Discriminant Embedding for Local Image Descriptors

Gang Hua, Matthew Brown, Simon Winder

Research output: Contribution to conferencePaperpeer-review

160 Citations (SciVal)


Invariant feature descriptors such as SIFT and GLOH have been demonstrated to be very robust for image matching and visual recognition. However, such descriptors are generally parameterised in very high dimensional spaces e.g. 128 dimensions in the case of SIFT. This limits the performance of feature matching techniques in terms of speed and scalability. Furthermore, these descriptors have traditionally been carefully hand crafted by manually tuning many parameters. In this paper, we tackle both of these problems by formulating descriptor design as a non- parametric dimensionality reduction problem. In contrast to previous approaches that use only the global statistics of the inputs, we adopt a discriminative approach. Starting from a large training set of labelled match/non-match pairs, we pursue lower dimensional embeddings that are optimised for their discriminative power. Extensive comparative experiments demonstrate that we can exceed the performance of the current state of the art techniques such as SIFT with far fewer dimensions, and with virtually no parameters to be tuned by hand.
Original languageEnglish
Publication statusPublished - Oct 2007
EventICCV 2007: IEEE 11th International Conference on Computer Vision, 2007 - Rio de Janeiro
Duration: 14 Oct 200721 Oct 2007


ConferenceICCV 2007: IEEE 11th International Conference on Computer Vision, 2007
CityRio de Janeiro


Dive into the research topics of 'Discriminant Embedding for Local Image Descriptors'. Together they form a unique fingerprint.

Cite this