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. 发明授权

US07873214B2 Unsupervised color image segmentation by dynamic color gradient thresholding 有权
标题翻译：通过动态颜色渐变阈值进行无监督的彩色图像分割
公开(公告)号：US07873214B2
公开(公告)日：2011-01-18
申请号：US11742306
申请日：2007-04-30
申请人： Mark Shaw , Ranjit Bhaskar , Guru Prashanth Balasubramanian , Eli Saber , Vladimir Misic , Eric Robert Peskin
发明人： Mark Shaw , Ranjit Bhaskar , Guru Prashanth Balasubramanian , Eli Saber , Vladimir Misic , Eric Robert Peskin
IPC分类号： G06K9/34
CPC分类号： G06K9/342 , G06K9/4652
摘要： A method for segmenting an image includes computing a color gradient map based on an inputted image and selecting at least one initial seed of at least one pixel based on the color gradient map. The method further includes growing a region of pixels adjacent to the initial seed and merging adjacent regions of pixels using a measure of similarity.
摘要翻译：用于分割图像的方法包括基于输入的图像计算颜色梯度图，并且基于颜色梯度图选择至少一个像素的至少一个初始种子。该方法还包括生长与初始种子相邻的像素区域，并使用相似度测量来合并像素的相邻区域。

2. 发明申请

US20080267498A1 UNSUPERVISED COLOR IMAGE SEGMENTATION BY DYNAMIC COLOR GRADIENT THRESHOLDING 有权
标题翻译：通过动态色彩梯度阈值进行不确定的彩色图像分割
公开(公告)号：US20080267498A1
公开(公告)日：2008-10-30
申请号：US11742306
申请日：2007-04-30
申请人： Mark Shaw , Ranjit Bhaskar , Guru Prashanth Balasubramanian , Eli Saber , Vladimir Misic , Eric Robert Peskin
发明人： Mark Shaw , Ranjit Bhaskar , Guru Prashanth Balasubramanian , Eli Saber , Vladimir Misic , Eric Robert Peskin
IPC分类号： G06K9/34
CPC分类号： G06K9/342 , G06K9/4652
摘要： A method for segmenting an image includes computing a color gradient map based on an inputted image and selecting at least one initial seed of at least one pixel based on the color gradient map. The method further includes growing a region of pixels adjacent to the initial seed and merging adjacent regions of pixels using a measure of similarity.
摘要翻译：用于分割图像的方法包括基于输入的图像计算颜色梯度图，并且基于颜色梯度图选择至少一个像素的至少一个初始种子。该方法还包括生长与初始种子相邻的像素区域，并使用相似度测量来合并像素的相邻区域。

3. 发明授权

US08515171B2 Methods for adaptive and progressive gradient-based multi-resolution color image segmentation and systems thereof 有权
标题翻译：用于自适应和渐进梯度的多分辨率彩色图像分割的方法及其系统
公开(公告)号：US08515171B2
公开(公告)日：2013-08-20
申请号：US12655933
申请日：2010-01-11
申请人： Sreenath Rao Vantaram , Eli Saber , Sohail Dianat , Mark Shaw , Ranjit Bhaskar
发明人： Sreenath Rao Vantaram , Eli Saber , Sohail Dianat , Mark Shaw , Ranjit Bhaskar
IPC分类号： G06K9/34 , G06K9/00 , G06K9/66
CPC分类号： G06T7/174 , G06T7/11 , G06T7/136 , G06T7/155 , G06T7/168 , G06T7/187 , G06T2207/10024 , G06T2207/20036 , G06T2207/20064
摘要： A multi-resolution color image segmentation algorithm which takes advantage of gradient information in an adaptive and progressive framework is described. A gradient-based segmentation method is initiated with a dyadic wavelet decomposition scheme of an arbitrary input image, accompanied by a vector gradient calculation of its color converted counterpart. The resultant gradient map is used to automatically and adaptively generate thresholds for segregating regions of varying gradient densities, at different resolution levels of the input image pyramid. In combination with a confidence map and non-linear spatial filtering techniques, regions of high confidence are passed from one resolution level to another until the final segmentation at highest (original) resolution is achieved.
摘要翻译：描述了利用自适应和渐进框架中的梯度信息的多分辨率彩色图像分割算法。基于梯度的分割方法由任意输入图像的二元小波分解方案启动，伴随着其颜色转换对应物的向量梯度计算。结果梯度图用于在输入图像金字塔的不同分辨率水平下自动和自适应地生成用于分离具有不同梯度密度的区域的阈值。结合置信图和非线性空间滤波技术，高信度的区域从一个分辨率级别传递到另一个分辨率级别，直到达到最高（原始）分辨率的最终分割。

4. 发明申请

US20090080773A1 Image segmentation using dynamic color gradient threshold, texture, and multimodal-merging 审中-公开
标题翻译：使用动态颜色渐变阈值，纹理和多模态合并的图像分割
公开(公告)号：US20090080773A1
公开(公告)日：2009-03-26
申请号：US11858826
申请日：2007-09-20
申请人： Mark Shaw , Ranjit Bhaskar , Luis Garcia Ugarriza , Eli Saber , Vincent Amuso
发明人： Mark Shaw , Ranjit Bhaskar , Luis Garcia Ugarriza , Eli Saber , Vincent Amuso
IPC分类号： G06K9/34
CPC分类号： G06T7/41 , G06T7/11 , G06T7/187 , G06T2207/10024
摘要： A method for segmenting an image receives the image. The image has a number of pixels and a number of color channels. The image is initially segmented into a number of initial regions at least by dynamically selecting a plurality of seeds within the image using a dynamic color gradient threshold and growing the initial regions from the seeds until the initial regions encompass all the pixels of the image. A texture channel of the image is generated at least by applying an entropy filter to each of a plurality of quantized colors of the image. The initial regions into which the image has been initially segmented are multimodal-merged based on the color channels and the texture channel of the image, to yield a number of merged regions corresponding to segmentation of the image.
摘要翻译：用于分割图像的方法接收图像。该图像具有多个像素和多个颜色通道。至少通过使用动态颜色梯度阈值动态地选择图像内的多个种子，并且从种子生长初始区域直到初始区域包含图像的所有像素，该图像最初被分割成多个初始区域。至少通过对图像的多个量化颜色中的每一个应用熵滤波来生成图像的纹理通道。图像初始分割到的初始区域是基于图像的颜色通道和纹理通道进行多模式合并的，以产生与图像分割对应的多个合并区域。

5. 发明申请

US20100183225A1 Methods for adaptive and progressive gradient-based multi-resolution color image segmentation and systems thereof 有权
标题翻译：用于自适应和渐进梯度的多分辨率彩色图像分割的方法及其系统
公开(公告)号：US20100183225A1
公开(公告)日：2010-07-22
申请号：US12655933
申请日：2010-01-11
申请人： Sreenath Rao Vantaram , Eli Saber , Sohail Dianat , Mark Shaw , Ranjit Bhaskar
发明人： Sreenath Rao Vantaram , Eli Saber , Sohail Dianat , Mark Shaw , Ranjit Bhaskar
IPC分类号： G06K9/34
CPC分类号： G06T7/174 , G06T7/11 , G06T7/136 , G06T7/155 , G06T7/168 , G06T7/187 , G06T2207/10024 , G06T2207/20036 , G06T2207/20064
摘要： A multi-resolution color image segmentation algorithm which takes advantage of gradient information in an adaptive and progressive framework is described. A gradient-based segmentation method is initiated with a dyadic wavelet decomposition scheme of an arbitrary input image, accompanied by a vector gradient calculation of its color converted counterpart. The resultant gradient map is used to automatically and adaptively generate thresholds for segregating regions of varying gradient densities, at different resolution levels of the input image pyramid. In combination with a confidence map and non-linear spatial filtering techniques, regions of high confidence are passed from one resolution level to another until the final segmentation at highest (original) resolution is achieved.
摘要翻译：描述了利用自适应和渐进框架中的梯度信息的多分辨率彩色图像分割算法。基于梯度的分割方法由任意输入图像的二元小波分解方案启动，伴随着其颜色转换对应物的向量梯度计算。结果梯度图用于在输入图像金字塔的不同分辨率水平下自动和自适应地生成用于分离具有不同梯度密度的区域的阈值。结合置信图和非线性空间滤波技术，高信度的区域从一个分辨率级别传递到另一个分辨率级别，直到达到最高（原始）分辨率的最终分割。

6. 发明授权

US07463385B2 Color map selection 有权
标题翻译：彩色地图选择
公开(公告)号：US07463385B2
公开(公告)日：2008-12-09
申请号：US11173010
申请日：2005-06-30
申请人： Jay S. Gondak , Je-Ho Lee , Ranjit Bhaskar
发明人： Jay S. Gondak , Je-Ho Lee , Ranjit Bhaskar
IPC分类号： G06K15/00
CPC分类号： G06K15/00 , H04N1/6022
摘要： Systems, devices, and methods performed by program instructions, are provided for color map selection. One method includes instructions which execute to generate a first color map from a set of colors. The instructions execute to generate a second color map from the set of colors and an additional color and to select a color value from between the first color map and the second color map dependent on a presence of the additional color.
摘要翻译：提供了程序指令执行的系统，设备和方法，用于选择颜色图。一种方法包括执行从一组颜色生成第一颜色图的指令。执行指令以从该组颜色和附加颜色生成第二颜色图，并且根据附加颜色的存在从第一颜色图和第二颜色图之间选择颜色值。

7. 发明授权

US06661533B1 Tone dependent variable halftoning with adjustable algorithm selection 有权
标题翻译：音调依赖变量半色调与可调整的算法选择
公开(公告)号：US06661533B1
公开(公告)日：2003-12-09
申请号：US09338847
申请日：1999-06-23
申请人： Ranjit Bhaskar , Kevin R. Hudson , Jay S Gondek
发明人： Ranjit Bhaskar , Kevin R. Hudson , Jay S Gondek
IPC分类号： G06R1500
CPC分类号： H04N1/52
摘要： Optimally determined halftoning algorithms are applied to tone values by selecting among combinations of at least two algorithms that best address the tradeoff between output quality and rendering performance. Input tone values are scrutinized and matched with the algorithm combination that processes the associated tone values in a manner that increases performance (including data compressibility) without sacrificing output quality. The selection process is computationally simple and fast. Reliability is ensured because the combinations of halftoning algorithms are tabulated as a result of analysis of test samples of the printed output.
摘要翻译：通过选择最佳地解决输出质量和渲染性能之间权衡的至少两种算法的组合，将最佳确定的半色调算法应用于色调值。输入音调值被仔细检查，并与以不影响输出质量的方式提高性能（包括数据压缩性）的方式处理相关音调值的算法组合相匹配。选择过程计算简单快捷。由于打印输出的测试样本的分析结果列出了半色调算法的组合，因此确保了可靠性。

8. 发明授权

US6002804A Tone dependent variable halftoning with adjustable algorithm selection 失效
公开(公告)号：US6002804A
公开(公告)日：1999-12-14
申请号：US48919
申请日：1998-03-26
申请人： Ranjit Bhaskar , Kevin R. Hudson , Jay S Gondek
发明人： Ranjit Bhaskar , Kevin R. Hudson , Jay S Gondek
IPC分类号： H04N1/52 , G06F15/00 , H04N1/46
CPC分类号： H04N1/52
摘要： Optimally determined halftoning algorithms are applied to tone values by selecting among combinations of at least two algorithms that best address the tradeoff between output quality and rendering performance. Input tone values are scrutinized and matched with the algorithm combination that processes the associated tone values in a manner that increases performance (including data compressibility) without sacrificing output quality. The selection process is computationally simple and fast. Reliability is ensured because the combinations of halftoning algorithms are tabulated as a result of analysis of test samples of the printed output.

9. 发明授权

US07034968B2 Color calibration chart 有权
公开(公告)号：US07034968B2
公开(公告)日：2006-04-25
申请号：US09943923
申请日：2001-08-31
申请人： Ranjit Bhaskar , Jay S Gondek , Thomas G Berge , Jefferson P Ward
发明人： Ranjit Bhaskar , Jay S Gondek , Thomas G Berge , Jefferson P Ward
IPC分类号： H04N1/46
CPC分类号： H04N1/00023 , H04N1/6033
摘要： A test page produced by ink pens for calibrating drop weights for at least a first and a second printheads, comprising: a page with an area for color swatches; a plurality of color swatches disposed in the area; and a predetermined substantially uniform color background disposed in said area between and around said plurality of color swatches. In a system embodiment of the present invention, a sensor may be used for sensing spectral data for each color swatch in a plurality of color swatches; and a component may be provided for comparing the sensed spectral data for each color swatch in a plurality of the color swatches to spectral data for the background color and selecting one of the plurality of color swatches which has spectral data which is closest to the background color for use in adjusting ink volume for at least one of the ink pens.

10. 发明授权

US06972868B1 Image data compression method 失效
标题翻译：图像数据压缩方法
公开(公告)号：US06972868B1
公开(公告)日：2005-12-06
申请号：US09710810
申请日：2000-11-09
申请人： Jay S. Gondek , Ranjit Bhaskar , Steven O. Miller
发明人： Jay S. Gondek , Ranjit Bhaskar , Steven O. Miller
IPC分类号： H04N7/26 , H03M7/46 , H04N1/41 , H04N1/415 , G06F15/00 , G06K9/46
CPC分类号： H04N1/41
摘要： A method of compressing a set of image data organized into a matrix of pixels includes selecting a multi-pixel block portion of the data, then performing a mathematical function on the multi-pixel block portion to generate a first result. The multi-pixel block portion is divided into at least two segments, and a function is performed on each of the segments to generate a second result and a third result. Based on a comparison of the first, second, and third results, determining whether or not to compress the multi-pixel block portion. The function may be a deviation or mean measurement and serve to determine the noise level and image detail level to determine whether to compress or divide the block into sub blocks. Sub blocks may be recursively analyzed for compression or subdivision until all sub blocks are compressed or divided into single pixels.
摘要翻译：压缩被组织成像素矩阵的一组图像数据的方法包括选择数据的多像素块部分，然后在多像素块部分上执行数学函数以产生第一结果。多像素块部分被划分为至少两个段，并且对每个段执行功能以产生第二结果和第三结果。基于第一，第二和第三结果的比较，确定是否压缩多像素块部分。该功能可以是偏差或平均测量，并且用于确定噪声水平和图像细节水平，以确定是否将块压缩或划分成子块。可以递归地分析子块以进行压缩或细分，直到所有子块被压缩或分成单个像素。

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