公开(公告)号：US20100079448A1

公开(公告)日：2010-04-01

申请号：US12242592

申请日：2008-09-30

申请人： Liang-Gee Chen ,  Chao-Chung Cheng ,  Chung-Te Li ,  Ling-Hsiu Huang

发明人： Liang-Gee Chen ,  Chao-Chung Cheng ,  Chung-Te Li ,  Ling-Hsiu Huang

IPC分类号： G06T15/00 ,  G09G5/00

CPC分类号： G06T17/00 ,  G06T7/11 ,  G06T7/529

摘要： A system and method of generating three-dimensional (3D) depth information is disclosed. A classification and segmentation unit segments a two-dimensional (2D) image into a number of segments, such that pixels having similar characteristics are classified into the same segment. A spatial-domain texel density analysis unit performs texel density analysis on the 2D image to obtain textual density. A depth assignment unit assigns depth information to the 2D image according to the analyzed textual density.

摘要翻译： 公开了一种产生三维（3D）深度信息的系统和方法。 分类和分割单元将二维（2D）图像分割成多个段，使得具有相似特征的像素被分类成相同的段。 空间域纹素密度分析单元对2D图像执行纹理密度分析以获得文本密度。 深度分配单元根据分析的文本密度将深度信息分配给2D图像。

公开(公告)号：US08610758B2

公开(公告)日：2013-12-17

申请号：US12875158

申请日：2010-09-03

申请人： Chao-Chung Cheng ,  Chung-Te Li ,  Liang-Gee Chen ,  Ling-Hsiu Huang

发明人： Chao-Chung Cheng ,  Chung-Te Li ,  Liang-Gee Chen ,  Ling-Hsiu Huang

IPC分类号： H04N13/02

CPC分类号： H04N13/261 ,  H04N13/271

摘要： In accordance with at least some embodiments of the present disclosure, a process for generating a depth map for converting a two-dimensional (2D) image to a three-dimensional (3D) image is described. The process may include generating a depth gradient map from the 2D image, wherein the depth gradient map is configured to associate one or more edge counts with one or more depth values, extracting an image component from the 2D image, wherein the image component is associated with a color component in a color space, determining a set of gains to adjust the depth gradient map based on the image component, and generating the depth map by performing depth fusion based on the depth gradient map and the set of gains.

摘要翻译： 根据本公开的至少一些实施例，描述了用于生成用于将二维（2D）图像转换为三维（3D）图像的深度图的处理。 该过程可以包括从2D图像生成深度梯度图，其中深度梯度图被配置为将一个或多个边缘计数与一个或多个深度值相关联，从2D图像中提取图像分量，其中图像分量相关联 在颜色空间中具有颜色分量，基于图像分量确定一组增益以调整深度梯度图，并且基于深度梯度图和增益集执行深度融合来生成深度图。

公开(公告)号：US08059911B2

公开(公告)日：2011-11-15

申请号：US12242672

申请日：2008-09-30

申请人： Liang-Gee Chen ,  Chao-Chung Cheng ,  Chung-Te Li ,  Ling-Hsiu Huang

发明人： Liang-Gee Chen ,  Chao-Chung Cheng ,  Chung-Te Li ,  Ling-Hsiu Huang

IPC分类号： G06K9/40

CPC分类号： G06T5/003 ,  G06T5/008 ,  G06T5/20 ,  G06T5/40 ,  G06T7/50 ,  G06T2200/04 ,  G06T2207/20192

摘要： A depth-based image enhancement system is disclosed. A depth estimation unit generates three-dimensional (3D) depth information from a two-dimensional (2D) image. Subsequently, an image enhancement unit enhances the 2D image according to the 3D depth information.

摘要翻译： 公开了一种基于深度的图像增强系统。 深度估计单元从二维（2D）图像生成三维（3D）深度信息。 随后，图像增强单元根据3D深度信息增强2D图像。

公开(公告)号：US08050507B2

公开(公告)日：2011-11-01

申请号：US12242650

申请日：2008-09-30

申请人： Liang-Gee Chen ,  Chao-Chung Cheng ,  Chung-Te Li ,  Ling-Hsiu Huang

发明人： Liang-Gee Chen ,  Chao-Chung Cheng ,  Chung-Te Li ,  Ling-Hsiu Huang

IPC分类号： G06K9/40

CPC分类号： G06T7/529

摘要： A system of generating three-dimensional (3D) depth information is disclosed. A color and object independent local blurriness estimation unit analyzes blurriness of each pixel of a two-dimensional (2D) image. Subsequently, a depth assignment unit assigns depth information to the 2D image according to the analyzed blurriness.

摘要翻译： 公开了一种产生三维（3D）深度信息的系统。 颜色和对象独立的局部模糊估计单元分析二维（2D）图像的每个像素的模糊度。 随后，深度分配单元根据分析的模糊度将深度信息分配给2D图像。

公开(公告)号：US20100079453A1

公开(公告)日：2010-04-01

申请号：US12242567

申请日：2008-09-30

申请人： Liang-Gee Chen ,  Chao-Chung Cheng ,  Yi-Min Tsai ,  Ling-Hsiu Huang

发明人： Liang-Gee Chen ,  Chao-Chung Cheng ,  Yi-Min Tsai ,  Ling-Hsiu Huang

IPC分类号： G06T15/20

CPC分类号： G06T7/536

摘要： A system and method of generating three-dimensional (3D) depth information is disclosed. The vanishing point of a two-dimensional (2D) input image is detected based on vanishing lines. The 2D image is classified and segmented into structures based on detected edges. The classified structures are then respectively assigned depth information.

摘要翻译： 公开了一种产生三维（3D）深度信息的系统和方法。 基于消失线检测二维（2D）输入图像的消失点。 基于检测到的边缘，2D图像被分类和分割成结构。 分类结构分别被分配深度信息。

公开(公告)号：US08094163B2

公开(公告)日：2012-01-10

申请号：US12331359

申请日：2008-12-09

申请人： Homer H. Chen ,  Tai-Hsiang Huang ,  Su-Ling Yeh ,  San-Yuan Lin ,  Lin-Kai Bu ,  Ling-Hsiu Huang

发明人： Homer H. Chen ,  Tai-Hsiang Huang ,  Su-Ling Yeh ,  San-Yuan Lin ,  Lin-Kai Bu ,  Ling-Hsiu Huang

IPC分类号： G09G5/00 ,  H04N5/44 ,  H04N5/445 ,  H04N5/50 ,  H04N7/10 ,  G06K9/40 ,  G06F17/00

CPC分类号： H04N21/44012 ,  H04N21/23412 ,  H04N21/234318 ,  H04N21/8456

摘要： A method of directing a viewer's attention in an image display to enhance the perceived image quality and thus the viewer's preference of the image is disclosed. An image with an area of interest (AOI) is provided. The AOI is briefly displayed for a first time period. Subsequently, the image is normally displayed in its entirety for a second time period that is longer than the first time period. As a result, the viewer's attention is involuntarily directed to the AOI in a subliminal manner.

摘要翻译： 公开了一种将观众的注意力引导到图像显示器中以增强感知图像质量并因此提高观看者对图像的喜好的方法。 提供具有感兴趣区域（AOI）的图像。 AOI将在第一时间内简要显示。 随后，通常将图像整体显示为比第一时间段长的第二时间段。 结果，观众的注意力不经意地以潜意识的方式指向AOI。

公开(公告)号：US20090232411A1

公开(公告)日：2009-09-17

申请号：US12262157

申请日：2008-10-30

申请人： Homer H. Chen ,  Tai-Hsiang Huang ,  Ling-Hsiu Huang

发明人： Homer H. Chen ,  Tai-Hsiang Huang ,  Ling-Hsiu Huang

IPC分类号： G06K9/40

CPC分类号： G09G3/2007 ,  G09G2320/02 ,  G09G2320/0233 ,  G09G2320/0238 ,  G09G2320/0271 ,  G09G2320/062 ,  G09G2320/0626 ,  G09G2320/0646

摘要： A method for enhancing a perceptibility of an image, includes the steps of: processing the image in accordance with a first luminance characteristic and a second luminance characteristic of the image, wherein a plurality of pixels with the first luminance characteristic are brighter than a plurality of pixels with the second luminance characteristic; compressing the plurality of pixels with the first luminance characteristic; and adjusting the plurality of pixels with the second luminance characteristic.

摘要翻译： 一种用于增强图像感知度的方法包括以下步骤：根据图像的第一亮度特性和第二亮度特性处理图像，其中具有第一亮度特性的多个像素比多个 具有第二亮度特性的像素; 以所述第一亮度特征压缩所述多个像素; 以及用所述第二亮度特性来调整所述多个像素。

公开(公告)号：US08636361B2

公开(公告)日：2014-01-28

申请号：US13187287

申请日：2011-07-20

申请人： Homer H. Chen ,  Su-Ling Yeh ,  Tai-Hsiang Huang ,  Wen-Fu Lee ,  Ling-Hsiu Huang

发明人： Homer H. Chen ,  Su-Ling Yeh ,  Tai-Hsiang Huang ,  Wen-Fu Lee ,  Ling-Hsiu Huang

IPC分类号： A61B3/00 ,  A61H5/00 ,  A61B3/113

CPC分类号： A61H5/00 ,  A61B3/113 ,  G06K9/00604

摘要： A learning-based visual attention prediction method is disclosed. The method includes a correlation relationship between the fixation density and at least one feature information being learned by training, followed by a test video sequence of test frames being received. Afterward, at least one tested feature map is generated for each test frame based on the feature information. Finally, the tested feature map is mapped into a saliency map, which indicates the fixation strength of the corresponding test frame, according to the correlation relationship.

摘要翻译： 公开了一种基于学习的视觉注意预测方法。 该方法包括通过训练学习的至少一个特征信息之间的相关关系，随后接收测试帧的测试视频序列。 之后，基于特征信息为每个测试帧生成至少一个测试的特征图。 最后，根据相关关系，将测试的特征图映射到显着图中，显示相应测试帧的固定强度。

公开(公告)号：US20130021578A1

公开(公告)日：2013-01-24

申请号：US13187287

申请日：2011-07-20

申请人： Homer H. Chen ,  Su-Ling Yeh ,  Tai-Hsiang Huang ,  Wen-Fu Lee ,  Ling-Hsiu Huang

发明人： Homer H. Chen ,  Su-Ling Yeh ,  Tai-Hsiang Huang ,  Wen-Fu Lee ,  Ling-Hsiu Huang

IPC分类号： A61B3/113 ,  G06K9/62

CPC分类号： A61H5/00 ,  A61B3/113 ,  G06K9/00604

摘要： A learning-based visual attention prediction method is disclosed. The method includes a correlation relationship between the fixation density and at least one feature information being learned by training, followed by a test video sequence of test frames being received. Afterward, at least one tested feature map is generated for each test frame based on the feature information. Finally, the tested feature map is mapped into a saliency map, which indicates the fixation strength of the corresponding test frame, according to the correlation relationship.

摘要翻译： 公开了一种基于学习的视觉注意预测方法。 该方法包括通过训练学习的至少一个特征信息之间的相关关系，随后接收测试帧的测试视频序列。 之后，基于特征信息为每个测试帧生成至少一个测试的特征图。 最后，根据相关关系，将测试的特征图映射到显着图，该图显示相应测试帧的固定强度。

公开(公告)号：US08432491B2

公开(公告)日：2013-04-30

申请号：US13220533

申请日：2011-08-29

申请人： Homer H. Chen ,  Su-Ling Yeh ,  Tai-Hsiang Huang ,  Yung-Hao Yang ,  Hsin-I Liao ,  Ling-Hsiu Huang

发明人： Homer H. Chen ,  Su-Ling Yeh ,  Tai-Hsiang Huang ,  Yung-Hao Yang ,  Hsin-I Liao ,  Ling-Hsiu Huang

IPC分类号： H04N1/62

CPC分类号： H04N21/4402 ,  H04N21/23412 ,  H04N21/44008 ,  H04N21/45452 ,  H04N21/458

摘要： An object-based system and method of directing visual attention by a subliminal cue is disclosed. An object detector detects an object in an input image, thereby resulting in a cued object served as an object-based subliminal cue. An enhancement unit enhances saliency of the cued object in the input image by respectively and differently adjusting image characteristic of the cued object and an area other than the cued object, thereby generating a cue image. A mixer selects between the cue image and the input image, thereby resulting in a sequence of output images composed of the input images and the cue images, each of which is interposed between the adjacent input images.

摘要翻译： 公开了一种基于目标的系统和通过潜意识线索指导视觉注意力的方法。 对象检测器检测输入图像中的对象，从而导致被提取的对象被用作基于对象的潜意识提示。 增强单元通过分别和不同地调整提示对象的图像特性和除了被提取的对象之外的区域来增强输入图像中的被提取对象的显着性，从而生成提示图像。 混合器在提示图像和输入图像之间进行选择，从而产生由输入图像和提示图像组成的输出图像序列，每个输入图像和提示图像都插入相邻的输入图像之间。