Methods and systems for automatic detection of continuous-tone regions in document images
    2.
    发明授权
    Methods and systems for automatic detection of continuous-tone regions in document images 有权
    文件图像中连续色调区域自动检测的方法和系统

    公开(公告)号:US07379594B2

    公开(公告)日:2008-05-27

    申请号:US10767394

    申请日:2004-01-28

    IPC分类号: G06K9/34

    CPC分类号: H04N1/40062 G06K9/00456

    摘要: Methods and systems for segmentation of digital mixed-content documents. Segmentation processes may include identification of text and background regions and identification of contone regions outside the text and background regions. Further analysis may be performed to identify additional text and background regions within the contone regions thereby identifying verified contone regions, which may then be divided into contone sub-regions.

    摘要翻译: 数字混合内容文件分割的方法和系统。 分割过程可以包括文本和背景区域的识别以及文本和背景区域之外的连续色调区域的识别。 可以进行进一步分析以识别连续色调区域内的附加文本和背景区域,从而识别经验证的连续色调区域,然后可以将其分为连续色调子区域。

    Seam for tube of cloth, fabric or flexible material
    3.
    发明授权
    Seam for tube of cloth, fabric or flexible material 失效
    缝管用于布料,织物或柔性材料

    公开(公告)号:US4512274A

    公开(公告)日:1985-04-23

    申请号:US413794

    申请日:1982-09-01

    IPC分类号: D05B93/00 D05B1/10 D05B1/18

    CPC分类号: D05B93/00

    摘要: This relates to a seam between two edge portions of fabric wherein one fabric edge portion is reversely folded beneath itself and the two edge portions are then disposed in overlapped relation with the two free edges of the fabric being generally aligned. Adjacent the folded edge there is a first line of stitching which extends through all three layers. There is also provided a second line of stitching which includes two needle threads and a single looper thread with one of the needle threads extending through all three thicknesses of the fabric and the second needle thread extending only through the one layer of fabric beyond the overlapped fabric portions. The second line of stitching includes a looper thread which not only extends between the loops of the two needle threads, but also transversely of the line of stitching between the adjacent needle thread loops wherein the looper thread serves to hold down and prevent unraveling of the free edges of the fabric. The two lines of stitching may be, particularly in the case of a tubular article being sewn, sewn on a modified feed-off-the-arm machine.

    摘要翻译: 这涉及织物的两个边缘部分之间的接缝,其中一个织物边缘部分在其自身下方反向折叠,并且两个边缘部分然后以与织物的两个自由边缘重叠的关系布置为大致对准。 在折叠边缘附近有一条第一条缝合线,其延伸穿过所有三层。 还提供了第二条缝合线,其包括两个针线和单个弯针线,其中一个针线延伸穿过织物的所有三个厚度,并且第二针线仅延伸穿过一层织物超过重叠织物 部分。 第二线缝线包括不仅在两个针螺纹的环之间延伸的弯针螺纹,而且还在相邻的针螺纹环之间的缝合线的横向上,其中弯针螺纹用于压紧并防止释放自由 织物的边缘。 两条缝合线可能是特别是在被缝制的管状物品的情况下,缝合在修改后的送料臂机器上。

    Methods and systems for background color extrapolation
    4.
    发明授权
    Methods and systems for background color extrapolation 有权
    用于背景颜色外推的方法和系统

    公开(公告)号:US08014596B2

    公开(公告)日:2011-09-06

    申请号:US11930486

    申请日:2007-10-31

    IPC分类号: G06K9/34

    CPC分类号: H04N1/40062

    摘要: Aspects of the present invention are related to methods and systems for determining a background color in a digital image. A background color value for a pixel in an image may be determined by summarizing the color values in a color buffer, wherein the color values in the buffer may have been selectively added to the color buffer, from the image data, based on one, or more, criteria which may be related to edge density, image uniformity, non-local color information, a foreground color estimate and other selection criterion. The background color for the pixel maybe determined in a forward scan and updated during a backward scan.

    摘要翻译: 本发明的方面涉及用于确定数字图像中的背景颜色的方法和系统。 可以通过总结颜色缓冲器中的颜色值来确定图像中的像素的背景颜色值,其中缓冲器中的颜色值可以从图像数据中选择性地添加到颜色缓冲器中,基于一个或 更多的可能与边缘密度,图像均匀性,非局部颜色信息,前景颜色估计和其他选择标准有关的标准。 像素的背景颜色可以在正向扫描中确定,并且在反向扫描期间被更新。

    Support and manipulation mechanism for leaf and debris collector
    5.
    发明授权
    Support and manipulation mechanism for leaf and debris collector 失效
    叶片和碎片收集器的支撑和操作机制

    公开(公告)号:US5181294A

    公开(公告)日:1993-01-26

    申请号:US732901

    申请日:1991-07-19

    IPC分类号: A01G1/12 B08B15/00 E01H1/08

    摘要: An apparatus for the collection of leaves and debris by a vacuuming process is described which features an improved mechanism for supporting and manipulating an intake hose. A stationary support frame is mounted on a leaf collecting apparatus and a swing arm is pivotally attached to the support frame about a vertical axis. An intake hose cradle is fixed to the swing arm and supports the intake hose from underneath. The intake hose may be adjusted vertically by a hydraulic actuator (extensible piston) located on the swing arm which pivots about a horizontal axis in response to movement of the hydraulic actuator. Further, the intake hose may be manipulated from side-to-side by a handle attached to the intake end of the hose, the swing arm allowing lateral movement by utilizing bearings as pivot points along the vertical axis.

    摘要翻译: 描述了一种用于通过抽真空方法收集叶子和碎屑的装置,其特征在于用于支撑和操纵进气软管的改进的机构。 固定支撑框架安装在叶片收集装置上,并且摆臂围绕垂直轴线可枢转地附接到支撑框架。 进气软管支架固定在摆臂上,从下面支撑进气软管。 进气软管可以通过位于摆臂上的液压致动器(可伸缩活塞)垂直调节,该液压致动器响应于液压致动器的移动而围绕水平轴线枢转。 此外,进气软管可以通过附接到软管的进气端的手柄从一侧到另一侧操作,该摆臂通过利用轴承作为沿着垂直轴线的枢转点来允许侧向运动。

    Object recognition using binary image quantization and hough kernels
    7.
    发明授权
    Object recognition using binary image quantization and hough kernels 失效
    使用二进制图像量化和休眠内核的对象识别

    公开(公告)号:US06807286B1

    公开(公告)日:2004-10-19

    申请号:US09548182

    申请日:2000-04-13

    IPC分类号: G06K900

    CPC分类号: G06K9/6211 G06K9/6255

    摘要: A system and process for recognizing an object in an input image involving first generating training images depicting the object. A set of prototype edge features is created that collectively represent the edge pixel patterns encountered within a sub-window centered on each pixel depicting an edge of the object in the training images. Next, a Hough kernel is defined for each prototype edge feature in the form of a set of offset vectors representing the distance and direction, from each edge pixel having an associated sub-window exhibiting an edge pixel pattern best represented by the prototype edge feature, to a prescribed reference point on a surface of the object. The offset vectors are represented as originating at a central point of the kernel. For each edge pixel in the input image, the prototype edge feature which best represents the edge pixel pattern exhibited within the sub-window centered on the edge pixel is identified. Then, for each input image pixel location, the number of offset vectors terminating at that location from Hough kernels centered on each edge pixel location of the input image is identified. The Hough kernel centered on each pixel location is the Hough kernel associated with the prototype edge feature best representing the edge pixel pattern exhibited within a sub-window centered on that input image edge pixel location. The object is declared to be present in the input image if any of the input image pixel locations have a quantity of offset vectors terminating thereat that equals or exceeds a detection threshold.

    摘要翻译: 一种用于识别输入图像中的对象的系统和过程,包括首先生成描绘对象的训练图像。 创建一组原型边缘特征,其共同地表示在描绘训练图像中的对象的边缘的每个像素的中心的子窗口内遇到的边缘像素图案。 接下来,以代表距离和方向的一组偏移向量的形式为每个原型边缘特征定义霍夫核,从具有相关子窗口的每个边缘像素表现出由原型边缘特征最佳表示的边缘像素图案, 到物体表面上规定的参考点。 偏移矢量被表示为在内核的中心点处产生的。 对于输入图像中的每个边缘像素,识别最佳表示以边缘像素为中心的子窗口内展现的边缘像素图案的原型边缘特征。 然后,对于每个输入图像像素位置,识别以位于输入图像的每个边缘像素位置为中心的霍夫粒子的该位置处终止的偏移矢量的数量。 以每个像素位置为中心的霍夫核心是与原型边缘特征相关联的霍恩核,其最佳地表示在以该输入图像边缘像素位置为中心的子窗口内展现的边缘像素图案。 如果任何输入图像像素位置具有等于或超过检测阈值的偏移量向量终止,则该对象被声明为存在于输入图像中。