公开(公告)号：US20160210727A1

公开(公告)日：2016-07-21

申请号：US14862005

申请日：2015-10-19

Applicant: Samsung Electronics Co., Ltd.

Inventor： Bo Yang ,  Li Tao

IPC: G06T3/40 ,  G06K9/46 ,  G06T5/00 ,  G06T7/00

CPC classification number: G06T3/403 ,  G06K9/4604 ,  G06T3/4053 ,  G06T5/003 ,  G06T2207/20192

Abstract: A method includes determining, by a hardware processor and based on an image frame, a first edge strength distribution on a horizontal edge map and a second edge strength distribution on a vertical edge map. The first and second edge strength distributions are redistributed to narrow at least one of the first and second edge strength distributions. Non-texture regions of pixels are determined based on a data correlation map of the image frame. Edge strength magnitudes for the pixels of the non-texture regions of the horizontal edge map and the vertical edge map are determined. A high resolution frame is generated by adjusting intensity of respective pixels of the non-texture region of the horizontal edge map and the vertical edge map, the adjusting being based on neighboring pixels edge strength magnitudes.

Abstract translation: 一种方法包括由硬件处理器和基于图像帧确定水平边缘图上的第一边缘强度分布和垂直边缘图上的第二边缘强度分布。 重新分配第一和第二边缘强度分布以使第一和第二边缘强度分布中的至少一个变窄。 基于图像帧的数据相关图确定像素的非纹理区域。 确定水平边缘图的非纹理区域的像素和垂直边缘图的边缘强度大小。 通过调整水平边缘图和垂直边缘图的非纹理区域的各个像素的强度来生成高分辨率帧，该调整基于相邻像素边缘强度幅度。

公开(公告)号：US09392241B2

公开(公告)日：2016-07-12

申请号：US14062631

申请日：2013-10-24

Applicant: CANON KABUSHIKI KAISHA

Inventor： Shinya Hirai

IPC: H04N9/64 ,  H04N5/217 ,  H04N9/04 ,  H04N9/78 ,  G06T5/00

CPC classification number: H04N9/646 ,  G06T3/4015 ,  G06T5/002 ,  G06T5/007 ,  G06T2207/10024 ,  G06T2207/20016 ,  G06T2207/20192 ,  H04N5/217 ,  H04N9/045 ,  H04N9/78 ,  H04N2201/0084

Abstract: A band processing circuit which generates image signals corresponding to different frequency bands from an image signal in which signals corresponding to different colors are arranged and which suppresses noise by synthesizing the image signals of the different frequency bands, a sampling circuit which generates image signal corresponding to the colors by sampling the image signal input from the band processing circuit in accordance with a predetermined arrangement, and a luminance/color generation circuit which generates a luminance signal in which aliasing is suppressed using an image signal output from the sampling circuit.

Abstract translation: 一种频带处理电路，其从布置有对应于不同颜色的信号的图像信号生成对应于不同频带的图像信号，并且通过合成不同频带的图像信号来抑制噪声;采样电路，其生成对应于 通过根据预定布置对从频带处理电路输入的图像信号进行采样的颜色，以及使用从采样电路输出的图像信号来生成其中抑制混叠的亮度信号的亮度/颜色生成电路。

公开(公告)号：US09384538B2

公开(公告)日：2016-07-05

申请号：US14444392

申请日：2014-07-28

Applicant: LI-COR, Inc.

Inventor： Patrick G. Humphrey

IPC: G06K9/00 ,  G06K9/40 ,  G06T5/40 ,  G06T5/00

CPC classification number: G06T5/40 ,  G06T5/002 ,  G06T5/20 ,  G06T7/0002 ,  G06T7/11 ,  G06T2207/20021 ,  G06T2207/20028 ,  G06T2207/20076 ,  G06T2207/20182 ,  G06T2207/20192

Abstract: A method for applying a filter to data to improve data quality and/or reduce file size. In one example, a region of interest of an image is identified. A histogram is generated of pixel intensity values in the region of interest. The histogram is iteratively updated to focus (zoom) in on the highest peak in the histogram. A Gaussian curve is fitted to the updated histogram. A bilateral filter is applied to the images, where parameters of the bilateral filter are based on the parameters of the Gaussian curve.

Abstract translation: 将过滤器应用于数据以提高数据质量和/或减小文件大小的方法。 在一个示例中，识别图像的感兴趣区域。 在感兴趣区域中生成像素强度值的直方图。 直方图被迭代地更新，以便在直方图中的最高峰上对焦（缩放）。 高斯曲线拟合到更新的直方图。 双边滤波器应用于图像，其中双边滤波器的参数基于高斯曲线的参数。

公开(公告)号：US20160182893A1

公开(公告)日：2016-06-23

申请号：US14972477

申请日：2015-12-17

Applicant: CANON KABUSHIKI KAISHA

Inventor： ERNEST YIU CHEONG WAN

IPC: H04N13/02 ,  G06T5/20 ,  G06T7/00

CPC classification number: H04N13/271 ,  G06T5/30 ,  G06T7/593 ,  G06T2207/10021 ,  G06T2207/10028 ,  G06T2207/20028 ,  G06T2207/20192 ,  H04N13/128 ,  H04N13/207 ,  H04N13/211 ,  H04N13/246 ,  H04N13/282 ,  H04N2013/0081

Abstract: To extend the working range of depth from defocus (DFD) particularly on small depth of field (DoF) images, DFD is performed on an image pair at multiple spatial resolutions and the depth estimates are then combined. Specific implementations construct a Gaussian pyramid for each image of an image pair, perform DFD on the corresponding pair of images at each level of the two image pyramids, convert DFD depth scores to physical depth values using calibration curves generated for each level, and combine the depth values from all levels in a coarse-to-fine manner to obtain a final depth map that covers the entire depth range of the scene.

Abstract translation: 为了从散焦（DFD），特别是在小景深（DoF）图像上扩展深度的工作范围，在多个空间分辨率的图像对上执行DFD，然后组合深度估计。 具体实现为图像对的每个图像构造高斯金字塔，在两个图像金字塔的每个级别的相应图像对上执行DFD，使用为每个级别生成的校准曲线将DFD深度分数转换为物理深度值，并将 从粗略到精细的方式从所有级别的深度值，以获得覆盖场景的整个深度范围的最终深度图。

公开(公告)号：US09364196B2

公开(公告)日：2016-06-14

申请号：US13133654

申请日：2009-12-11

Applicant: Essa El-Aklouk ,  John Brydon

Inventor： Essa El-Aklouk ,  John Brydon

IPC: A61B8/00 ,  A61B8/14 ,  G06T7/60 ,  G06T7/00

CPC classification number: A61B8/14 ,  A61B8/145 ,  G06T7/62 ,  G06T2207/10132 ,  G06T2207/20182 ,  G06T2207/20192 ,  G06T2207/30084

Abstract: A method and apparatus for determining the volume of a bodily structure including the steps of acquiring at least two ultrasound images, estimating the location of the perimeter of a structure of interest as viewed in cross section in each said ultrasound image, calculating the cross sectional area of such structure as so viewed, and combining the perimeter and area information from the at least two images to calculate the volume of the structure.

Abstract translation: 一种用于确定身体结构的体积的方法和装置，包括以下步骤：获取至少两个超声图像，估计在每个所述超声图像中在横截面中观察的感兴趣结构的周边的位置，计算横截面积 具有如此观看的结构，并且将来自至少两个图像的周边和区域信息组合以计算结构的体积。

公开(公告)号：US20160150161A1

公开(公告)日：2016-05-26

申请号：US15012239

申请日：2016-02-01

Applicant: FUJIFILM Corporation

Inventor： Kosuke IRIE ,  Masahiko SUGIMOTO ,  Yousuke NARUSE ,  Kenkichi HAYASHI

IPC: H04N5/243 ,  H04N5/232 ,  H04N5/238

CPC classification number: H04N5/243 ,  G06T5/003 ,  G06T2207/20192 ,  H04N5/23238 ,  H04N5/23296 ,  H04N5/238 ,  H04N9/045

Abstract: A restoration filter based on a point spread function of an optical system is applied to source image data acquired through photographing using the optical system to acquire restored image data (S13: filter application step). Adjustment of an amplification factor of the difference between source image data and restored image data is performed, and recovered image data is acquired from the difference after adjustment and source image data (S15: gain adjustment step). In the filter application step, a common filter determined regardless of a value of a magnification of an optical zoom of the optical system is used as the restoration filter, and in the gain adjustment step, the amplification factor is determined based on the magnification of the optical zoom of the optical system.

Abstract translation: 将基于光学系统的点扩散功能的恢复滤波器应用于通过使用光学系统拍摄获得的源图像数据，以获取恢复的图像数据（S13：滤波器应用步骤）。 执行源图像数据和恢复的图像数据之间的差异的放大因子的调整，并且从调整后的差异和源图像数据获取恢复的图像数据（S15：增益调整步骤）。 在滤波器应用步骤中，使用不考虑光学系统的光学变焦的倍率的值而确定的公共滤波器作为恢复滤波器，并且在增益调整步骤中，基于放大率 光学系统的光学变焦。

公开(公告)号：US20160148368A1

公开(公告)日：2016-05-26

申请号：US15013378

申请日：2016-02-02

Applicant: CIMPRESS SCHWEIZ GMBH

Inventor： Vyacheslav Nykyforov

IPC: G06T7/00 ,  G06T7/40 ,  G06K9/20 ,  G06K9/46 ,  G06T5/00

CPC classification number: G06T7/194 ,  G06K9/2081 ,  G06K9/342 ,  G06K9/38 ,  G06K9/46 ,  G06K9/4604 ,  G06K9/4652 ,  G06K9/6267 ,  G06K2009/4666 ,  G06T5/00 ,  G06T5/002 ,  G06T7/0004 ,  G06T7/11 ,  G06T7/13 ,  G06T7/162 ,  G06T7/90 ,  G06T2207/10024 ,  G06T2207/20072 ,  G06T2207/20192 ,  G06T2207/30108 ,  H04N1/00209 ,  H04N1/3872 ,  H04N1/409

Abstract: Automated systems, methods and tools that automatically extract and select portions of an image to automatically generate a premium finish mask specific to the image which require little or no human intervention are presented. Graphical user interface tools allowing a user to provide an image and to indicate regions of the image for application of premium finish are also presented.

公开(公告)号：US09349165B2

公开(公告)日：2016-05-24

申请号：US14061131

申请日：2013-10-23

Applicant: Adobe Systems Incorporated

Inventor： Sunghyun Cho ,  Jue Wang ,  Jen-Chan Chien ,  Dong Feng

IPC: G06K9/46 ,  G06K9/66 ,  G06T5/00

CPC classification number: G06T5/003 ,  G06T5/20 ,  G06T11/001 ,  G06T2207/10024 ,  G06T2207/20192 ,  G06T2207/20201 ,  G06T2207/20221

Abstract: A computer-implemented method and apparatus are described for automatically selecting a region in a blurred image for blur kernel estimation. The method may include accessing a blurred image and defining a size for each of a plurality of regions in the image. Thereafter, metrics for at least two of the plurality of regions are determined, wherein the metrics are based on a number of edge orientations within each region. A region is selected from the plurality of regions based on the determined metrics, and a blur kernel for deblurring the blurred image is then estimated for the selected region. The blurred image is then deblurred using the blur kernel.

Abstract translation: 描述了用于自动选择模糊图像中的区域以进​​行模糊核估计的计算机实现的方法和装置。 该方法可以包括访问模糊图像并且为图像中的多个区域中的每一个定义大小。 此后，确定多个区域中的至少两个的度量，其中度量基于每个区域内的边缘取向的数量。 基于所确定的度量，从多个区域中选择区域，然后针对所选择的区域估计用于去模糊模糊图像的模糊核心。 然后使用模糊内核去除模糊的图像。

公开(公告)号：US09349161B2

公开(公告)日：2016-05-24

申请号：US13930226

申请日：2013-06-28

Applicant: CANON KABUSHIKI KAISHA

Inventor： Hirokazu Tamura

IPC: G06K9/40 ,  G06T5/00 ,  G06T5/20

CPC classification number: G06T5/001 ,  G06T5/003 ,  G06T5/20 ,  G06T2207/10008 ,  G06T2207/10024 ,  G06T2207/20192 ,  G06T2207/30176

Abstract: Edge enhancement processing is performed for the luminance of each pixel of an image, and the correction value of the pixel after the edge enhancement processing is decided according to the saturation of each pixel of the image. The value of the pixel after the edge enhancement processing is corrected using the decided correction value.

Abstract translation: 对图像的每个像素的亮度执行边缘增强处理，并且根据图像的每个像素的饱和度来确定边缘增强处理之后的像素的校正值。 使用所确定的校正值来校正边缘增强处理之后的像素的值。

公开(公告)号：US20160140697A1

公开(公告)日：2016-05-19

申请号：US15003849

申请日：2016-01-22

Applicant: FUJIFILM Corporation

Inventor： Masahiko SUGIMOTO ,  Kenkichi HAYASHI ,  Yousuke NARUSE ,  Kosuke IRIE

IPC: G06T5/00 ,  G06T7/20 ,  H04N5/225 ,  G06T5/20

CPC classification number: G06T5/003 ,  G06T5/20 ,  G06T5/50 ,  G06T7/20 ,  G06T2207/10016 ,  G06T2207/20192 ,  G06T2207/20201 ,  H04N5/225 ,  H04N5/23229

Abstract: Disclosed are an image processing device, an imaging device, an image processing method, and a program capable of acquiring a moving image with excellent image quality while maintaining continuity of a restoration process between frames even if there is a rapid change of a photographing environment in a moving image. An image processing device includes a restoration control processing unit 36 which subjects a moving image including a plurality of frames acquired by photographing using an optical system to a restoration process based on a point spread function of the optical system to acquire recovered image data. The restoration control processing unit 36 controls the restoration process for a frame to be processed among a plurality of frames based on imaging information of a reference frame including a frame after the frame to be processed in a time series.

Abstract translation: 公开了一种图像处理装置，成像装置，图像处理方法和程序，其能够获得具有优异图像质量的运动图像，同时保持帧之间的恢复处理的连续性，即使存在拍摄环境的快速变化 运动图像。 一种图像处理装置包括：恢复控制处理单元36，其基于光学系统的点扩展功能，使用光学系统拍摄包含通过拍摄获得的多个帧的运动图像进行恢复处理，以获取恢复的图像数据。 恢复控制处理单元36基于包括在时间序列中的要处理的帧之后的帧的参考帧的成像信息，控制多个帧之间的要处理的帧的恢复处理。