会员体验
专利管家(专利管理)
工作空间(专利管理)
风险监控(情报监控)
数据分析(专利分析)
侵权分析(诉讼无效)
联系我们
交流群
官方交流:
QQ群: 891211   
微信请扫码    >>>
现在联系顾问~
热词
    • 4. 发明授权
    • Quadrature shape detection using the flow integration transform
    • 使用流积分变换的正交形状检测
    • US5550933A
    • 1996-08-27
    • US249342
    • 1994-05-27
    • George D. Stetten
    • George D. Stetten
    • G06K9/64G06K9/48
    • G06K9/6204
    • A transform, the Flow Integration Transform (FIT), is applied for determining the presence of a preconceived shape in a gray scale image. The FIT represents a form of Quadrature Shape Detection. The expected contour serves as a filter for detecting potential targets as periodic signals. The FIT performs a line integral of two vectors: (1) the flow, a vector equal to the gradient of the image's intensity but rotated by 90 degrees, and (2) the local tangent to the path of integration. The path of integration follows the expected contour. The integration is performed starting at each point in the image, producing a two-dimensional transform whose pixel value corresponds to the relative presence of the contour at that location in the input image. The transform exhibits the feature that information widely dispersed in the image becomes concentrated in a local area of the transform.
    • 流变积分变换(FIT)被应用于确定在灰度图像中存在预先成形的形状。 FIT表示正交形状检测的一种形式。 期望的轮廓用作用于检测潜在目标作为周期信号的滤波器。 FIT执行两个向量的线积分:(1)流量,等于图像强度的梯度但旋转90度的矢量,以及(2)积分路径的局部切线。 整合的路径遵循预期的轮廓。 从图像中的每个点开始执行积分,产生二维变换,其像素值对应于输入图像中该位置处的轮廓的相对存在。 该变换表现出广泛分散在图像中的信息变得集中在变换的局部区域中的特征。