000152487 001__ 152487
000152487 005__ 20180317092318.0
000152487 037__ $$aREP_WORK
000152487 245__ $$aLDAHash: Improved matching with smaller descriptors
000152487 269__ $$a2010
000152487 260__ $$c2010
000152487 300__ $$a26
000152487 336__ $$aReports
000152487 520__ $$aSIFT-like local feature descriptors are ubiquitously employed in such computer vision applications as content-based retrieval, video analysis, copy detection, object recognition, photo-tourism and 3D reconstruction.  Feature descriptors can be designed to be invariant to certain classes of photometric and geometric transformations, in particular, affine and intensity scale transformations. However, real transformations that an image can undergo can only be approximately modeled in this way, and thus most descriptors are only approximately invariant in practice.  Secondly, descriptors are usually high-dimensional (e.g. SIFT is represented as a 128-dimensional vector). In large-scale retrieval and matching problems, this can pose challenges in storing and retrieving descriptor data.  We map the descriptor vectors into the Hamming space, in which the Hamming metric is used to compare the resulting representations.  This way, we reduce the size of the descriptors by representing them as short binary strings and learn descriptor invariance from examples.   We show extensive experimental validation, demonstrating the advantage of the proposed approach.
000152487 6531_ $$aLocal features
000152487 6531_ $$amatching
000152487 6531_ $$a3D reconstruction
000152487 6531_ $$ametric learning
000152487 6531_ $$asimilarity-sensitive hashing
000152487 6531_ $$abinarization
000152487 6531_ $$aDAISY
000152487 6531_ $$aSIFT
000152487 700__ $$0244088$$aStrecha, Christoph$$g182325
000152487 700__ $$aBronstein, Alexander M.
000152487 700__ $$aBronstein, Michael M.
000152487 700__ $$0240252$$aFua, Pascal$$g112366
000152487 8564_ $$uhttp://cvlab.epfl.ch/software/index.php$$zURL
000152487 8564_ $$s7815674$$uhttps://infoscience.epfl.ch/record/152487/files/ldahashtr2010.pdf$$yn/a$$zn/a
000152487 909CO $$ooai:infoscience.tind.io:152487$$preport$$pIC
000152487 909C0 $$0252087$$pCVLAB$$xU10659
000152487 917Z8 $$x182325
000152487 937__ $$aEPFL-REPORT-152487
000152487 973__ $$aEPFL$$sPUBLISHED
000152487 980__ $$aREPORT