LDAHash: Improved matching with smaller descriptors

Christoph Strecha, Alexander M. Bronstein, Michael M. Bronstein, Pascal Fua

Research output: Contribution to journalArticlepeer-review

Abstract

SIFT-like local feature descriptors are ubiquitously employed in computer vision applications such 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. Second, 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.

Original languageEnglish
Article number5770264
Pages (from-to)66-78
Number of pages13
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Volume34
Issue number1
DOIs
StatePublished - 2012
Externally publishedYes

Keywords

  • 3D reconstruction
  • DAISY
  • Local features
  • SIFT
  • binarization
  • matching
  • metric learning
  • similarity-sensitive hashing

Fingerprint

Dive into the research topics of 'LDAHash: Improved matching with smaller descriptors'. Together they form a unique fingerprint.

Cite this