1.1 --- /dev/null	Thu Jan 01 00:00:00 1970 +0000
     1.2 +++ b/org/literature-review.org	Sun Mar 10 18:17:53 2013 +0000
     1.3 @@ -0,0 +1,50 @@
     1.4 +* Object Recognition from Local Scale-Invariant Features, David G. Lowe
     1.5 +  
     1.6 +  This is the famous SIFT paper that is mentioned everywhere.
     1.7 +
     1.8 +  This is a way to find objects in images given an image of that
     1.9 +  object. It is moderately risistant to variations in the sample image
    1.10 +  and the target image. Basically, this is a fancy way of picking out
    1.11 +  a test pattern embedded in a larger pattern. It would fail to learn
    1.12 +  anything resembling object categories, for instance. Usefull concept
    1.13 +  is the idea of storing the local scale and rotation of each feature
    1.14 +  as it is extracted from the image, then checking to make sure that
    1.15 +  proposed matches all more-or-less agree on shift, rotation, scale,
    1.16 +  etc.  Another good idea is to use points instead of edges, since
    1.17 +  they seem more robust.
    1.18 +
    1.19 +** References:
    1.20 + - Basri, Ronen, and David. W. Jacobs, “Recognition using region
    1.21 +  correspondences,” International Journal of Computer Vision, 25, 2
    1.22 +  (1996), pp. 141–162.
    1.23 +  
    1.24 + - Edelman, Shimon, Nathan Intrator, and Tomaso Poggio, “Complex
    1.25 +  cells and object recognition,” Unpublished Manuscript, preprint at
    1.26 +  http://www.ai.mit.edu/edelman/mirror/nips97.ps.Z
    1.27 +  
    1.28 + - Lindeberg, Tony, “Detecting salient blob-like image structures
    1.29 +  and their scales with a scale-space primal sketch: a method for
    1.30 +  focus-of-attention,” International Journal of Computer Vision, 11, 3
    1.31 +  (1993), pp. 283–318.
    1.32 +  
    1.33 + - Murase, Hiroshi, and Shree K. Nayar, “Visual learning and
    1.34 +  recognition of 3-D objects from appearance,” International Journal
    1.35 +  of Computer Vision, 14, 1 (1995), pp. 5–24.
    1.36 +
    1.37 + - Ohba, Kohtaro, and Katsushi Ikeuchi, “Detectability, uniqueness,
    1.38 +  and reliability of eigen windows for stable verification of
    1.39 +  partially occluded objects,” IEEE Trans. on Pattern Analysis and
    1.40 +  Machine Intelligence, 19, 9 (1997), pp. 1043–48.
    1.41 +
    1.42 + - Zhang, Z., R. Deriche, O. Faugeras, Q.T. Luong, “A robust
    1.43 +  technique for matching two uncalibrated images through the recovery
    1.44 +  of the unknown epipolar geometry,” Artificial In- telligence, 78,
    1.45 +  (1995), pp. 87-119.
    1.46 +
    1.47 +    
    1.48 +     
    1.49 +
    1.50 +
    1.51 +    
    1.52 +
    1.53 +

     2.1 --- a/org/notes.org	Thu Mar 07 07:54:38 2013 +0000
     2.2 +++ b/org/notes.org	Sun Mar 10 18:17:53 2013 +0000
     2.3 @@ -31,7 +31,7 @@
     2.4  
     2.5  Microsoft Research flickr city square
     2.6  
     2.7 -celiu -- M$ motion guy 
     2.8 +Ce Liu -- M$ motion guy 
     2.9  
    2.10  prakesh -- read paper
    2.11