1 / 31

Blob detection

Blob detection. Feature detection with s cale selection. We want to extract features with characteristic scale that is covariant with the image transformation. Blob detection: basic idea.

ophrah
Télécharger la présentation

Blob detection

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. Blob detection

  2. Feature detection with scale selection • We want toextract features with characteristic scale that is covariant with the image transformation

  3. Blob detection: basic idea • To detect blobs, convolve the image with a “blob filter” at multiple scales and look for maxima of filter response in the resulting scale space

  4. Blob filter • Laplacian of Gaussian: Circularly symmetric operator for blob detection in 2D

  5. Recall: Edge detection Edge f Derivativeof Gaussian Edge = maximumof derivative Source: S. Seitz

  6. Edge detection, Take 2 Edge f Second derivativeof Gaussian (Laplacian) Edge = zero crossingof second derivative Source: S. Seitz

  7. maximum From edges to blobs • Edge = ripple • Blob = superposition of two ripples Spatial selection: the magnitude of the Laplacianresponse will achieve a maximum at the center ofthe blob, provided the scale of the Laplacian is“matched” to the scale of the blob

  8. original signal(radius=8) increasing σ Scale selection • We want to find the characteristic scale of the blob by convolving it with Laplacians at several scales and looking for the maximum response • However, Laplacian response decays as scale increases:

  9. Scale normalization • The response of a derivative of Gaussian filter to a perfect step edge decreases as σ increases

  10. Scale normalization • The response of a derivative of Gaussian filter to a perfect step edge decreases as σ increases • To keep response the same (scale-invariant), must multiply Gaussian derivative by σ • Laplacian is the second Gaussian derivative, so it must be multiplied by σ2

  11. Scale-normalized Laplacian response maximum Effect of scale normalization Original signal Unnormalized Laplacian response

  12. Blob detection in 2D • Laplacian of Gaussian: Circularly symmetric operator for blob detection in 2D Scale-normalized:

  13. Scale selection • At what scale does the Laplacian achieve a maximum response to a binary circle of radius r? r image Laplacian

  14. Scale selection • At what scale does the Laplacian achieve a maximum response to a binary circle of radius r? • To get maximum response, the zeros of the Laplacian have to be aligned with the circle • The Laplacian is given by (up to scale): • Therefore, the maximum response occurs at circle r 0 Laplacian image

  15. Characteristic scale • We define the characteristic scale of a blob as the scale that produces peak of Laplacian response in the blob center characteristic scale T. Lindeberg (1998). "Feature detection with automatic scale selection."International Journal of Computer Vision30 (2): pp 77--116.

  16. Scale-space blob detector • Convolve image with scale-normalized Laplacian at several scales

  17. Scale-space blob detector: Example

  18. Scale-space blob detector: Example

  19. Scale-space blob detector • Convolve image with scale-normalized Laplacian at several scales • Find maxima of squared Laplacian response in scale-space

  20. Scale-space blob detector: Example

  21. Efficient implementation • Approximating the Laplacian with a difference of Gaussians: (Laplacian) (Difference of Gaussians)

  22. Efficient implementation David G. Lowe. "Distinctive image features from scale-invariant keypoints.”IJCV 60 (2), pp. 91-110, 2004.

  23. From feature detection to feature description • Scaled and rotated versions of the same neighborhood will give rise to blobs that are related by the same transformation • What to do if we want to compare the appearance of these image regions? • Normalization: transform these regions into same-size circles • Problem: rotational ambiguity

  24. p 2 0 Eliminating rotation ambiguity • To assign a unique orientation to circular image windows: • Create histogram of local gradient directions in the patch • Assign canonical orientation at peak of smoothed histogram

  25. SIFT features • Detected features with characteristic scales and orientations: David G. Lowe. "Distinctive image features from scale-invariant keypoints.”IJCV 60 (2), pp. 91-110, 2004.

  26. SIFT descriptors David G. Lowe. "Distinctive image features from scale-invariant keypoints.”IJCV 60 (2), pp. 91-110, 2004.

  27. Invariance vs. covariance • Invariance: • features(transform(image)) = features(image) • Covariance: • features(transform(image)) = transform(features(image)) Covariant detection => invariant description

  28. Affine adaptation • Affine transformation approximates viewpoint changes for roughly planar objects and roughly orthographic cameras

  29. direction of the fastest change direction of the slowest change (max)-1/2 (min)-1/2 Affine adaptation Consider the second moment matrix of the window containing the blob: Recall: This ellipse visualizes the “characteristic shape” of the window

  30. Affine adaptation example Scale-invariant regions (blobs)

  31. Affine adaptation example Affine-adapted blobs

More Related