Image segmentation from focus varied images using graph cuts
    2.
    发明授权
    Image segmentation from focus varied images using graph cuts 有权
    图像分割从焦点变化的图像使用图形切割

    公开(公告)号:US09025043B2

    公开(公告)日:2015-05-05

    申请号:US13119541

    申请日:2008-09-24

    CPC分类号: G03B13/18

    摘要: A system for providing an adjusted image of a scene includes an optical assembly, a capturing system coupled to the optical assembly, and a control system. The optical assembly is adjustable to alternatively be focused on a first focal area and a second focal area that is different than the first focal area. The capturing system captures a first frame of the scene when the optical assembly is focused at the first focal area, and a second frame of the scene when the optical assembly is focused at the second focal area. The first frame includes a plurality of first pixels and the second frame includes a plurality of second pixels. The control system analyzes the first frame and the second frame and utilizes graph cuts techniques to assign a depth label to at least a portion of the first frame.

    摘要翻译: 用于提供场景的调整图像的系统包括光学组件,耦合到光学组件的捕获系统和控制系统。 光学组件可调节以可选地聚焦在与第一焦点区域不同的第一焦点区域和第二焦点区域上。 当光学组件聚焦在第一焦点区域时,捕获系统捕获场景的第一帧,以及当光学组件聚焦在第二焦点区域时的场景的第二帧。 第一帧包括多个第一像素,第二帧包括多个第二像素。 控制系统分析第一帧和第二帧,并利用图切割技术将深度标签分配给第一帧的至少一部分。

    Device and method for estimating whether an image is blurred
    3.
    发明授权
    Device and method for estimating whether an image is blurred 有权
    用于估计图像是否模糊的装置和方法

    公开(公告)号:US08472744B2

    公开(公告)日:2013-06-25

    申请号:US12810486

    申请日:2009-05-26

    申请人: Li Hong

    发明人: Li Hong

    IPC分类号: G06K9/00 G06T5/00 H04N5/232

    摘要: A method for estimating whether an image (14) is either blurred or sharp includes the steps of (i) determining an image gradient histogram distrbution (410) of at least a portion of the image (14), (ii) comparing at least a portion of the image gradient histogram distribution (410) to a Gaussian model (414), and (iii) estimating a defocus blur size of at least a portion of the image (14) Additional methods for evaluating whether the image (14) has motion blur are provided herein For example, a dominant gradient orientation can be detected by histogram analysis (716), and the dominant gradient orientation (718) can be used to determine a possible motion blur direction (720) Alternatively, a dominant gradient orientation can be detected using principal component analysis (“PCA”) on the image.

    摘要翻译: 一种用于估计图像(14)是模糊还是尖锐的方法包括以下步骤:(i)确定图像(14)的至少一部分的图像梯度直方图分布(410),(ii)比较至少一个 图像梯度直方图分布(410)的部分与高斯模型(414)相关联,以及(iii)估计图像的至少一部分的散焦模糊尺寸(14)用于评估图像(14)是否具有运动的附加方法 模糊在这里提供例如,可以通过直方图分析(716)检测主要梯度取向,并且可以使用主梯度取向(718)来确定可能的运动模糊方向(720)。或者,主要梯度取向可以是 使用主成分分析(“PCA”)检测图像。

    Method and apparatus for processing an image
    4.
    发明授权
    Method and apparatus for processing an image 失效
    用于处理图像的方法和装置

    公开(公告)号:US06782143B1

    公开(公告)日:2004-08-24

    申请号:US09476221

    申请日:1999-12-30

    申请人: Simant Dube Li Hong

    发明人: Simant Dube Li Hong

    IPC分类号: G06K932

    CPC分类号: G06T3/403

    摘要: In a first aspect, a method and an apparatus for processing an image classifies the image content of a portion of the image, and in response thereto, selects between linear interpolation (e.g., cubic) and non-linear interpolation (median) methods to interpolate data points for the portion of the image. In one embodiment, non-linear interpolation is selected if the image content of the portion of the image is bi-level, or if portion of the image includes an edge and lacks a specified measure of correlation along a line. Linear interpolation is used in portions where the image content does not include an identified edge and in portions where there is an identified edge in combination with an identified edge direction or a path of isobrightness. In a second aspect, a method and apparatus for use in classifying the image content of a portion of an image calculates a reference value from pixel values for a portion of an image and generates data indicative of which pixel values are greater than the reference value and which pixel values are less than the reference value.

    摘要翻译: 在第一方面,一种用于处理图像的方法和装置对图像的一部分的图像内容进行分类,并且响应于此,在线性内插(例如,立方体)和非线性内插(中值)方法之间进行内插 图像部分的数据点。 在一个实施例中,如果图像的部分的图像内容是双电平的,或者如果图像的一部分包括边缘并且沿着一条线缺乏相关的指定度量,则选择非线性内插。 线性内插用于图像内容不包括识别边缘的部分,并且在识别的边缘方向或等离子体路径中存在识别边缘的部分中。 在第二方面中,用于对图像的一部分进行分类的图像内容使用的方法和装置根据图像的一部分的像素值计算参考值,并产生指示哪些像素值大于参考值的数据,以及 哪些像素值小于参考值。

    Method and apparatus for processing an image in an image compression/decompression system that uses hierachical coding
    5.
    发明授权
    Method and apparatus for processing an image in an image compression/decompression system that uses hierachical coding 有权
    在使用层次编码的图像压缩/解压缩系统中处理图像的方法和装置

    公开(公告)号:US06633677B1

    公开(公告)日:2003-10-14

    申请号:US09475367

    申请日:1999-12-30

    申请人: Simant Dube Li Hong

    发明人: Simant Dube Li Hong

    IPC分类号: G06K936

    CPC分类号: G06T17/00 G06T9/004

    摘要: A component of an image processor receives at least a portion of one or more reconstructed versions of an image including a causal context of an object pixel of the image, and provides a prediction for the object pixel computed as a weighted sum according to at least one measure of correlation and a weighting policy. A component receives a first prediction of an object pixel and reconstructed versions of an image, and provides a second prediction for the object pixel in accordance with the first prediction for the object pixel and a substantially mean error for the context. A component receives one or more prediction differences versions of the image including a causal context prediction difference of an object prediction difference of the image, and provides a prediction for the object prediction difference computed as a weighted sum according to at least one measure of correlation and a weighting policy.

    摘要翻译: 图像处理器的组件接收包括图像的对象像素的因果上下文的图像的一个或多个重建版本的至少一部分,并且根据至少一个对像素计算的对象像素作为加权和来提供预测 衡量相关性和加权政策。 组件接收对象像素和图像的重建版本的第一预测,并且根据对象像素的第一预测和上下文的基本平均误差为对象像素提供第二预测。 组件接收图像的一个或多个预测差异版本,包括图像的对象预测差异的因果上下文预测差异,并且根据至少一个相关度测量提供作为加权和计算的对象预测差异的预测, 加权政策。

    Blur detection system for night scene images
    6.
    发明授权
    Blur detection system for night scene images 有权
    模糊检测系统,用于夜景图像

    公开(公告)号:US09412039B2

    公开(公告)日:2016-08-09

    申请号:US13823015

    申请日:2010-11-03

    申请人: Li Hong Itaru Homma

    发明人: Li Hong Itaru Homma

    摘要: A system (300) for detecting whether an image (16) is blurred performs the steps of: identifying valid light trails in the test image (308), and classifying the test image as blurred if there is a sufficient number of matching valid light trails oriented in a repetitive pattern (310). The system (300) is designed to automatically detect whether a night scene image (16) is blurred based on the existence and characteristics of any light trails (552) in the captured image (16). Because the method extracts the characteristics of the light trails (552) and analyzes these light trails (552), it accurately detects blur in the challenging night scene images and has a relatively low false positive rate.

    摘要翻译: 用于检测图像(16)是否模糊的系统(300)执行以下步骤:识别测试图像(308)中的有效光迹,并且如果存在足够数量的匹配有效光迹,则将测试图像分类为模糊 面向重复模式(310)。 系统(300)被设计为基于捕获图像(16)中的任何光迹(552)的存在和特征来自动检测夜景图像(16)是否模糊。 由于该方法提取了光迹(552)的特征并分析了这些光迹(552),因此准确地检测了具有挑战性的夜景图像中的模糊,并具有相对较低的假阳性率。

    Automatic illuminant estimation that incorporates apparatus setting and intrinsic color casting information
    7.
    发明授权
    Automatic illuminant estimation that incorporates apparatus setting and intrinsic color casting information 有权
    自动光源估计,包含设备设置和内在色彩投影信息

    公开(公告)号:US09013596B2

    公开(公告)日:2015-04-21

    申请号:US13119574

    申请日:2008-09-24

    申请人: Li Hong

    发明人: Li Hong

    摘要: An image apparatus (10) for providing an estimated final illuminant of a scene (12) and subsequently providing an adjusted image (218) of a scene (12) includes a capturing system (226) and a control system (232). The capturing system (226) captures information for an input image (416) of the scene (12) while at an apparatus setting. The input image (416) is defined by a plurality of input colors. The control system (226) can compare at least one of the input colors to an illuminant database (245) that includes an illuminant gamut of observable colors for a plurality of possible illuminants, and can evaluate the apparatus setting to select one of the possible illuminants to be the estimated final illuminant. Examples of possible apparatus settings include an aperture size and an exposure time. With this design, the present invention is better able to distinguish between some possible outdoor illuminants and some possible indoor illuminants with improved accuracy. Additionally, the control system (226) can evaluate a consistency matching error for the plurality of possible illuminants to determine if the scene (12) has intrinsic color casting.

    摘要翻译: 一种用于提供场景(12)的估计的最终光源并随后提供场景(12)的调整图像(218)的图像设备(10)包括捕获系统(226)和控制系统(232)。 拍摄系统(226)在设备设置时捕获场景(12)的输入图像(416)的信息。 输入图像(416)由多个输入颜色定义。 控制系统(226)可以将输入颜色中的至少一个比较到包括多个可能发光体的可观察颜色的发光体色域的光源数据库(245),并且可以评估设备设置以选择可能的发光体之一 成为估计的最终光源。 可能的设备设置的示例包括孔径尺寸和曝光时间。 通过这种设计,本发明能够更好地以提高的精度来区分一些可能的室外光源和一些可能的室内光源。 另外,控制系统(226)可以评估多个可能的发光体的一致性匹配误差,以确定场景(12)是否具有固有的颜色投射。

    Method and device for image deblurring using joint bilateral filtering
    8.
    发明授权
    Method and device for image deblurring using joint bilateral filtering 有权
    使用联合双边滤波的图像去模糊的方法和装置

    公开(公告)号:US08588541B2

    公开(公告)日:2013-11-19

    申请号:US13002041

    申请日:2008-09-24

    申请人: Li Hong

    发明人: Li Hong

    IPC分类号: G06K9/40

    摘要: A system (12) for providing an adjusted image (228) of a scene (10) from a blurred captured image (14) includes a control system (26) that provides the adjusted image (228). The control system (26) can create a downsampled blurred image (236) from the captured image (14), deblur the downsampled blurred image (236) to create a downsampled deblurred image (238), and upsample the downsampled deblurred image (238) to create the adjusted image (228). With this design, because the deblurring is performed on the downsampled blurred image (236), the computational and memory costs are substantially less than if this task is performed on the original captured image (14). Further, the control system (26) can create the adjusted image (228) using a joint bilateral filter that combines information from the blurred captured image (14) and the downsampled deblurred image (238).

    摘要翻译: 用于从模糊的拍摄图像(14)提供场景(10)的调整图像(228)的系统(12)包括提供经调整的图像(228)的控制系统(26)。 控制系统(26)可以从捕获的图像(14)创建下采样的模糊图像(236),去除下采样的模糊图像(236)以创建下采样的去模糊图像(238),并对下采样的去模糊图像(238)进行上采样, 以创建经调整的图像(228)。 利用这种设计,由于在下采样的模糊图像(236)上执行去模糊,所以计算和存储器成本显着小于如果对原始捕获图像执行该任务(14)。 此外,控制系统(26)可以使用组合来自模糊拍摄图像(14)和下采样去模糊图像(238)的信息的联合双边滤波器来创建调整图像(228)。

    AUTOMATIC ILLUMINANT ESTIMATION THAT INCORPORATES APPARATUS SETTING AND INTRINSIC COLOR CASTING INFORMATION
    9.
    发明申请
    AUTOMATIC ILLUMINANT ESTIMATION THAT INCORPORATES APPARATUS SETTING AND INTRINSIC COLOR CASTING INFORMATION 有权
    自动发光装置设计和内置彩色投影信息的估计

    公开(公告)号:US20110164150A1

    公开(公告)日:2011-07-07

    申请号:US13119574

    申请日:2008-09-24

    申请人: Li Hong

    发明人: Li Hong

    IPC分类号: H04N9/68 G06K9/00

    摘要: An image apparatus (10) for providing an estimated final illuminant of a scene (12) and subsequently providing an adjusted image (218) of a scene (12) includes a capturing system (226) and a control system (232). The capturing system (226) captures information for an input image (416) of the scene (12) while at an apparatus setting. The input image (416) is defined by a plurality of input colors. The control system (226) can compare at least one of the input colors to an illuminant database (245) that includes an illuminant gamut of observable colors for a plurality of possible illuminants, and can evaluate the apparatus setting to select one of the possible illuminants to be the estimated final illuminant. Examples of possible apparatus settings include an aperture size and an exposure time. With this design, the present invention is better able to distinguish between some possible outdoor illuminants and some possible indoor illuminants with improved accuracy. Additionally, the control system (226) can evaluate a consistency matching error for the plurality of possible illuminants to determine if the scene (12) has intrinsic color casting.

    摘要翻译: 一种用于提供场景(12)的估计的最终光源并随后提供场景(12)的调整图像(218)的图像设备(10)包括捕获系统(226)和控制系统(232)。 拍摄系统(226)在设备设置时捕获场景(12)的输入图像(416)的信息。 输入图像(416)由多个输入颜色定义。 控制系统(226)可以将输入颜色中的至少一个比较到包括多个可能发光体的可观察颜色的发光体色域的光源数据库(245),并且可以评估设备设置以选择可能的发光体之一 成为估计的最终光源。 可能的设备设置的示例包括孔径尺寸和曝光时间。 通过这种设计,本发明能够更好地以提高的精度来区分一些可能的室外光源和一些可能的室内光源。 另外,控制系统(226)可以评估多个可能的发光体的一致性匹配误差,以确定场景(12)是否具有固有的颜色投射。