Difference between revisions of "Object Recognition"

From Robot Intelligence
Jump to: navigation, search
Line 18: Line 18:
  
 
* Shape-Based Feature Point Extraction
 
* Shape-Based Feature Point Extraction
** Contour Fragment-based SPCF (Sampled Points from Contour Fragments) feaetures
+
** Contour Fragment-based SPCF (Sampled Points from Contour Fragments) features
  
 
* Descriptor Computation in Bisected Local Regions
 
* Descriptor Computation in Bisected Local Regions
 
** Rotation-invariant shape contexts with geometric blur
 
** Rotation-invariant shape contexts with geometric blur
 
** Color histogram in the  opponent color space
 
** Color histogram in the  opponent color space
::[[File:iden_blr.png|500px]]
+
::[[File:iden_blr.png]]

Revision as of 18:12, 17 June 2016

Object Categorization

  • Affine Category Shape Model
    • Contour fragment-based SPCF (Sampled Points from Contour Fragments) features
    • Rotation-invariant shape contexts with geometric blur
Cate pairwise.png
  • Spectral Matching
    • Pairwise geometric descriptors between features
  • Object Localization
    • RANSAC-based outlier removal
Cate overview.png


Object Identification

  • Shape-Based Feature Point Extraction
    • Contour Fragment-based SPCF (Sampled Points from Contour Fragments) features
  • Descriptor Computation in Bisected Local Regions
    • Rotation-invariant shape contexts with geometric blur
    • Color histogram in the opponent color space
Iden blr.png