×

Efficient scale-space extraction and description of interest points

  • US 20110194772A1
  • Filed: 09/01/2010
  • Published: 08/11/2011
  • Est. Priority Date: 02/08/2010
  • Status: Active Grant
First Claim
Patent Images

1. A method for keypoints scale-space extraction and description in an image, the method comprising the following steps:

  • a) Filtering the image with triangle kernel filters at different scalesb) Computing an approximation of a determinant of Hessian at each scale, where this approximation at each scale k, is calculated as |∂

    kxx(i, j)·



    kyy(i, j)−



    kxy(i, j)2| where
    text missing or illegible when filed
    text missing or illegible when filed
    text missing or illegible when filedwhere L(k, i, j) is the filtered image response obtained in step a) at scale k at point (i, j) and here d1 and d2 are design parametersc) Searching for extremum values both within a single scale and along the scale space of the approximation of the determinant of Hessian obtained in step b) and calculating the keypoints from these extrema valuesd) For each keypoint, localised at an extremum value, detecting the dominant orientations from gradient information calculated using the filtered image response obtained in step a)e) Calculating for each dominant orientation a keypoint descriptor

View all claims
  • 3 Assignments
Timeline View
Assignment View
    ×
    ×