FJW's blog

Menu Close
  • Home
  • Archives
  • Categories

CV_Features

09/18/2017 Computer Vision

1. Blobs as Interest Points

  • Characteristic scale

    • 2nd derivative of Gaussian.
  • Normalize LOG

    • Basic Laplacian detector = local maxima of characteristic scale.
    • LOG is good for finding scale.
  • Use difference

2. Combine the Harris and Laplace

  • Combine methods to enhance detection and reliability.

3. SIFT

  • Scale-Invariant Feature Transform (SIFT).
Computer Vision

Prev
Django
Next
Probability, statistical distributions, descriptive statistics
Contents
  1. 1. 1. Blobs as Interest Points
  2. 2. 2. Combine the Harris and Laplace
  3. 3. 3. SIFT
© 2017-2025 upbad.com All Rights Reserved.