A One-pass Resource-Allocating Codebook for Patch-based Visual Object Recognition


Ramanan, Amirthalingam and Niranjan, Mahesan (2010) A One-pass Resource-Allocating Codebook for Patch-based Visual Object Recognition At IEEE Workshop on Machine Learning for Signal Processing, Finland. 29 Aug - 01 Sep 2010.

Download

[img] PDF MLSP10.pdf - Other
Download (100kB)

Description/Abstract

Frequencies of occurrence of low-level image features is the representation of choice in the design of state-of-the-art visual object recognition systems. A crucial step in this process is the construction of a codebook of visual features, which is usually done by cluster analysis of a large number of low-level image features detected as interest points. However, clustering is a process that retains regions of high density in a distribution and it follows that the resulting codebook need not have discriminant properties. Here we extend our recent work on constructing a one-pass discriminant codebook design procedure inspired by the resource allocating network model from the artificial neural networks literature. Unlike clustering, this approach retains data spread out more widely in the input space, thereby including rare low-level features in the codebook. It simultaneously achieves increased discrimination and a drastic reduction in the computational needs. We illustrate some properties of our method and compare it to a closely related approach.

Item Type: Conference or Workshop Item (Paper)
Additional Information: Event Dates: August 29 - September 1, 2010
Venue - Dates: IEEE Workshop on Machine Learning for Signal Processing, Finland, 2010-08-29 - 2010-09-01
Keywords: Visual Codebook, Bag-of-features, SIFT, Cluster analysis, Object Recognition
Organisations: Southampton Wireless Group
ePrint ID: 265448
Date :
Date Event
18 June 2010Published
Date Deposited: 04 Jul 2010 18:09
Last Modified: 17 Apr 2017 19:18
Further Information:Google Scholar
URI: http://eprints.soton.ac.uk/id/eprint/265448

Actions (login required)

View Item View Item