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

US08208043B2 Lens cleaning warning system and method 有权
标题翻译：镜头清洁警告系统及方法
公开(公告)号：US08208043B2
公开(公告)日：2012-06-26
申请号：US12118022
申请日：2008-05-09
申请人： Yining Deng , David Pope
发明人： Yining Deng , David Pope
IPC分类号： H04N5/217 , H04N9/68 , H04N5/222
CPC分类号： H04N5/3572 , G06T7/0002 , G06T7/13 , G06T2207/30168
摘要： Lens cleaning warning systems and methods. A system includes an image processing unit configured to analyze image data to determine whether the image data indicates lens flare and, if so, provide an indication to the user that the lens is contaminated.
摘要翻译：镜头清洁警告系统和方法。系统包括：图像处理单元，被配置为分析图像数据以确定图像数据是否指示透镜闪光，并且如果是，则向用户提供透镜被污染的指示。

2. 发明授权

US07212667B1 Color image processing method for indexing an image using a lattice structure 有权
标题翻译：彩色图像处理方法，用于使用格子结构索引图像
公开(公告)号：US07212667B1
公开(公告)日：2007-05-01
申请号：US09562077
申请日：2000-05-01
申请人： Hyun-doo Shin , Yang-lim Choi , Yining Deng , Bangalore S. Manjunath
发明人： Hyun-doo Shin , Yang-lim Choi , Yining Deng , Bangalore S. Manjunath
IPC分类号： G06K9/00
CPC分类号： H04N1/644 , G06F17/3025 , H04N5/4401
摘要： A color image processing method is provided. The color image processing method includes the step of: (a) indexing a color image by assigning representative colors of an image to a color space divided into a plurality of regions. The color image processing method may be applied to object-based image processing such as MPEG-7, and fast search and retrieval of multimedia content can be made.
摘要翻译：提供彩色图像处理方法。彩色图像处理方法包括以下步骤：（a）通过将图像的代表颜色分配给划分为多个区域的色彩空间来对彩色图像进行索引。彩色图像处理方法可以应用于诸如MPEG-7的基于对象的图像处理，并且可以进行多媒体内容的快速搜索和检索。

3. 发明申请

US20060187234A1 System and method for blending images 有权
标题翻译：用于混合图像的系统和方法
公开(公告)号：US20060187234A1
公开(公告)日：2006-08-24
申请号：US11060918
申请日：2005-02-18
申请人： Yining Deng , D. Silverstein
发明人： Yining Deng , D. Silverstein
IPC分类号： G09G5/02
CPC分类号： G06F3/1446 , G09G2300/026 , G09G2310/0232 , G09G2340/10 , G09G2360/16 , H04N5/2624
摘要： A method of blending a pair of images, each image comprising a plurality of pixels having an intensity. A blending edge is determined for each image, each blending edge comprising at least one group of pixels, with each pixel at a pixel position, and an average intensity of pixels of the blending edges is determined at each pixel position. The method includes determining a scaling factor based on a relationship between the average intensity and the intensity of the pixel of the at least one group of pixels of the blending edge at each pixel position of each image. A blending area is determined for each image, each blending area comprising at least one group of pixels having a pixel at each of the pixel positions. The intensity of the pixel at each pixel position of the at least one group of pixels of the blending area of each image is scaled with the corresponding scaling factor.
摘要翻译：一种混合一对图像的方法，每个图像包括具有强度的多个像素。为每个图像确定混合边缘，每个混合边缘包括至少一组像素，每个像素在像素位置处，并且在每个像素位置处确定混合边缘的平均像素强度。该方法包括基于每个图像的每个像素位置处的混合边缘的至少一组像素的像素的平均强度和强度之间的关系来确定缩放因子。为每个图像确定混合区域，每个混合区域包括在每个像素位置处具有像素的至少一组像素。每个图像的混合区域的至少一组像素的每个像素位置处的像素的强度用相应的缩放因子缩放。

4. 发明申请

US20060115182A1 System and method of intensity correction 审中-公开
标题翻译：系统和强度校正方法
公开(公告)号：US20060115182A1
公开(公告)日：2006-06-01
申请号：US11001228
申请日：2004-11-30
申请人： Yining Deng , D. Silverstein
发明人： Yining Deng , D. Silverstein
IPC分类号： G06K9/36
CPC分类号： G06T5/40 , G06T5/009 , G06T2200/32
摘要： A method of intensity correction of at least two frames, each frame comprising a sequence of at least two images, each image at a different image position in the sequence and each pair of adjacent images having an overlap region. The method includes selecting an image at a same image position in each frame as a reference image. A set of global intensity transformations is determined, one global intensity transformation for all pairs of adjacent images at corresponding pairs of adjacent images positions of all frames, wherein the global intensity transformations are relative to the reference images. Each global intensity transformation is applied to each pixel of one image at each corresponding pair of adjacent image positions.
摘要翻译：一种至少两帧的强度校正方法，每帧包括至少两幅图像的序列，该序列中不同图像位置处的每幅图像和每对相邻图像具有重叠区域。该方法包括在每帧中的相同图像位置选择图像作为参考图像。确定一组全局强度变换，对于所有帧的相邻相邻图像位置对的所有对相邻图像的一个全局强度变换，其中全局强度变换相对于参考图像。每个全局强度变换被应用于每个对应的一对相邻图像位置处的一个图像的每个像素。

5. 发明申请

US20050226531A1 System and method for blending images into a single image 有权
标题翻译：将图像混合成单个图像的系统和方法
公开(公告)号：US20050226531A1
公开(公告)日：2005-10-13
申请号：US10814302
申请日：2004-04-01
申请人： D. Silverstein , Yining Deng
发明人： D. Silverstein , Yining Deng
IPC分类号： G06K9/36
CPC分类号： G06T3/40 , G06T3/00 , G06T5/50
摘要： A method and system for blending images into a single image. Initially two images of a view are selected, wherein the images have overlapping content of the view. The images can differ from each other in such characteristics as time, camera location, camera settings, and lighting. The images are divided into strips along a common plane in a region of each image where the images overlap. A strip from each image is selected where the images are a close match. Pixel by pixel difference values between the two strips are calculated, and a cut line is determined where the differences between the two strips are minimized. Each image is cut along the corresponding cut line, and the cut images are blended together to form a single image of the view. The blended single image can be further processed by warping the image along the cut line to provide for a smoother fit between the two images.
摘要翻译：将图像混合成单个图像的方法和系统。最初选择视图的两个图像，其中图像具有视图的重叠内容。在时间，相机位置，相机设置和照明等特性中，图像可能彼此不同。在图像重叠的每个图像的区域中，图像沿共同平面分割成条带。选择每个图像的条带，其中图像是紧密匹配的。计算两个条带之间的像素差值，并且确定两条条之间的差异最小化的切割线。每个图像沿着相应的切割线切割，并且将切割的图像混合在一起以形成视图的单个图像。可以通过沿着切割线弯曲图像来进一步处理混合的单个图像，以提供两个图像之间更平滑的配合。

6. 发明授权

US09049396B2 Creating composite images based on image capture device poses corresponding to captured images 有权
标题翻译：基于图像捕获设备创建合成图像对应于捕获的图像
公开(公告)号：US09049396B2
公开(公告)日：2015-06-02
申请号：US10954112
申请日：2004-09-29
申请人： D. Amnon Silverstein , Yining Deng
发明人： D. Amnon Silverstein , Yining Deng
IPC分类号： H04N1/46 , H04N1/387 , G06T3/00 , G06T3/40
CPC分类号： H04N1/3876 , G06T3/005 , G06T3/4038
摘要： An exemplary method for creating a composite image includes the steps of capturing a plurality of images with an image capture device which includes a sensor, determining an image capture device pose corresponding to each of the images based on data from the sensor, transforming each of the images based on its corresponding pose, projecting the transformed images to a common projection space, and combining the projected images to form a composite image.
摘要翻译：用于创建合成图像的示例性方法包括以下步骤：利用包括传感器的图像捕获装置捕获多个图像，基于来自传感器的数据确定与每个图像相对应的图像捕获装置姿势，基于其对应姿态的图像，将变换的图像投影到公共投影空间，以及组合投影图像以形成合成图像。

7. 发明授权

US07813589B2 System and method for blending images into a single image 有权
标题翻译：将图像混合成单个图像的系统和方法
公开(公告)号：US07813589B2
公开(公告)日：2010-10-12
申请号：US10814302
申请日：2004-04-01
申请人： D. Amnon Silverstein , Yining Deng
发明人： D. Amnon Silverstein , Yining Deng
IPC分类号： G06K9/36 , G09G5/00
CPC分类号： G06T3/40 , G06T3/00 , G06T5/50
摘要： A method and system for blending images into a single image. Initially two images of a view are selected, wherein the images have overlapping content of the view. The images can differ from each other in such characteristics as time, camera location, camera settings, and lighting. The images are divided into strips along a common plane in a region of each image where the images overlap. A strip from each image is selected where the images are a close match. Pixel by pixel difference values between the two strips are calculated, and a cut line is determined where the differences between the two strips are minimized. Each image is cut along the corresponding cut line, and the cut images are blended together to form a single image of the view. The blended single image can be further processed by warping the image along the cut line to provide for a smoother fit between the two images.
摘要翻译：将图像混合成单个图像的方法和系统。最初选择视图的两个图像，其中图像具有视图的重叠内容。在时间，相机位置，相机设置和照明等特性中，图像可能彼此不同。在图像重叠的每个图像的区域中，图像沿共同平面分割成条带。选择每个图像的条带，其中图像是紧密匹配的。计算两个条带之间的像素差值，并且确定两条条之间的差异最小化的切割线。每个图像沿着相应的切割线切割，并且将切割的图像混合在一起以形成视图的单个图像。可以通过沿着切割线弯曲图像来进一步处理混合的单个图像，以提供两个图像之间更平滑的配合。

8. 发明授权

US07450137B2 System and method for blending images 有权
标题翻译：用于混合图像的系统和方法
公开(公告)号：US07450137B2
公开(公告)日：2008-11-11
申请号：US11060918
申请日：2005-02-18
申请人： Yining Deng , D. Amnon Silverstein
发明人： Yining Deng , D. Amnon Silverstein
IPC分类号： G09G5/00
CPC分类号： G06F3/1446 , G09G2300/026 , G09G2310/0232 , G09G2340/10 , G09G2360/16 , H04N5/2624
摘要： A method of blending a pair of images, each image comprising a plurality of pixels having an intensity. A blending edge is determined for each image, each blending edge comprising at least one group of pixels, with each pixel at a pixel position, and an average intensity of pixels of the blending edges is determined at each pixel position. The method includes determining a scaling factor based on a relationship between the average intensity and the intensity of the pixel of the at least one group of pixels of the blending edge at each pixel position of each image. A blending area is determined for each image, each blending area comprising at least one group of pixels having a pixel at each of the pixel positions. The intensity of the pixel at each pixel position of the at least one group of pixels of the blending area of each image is scaled with the corresponding scaling factor.
摘要翻译：一种混合一对图像的方法，每个图像包括具有强度的多个像素。为每个图像确定混合边缘，每个混合边缘包括至少一组像素，每个像素在像素位置处，并且在每个像素位置处确定混合边缘的平均像素强度。该方法包括基于每个图像的每个像素位置处的混合边缘的至少一组像素的像素的平均强度和强度之间的关系来确定缩放因子。为每个图像确定混合区域，每个混合区域包括在每个像素位置处具有像素的至少一组像素。每个图像的混合区域的至少一组像素的每个像素位置处的像素的强度用相应的缩放因子缩放。

9. 发明授权

US06778697B1 Color image processing method and apparatus thereof 有权
标题翻译：彩色图像处理方法及其装置
公开(公告)号：US06778697B1
公开(公告)日：2004-08-17
申请号：US09497519
申请日：2000-02-04
申请人： Hyun-doo Shin , Yang-lim Choi , Yining Deng , Bangalore S. Manjunath
发明人： Hyun-doo Shin , Yang-lim Choi , Yining Deng , Bangalore S. Manjunath
IPC分类号： G06K900
CPC分类号： G06K9/4652 , G06F17/3025 , G06T7/90
摘要： A color image processing method for retrieving a color feature descriptor for describing color features of an image is provided. The color image processing method includes the steps of (a) obtaining color vectors of an input image, (b) classifying the color vectors to obtain dominant colors of the input image and the ratios thereof, and (c) representing the dominant colors and the ratios thereof as a color feature descriptor of the input image. The color image processing method is applied to an object-based image processing method, thereby allowing fast search and retrieval of multi-media contents.
摘要翻译：提供了一种用于检索用于描述图像的颜色特征的颜色特征描述符的彩色图像处理方法。彩色图像处理方法包括以下步骤：（a）获得输入图像的颜色矢量，（b）对颜色矢量进行分类以获得输入图像的主要颜色及其比例，以及（c）表示主色和作为输入图像的颜色特征描述符。彩色图像处理方法应用于基于对象的图像处理方法，从而允许快速搜索和检索多媒体内容。

10. 发明授权

US06580824B2 Classification of photos with sepia tones 失效
公开(公告)号：US06580824B2
公开(公告)日：2003-06-17
申请号：US09853652
申请日：2001-05-14
申请人： Yining Deng , Daniel Tretter
发明人： Yining Deng , Daniel Tretter
IPC分类号： G06K900
CPC分类号： G06K9/4652 , G06K9/00664 , G06T7/90 , G06T2207/10016 , G06T2207/20081 , H04N1/56
摘要： Methods and systems that classify sepia-toned digital images are described. An exemplary method includes converting RGB values of a digital image to hue saturation intensity (HSV) values. Pixels of the digital image that are not above a predetermined intensity or saturation threshold are removed from the image. The remaining pixels are analyzed and classified as sepia-toned images based on the results of the analysis. Additionally, a method for training a system to recognize sepia-toned images is disclosed.

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