|
rlm@369
|
1 * Object Recognition from Local Scale-Invariant Features, David G. Lowe
|
|
rlm@369
|
2
|
|
rlm@369
|
3 This is the famous SIFT paper that is mentioned everywhere.
|
|
rlm@369
|
4
|
|
rlm@369
|
5 This is a way to find objects in images given an image of that
|
|
rlm@369
|
6 object. It is moderately risistant to variations in the sample image
|
|
rlm@369
|
7 and the target image. Basically, this is a fancy way of picking out
|
|
rlm@369
|
8 a test pattern embedded in a larger pattern. It would fail to learn
|
|
rlm@369
|
9 anything resembling object categories, for instance. Usefull concept
|
|
rlm@369
|
10 is the idea of storing the local scale and rotation of each feature
|
|
rlm@369
|
11 as it is extracted from the image, then checking to make sure that
|
|
rlm@369
|
12 proposed matches all more-or-less agree on shift, rotation, scale,
|
|
rlm@369
|
13 etc. Another good idea is to use points instead of edges, since
|
|
rlm@369
|
14 they seem more robust.
|
|
rlm@369
|
15
|
|
rlm@369
|
16 ** References:
|
|
rlm@369
|
17 - Basri, Ronen, and David. W. Jacobs, “Recognition using region
|
|
rlm@369
|
18 correspondences,” International Journal of Computer Vision, 25, 2
|
|
rlm@369
|
19 (1996), pp. 141–162.
|
|
rlm@369
|
20
|
|
rlm@369
|
21 - Edelman, Shimon, Nathan Intrator, and Tomaso Poggio, “Complex
|
|
rlm@369
|
22 cells and object recognition,” Unpublished Manuscript, preprint at
|
|
rlm@369
|
23 http://www.ai.mit.edu/edelman/mirror/nips97.ps.Z
|
|
rlm@369
|
24
|
|
rlm@369
|
25 - Lindeberg, Tony, “Detecting salient blob-like image structures
|
|
rlm@369
|
26 and their scales with a scale-space primal sketch: a method for
|
|
rlm@369
|
27 focus-of-attention,” International Journal of Computer Vision, 11, 3
|
|
rlm@369
|
28 (1993), pp. 283–318.
|
|
rlm@369
|
29
|
|
rlm@369
|
30 - Murase, Hiroshi, and Shree K. Nayar, “Visual learning and
|
|
rlm@369
|
31 recognition of 3-D objects from appearance,” International Journal
|
|
rlm@369
|
32 of Computer Vision, 14, 1 (1995), pp. 5–24.
|
|
rlm@369
|
33
|
|
rlm@369
|
34 - Ohba, Kohtaro, and Katsushi Ikeuchi, “Detectability, uniqueness,
|
|
rlm@369
|
35 and reliability of eigen windows for stable verification of
|
|
rlm@369
|
36 partially occluded objects,” IEEE Trans. on Pattern Analysis and
|
|
rlm@369
|
37 Machine Intelligence, 19, 9 (1997), pp. 1043–48.
|
|
rlm@369
|
38
|
|
rlm@369
|
39 - Zhang, Z., R. Deriche, O. Faugeras, Q.T. Luong, “A robust
|
|
rlm@369
|
40 technique for matching two uncalibrated images through the recovery
|
|
rlm@369
|
41 of the unknown epipolar geometry,” Artificial In- telligence, 78,
|
|
rlm@369
|
42 (1995), pp. 87-119.
|
|
rlm@369
|
43
|
|
rlm@369
|
44
|
|
rlm@369
|
45
|
|
rlm@369
|
46
|
|
rlm@369
|
47
|
|
rlm@369
|
48
|
|
rlm@369
|
49
|
|
rlm@369
|
50
|
