Efficient Matching with Invariant Local Descriptors - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 1998

Efficient Matching with Invariant Local Descriptors


We are addressing the problem of matching images of scene or of objects when a large collection of reference objects is considered. The paper addresses also the issue of dealing with illumination change and camera position changes. Our approach is firstly based on the use of invariants. Invariants have to be computed locally so that the resulting values will not affected by partial occlusion or accidental highlights. In- variants proved to be a very discriminant piece of information and stored in a hash table they allow efficient indexing of visual shape. Final recognition can be performed using simply a robust voting technique or can be improved using Bayesian decision.

Dates and versions

inria-00548332 , version 1 (20-12-2010)



Roger Mohr, Patrick Gros, Cordelia Schmid. Efficient Matching with Invariant Local Descriptors. Joint IAPR International Workshops SSPR'98 and SPR'98, Aug 1998, Sydney, Australia. pp.54--71, ⟨10.1007/BFb0033226⟩. ⟨inria-00548332⟩
83 View
0 Download



Gmail Facebook X LinkedIn More