公开(公告)号：US20080187224A1

公开(公告)日：2008-08-07

申请号：US11670963

申请日：2007-02-03

申请人： Jin Wang ,  Jianfeng Li ,  Huaqui Zhang ,  Guogang Wang

发明人： Jin Wang ,  Jianfeng Li ,  Huaqui Zhang ,  Guogang Wang

IPC分类号： G06K9/46

CPC分类号： G06T11/60

摘要： A method is provided for cloning a facial feature template image into an original image including a face to form a new image. The method includes detecting the face and facial features in the original image, reducing the original and the template images, cloning the reduced template image into the reduced original image to form a new image, enlarging the new image, and displaying the enlarged new image. The method may use Poisson cloning where a resulting system of linear equations is solved by applying a Thomas algorithm to determine an initial solution and applying a Conjugate Gradient algorithm using the initial solution to determine a final solution to the system of linear equations.

摘要翻译： 提供了一种将面部特征模板图像克隆成包括脸部的原始图像以形成新图像的方法。 该方法包括检测原始图像中的面部和面部特征，减少原始图像和模板图像，将缩小的模板图像克隆到缩小的原始图像中，形成新图像，放大新图像，并显示放大的新图像。 该方法可以使用泊松克隆，其中通过应用Thomas算法来求解所得到的线性方程式的系统来确定初始解，并使用初始解来应用共轭梯度算法来确定线性方程组的最终解。

公开(公告)号：US07796787B2

公开(公告)日：2010-09-14

申请号：US11670963

申请日：2007-02-03

申请人： Jin Wang ,  Jianfeng Li ,  Huaqui Zhang ,  Guogang Wang

发明人： Jin Wang ,  Jianfeng Li ,  Huaqui Zhang ,  Guogang Wang

IPC分类号： G06K9/00

CPC分类号： G06T11/60

摘要： A method is provided for cloning a facial feature template image into an original image including a face to form a new image. The method includes detecting the face and facial features in the original image, reducing the original and the template images, cloning the reduced template image into the reduced original image to form a new image, enlarging the new image, and displaying the enlarged new image. The method may use Poisson cloning where a resulting system of linear equations is solved by applying a Thomas algorithm to determine an initial solution and applying a Conjugate Gradient algorithm using the initial solution to determine a final solution to the system of linear equations.

摘要翻译： 提供了一种将面部特征模板图像克隆成包括脸部的原始图像以形成新图像的方法。 该方法包括检测原始图像中的面部和面部特征，减少原始图像和模板图像，将缩小的模板图像克隆到缩小的原始图像中，形成新图像，放大新图像，并显示放大的新图像。 该方法可以使用泊松克隆，其中通过应用Thomas算法来求解所得到的线性方程式的系统来确定初始解，并使用初始解来应用共轭梯度算法来确定线性方程组的最终解。

公开(公告)号：US20120287115A1

公开(公告)日：2012-11-15

申请号：US13104030

申请日：2011-05-10

申请人： JunJie Ding ,  GuoGang Wang ,  Jin Wang

发明人： JunJie Ding ,  GuoGang Wang ,  Jin Wang

IPC分类号： G06T15/00

CPC分类号： G06T13/20 ,  G06T2200/24

摘要： A method for generating image frames includes setting a 3D display mode of the image frames, configuring at least one parameter of the image frames, and displaying the image frames according to the 3D display mode and the at least one parameter of the image frames. When an input command is received while displaying the image frames, the input command is determined to correspond to parameters of the image frames or not. If the input command does not correspond to parameters of image frames, the parameters of image frames are reconfigured according to the input command.

摘要翻译： 一种用于生成图像帧的方法包括设置图像帧的3D显示模式，配置图像帧的至少一个参数，以及根据3D显示模式和图像帧的至少一个参数显示图像帧。 当显示图像帧时接收到输入命令时，确定输入命令对应于图像帧的参数。 如果输入命令不符合图像帧的参数，则根据输入命令重新配置图像帧的参数。

公开(公告)号：US07953253B2

公开(公告)日：2011-05-31

申请号：US11323653

申请日：2005-12-31

申请人： Jiangen Cao ,  Shu Li ,  Guogang Wang ,  Jin Wang

发明人： Jiangen Cao ,  Shu Li ,  Guogang Wang ,  Jin Wang

IPC分类号： G06K9/00 ,  G06K9/56 ,  G06K9/36

CPC分类号： G06K9/00234 ,  G06K9/00248 ,  G06K9/00281 ,  G06K9/00604 ,  G06K9/4614

摘要： A method for detecting a facial area on a color image includes (a) placing a search window on the color image, (b) determining if a center pixel of the search window is a skin color pixel, indicating that the search window is a possible facial area candidate, (c) applying a 3-rectangle filter to the search window to determine if the search window is a possible facial area candidate, (d) applying a 4-rectangle filter to the search window to determine if the search window is a possible facial area candidate, (e) if steps (b), (c), (d) all determine that the search window is a possible facial area candidate, applying an AdaBoost filter to the search window to determine if the search window is a facial area candidate, and (f) if step (e) determines that the search window is a facial area candidate, saving the location of the search window.

摘要翻译： 用于检测彩色图像上的面部区域的方法包括（a）在彩色图像上放置搜索窗口，（b）确定搜索窗口的中心像素是皮肤颜色像素，指示搜索窗口是可能的 面部区域候选者，（c）将三矩形滤波器应用于搜索窗口以确定搜索窗口是否是可能的面部区域候选，（d）将四矩形滤波器应用于搜索窗口以确定搜索窗口是否为 可能的面部区域候选者，（e）如果步骤（b），（c），（d）都确定搜索窗口是可能的面部区域候选者，则将AdaBoost过滤器应用于搜索窗口以确定搜索窗口是否为 面部候选人，以及（f）如果步骤（e）确定搜索窗口是面部区域候选者，则保存搜索窗口的位置。

公开(公告)号：US20070154095A1

公开(公告)日：2007-07-05

申请号：US11323653

申请日：2005-12-31

申请人： Jiangen Cao ,  Shu Li ,  Guogang Wang ,  Jin Wang

发明人： Jiangen Cao ,  Shu Li ,  Guogang Wang ,  Jin Wang

IPC分类号： G06K9/46 ,  G06K9/34 ,  G06K9/00

CPC分类号： G06K9/00234 ,  G06K9/00248 ,  G06K9/00281 ,  G06K9/00604 ,  G06K9/4614

摘要： A method for detecting a facial area on a color image includes (a) placing a search window on the color image, (b) determining if a center pixel of the search window is a skin color pixel, indicating that the search window is a possible facial area candidate, (c) applying a 3-rectangle filter to the search window to determine if the search window is a possible facial area candidate, (d) applying a 4-rectangle filter to the search window to determine if the search window is a possible facial area candidate, (e) if steps (b), (c), (d) all determine that the search window is a possible facial area candidate, applying an AdaBoost filter to the search window to determine if the search window is a facial area candidate, and (f) if step (e) determines that the search window is a facial area candidate, saving the location of the search window.

摘要翻译： 用于检测彩色图像上的面部区域的方法包括（a）在彩色图像上放置搜索窗口，（b）确定搜索窗口的中心像素是皮肤颜色像素，指示搜索窗口是可能的 面部区域候选者，（c）将三矩形滤波器应用于搜索窗口以确定搜索窗口是否是可能的面部区域候选，（d）将四矩形滤波器应用于搜索窗口以确定搜索窗口是否为 可能的面部区域候选者，（e）如果步骤（b），（c），（d）都确定搜索窗口是可能的面部区域候选者，则将AdaBoost过滤器应用于搜索窗口以确定搜索窗口是否为 面部候选人，以及（f）如果步骤（e）确定搜索窗口是面部区域候选者，则保存搜索窗口的位置。

公开(公告)号：US08897490B2

公开(公告)日：2014-11-25

申请号：US13069401

申请日：2011-03-23

申请人： ZhiWei Zhang ,  JianFeng Li ,  Li Mei ,  Jin Wang

发明人： ZhiWei Zhang ,  JianFeng Li ,  Li Mei ,  Jin Wang

IPC分类号： G06K9/00 ,  G06F3/01

CPC分类号： G06F3/017

摘要： A vision-based user interface includes an image input unit for capturing frame images, an image processor for recognizing a posture in at least one of the captured frame images, and generating a recognized gesture according to the posture, and a control unit for generating a control command corresponding to the recognized gesture.

摘要翻译： 基于视觉的用户界面包括用于捕获帧图像的图像输入单元，用于识别所捕获的帧图像中的至少一个中的姿势并根据姿势生成识别的手势的图像处理器，以及用于生成 对应于识别的手势的控制命令。

公开(公告)号：US08731248B2

公开(公告)日：2014-05-20

申请号：US13397690

申请日：2012-02-16

申请人： JianFeng Li ,  Jin Wang

发明人： JianFeng Li ,  Jin Wang

IPC分类号： G06K9/00

CPC分类号： G06K9/00281 ,  G06K9/0061

摘要： A method of correcting an eye circle on an image with at least one eye visible and the eye circle being located beneath the eye includes defining a core area of the image for correction, the core area being located substantially below a position of the eye in the image. The method also defines a processing area being larger in area than the core area and including the core area, and defines a surrounding area as a remaining area of the processing area not being located within the core area. An average brightness of the core area is compared to an average brightness of the surrounding area. Then a smoothing process is performed to blend the core area with the surrounding area to correct the eye circle when the average brightness of the core area is greater than that of the surrounding area by more than a first threshold.

摘要翻译： 一种用至少一只眼睛可见的眼睛校正眼睛圈的方法，眼睛眼睛位于眼睛下方包括限定用于校正的图像的核心区域，该核心区域基本上位于眼睛的位置上 图片。 该方法还定义了比核心区域更大的处理区域并且包括核心区域，并且将周边区域定义为处于不位于核心区域内的处理区域的剩余区域。 核心区域的平均亮度与周围区域的平均亮度进行比较。 然后，当核心区域的平均亮度大于周围区域的平均亮度大于第一阈值时，执行平滑处理以将核心区域与周围区域相混合以校正眼睛圆圈。

公开(公告)号：US20120242566A1

公开(公告)日：2012-09-27

申请号：US13069401

申请日：2011-03-23

申请人： ZhiWei Zhang ,  JianFeng Li ,  Li Mei ,  Jin Wang

发明人： ZhiWei Zhang ,  JianFeng Li ,  Li Mei ,  Jin Wang

IPC分类号： G06F3/01

CPC分类号： G06F3/017

摘要： A vision-based user interface includes an image input unit for capturing frame images, an image processor for recognizing a posture in at least one of the captured frame images, and generating a recognized gesture according to the posture, and a control unit for generating a control command corresponding to the recognized gesture.

摘要翻译： 基于视觉的用户界面包括用于捕获帧图像的图像输入单元，用于识别所捕获的帧图像中的至少一个中的姿势并根据姿势生成识别的手势的图像处理器，以及用于生成 对应于识别的手势的控制命令。

公开(公告)号：US20130216154A1

公开(公告)日：2013-08-22

申请号：US13397690

申请日：2012-02-16

申请人： JianFeng Li ,  Jin Wang

发明人： JianFeng Li ,  Jin Wang

IPC分类号： G06K9/40

CPC分类号： G06K9/00281 ,  G06K9/0061

摘要： A method of correcting an eye circle on an image with at least one eye visible and the eye circle being located beneath the eye includes defining a core area of the image for correction, the core area being located substantially below a position of the eye in the image. The method also defines a processing area being larger in area than the core area and including the core area, and defines a surrounding area as a remaining area of the processing area not being located within the core area. An average brightness of the core area is compared to an average brightness of the surrounding area. Then a smoothing process is performed to blend the core area with the surrounding area to correct the eye circle when the average brightness of the core area is greater than that of the surrounding area by more than a first threshold.

摘要翻译： 一种用至少一只眼睛可见的眼睛校正眼睛圈的方法，眼睛眼睛位于眼睛下方包括限定用于校正的图像的核心区域，该核心区域基本上位于眼睛的位置上 图片。 该方法还定义了比核心区域更大的处理区域并且包括核心区域，并且将周边区域定义为处于不位于核心区域内的处理区域的剩余区域。 核心区域的平均亮度与周围区域的平均亮度进行比较。 然后，当核心区域的平均亮度大于周围区域的平均亮度大于第一阈值时，执行平滑处理以将核心区域与周围区域相混合以校正眼睛圆圈。

公开(公告)号：US20130170766A1

公开(公告)日：2013-07-04

申请号：US13338265

申请日：2011-12-28

申请人： HeHuan Xu ,  JianFeng Li ,  Jin Wang

发明人： HeHuan Xu ,  JianFeng Li ,  Jin Wang

IPC分类号： G06K9/42

CPC分类号： G06K9/6202 ,  G06T11/00

摘要： A method of performing eyebrow shaping on an image containing a face with eyebrows visible on the face includes loading the image into a computing device having a processor. The processor selects a mask from a predefined list of masks, the mask having a desired eyebrow shape to be used for shaping the eyebrows shown in the image. The processor then adjusts the mask according to a shape of the face to produce an adjusted mask. Next the processor simultaneously superimposes the adjusted mask over the eyebrows and thins the eyebrows by changing an overall vertical height of the eyebrows in order to produce shaped eyebrows. The processor then outputs an enhanced image having the shaped eyebrows.