UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Evolving weighting schemes for the Bag of Visual Words

Jair Escalante, H; Ponce-Lopez, V; Escalera, S; Baro, X; Morales-Reyes, A; Martinez-Carranza, J; (2017) Evolving weighting schemes for the Bag of Visual Words. Neural Computing and Applications , 28 (5) pp. 925-939. 10.1007/s00521-016-2223-x. Green open access

[thumbnail of Ponce Lopez_NCA2016_EvolvingWeighting.pdf]
Preview
Text
Ponce Lopez_NCA2016_EvolvingWeighting.pdf - Accepted Version

Download (8MB) | Preview

Abstract

The Bag of Visual Words (BoVW) is an established representation in computer vision. Taking inspiration from text mining, this representation has proved to be very effective in many domains. However, in most cases, standard term-weighting schemes are adopted (e.g., term-frequency or TF-IDF). It remains open the question of whether alternative weighting schemes could boost the performance of methods based on BoVW. More importantly, it is unknown whether it is possible to automatically learn and determine effective weighting schemes from scratch. This paper brings some light into both of these unknowns. On the one hand, we report an evaluation of the most common weighting schemes used in text mining, but rarely used in computer vision tasks. Besides, we propose an evolutionary algorithm capable of automatically learning weighting schemes for computer vision problems. We report empirical results of an extensive study in several computer vision problems. Results show the usefulness of the proposed method.

Type: Article
Title: Evolving weighting schemes for the Bag of Visual Words
Open access status: An open access version is available from UCL Discovery
DOI: 10.1007/s00521-016-2223-x
Publisher version: http://dx.doi.org/10.1007/s00521-016-2223-x
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
Keywords: Bag of Visual Words, Bag of features, Genetic programming, Term-weighting schemes, Computer vision, RECOGNITION
UCL classification: UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of the Built Environment
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of the Built Environment > Bartlett School Env, Energy and Resources
URI: https://discovery.ucl.ac.uk/id/eprint/10115348
Downloads since deposit
80Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item