1.1 --- a/org/literature-review.org	Tue Mar 12 03:54:19 2013 +0000
     1.2 +++ b/org/literature-review.org	Tue Mar 12 03:54:30 2013 +0000
     1.3 @@ -1,3 +1,7 @@
     1.4 +When I write my thesis, I want it to have links to every 
     1.5 +
     1.6 +
     1.7 +
     1.8  * Object Recognition from Local Scale-Invariant Features, David G. Lowe
     1.9    
    1.10    This is the famous SIFT paper that is mentioned everywhere.
    1.11 @@ -41,10 +45,36 @@
    1.12    of the unknown epipolar geometry,” Artificial In- telligence, 78,
    1.13    (1995), pp. 87-119.
    1.14  
    1.15 -    
    1.16 -     
    1.17  
    1.18  
    1.19 -    
    1.20  
    1.21  
    1.22 +* Alignment by Maximization of Mutual Information, Paul A. Viola
    1.23 +
    1.24 +  PhD Thesis recommended by Winston. Describes a system that is able
    1.25 +  to align a 3D computer model of an object with an image of that
    1.26 +  object. 
    1.27 +  
    1.28 +  - Pages 9-19 is a very adequate intro to the algorithm.
    1.29 +  
    1.30 +  - Has a useful section on entropy and probability at the beginning
    1.31 +    which is worth reading, especially the part about entropy.
    1.32 +
    1.33 +  - Differential entropy seems a bit odd -- you would think that it
    1.34 +    should be the same as normal entropy for a discrete distrubition
    1.35 +    embedded in continuous space. How do you measure the entropy of a
    1.36 +    half continuous, half discrete random variable?
    1.37 +
    1.38 +  - Expectation Maximation (Mixture of Gaussians cool stuff)
    1.39 +    (Dempster 1977)
    1.40 +
    1.41 +  - Good introduction to Parzen Window Density Estimation. Parzen
    1.42 +    density functions trade construction time for evaulation
    1.43 +    time.(Pg. 41)
    1.44 +
    1.45 +  Occlusion? Seems a bit holistic.
    1.46 +
    1.47 +
    1.48 +** References
    1.49 + - "excellent" book on entropy (Cover & Thomas, 1991)
    1.50 + 
    1.51 \ No newline at end of file