Featured post

c# - Usage of Server Side Controls in MVC Frame work -

i using asp.net 4.0 , mvc 2.0 web application. project requiremrnt have use server side control in application not possibl in noraml case. ideally want use adrotator control , datalist control. i saw few samples , references in codepleax mvc controllib howwver found less useful. can tell how utilize theese controls in asp.net application along mvc. note: please provide functionalities related adrotator , datalist controls not equivalent functionalities thanks in advace. mvc pages not use normal .net solution makes use of normal .net components impossible. a normal .net page use event driven solution call different methods service side mvc use actions , view completly different way handle things. also, mvc not use viewstate normal .net controlls require. found article discussing mixing of normal .net , mvc.

optimization - Retrieving the most significant features gained from SIFT / SURF -


i'm using surf extract features images , match them others. problem images have in excess of 20000 features slows down matching crawl.

is there way can extract n significant features set?

i tried computing mser image , use features within regions. gives me reduction anywhere 5% 40% without affecting matching quality negatively, that's unreliable , still not enough.
additionally size image down, seems affect quality of features severely in cases.
surf offers few parameters (hessian threshold, octaves , layers per octave) couldn't find on how changing these affect feature significance.

after researching , testing have found hessian value each feature rough estimate of it's strength, using top n features sorted hessian not optimal.
achieved better results when doing following until number of features below target of n:

  • size image down, if overly large
  • only features lie in mser regions considered
  • for features lie close each other, feature higher hessian considered
  • of n features per image want save, 75% features highest hessian values
  • the remaining features taken randomly remainder, weighted distribution of hessian values computed through histogram

now need find suitable n, around 1500 seems enough currently.


Comments

Popular posts from this blog

ios - Very simple iPhone App crashes on UILabel settext -

mysql - Why there can be only one TIMESTAMP column with CURRENT_TIMESTAMP in DEFAULT clause? -

c# - Usage of Server Side Controls in MVC Frame work -