Image processing methods and apparatus
    1.
    发明授权
    Image processing methods and apparatus 有权
    图像处理方法和装置

    公开(公告)号:US06954228B1

    公开(公告)日:2005-10-11

    申请号:US09359523

    申请日:1999-07-23

    IPC分类号: H04N5/228 H04N9/73

    CPC分类号: H04N9/735

    摘要: A method includes capturing an optical image to form raw data indicative of the optical image and using a look-up table to transform the raw data into transformed data that indicates a second image. A white color balance of the second image is computed, and the values in the look-up table are modified based on the computed white color balance.

    摘要翻译: 一种方法包括捕获光学图像以形成指示光学图像的原始数据,并使用查找表将原始数据变换为指示第二图像的变换数据。 计算第二图像的白色平衡,并且基于所计算的白色平衡来修改查找表中的值。

    Image processing architecture
    2.
    发明授权
    Image processing architecture 有权
    图像处理架构

    公开(公告)号:US06757430B2

    公开(公告)日:2004-06-29

    申请号:US09473643

    申请日:1999-12-28

    IPC分类号: G06K934

    CPC分类号: G06K9/00456

    摘要: A system includes a central processing unit, a bus and circuit. The central processing unit is coupled to the bus and segments an image into at least one text region and at least one graphics region. At least one of the circuit modules is associated with the processing of the text region(s), and at least one of the circuit modules is associated with the processing of the graphics region(s).

    摘要翻译: 系统包括中央处理单元,总线和电路。 中央处理单元耦合到总线并将图像分割成至少一个文本区域和至少一个图形区域。 至少一个电路模块与文本区域的处理相关联,并且至少一个电路模块与图形区域的处理相关联。

    Efficient companding algorithm suitable for color imaging
    3.
    发明授权
    Efficient companding algorithm suitable for color imaging 有权
    高效压缩算法适用于彩色成像

    公开(公告)号:US06351555B1

    公开(公告)日:2002-02-26

    申请号:US09482551

    申请日:2000-01-13

    IPC分类号: G06K900

    摘要: A companding method is disclosed where a set of factors related to the color characteristics of captured images are determined. Using these characteristics, a companding scheme is developed such that each pixel is lowered in resolution, but in such a manner that the image retains important features. These factors related to color characteristics are determined in part by analyzing histograms related to the image.

    摘要翻译: 公开了一种压缩方法,其中确定与拍摄图像的颜色特性相关的一组因素。 使用这些特征,开发了压缩方案,使得每个像素以分辨率降低,但是以使得图像保持重要特征的方式。 与颜色特征相关的这些因素部分地通过分析与图像相关的直方图来确定。

    Auto-focusing algorithm using discrete wavelet transform
    4.
    发明授权
    Auto-focusing algorithm using discrete wavelet transform 有权
    使用离散小波变换的自动对焦算法

    公开(公告)号:US6151415A

    公开(公告)日:2000-11-21

    申请号:US211309

    申请日:1998-12-14

    CPC分类号: H04N5/23212 H04N19/63

    摘要: What is disclosed is a method that includes generating an overall sharpness parameter for a given focus position by performing a Discrete Wavelet Transform upon an image captured by an imaging device and automatically focusing said imaging device to an optimal focus position by comparing a plurality of different sharpness parameters. The optimal focusing position is automatically determined by finding the highest sharpness parameter for a given scene.

    摘要翻译: 所公开的是一种方法,其包括通过在由成像装置捕获的图像上执行离散小波变换来产生给定焦点位置的整体锐度参数,并通过将多个不同锐度进行比较来自动将所述成像装置聚焦到最佳聚焦位置 参数。 通过找到给定场景的最高锐度参数来自动确定最佳聚焦位置。

    Scaling algorithm for efficient color representation/recovery in video
    5.
    发明授权
    Scaling algorithm for efficient color representation/recovery in video 有权
    视频中有效的颜色表示/恢复的缩放算法

    公开(公告)号:US06236433B1

    公开(公告)日:2001-05-22

    申请号:US09163022

    申请日:1998-09-29

    IPC分类号: H04N314

    摘要: What is disclosed is a method comprising defining a scaling region by indicating in a CFA (Color Filter Array) a starting location, and generating a super-pixel which is a downscaled version of the scaling region, the super-pixel fully color interpolated, the downscaling and the color interpolation achieved in an integrated manner.

    摘要翻译: 所公开的是一种方法,包括通过在CFA(颜色滤波器阵列)中指示起始位置来定义缩放区域,以及生成缩放区域的缩小版本的超像素,内插的超像素, 缩小颜色和色彩插值以一体化方式实现。

    Dual mode digital camera for video and still operation
    6.
    发明授权
    Dual mode digital camera for video and still operation 失效
    双模数码相机用于视频和静态操作

    公开(公告)号:US6151069A

    公开(公告)日:2000-11-21

    申请号:US963097

    申请日:1997-11-03

    摘要: A cost effective digital image capture apparatus such as a digital camera that operates in both still mode and video mode, using a common programmable image processing chain and fixed optics. The full resolution of the image sensor (yielding raw image data) may be used in still mode, with adequate signal-to-noise ratio (SNR) achieved either from the scene ambient lighting or from supplemental light supplied by a strobe. In video mode, the apparatus may be configured to capture video image data by programming the parameters for image processing methodologies such as scaling, decorrelation, and encoding into a look-up table (LUT) which in turn configures logic circuitry to spatially scale and compress if necessary the raw image data in order to meet storage and transmission bandwidth constraints for video images. In video mode, adequate SNR may be achieved despite the lower light conditions, encountered, for example, during videoconferencing, by averaging pixels together during scaling.

    摘要翻译: 一种具有成本效益的数字图像采集装置,例如在静止模式和视频模式下操作的数字照相机,使用公共可编程图像处理链和固定光学器件。 图像传感器的全分辨率(产生原始图像数据)可以在静止模式下使用,具有从场景环境照明或由闪光灯提供的补充光获得的足够的信噪比(SNR)。 在视频模式中,该装置可以被配置为通过将诸如缩放,去相关和编码的图像处理方法的参数编程到查找表(LUT)中来捕获视频图像数据,该查询表又将逻辑电路配置成在空间上缩放和压缩 如有必要,原始图像数据为了满足视频图像的存储和传输带宽限制。 在视频模式中,尽管在例如视频会议期间遇到较低的光线条件,但通过在缩放期间将像素平均化在一起,可以实现足够的SNR。

    Using an electronic camera to build a file containing text
    7.
    发明授权
    Using an electronic camera to build a file containing text 失效
    使用电子照相机构建包含文本的文件

    公开(公告)号:US06563948B2

    公开(公告)日:2003-05-13

    申请号:US09301753

    申请日:1999-04-29

    IPC分类号: G06K900

    CPC分类号: G06K9/228

    摘要: An embodiment of the invention is directed to a method of building an electronic file, using an electronic camera such as a digital camera, that captures 3-dimensional objects. A number of image data tiles that represent the images are generated by the camera. A number of text data tiles each containing text recognized in a corresponding one of the image data tiles is generated. The method includes searching for overlapping text in the text tiles, and pasting the text tiles in proper alignment into an electronic file.

    摘要翻译: 本发明的实施例涉及使用诸如数码相机的电子照相机来构建电子文件的方法,其捕获三维物体。 表示图像的多个图像数据瓦片由相机生成。 生成多个文本数据块,每个文本数据块包含在对应的一个图像数据块中识别的文本。 该方法包括搜索文本块中的重叠文本,并将文本块贴合到电子文件中。

    Scaling algorithm and architecture for integer scaling in video
    9.
    发明授权
    Scaling algorithm and architecture for integer scaling in video 失效
    视频中整数缩放的缩放算法和架构

    公开(公告)号:US06348929B1

    公开(公告)日:2002-02-19

    申请号:US09008131

    申请日:1998-01-16

    IPC分类号: H04N314

    CPC分类号: G06T3/4015 H04N19/59

    摘要: A method for scaling of an image that includes providing an N-tap filter to be applied upon an image region and applying the N-tap filter variously to the image region and obtaining therefrom at least one scaled image pixel, such that N is equal to the scaling factor plus one. For instance, a 4:1 scaling procedure is achieved using a five-tap filter. By carefully selecting the coefficient of the five-tap filter, 2:1 scaling with a three-tap filter may be achieved using the same hardware and adding control signals and selectors. The scaling methodology and apparatus work directly in the CFA domain and provide efficient single pass dual-moded or multi-moded scaling capability.

    摘要翻译: 一种用于缩放图像的方法,包括提供要施加在图像区域上的N抽头滤波器,并且将N抽头滤波器各种地应用于图像区域,并从中获得至少一个缩放图像像素,使得N等于 缩放因子加1。 例如,使用五抽头滤波器实现4:1缩放程序。 通过仔细选择五抽头滤波器的系数,可以使用相同的硬件并添加控制信号和选择器,使用三抽头滤波器进行2:1缩放。 缩放方法和设备直接在CFA域中工作,并提供高效的单通道双模式或多模式缩放功能。

    Machine vision system for enterprise management
    10.
    发明授权
    Machine vision system for enterprise management 有权
    机器视觉系统企业管理

    公开(公告)号:US07617167B2

    公开(公告)日:2009-11-10

    申请号:US10820906

    申请日:2004-04-08

    IPC分类号: G06N5/00 G06F17/00

    CPC分类号: G06Q10/06

    摘要: A system for use in managing activity of interest within an enterprise is provided. The system comprises a computer configured to (i) receive sensor data that is related to key activity to the enterprise, such key activity comprising a type of object and the object's activity at a predetermined location associated with the enterprise, the sensor providing information from which an object's type and activity at the predetermined location can be derived, (ii) process the sensor data to produce output that is related to key activity to the enterprise, and (ii) store the information extracted from the processed data in a suitable manner for knowledge extraction and future analysis. According to a preferred embodiment, the object is human, machine or vehicular, and the computer is further configured to correlate sensor data to key activity to the enterprise and the output includes feedback data based on the correlation.

    摘要翻译: 提供了一种用于管理企业内感兴趣活动的系统。 该系统包括计算机,其被配置为(i)接收与企业的关键活动相关的传感器数据,这种关键活动包括在与企业相关联的预定位置处的对象类型和对象的活动,所述传感器提供信息 可以导出在预定位置处的对象的类型和活动,(ii)处理传感器数据以产生与企业的关键活动相关的输出,以及(ii)以适当的方式存储从处理数据中提取的信息 知识提取和未来分析。 根据一个优选实施例,该目标是人类,机器或车辆,并且计算机还被配置为将传感器数据与企业的关键活动相关联,并且输出包括基于相关性的反馈数据。