公开(公告)号：US08270715B2

公开(公告)日：2012-09-18

申请号：US12339723

申请日：2008-12-19

Applicant: Chung-Fang Chien ,  Che-Lun Chuang

Inventor： Chung-Fang Chien ,  Che-Lun Chuang

IPC: G06K9/00

CPC classification number: G06K9/0061

Abstract: A method for correcting red-eye is described. Through facial features, at least one facial region is obtained in an image, a nose position in each facial region is obtained by using a nose feature, and at least one eye position is obtained based on a relative position relation between the nose and the eyes. After a color gamut of the image is converted, a red region is obtained from the eye position, and a plurality of edges is formed by using a luminance of the color gamut on the image with the converted color gamut according to the eye feature, so as to exclude the red region out of the plurality of edges, thereby improving accuracy of the red region on the eye position. Then, the red region is covered by an iris color, so as to correct the red-eye.

Abstract translation: 描述了一种用于校正红眼的方法。 通过面部特征，在图像中获得至少一个面部区域，通过使用鼻部特征获得每个面部区域中的鼻部位置，并且基于鼻子和眼睛之间的相对位置关系获得至少一个眼睛位置 。 在图像的色域被转换后，从眼睛位置获得红色区域，并且通过使用根据眼睛特征的具有转换色域的图像上的色域的亮度来形成多个边缘，因此 以排除多个边缘之外的红色区域，从而提高眼睛位置上的红色区域的精度。 然后，红色区域被虹膜颜色覆盖，以便校正红眼。

公开(公告)号：US20090161951A1

公开(公告)日：2009-06-25

申请号：US12339723

申请日：2008-12-19

Applicant: Chung-Fang Chien ,  Che-Lun Chuang

Inventor： Chung-Fang Chien ,  Che-Lun Chuang

IPC: G06K9/00

CPC classification number: G06K9/0061

Abstract: A method for correcting red-eye is described. Through facial features, at least one facial region is obtained in an image, a nose position in each facial region is obtained by using a nose feature, and at least one eye position is obtained based on a relative position relation between the nose and the eyes. After a color gamut of the image is converted, a red region is obtained from the eye position, and a plurality of edges is formed by using a luminance of the color gamut on the image with the converted color gamut according to the eye feature, so as to exclude the red region out of the plurality of edges, thereby improving accuracy of the red region on the eye position. Then, the red region is covered by an iris color, so as to correct the red-eye.

Abstract translation: 描述了一种用于校正红眼的方法。 通过面部特征，在图像中获得至少一个面部区域，通过使用鼻部特征获得每个面部区域中的鼻部位置，并且基于鼻子和眼睛之间的相对位置关系获得至少一个眼睛位置 。 在图像的色域被转换后，从眼睛位置获得红色区域，并且通过使用根据眼睛特征的具有转换色域的图像上的色域的亮度来形成多个边缘，因此 以排除多个边缘之外的红色区域，从而提高眼睛位置上的红色区域的精度。 然后，红色区域被虹膜颜色覆盖，以便校正红眼。

公开(公告)号：US20120288215A1

公开(公告)日：2012-11-15

申请号：US13195851

申请日：2011-08-02

Applicant: Che-Lun Chuang ,  Chung-Ta Wu ,  Hong-Long Chou

Inventor： Che-Lun Chuang ,  Chung-Ta Wu ,  Hong-Long Chou

IPC: G06K9/36

CPC classification number: G06T3/40 ,  G06T7/136 ,  G06T7/231 ,  G06T2207/20221

Abstract: An image processing device and the processing method thereof are provided. The device includes an image correcting module, an object-motion detection module and an image blending module. The image correcting module estimates a plurality of local motions of the non-selected images relative to the target image and a plurality of global motions, and performs a plurality of motion corrections to generate a plurality of corrected images. The object-motion detection module judges whether or not the difference between each of the local motions and the corresponding global motion is greater than a threshold value to generate a plurality of object-motion indicators. The image blending module performs an arithmetic operation on each pixel of the target image and each pixel of the corrected images according to the object-motion indicators so as to generate a super-resolution image.

Abstract translation: 提供了图像处理装置及其处理方法。 该装置包括图像校正模块，物体运动检测模块和图像混合模块。 图像校正模块估计相对于目标图像和多个全局运动的未选择图像的多个局部运动，并且执行多个运动校正以生成多个校正图像。 对象运动检测模块判断每个局部运动和对应的全局运动之间的差是否大于阈值，以产生多个对象运动指示器。 图像混合模块根据对象运动指示器对目标图像的每个像素和校正图像的每个像素执行算术运算，以产生超分辨率图像。

公开(公告)号：US08711231B2

公开(公告)日：2014-04-29

申请号：US13198725

申请日：2011-08-05

Applicant: Che-Lun Chuang ,  Chung-Ta Wu ,  Hong-Long Chou

Inventor： Che-Lun Chuang ,  Chung-Ta Wu ,  Hong-Long Chou

IPC: H04N5/228

CPC classification number: G06T3/4053 ,  G06T7/269 ,  G06T2207/20201 ,  G06T2207/20221 ,  H04N5/2628

Abstract: A digital image processing device and processing method thereof are provided. The device includes a digital image capturing module, an image enlarging module, an image correcting module, and an image blending module. The digital image capturing module captures a plurality of first resolution images. The image enlarging module enlarges the first resolution images and produces a plurality of second resolution images. The image correcting module selects a target image and produces a plurality of corrected images. The image blending module performs direction gradient operation on each of the pixels of the target and corrected images and produces a plurality of gradient differential values. The image blending module performs a weighting sum operation on each of the pixels of the target and corrected images and produces a third resolution images.

Abstract translation: 提供了一种数字图像处理装置及其处理方法。 该装置包括数字图像捕获模块，图像放大模块，图像校正模块和图像混合模块。 数字图像捕获模块捕获多个第一分辨率图像。 图像放大模块放大第一分辨率图像并产生多个第二分辨率图像。 图像校正模块选择目标图像并产生多个校正图像。 图像混合模块对目标和校正图像的每个像素执行方向梯度操作，并产生多个梯度差分值。 图像混合模块对目标和校正图像的每个像素执行加权和运算，并产生第三分辨率图像。

公开(公告)号：US08467630B2

公开(公告)日：2013-06-18

申请号：US13195851

申请日：2011-08-02

Applicant: Che-Lun Chuang ,  Chung-Ta Wu ,  Hong-Long Chou

Inventor： Che-Lun Chuang ,  Chung-Ta Wu ,  Hong-Long Chou

IPC: G06K9/32 ,  G06K9/40

CPC classification number: G06T3/40 ,  G06T7/136 ,  G06T7/231 ,  G06T2207/20221

Abstract: An image processing device and the processing method thereof are provided. The device includes an image correcting module, an object-motion detection module and an image blending module. The image correcting module estimates a plurality of local motions of the non-selected images relative to the target image and a plurality of global motions, and performs a plurality of motion corrections to generate a plurality of corrected images. The object-motion detection module judges whether or not the difference between each of the local motions and the corresponding global motion is greater than a threshold value to generate a plurality of object-motion indicators. The image blending module performs an arithmetic operation on each pixel of the target image and each pixel of the corrected images according to the object-motion indicators so as to generate a super-resolution image.

Abstract translation: 提供了图像处理装置及其处理方法。 该装置包括图像校正模块，物体运动检测模块和图像混合模块。 图像校正模块估计相对于目标图像和多个全局运动的未选择图像的多个局部运动，并且执行多个运动校正以生成多个校正图像。 对象运动检测模块判断每个局部运动和对应的全局运动之间的差是否大于阈值以产生多个对象运动指示器。 图像混合模块根据对象运动指示器对目标图像的每个像素和校正图像的每个像素执行算术运算，以产生超分辨率图像。

公开(公告)号：US08235543B2

公开(公告)日：2012-08-07

申请号：US12472911

申请日：2009-05-27

Applicant: Che-Lun Chuang ,  Chung-Ta Wu

Inventor： Che-Lun Chuang ,  Chung-Ta Wu

IPC: G06K9/00

CPC classification number: H04N9/045 ,  H04N5/3572

Abstract: A compensation method for alleviating color shading in a digital image is adapted to correct a color shading phenomenon in a digital image that causes luminance differences between regions in the digital image. The compensation method includes capturing a uniform color block image; calculating horizontal compensation coefficients of a plurality of horizontal segments of the color block image; performing a linear interpolation process on the horizontal compensation coefficients to generate corresponding horizontal interpolation coefficients, and calculating determination horizontal correction coefficients corresponding to all the horizontal segments, respectively; calculating vertical compensation coefficients of a plurality of vertical segments; multiplying the determination horizontal correction coefficients by the vertical compensation coefficients, respectively, so as to obtain a color shading compensation coefficient of each segment, respectively; and multiplying an average luminance value of each segment by a corresponding color shading compensation coefficient, respectively, thus compensating for color shading in the color block image.

Abstract translation: 用于减轻数字图像中的着色的补偿方法适于校正导致数字图像中的区域之间的亮度差的数字图像中的着色现象​​。 补偿方法包括捕获均匀的彩色块图像; 计算所述彩色块图像的多个水平段的水平补偿系数; 对水平补偿系数进行线性插补处理，生成相应的水平内插系数，分别计算与所有水平段对应的确定水平校正系数; 计算多个垂直段的垂直补偿系数; 分别将确定水平校正系数乘以垂直补偿系数，以分别获得每个段的着色补偿系数; 并且分别将每个片段的平均亮度值乘以相应的色彩补偿系数，从而补偿色块图像中的色彩。

公开(公告)号：US20110158515A1

公开(公告)日：2011-06-30

申请号：US12767553

申请日：2010-04-26

Applicant: Che-Lun Chuang ,  Chung-Ta Wu

Inventor： Che-Lun Chuang ,  Chung-Ta Wu

IPC: G06K9/00

CPC classification number: H04N1/58

Abstract: A method for removing color fringe is presented. First, detection and correction of color fringe are performed on an original-size image and a small-size image respectively, so as to generate respective corrected images and corresponding color fringe maps. Then, the corrected small-size image and its corresponding color fringe map are enlarged to the same resolution as the original-size image. Finally, the two corrected images are blended according to the respective corresponding color fringe maps.

Abstract translation: 提出了一种去除颜色条纹的方法。 首先，分别对原稿尺寸图像和小尺寸图像执行彩色条纹的检测和校正，以便产生相应的校正图像和对应的颜色条纹图。 然后，校正后的小尺寸图像及其相应的颜色条纹图被放大到与原始尺寸图像相同的分辨率。 最后，根据各自对应的颜色条纹图来混合两个校正图像。

公开(公告)号：US20130176466A1

公开(公告)日：2013-07-11

申请号：US13414273

申请日：2012-03-07

Applicant: Che-Lun Chuang ,  Chung-Ta Wu ,  Hsin-Te Wang ,  Yi-Hsien Lin

Inventor： Che-Lun Chuang ,  Chung-Ta Wu ,  Hsin-Te Wang ,  Yi-Hsien Lin

IPC: H04N9/64

CPC classification number: H04N5/3595

Abstract: A device and a method for reducing a smear effect. The device comprises an image sensing module and a smear reduction module. The image sensing module captures an image and optical black data generated from the optical area of the image sensing module. The smear reduction module searches the optical black data generated in the lower boundary of the optical black area corresponding to which generated in the upper boundary of the optical black area according to coordinates of the optical black data. Thereby, the smear reduction module can compute an offset line representing an offset of the optical black data, and the smear reduction module compensates the smear effect occurring in the image.

Abstract translation: 一种减轻拖尾效应的装置和方法。 该装置包括图像感测模块和模糊减少模块。 图像感测模块捕获从图像感测模块的光学区域生成的图像和光学黑色数据。 减号模块根据光学黑色数据的坐标来搜索在光学黑色区域的上边界中生成的光学黑色区域的下边界中生成的光学黑色数据。 因此，拖尾模块可以计算表示光学黑色数据的偏移的偏移线，并且模糊减少模块补偿在图像中发生的拖影效应。

公开(公告)号：US20120287311A1

公开(公告)日：2012-11-15

申请号：US13198725

申请日：2011-08-05

Applicant: Che-Lun Chuang ,  Chung-Ta Wu ,  Hong-Long Chou

Inventor： Che-Lun Chuang ,  Chung-Ta Wu ,  Hong-Long Chou

IPC: H04N5/262

CPC classification number: G06T3/4053 ,  G06T7/269 ,  G06T2207/20201 ,  G06T2207/20221 ,  H04N5/2628

Abstract: A digital image processing device and processing method thereof are provided. The device includes a digital image capturing module, an image enlarging module, an image correcting module, and an image blending module. The digital image capturing module captures a plurality of first resolution images. The image enlarging module enlarges the first resolution images and produces a plurality of second resolution images. The image correcting module selects a target image and produces a plurality of corrected images. The image blending module performs direction gradient operation on each of the pixels of the target and corrected images and produces a plurality of gradient differential values. The image blending module performs a weighting sum operation on each of the pixels of the target and corrected images and produces a third resolution images.

Abstract translation: 提供了一种数字图像处理装置及其处理方法。 该装置包括数字图像捕获模块，图像放大模块，图像校正模块和图像混合模块。 数字图像捕获模块捕获多个第一分辨率图像。 图像放大模块放大第一分辨率图像并产生多个第二分辨率图像。 图像校正模块选择目标图像并产生多个校正图像。 图像混合模块对目标和校正图像的每个像素执行方向梯度操作，并产生多个梯度差分值。 图像混合模块对目标和校正图像的每个像素执行加权和运算，并产生第三分辨率图像。

公开(公告)号：US20120281120A1

公开(公告)日：2012-11-08

申请号：US13221929

申请日：2011-08-31

Applicant: Che-Lun Chuang ,  Chung-Ta Wu ,  Hong-Long Chou

Inventor： Che-Lun Chuang ,  Chung-Ta Wu ,  Hong-Long Chou

IPC: H04N5/217

CPC classification number: H04N5/3532 ,  H04N5/2329

Abstract: An image processing method and an image processing apparatus are provided. In the image processing method, each of a plurality of original images is divided into K bands, where K is a positive integer greater than or equal to 1. A plurality of local motions of each band in any two adjacent of the original images are calculated, and a global motion of each band is calculated according to the local motions of the band. A horizontal component velocity and a vertical component velocity of each band are generated according to the global motion and a capturing time difference. A plurality of transformation matrixes corresponding to the bands are generated according to the horizontal component velocities, the vertical component velocities, a row readout time, and the width of a valid area. One of the two adjacent original images is transformed according to the transformation matrixes to generate a compensated image.

Abstract translation: 提供了图像处理方法和图像处理装置。 在图像处理方法中，将多个原始图像中的每一个划分为K个频带，其中K是大于或等于1的正整数。计算原始图像中任何两个相邻的每个频带的多个局部运动 ，并且根据频带的局部运动来计算每个频带的全局运动。 根据全局运动和拍摄时间差产生每个频带的水平分量速度和垂直分量速度。 根据水平分量速度，垂直分量速度，行读出时间和有效区域的宽度，生成与频带对应的多个变换矩阵。 根据变换矩阵对两个相邻原始图像中的一个进行变换以生成补偿图像。