公开(公告)号：US08655109B2

公开(公告)日：2014-02-18

申请号：US13565334

申请日：2012-08-02

Applicant: Zhe Lin ,  Scott D. Cohen ,  Jen-Chan Chien ,  Sarah A. Kong ,  Jianchao Yang

Inventor： Zhe Lin ,  Scott D. Cohen ,  Jen-Chan Chien ,  Sarah A. Kong ,  Jianchao Yang

IPC: G06K9/32 ,  G06K9/00

CPC classification number: G06T3/4053

Abstract: Methods and systems for a regression-based learning model in image upscaling are disclosed. In one embodiment, a set of image patch pairs for each of a set of images is generated. Each of the image patch pairs contains a natural image and a corresponding downscaled lower-resolution image. A regression model based at least in part on the set of image patch pairs is defined. The regression model represents a gradient of a function of the downscaled lower-resolution image. An image is upscaled based at least in part on the regression model.

Abstract translation: 公开了一种基于回归的学习模型在图像放大中的方法和系统。 在一个实施例中，生成用于一组图像中的每一个的一组图像补丁对。 每个图像补丁对包含自然图像和对应的缩小的较低分辨率图像。 定义了至少部分基于图像补丁对集合的回归模型。 回归模型表示缩小的较低分辨率图像的函数的梯度。 至少部分基于回归模型，图像被放大。

公开(公告)号：US20140023291A1

公开(公告)日：2014-01-23

申请号：US13551439

申请日：2012-07-17

Applicant: Zhe Lin

Inventor： Zhe Lin

IPC: G06K9/64

CPC classification number: G06T5/003 ,  G06T2207/20012 ,  G06T2207/20016

Abstract: Various embodiments of methods and apparatus for image deblurring and sharpening using local patch self-similarity are disclosed. In some embodiments, an input blurred image is down-sampled to generate a downsized image. The downsized image is convolved with a blur kernel to obtain a smoothed image. For each of a plurality of patches of the input blurred image, a corresponding patch in the smoothed image is found. High frequency components between each of the plurality of corresponding patches in the smoothed image and corresponding patches of the downsized image are computed. The high frequency components are applied to the plurality of patches of the input blurred images to generate a deblurred version of the input blurred image.

Abstract translation: 公开了使用局部斑块自相似性的图像去模糊和锐化的方法和装置的各种实施例。 在一些实施例中，对输入模糊图像进行下采样以产生小尺寸图像。 缩小的图像与模糊内核卷积以获得平滑的图像。 对于输入的模糊图像的多个斑块中的每一个，找到平滑图像中的相应补丁。 计算平滑化图像中的多个相应补丁中的每一个之间的高频分量以及小尺寸图像的相应补丁。 将高频分量应用于输入模糊图像的多个斑块，以产生输入模糊图像的去模糊版本。

公开(公告)号：US20130132377A1

公开(公告)日：2013-05-23

申请号：US12869460

申请日：2010-08-26

Applicant: Zhe Lin ,  Jonathan W. Brandt

Inventor： Zhe Lin ,  Jonathan W. Brandt

IPC: G06F17/30

CPC classification number: G06F16/583

Abstract: Methods and systems for performing fast, large-scale, localized Bag-of-Features (Local BoF) retrieval are disclosed. In some embodiments, a method may include receiving a query image and ranking each image of a large set of database images as a function of its similarity to the query image with a Local BoF operation. A Local BoF operation may be configured to localize, for each ranked image, a region that has a highest similarity to the query image. As such, the systems and methods described herein may be suitable for use in large-scale image search and retrieval or categorization operations that may identify objects of interest with arbitrary rotations, significantly different viewpoints, in the presence of clutter. In some embodiments, systems and methods described herein may be used as building blocks of various computer vision and image processing applications including, for example, object recognition and categorization, 3D modeling, mapping, navigation, gesture interfaces, etc.

Abstract translation: 公开了用于执行快速，大规模，局部的特征（本地BoF）检索的方法和系统。 在一些实施例中，一种方法可以包括接收查询图像，并且根据其与具有本地BoF操作的查询图像的相似性对数据库图像的大量图像进行排序。 本地BoF操作可以被配置为对于每个排名的图像来定位与查询图像具有最高相似性的区域。 因此，本文描述的系统和方法可适用于在存在杂波的情况下可用于识别具有任意旋转，显着不同的视点的感兴趣对象的大规模图像搜索和检索或分类操作。 在一些实施例中，本文描述的系统和方法可以用作各种计算机视觉和图像处理应用的构建块，包括例如对象识别和分类，3D建模，映射，导航，手势界面等。

公开(公告)号：US20130044958A1

公开(公告)日：2013-02-21

申请号：US13563556

申请日：2012-07-31

Applicant: Jonathan W. Brandt ,  Zhe Lin ,  Vuong Le

Inventor： Jonathan W. Brandt ,  Zhe Lin ,  Vuong Le

IPC: G06K9/62 ,  G06K9/46

CPC classification number: G06K9/00248 ,  G06T5/005

Abstract: Various embodiments of methods and apparatus for facial retouching are disclosed. In one embodiment, a face in an input image is detected. One or more transformation parameters for the detected face are estimated based on a profile model. The profile model is applied to obtain a set of feature points for each facial component of the detected face. Global and component-based shape models are applied to generate feature point locations of each facial component of the detected face.

Abstract translation: 公开了用于面部修饰的方法和装置的各种实施例。 在一个实施例中，检测输入图像中的脸部。 基于轮廓模型估计检测到的面部的一个或多个变换参数。 应用轮廓模型以获得检测到的面部的每个面部分量的一组特征点。 应用全局和基于组件的形状模型来生成检测到的面部的每个面部组件的特征点位置。

公开(公告)号：US20130034313A1

公开(公告)日：2013-02-07

申请号：US13565334

申请日：2012-08-02

Applicant: Zhe Lin ,  Scott D. Cohen ,  Jen-Chan Chien ,  Sarah A. Kong ,  Jianchao Yang

Inventor： Zhe Lin ,  Scott D. Cohen ,  Jen-Chan Chien ,  Sarah A. Kong ,  Jianchao Yang

IPC: G06K9/32

CPC classification number: G06T3/4053

Abstract: Methods and systems for a regression-based learning model in image upscaling are disclosed. In one embodiment, a set of image patch pairs for each of a set of images is generated. Each of the image patch pairs contains a natural image and a corresponding downscaled lower-resolution image. A regression model based at least in part on the set of image patch pairs is defined. The regression model represents a gradient of a function of the downscaled lower-resolution image. An image is upscaled based at least in part on the regression model.

Abstract translation: 公开了一种基于回归的学习模型在图像放大中的方法和系统。 在一个实施例中，生成用于一组图像中的每一个的一组图像补丁对。 每个图像补丁对包含自然图像和对应的缩小的较低分辨率图像。 定义了至少部分基于图像补丁对集合的回归模型。 回归模型表示缩小的较低分辨率图像的函数的梯度。 至少部分基于回归模型，图像被放大。

公开(公告)号：US20130034311A1

公开(公告)日：2013-02-07

申请号：US13565379

申请日：2012-08-02

Applicant: Zhe Lin ,  Scott D. Cohen ,  Jen-Chan Chien ,  Sarah A. Kong ,  Jianchao Yang

Inventor： Zhe Lin ,  Scott D. Cohen ,  Jen-Chan Chien ,  Sarah A. Kong ,  Jianchao Yang

IPC: G06K9/40

CPC classification number: G06T3/4053

Abstract: Methods and systems for denoising and artifact removal in image upscaling are disclosed. In one embodiment, a low frequency band image intermediate is obtained from an input image. An upsampled image intermediate is obtained from the input image by upsampling. A result image is estimated, based at least in part on the upsampled image intermediate, the low frequency band image intermediate, and the input image. The input image is of a smaller scale than the result image. The estimating the result image further includes eliminating from the result image noise that is present in the input image.

Abstract translation: 公开了在图像升高中去除和去除伪影的方法和系统。 在一个实施例中，从输入图像获得低频带图像中间体。 通过上采样从输入图像获得上采样图像中间值。 至少部分地基于上采样图像中间，低频带图像中间和输入图像来估计结果图像。 输入图像的尺寸小于结果图像。 估计结果图像还包括消除输入图像中存在的结果图像噪声。

公开(公告)号：US20100097365A1

公开(公告)日：2010-04-22

申请号：US12354844

申请日：2009-01-16

Applicant: Wen-Chen FANG ,  Chun-Chin Tseng ,  Wen-Zhe Lin ,  Pei-Chi Tsai

Inventor： Wen-Chen FANG ,  Chun-Chin Tseng ,  Wen-Zhe Lin ,  Pei-Chi Tsai

IPC: G09G5/00 ,  G09G3/36

CPC classification number: G09G3/3648 ,  G09G3/3696 ,  G09G2310/0245 ,  G09G2320/0257 ,  G09G2330/022 ,  G09G2330/027

Abstract: The present invention discloses a liquid crystal display device and a control method thereof. In the present invention, a clock controller detects an external clock signal and outputs a switching signal according to the external clock signal. According the information carried by the switching signal, a shutoff switching circuit controls a gamma voltage generator and a common voltage circuit to output voltages making a pixel electrode and a common electrode have a zero voltage difference. Thereby, the pixel charges are completely released after system shutoff, and the shutoff retained images are instantly eliminated.

Abstract translation: 本发明公开了一种液晶显示装置及其控制方法。 在本发明中，时钟控制器检测外部时钟信号，并根据外部时钟信号输出开关信号。 根据开关信号所携带的信息，切断开关电路控制伽马电压发生器和公共电压电路以输出使像素电极和公共电极具有零电压差的电压。 因此，在系统关闭之后，像素电荷被完全释放，并且立即消除关闭保持的图像。