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

US20050244052A1 Edge-sensitive denoising and color interpolation of digital images 有权
标题翻译：数字图像的边缘去噪和颜色插值
公开(公告)号：US20050244052A1
公开(公告)日：2005-11-03
申请号：US10835609
申请日：2004-04-29
申请人： Renato Keshet , Casey Miller , Benjamin Kimbell
发明人： Renato Keshet , Casey Miller , Benjamin Kimbell
IPC分类号： G06K9/00 , G06T3/40 , G06T5/00 , H04N5/228 , H04N9/07
CPC分类号： G06T3/4015 , G06T5/002 , G06T5/005 , G06T5/20 , G06T2207/10024 , G06T2207/20012 , G06T2207/20192 , H04N9/07
摘要： A method of processing a mosaic digital image includes simultaneously performing edge-sensitive denoising and color interpolation on a first color plane of the digital image. The interpolation fills in missing pixel information in the first color plane.
摘要翻译：一种处理马赛克数字图像的方法包括在数字图像的第一颜色平面上同时执行边缘敏感去噪和颜色插值。插值填充第一个颜色平面中丢失的像素信息。

2. 发明授权

US07418130B2 Edge-sensitive denoising and color interpolation of digital images 有权
标题翻译：数字图像的边缘去噪和颜色插值
公开(公告)号：US07418130B2
公开(公告)日：2008-08-26
申请号：US10835609
申请日：2004-04-29
申请人： Renato Keshet , Casey Miller , Benjamin D. Kimbell
发明人： Renato Keshet , Casey Miller , Benjamin D. Kimbell
IPC分类号： G06K9/00
CPC分类号： G06T3/4015 , G06T5/002 , G06T5/005 , G06T5/20 , G06T2207/10024 , G06T2207/20012 , G06T2207/20192 , H04N9/07
摘要： A method of processing a mosaic digital image includes simultaneously performing edge-sensitive denoising and color interpolation on a first color plane of the digital image. The interpolation fills in missing pixel information in the first color plane.
摘要翻译：一种处理马赛克数字图像的方法包括在数字图像的第一颜色平面上同时执行边缘敏感去噪和颜色插值。插值填充第一个颜色平面中丢失的像素信息。

3. 发明申请

US20120029880A1 METHOD AND SYSTEM FOR DETERMINING A SPECTRAL VECTOR FROM MEASURED ELECTRO-MAGNETIC-RADIAION INTENSITIES 审中-公开
标题翻译：从测量的电磁辐射强度确定光谱矢量的方法和系统
公开(公告)号：US20120029880A1
公开(公告)日：2012-02-02
申请号：US13147363
申请日：2009-01-30
申请人： Michal Aharon , Doron Shaked , Renato Keshet
发明人： Michal Aharon , Doron Shaked , Renato Keshet
IPC分类号： G06F15/00
CPC分类号： G01R29/0892 , G01J3/465 , G01J2003/467 , H04N1/6088
摘要： Embodiments of the present invention are directed to determining the spectral vector of electromagnetic radiation reflected from, transmitted through, or emitted from a sample using a set of n intensity measurements. In general, the spectral vector has a dimension k that is greater than the number of measured intensities n. However, in many cases, the physical and chemical constraints of a system, when properly identified and modeled, effectively reduce the number of unknowns, generally the k components of the spectral vector, to an extent that allows for the spectral vector to be characterized from a relatively small number n of measured intensities.
摘要翻译：本发明的实施例涉及使用一组n个强度测量来确定从样品反射，透射或从样品发射的电磁辐射的光谱向量。通常，光谱矢量的尺寸k大于测量的强度n的数量。然而，在许多情况下，系统的物理和化学约束在适当地识别和建模时有效地将未知数（通常是频谱矢量的k分量）的数量有效地减少到允许频谱向量的特征相对较小的n个测量的强度。

4. 发明申请

US20050025380A1 Digital image processing methods, digital image devices, and articles of manufacture 有权
标题翻译：数字图像处理方法，数字图像装置和制品
公开(公告)号：US20050025380A1
公开(公告)日：2005-02-03
申请号：US10632292
申请日：2003-07-31
申请人： Renato Keshet , Ron Maurer , Robert Sobol , Christopher Whitman
发明人： Renato Keshet , Ron Maurer , Robert Sobol , Christopher Whitman
IPC分类号： G06K9/00 , G06K9/40 , G06T3/40 , G06T5/00
CPC分类号： G06K9/00127 , G06T3/4015 , G06T5/002 , G06T5/003 , G06T5/20 , G06T2207/20012 , G06T2207/20028 , G06T2207/20192
摘要： Digital image processing methods, digital image devices and articles of manufacture are described. According to one aspect, a digital image processing method includes providing digital image data of a plurality of colors of an image, wherein the image data comprises a plurality of sets individually comprising mosaic data of one of a plurality of colors at a plurality of pixel locations, analyzing image data of one of the pixel locations with respect to image data of another of the pixel locations, and adjusting the image data of the one pixel location responsive to the analyzing, wherein the adjusting comprises adjusting to one of denoise the image data and sharpen the image data.
摘要翻译：描述了数字图像处理方法，数字图像装置和制造物品。根据一个方面，一种数字图像处理方法包括提供图像的多种颜色的数字图像数据，其中图像数据包括多个集合，该多个集合分别包括多个像素位置处的多种颜色之一的马赛克数据分析相对于另一个像素位置的图像数据的像素位置之一的图像数据，以及响应于分析来调整所述一个像素位置的图像数据，其中所述调整包括调整为去除所述图像数据和锐化图像数据。

5. 发明申请

US20120121179A1 UNIFIED SPATIAL IMAGE PROCESSING 有权
标题翻译：统一的空间图像处理
公开(公告)号：US20120121179A1
公开(公告)日：2012-05-17
申请号：US13231411
申请日：2011-09-13
申请人： Renato Keshet , Pavel Kisilev , Mani Fischer , Doron Shaked , Boris Oicherman
发明人： Renato Keshet , Pavel Kisilev , Mani Fischer , Doron Shaked , Boris Oicherman
IPC分类号： G06K9/40
CPC分类号： G06T5/003 , G06T5/002 , G06T5/007 , G06T2207/20016
摘要： A method for enhancing an input image to produce an enhanced output image is provided. The method includes constructing a photographic-mask intermediate image without low-contrast details and a temporary-image intermediate image with enhanced mid-contrast details, retained high-contrast details, and reduced low-contrast details, and employing values for the photographic-mask intermediate image and temporary-image intermediate image to produce the enhanced output image that is globally and locally contrast-enhanced, sharpened, and denoised.
摘要翻译：提供了一种用于增强输入图像以产生增强的输出图像的方法。该方法包括构造没有低对比度细节的照相掩模中间图像和具有增强的中间对比度细节的临时图像中间图像，保留的高对比度细节和降低的低对比度细节，以及采用摄影掩模的值中间图像和临时图像中间图像，以产生全局和局部对比度增强，锐化和去噪的增强输出图像。

6. 发明申请

US20120070101A1 ESTIMATING 3D STRUCTURE FROM A 2D IMAGE 失效
标题翻译：从2D图像估计3D结构
公开(公告)号：US20120070101A1
公开(公告)日：2012-03-22
申请号：US13259253
申请日：2009-12-16
申请人： Hadas Kogan , Ron Maurer , Renato Keshet
发明人： Hadas Kogan , Ron Maurer , Renato Keshet
IPC分类号： G06K9/36
CPC分类号： G06T7/536 , G06T2207/20061 , G06T2207/20076
摘要： A method for estimating three-dimensional structure from a two-dimensional image (502) includes obtaining first and second vanishing points (120, 122); comparing image patches (202) along first and second virtual lines (204, 208) extending from the first and second vanishing points (120, 122), respectively, and through a pixel; generating values for each of the first and second virtual lines (204, 208) based on the comparison of the image patches (202); accumulating the values for each the pixel in the two-dimensional image (502); and determining a corner pixel (106) based on a highest of the accumulated values.
摘要翻译：一种用于从二维图像（502）估计三维结构的方法包括获得第一和第二消失点（120,122）; 沿着分别从第一和第二消失点（120,122）延伸并穿过像素的第一和第二虚拟线（204,208）比较图像贴片（202）基于所述图像块（202）的比较来生成所述第一和第二虚拟线（204,208）中的每一个的值; 累积二维图像中每个像素的值（502）; 以及基于累积值的最高值确定拐角像素（106）。

7. 发明授权

US07742660B2 Scale-space self-similarity image processing 有权
标题翻译：尺度空间自相似图像处理
公开(公告)号：US07742660B2
公开(公告)日：2010-06-22
申请号：US11096651
申请日：2005-03-31
申请人： Renato Keshet
发明人： Renato Keshet
IPC分类号： G06K9/32 , G06K9/40
CPC分类号： G06K9/40 , G06T5/002 , G06T5/003 , G06T5/20
摘要： Image processing includes computing image ft from image fs, where images ft and fs are representations of a self-similar image at scales t and s in a scale-space, where t
摘要翻译：图像处理包括从图像fs计算图像ft，其中图像ft和fs是在尺度空间中的尺度t和s处的自相似图像的表示，其中t

8. 发明申请

US20090034870A1 Unified spatial image processing 审中-公开
标题翻译：统一空间图像处理
公开(公告)号：US20090034870A1
公开(公告)日：2009-02-05
申请号：US11888572
申请日：2007-07-31
申请人： Renato Keshet , Pavel Kisilev , Mani Fischer , Doron Shaked , Boris Oicherman
发明人： Renato Keshet , Pavel Kisilev , Mani Fischer , Doron Shaked , Boris Oicherman
IPC分类号： G06K9/40
CPC分类号： G06T5/001 , G06T2207/20016 , G06T2207/20028
摘要： Various embodiments of the present invention are directed to methods and systems for image processing that are unified in nature, carrying out many image-enhancement tasks together in a unified approach, rather than sequentially executing separately implemented, discrete image-enhancement tasks. In addition, the methods and systems of the present invention can apply image-enhancement to local, spatial regions of an image, rather than relying on global application of enhancement techniques that result in production of artifacts and distortions. In certain embodiments of the present invention, various different types of intermediate images are produced at each of a number of different scales from a received, input image. From these intermediate images, a photographic mask and temporary image are obtained, and the photographic mask and temporary image are then employed, along with a look-up table or function that receives values from the photographic mask and temporary image, to compute an enhanced, output image. In a described embodiment of the present invention, the intermediate images include low-pass, band-pass, photographic-mask, and temporary-image intermediate images computed at each of a number of different scales.
摘要翻译：本发明的各种实施例涉及用于图像处理的方法和系统，这些方法和系统本质上是统一的，以统一的方式一起执行许多图像增强任务，而不是顺序执行单独实现的离散图像增强任务。此外，本发明的方法和系统可以将图像增强应用于图像的局部，空间区域，而不是依赖于导致产生伪像和失真的增强技术的全局应用。在本发明的某些实施例中，在从接收的输入图像的多个不同尺度的每一个处产生各种不同类型的中间图像。从这些中间图像，获得摄影掩模和临时图像，然后使用摄影掩模和临时图像，以及从摄影掩模和临时图像接收值的查找表或功能，以计算增强的，输出图像。在本发明的一个描述的实施例中，中间图像包括在多个不同尺度的每一个处计算的低通，带通，照相掩模和临时图像中间图像。

9. 发明授权

US07289247B2 Method and system for utilizing a self-similarity technique to process an image 有权
标题翻译：利用自相似性技术处理图像的方法和系统
公开(公告)号：US07289247B2
公开(公告)日：2007-10-30
申请号：US10679884
申请日：2003-10-06
申请人： Renato Keshet
发明人： Renato Keshet
IPC分类号： G06K15/00 , G06K1/00
CPC分类号： G06T5/003 , G06T2207/10008
摘要： A method and system for utilizing a self-similarity technique to process an image is disclosed. In accordance with embodiments of the present invention, an image is processed utilizing an image processing technique based on a self-similarity assumption. Through the use of the method and apparatus in accordance with the present invention, imperfections that are present in a degraded image can be compensated for in a simple, fast and non-iterative fashion thereby resulting in a higher quality image. A first aspect of the present invention is a method for utilizing a self-similarity technique to process an image. The method includes obtaining a corrupted image, altering the corrupted image to obtain an altered image, determining a plurality of parameters of a parametric mapping operator for mapping the altered image into the corrupted image and utilizing the plurality of parameters to map the corrupted image into an output image.
摘要翻译：公开了一种利用自相似技术处理图像的方法和系统。根据本发明的实施例，使用基于自相似性假设的图像处理技术处理图像。通过使用根据本发明的方法和装置，可以以简单，快速和非迭代的方式补偿存在于退化图像中的缺陷，从而导致更高质量的图像。本发明的第一方面是利用自相似性技术来处理图像的方法。该方法包括获得损坏的图像，改变损坏的图像以获得改变的图像，确定用于将改变的图像映射到损坏的图像中的参数映射运算符的多个参数，并利用多个参数将损坏的图像映射到输出图像。

10. 发明申请

US20050244073A1 Polynomial approximation based image filter methods, systems, and machine-readable media 有权
标题翻译：基于多项式近似的图像滤波方法，系统和机器可读介质
公开(公告)号：US20050244073A1
公开(公告)日：2005-11-03
申请号：US10833435
申请日：2004-04-28
申请人： Renato Keshet
发明人： Renato Keshet
IPC分类号： G06K9/40
CPC分类号： G06T5/002 , G06T5/003 , G06T5/20 , G06T2207/20192
摘要： Polynomial approximation based image filter methods, systems, and machine-readable media are described. In one aspect, multiple n-order polynomial approximations to a value of a target pixel of an input image are computed from multiple respective sets of m values of pixels in a neighborhood of the target pixel, wherein n≧0 and m≧n+1. A respective approximation error is computed from each of the computed n-order polynomial approximations. A value of a pixel of an output image is computed from the target pixel value and the computed approximation errors.
摘要翻译：描述了基于多项式近似的图像滤波方法，系统和机器可读介质。在一个方面，从目标像素附近的像素的m个多个像素组中计算对输入图像的目标像素的值的多次n次多项式近似，其中n> = 0且m> = n +1。从计算出的n阶多项式近似计算各自的近似误差。根据目标像素值和计算出的近似误差计算输出图像的像素的值。

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