公开(公告)号：US07298379B2

公开(公告)日：2007-11-20

申请号：US11056372

申请日：2005-02-10

Applicant: Ning Xu ,  Yeong-Taeg Kim

Inventor： Ning Xu ,  Yeong-Taeg Kim

IPC: G06K9/00 ,  G06K9/38 ,  G09G5/02

CPC classification number: H04N9/67

Abstract: This invention presents a YUV to RGB conversion method which preserves high precision of luminance information in an original YUV image signal when converting it to RGB signal. The method can be used to convert the original YUV signal to arbitrary quantization levels in RGB space. In addition, this invention presents methods of pre-quantization and re-quantization as to compensate conventional YUV to RGB color conversion.

Abstract translation: 本发明提出了一种YUV至RGB转换方法，当将其转换为RGB信号时，其保持原始YUV图像信号中的亮度信息的高精度。 该方法可用于将原始YUV信号转换为RGB空间中的任意量化级别。 此外，本发明提出了用于补偿常规YUV到RGB颜色转换的预量化和重新量化的方法。

公开(公告)号：US20070127819A1

公开(公告)日：2007-06-07

申请号：US11398103

申请日：2006-04-04

Applicant: Sangkeun Lee ,  Ning Xu ,  Yeong-Taeg Kim

Inventor： Sangkeun Lee ,  Ning Xu ,  Yeong-Taeg Kim

IPC: G06K9/46 ,  G06K9/66 ,  G06K9/00 ,  G06K9/68

CPC classification number: G06K9/00711 ,  G06F17/3079 ,  G06T7/20

Abstract: A method and apparatus for detecting and locating objects of interest in video sequences is provided. A frame is defined as an image belonging to video sequences. Each frame with the same or different size of original input sequences is searched by the same or different size window efficiently for detecting objects. The characteristics of temporal redundancies in video sequences are used in detecting objects in video sequences.

Abstract translation: 提供了一种用于检测和定位视频序列中的感兴趣对象的方法和装置。 帧被定义为属于视频序列的图像。 具有相同或不同大小的原始输入序列的每个帧通过相同或不同的大小窗口被有效地搜索以用于检测对象。 视频序列中的时间冗余的特征用于检测视频序列中的对象。

公开(公告)号：US20070126884A1

公开(公告)日：2007-06-07

申请号：US11448961

申请日：2006-06-06

Applicant: Ning Xu ,  Sangkeun Lee ,  Yeong-Taeg Kim

Inventor： Ning Xu ,  Sangkeun Lee ,  Yeong-Taeg Kim

IPC: H04H9/00 ,  H04N5/225

CPC classification number: H04H60/45 ,  G06K9/00221 ,  H04N5/44 ,  H04N5/63 ,  H04N7/163 ,  H04N21/4223 ,  H04N21/433 ,  H04N21/44008 ,  H04N21/4415 ,  H04N21/4532 ,  Y02D70/168

Abstract: A digital system is provided that combines a digital video camera with television displays, and controlled by a controller module to enhance television performance according to personal television settings, parental controls and energy saving functions, achieved by utilizing the camera and face detection/recognition methods implemented in the controller module.

Abstract translation: 提供一种数字系统，其将数字摄像机与电视显示器组合，并且由控制器模块控制，以根据个人电视设置，家长控制和节能功能来提高电视性能，通过利用相机和面部检测/识别方法实现 在控制器模块中。

公开(公告)号：US20070098294A1

公开(公告)日：2007-05-03

申请号：US11264973

申请日：2005-11-01

Applicant: Ning Xu ,  Yeong-Taeg Kim

Inventor： Ning Xu ,  Yeong-Taeg Kim

IPC: G06K9/40

CPC classification number: H04N19/86 ,  H04N19/117 ,  H04N19/14 ,  H04N19/17 ,  H04N19/176 ,  H04N19/182

Abstract: An image processing method and system removes quantization artifacts in digital video/images. The local neighborhood of the current pixel is segmented based on a pre-defined quantization level to generate a segment containing the current pixel. Then, the luminance values of the pixels within the segment are low-pass filtered. Several sub-gains are computed based on measurements of the segment, and the sub-gains are multiplied together and filtered to obtain a final gain value. The final gain value is used to linearly interpolate between the original luminance value and the filtered luminance value of the pixel to obtain an output luminance value.

Abstract translation: 图像处理方法和系统消除数字视频/图像中的量化伪像。 基于预定义的量化级别对当前像素的局部邻域进行分段，以生成包含当前像素的段。 然后，片段内的像素的亮度值被低通滤波。 基于段的测量来计算几个子增益，并将子增益相乘并过滤以获得最终增益值。 最终增益值用于在原始亮度值和滤波后的像素亮度值之间线性插值，以获得输出亮度值。

公开(公告)号：US06882743B2

公开(公告)日：2005-04-19

申请号：US09998768

申请日：2001-11-29

Applicant: Ravi Bansal ,  Ning Xu

Inventor： Ravi Bansal ,  Ning Xu

IPC: G06T5/00 ,  G06K9/00

CPC classification number: G06T7/0012 ,  G06T7/12 ,  G06T7/143 ,  G06T7/149 ,  G06T2207/10081 ,  G06T2207/20101 ,  G06T2207/30064

Abstract: There is provided a method for automatically segmenting lung nodules in a three-dimensional (3D) Computed Tomography (CT) volume dataset. An input is received corresponding to a user-selected point near a boundary of a nodule. A model is constructed of the nodule from the user-selected point, the model being a deformable circle having a set of parameters β that represent a shape of the nodule. Continuous parts of the boundary and discontinuities of the boundary are estimated until the set of parameters β converges, using dynamic programming and Expectation Maximization (EM). The nodule is segmented, based on estimates of the continuous parts of the boundary and the discontinuities of the boundary.

Abstract translation: 提供了一种在三维（3D）计算机断层扫描（CT）体积数据集中自动分割肺结节的方法。 接收对应于结节边界附近的用户选择点的输入。 模型由用户选择的点的结节构成，模型是具有代表结节形状的一组参数β的可变形圆。 边界的连续部分和边界的不连续性被估计，直到参数集合β收敛，使用动态规划和期望最大化（EM）。 根据边界的连续部分和边界的不连续性的估计，结节被分割。