use of zero-valued light transport coefficients, the memory and processing requirements for implementing dual photography are greatly reduced. This dual photography technique is applied to the calibration of projector-camera systems. A second method for calibrating projector-camera systems uses a known projection test pattern and a calibrated camera to associate projected markers on a real image to a captured image. Since the real location of the projected markers are determined by the camera, and the relative location of the markers on the test pattern is also known, the projector may be calibrated using homography techniques.
摘要翻译： 通过减少从（pxq）图像到（p + q）图像生成（pxq）投影像素阵列的光传输矩阵T所需的捕获图像的数量来简化双重照相的应用。 光传输矩阵的操纵也通过将每个投影像素仅与非零光传输值相关联的索引替换为矩阵T的使用来简化。 通过消除零值光传输系数的使用，实现双摄影的存储器和处理要求大大降低。 这种双摄影技术被应用于投影仪相机系统的校准。 用于校准投影仪相机系统的第二种方法使用已知的投影测试图案和校准的相机来将投影的标记物与真实图像相关联以捕捉图像。 由于投影标记的真实位置由相机确定，并且标记在测试图案上的相对位置也是已知的，所以可以使用单色技术来校准投影仪。
-
公开(公告)号：US07085015B2
公开(公告)日：2006-08-01
申请号：US10061573
申请日：2002-02-01
CPC分类号： G06T5/20 , H04N1/40075
摘要： Techniques for recovering an original image from its halftone version using information obtained from the dither matrix used to generate the halftone. The techniques involve determining a bounding region defined by (xmin, xmax) for each pixel location and color value, based on the information obtained from the dither matrix, and applying a low-pass filter to the halftone version as follows. For each pixel color, the post-low-pass-filtered value of that color is used, if the filtered value is greater than or equal to xmin and less than or equal to xmax, the xmin value is used, if the filtered value is less than xmin and the xmax value is used, if the filtered value is greater than xmax. Next, it is determined, for each pixel, whether its value for that color is to be used in an averaging process based on the distance between the bounding region of that pixel and neighborhood pixels' bounding regions.
摘要翻译： 使用从用于产生半色调的抖动矩阵获得的信息从其半色调版本恢复原始图像的技术。 这些技术涉及基于从抖动矩阵获得的信息来确定每个像素位置和颜色值由（x分钟，x最大）定义的边界区域，并应用 一个低通滤镜到半色调版本如下。 对于每个像素颜色，如果滤波值大于或等于x min min且小于或等于x max，则使用该颜色的低通滤波值 使用x分钟值，如果滤波值小于x分钟，并且使用x最大值 如果滤波值大于x最大值。 接下来，对于每个像素，基于该像素的边界区域和邻近像素的边界区域之间的距离，确定其在该颜色的值是否将用于平均处理。
-
公开(公告)号：US06456393B1
公开(公告)日：2002-09-24
申请号：US09136161
申请日：1998-08-18
IPC分类号： G06F312
CPC分类号： H04N1/32144 , H04N2201/0091 , H04N2201/3235 , H04N2201/3236 , H04N2201/327
摘要： A photocopier (10) scans a document and so modifies the resultant image as to embed in a resultant copy information that is visually imperceptible. To do so, it identifies regions (32, 33) that consist primarily of text-character parts. It embeds a message bitstream by selectively darkening the text pixels in such regions in accordance with the values of successive bits in the bitstream.
摘要翻译： 复印机（10）扫描文件，因此修改所得到的图像以嵌入视觉上不可察觉的结果副本信息。 为此，它识别主要由文本字符部分组成的区域（32,33）。 通过根据比特流中连续比特的值选择性地使这些区域中的文本像素变暗来嵌入消息比特流。
-
公开(公告)号：US06227725B1
公开(公告)日：2001-05-08
申请号：US09135871
申请日：1998-08-18
IPC分类号： G06K1502
CPC分类号： G06T5/004 , G06T5/20 , H04N1/40062 , H04N1/4092 , H04N1/4095
摘要： A scanner (12) of a photocopier system scans a document and generates output image signals that an image-processing circuit (14) processes in such a manner as to enhance text-region legibility, and a laser printer (16) generates the output copy in accordance with the resultant image. The image-processing circuitry (14) identifies dark, low-saturation pixels in the input image whose gradients are low but that border high-gradient pixels, and it sets these pixels to the blackest values, thus emphasizing text edges. With the remaining pixels, it reduces bright-region contrast, and this tends to suppress the visibility of text that has “bled through” from the document's reverse side or from documents disposed behind it.
摘要翻译： 复印机系统的扫描器（12）扫描文件并产生图像处理电路（14）以增强文本区域易读性的方式处理的输出图像信号，并且激光打印机（16）产生输出副本 根据所得图像。 图像处理电路（14）识别输入图像中的灰度较低，饱和度低的像素，其渐变低，但是边界高梯度像素，并且将这些像素设置为最黑的值，从而强调文本边缘。 对于剩余的像素，它可以减少亮度区域的对比度，这样可能会抑制从文档背面或从背后放置的文档中“流血”出来的文本的可见性。
-
38.发明授权
公开(公告)号：US6038340A
公开(公告)日：2000-03-14
申请号：US747069
申请日：1996-11-08
摘要： A system for detecting image black and white points for a digital image. The system includes image partitioning routines for partitioning a digital image into image blocks, a pixel counter for determining whether the image block contains sufficient black and white pixels to classify the block as having relatively black text on a relatively white background, block validity testing routines for determining whether the selected image block is valid by determining whether the number of relatively black pixels for the selected image block is greater than a predetermined black threshold and whether the number of relatively white pixels for the selected image block is greater than a predetermined white threshold, and pixel clustering routines for arranging the relatively black pixels of a valid block into black clusters and the relatively white pixels of a valid block into white clusters and for assigning one of the black cluster centroids based on a first predetermined set of rules as the image black point and one of the white cluster centroids based on a second predetermined set of rules as the image white point.
摘要翻译： 一种用于检测数字图像的黑白点的系统。 该系统包括用于将数字图像分割成图像块的图像分割程序，用于确定图像块是否包含足够的黑色和白色像素以将块分类为在相对白色背景上具有相对黑色文本的像素计数器，用于 通过确定所选择的图像块的相对黑色像素的数目是否大于预定的黑色阈值以及所选择的图像块的相对白色像素的数量是否大于预定的白色阈值来确定所选择的图像块是否有效， 以及用于将有效块的相对黑色像素布置成黑色群集并将有效块的相对白色像素布置成白色群集并基于第一预定规则集合分配黑色群集质心之一的像素聚类例程作为图像黑色 点和基于第二个的白色聚类中心之一 预定的规则集作为图像白点。
-
公开(公告)号：US5809213A
公开(公告)日：1998-09-15
申请号：US678884
申请日：1996-07-12
CPC分类号： H04N1/6033
摘要： A method and apparatus for automatic color correction is described. The method and apparatus implemented technique in which a nonlinear interpolation technique is applied to a relatively small number of measured sample values generated from color image patches to provide a color lookup table having a larger number of calibration values stored therein.
摘要翻译： 描述了用于自动色彩校正的方法和装置。 该方法和装置实现技术，其中非线性插值技术被应用于从彩色图像块生成的相对较少数量的测量样本值，以提供其中存储有更大数量的校准值的颜色查找表。
-
公开(公告)号：US08180167B2
公开(公告)日：2012-05-15
申请号：US12174513
申请日：2008-07-16
申请人： Anoop K. Bhattacharjya , Jing Xiao
发明人： Anoop K. Bhattacharjya , Jing Xiao
CPC分类号： G06K9/00241 , G06K9/00315 , G06T5/005 , G06T7/248 , G06T9/001 , G06T2207/10016 , G06T2207/30201 , H04N19/89
摘要： Disclosed are embodiments of systems and methods to use a model-based technique for image error recovery in data communication. A low-dimensional representation is constructed of an image that contains errors. A manifold comprising image representations and a statistical model of the manifold are used to correct the errors in the image.
摘要翻译： 公开了在数据通信中使用基于模型的图像错误恢复技术的系统和方法的实施例。 低维表示由包含错误的图像构成。 使用包括图像表示和歧管的统计模型的歧管来校正图像中的误差。
-
-
-
-
-
-
-
-
-
搜索结果
54 条记录 (耗时 0.031 秒)
