diff options
Diffstat (limited to 'SD-VBS/benchmarks/sift/src/matlab/siftdescriptor.m')
-rw-r--r-- | SD-VBS/benchmarks/sift/src/matlab/siftdescriptor.m | 79 |
1 files changed, 79 insertions, 0 deletions
diff --git a/SD-VBS/benchmarks/sift/src/matlab/siftdescriptor.m b/SD-VBS/benchmarks/sift/src/matlab/siftdescriptor.m new file mode 100644 index 0000000..7764897 --- /dev/null +++ b/SD-VBS/benchmarks/sift/src/matlab/siftdescriptor.m | |||
@@ -0,0 +1,79 @@ | |||
1 | % SIFTDESCRIPTOR Compute SIFT descriptors | ||
2 | % DESCR = SIFTDESCRIPTOR(G, P, SIGMA0, S, MINS) computes the SIFT | ||
3 | % descriptors DESCR of the SIFT frames P defined on the octave G of | ||
4 | % a Gaussian scale space. SIGMA0, S and MINS are the the parameter | ||
5 | % of the scale space as explained in PDF:SIFT.USER.SS. P has one | ||
6 | % column per frame, specifiying the center X1,X2, the scal index s | ||
7 | % and the orientation THETA of the frame. | ||
8 | % | ||
9 | % As the function operates on a single octave, in order to process | ||
10 | % features spanning several octaves, one must group them and call | ||
11 | % SIFTDESCRIPTOR() once per each octave. | ||
12 | % | ||
13 | % DESCR = SIFTDESCRIPTOR(I, P, SIGMA0) operates on a plain image | ||
14 | % I. The image I is assumed to be pre-smoothed at scale SIGMA0 and P | ||
15 | % is a matrix with a column per frame, specifying the center X1,X2 | ||
16 | % and the orientation THETA (but NOT the scale). | ||
17 | % | ||
18 | % REMARK. The scale parameter s in P is the scale index, NOT the | ||
19 | % scale coordinate (see the PDF doc. for a discussion). | ||
20 | % | ||
21 | % Other parameters can be specfied as option-value paris. These | ||
22 | % are | ||
23 | % | ||
24 | % 'Magnif' [3.0] | ||
25 | % Frame magnification factor. Each spatial bin of the SIFT | ||
26 | % histogram has an exentsion equal to magnif * sigma, where | ||
27 | % magnif is the frame magnification factor and sigma is the scale | ||
28 | % of the frame. | ||
29 | % | ||
30 | % 'NumSpatialBins' [4] | ||
31 | % This parameter specifies the number of spatial bins in each | ||
32 | % spatial direction x1 and x2. It must be a positive and even | ||
33 | % number. | ||
34 | % | ||
35 | % 'NumOrientBins' [8] | ||
36 | % This parameter specifies the number of orietnation bins. It | ||
37 | % must be a positive number. | ||
38 | % | ||
39 | % See also SIFT(), GAUSSIANSS(), DIFFSS(), SIFTLOCALMAX(), | ||
40 | % PDF:SIFT.USER.DESCRIPTOR. | ||
41 | |||
42 | % AUTORIGHTS | ||
43 | % Copyright (c) 2006 The Regents of the University of California. | ||
44 | % All Rights Reserved. | ||
45 | % | ||
46 | % Created by Andrea Vedaldi | ||
47 | % UCLA Vision Lab - Department of Computer Science | ||
48 | % | ||
49 | % Permission to use, copy, modify, and distribute this software and its | ||
50 | % documentation for educational, research and non-profit purposes, | ||
51 | % without fee, and without a written agreement is hereby granted, | ||
52 | % provided that the above copyright notice, this paragraph and the | ||
53 | % following three paragraphs appear in all copies. | ||
54 | % | ||
55 | % This software program and documentation are copyrighted by The Regents | ||
56 | % of the University of California. The software program and | ||
57 | % documentation are supplied "as is", without any accompanying services | ||
58 | % from The Regents. The Regents does not warrant that the operation of | ||
59 | % the program will be uninterrupted or error-free. The end-user | ||
60 | % understands that the program was developed for research purposes and | ||
61 | % is advised not to rely exclusively on the program for any reason. | ||
62 | % | ||
63 | % This software embodies a method for which the following patent has | ||
64 | % been issued: "Method and apparatus for identifying scale invariant | ||
65 | % features in an image and use of same for locating an object in an | ||
66 | % image," David G. Lowe, US Patent 6,711,293 (March 23, | ||
67 | % 2004). Provisional application filed March 8, 1999. Asignee: The | ||
68 | % University of British Columbia. | ||
69 | % | ||
70 | % IN NO EVENT SHALL THE UNIVERSITY OF CALIFORNIA BE LIABLE TO ANY PARTY | ||
71 | % FOR DIRECT, INDIRECT, SPECIAL, INCIDENTAL, OR CONSEQUENTIAL DAMAGES, | ||
72 | % INCLUDING LOST PROFITS, ARISING OUT OF THE USE OF THIS SOFTWARE AND | ||
73 | % ITS DOCUMENTATION, EVEN IF THE UNIVERSITY OF CALIFORNIA HAS BEEN | ||
74 | % ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. THE UNIVERSITY OF | ||
75 | % CALIFORNIA SPECIFICALLY DISCLAIMS ANY WARRANTIES, INCLUDING, BUT NOT | ||
76 | % LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR | ||
77 | % A PARTICULAR PURPOSE. THE SOFTWARE PROVIDED HEREUNDER IS ON AN "AS IS" | ||
78 | % BASIS, AND THE UNIVERSITY OF CALIFORNIA HAS NO OBLIGATIONS TO PROVIDE | ||
79 | % MAINTENANCE, SUPPORT, UPDATES, ENHANCEMENTS, OR MODIFICATIONS. | ||