Fast low-level multi-scale feature extraction for hexagonal images

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Downloads (Pure)

Abstract

Inspired by the human vision system and its capability to process in real-time, an efficient framework for low-level feature extraction on hexagonal pixel-based images is presented. This is achieved by utilizing the spiral architecture addressing scheme to simulate eye-tremor along with the convolution of non-overlapping gradient masks. Using sparse spiral convolution and the development of cluster operators, we obtain a set of output image responses “a-trous” that is subsequently collated into a consolidated output response; it is also demonstrated that this framework can be extended to feature extraction at different scales. We show that the proposed framework is considerably faster than using conventional spiral convolution or the use of look-up tables for direct access to hexagonal pixel neighbourhood addresses.
Original languageEnglish
Title of host publicationUnknown Host Publication
PublisherIEEE
Pages342-345
Number of pages4
ISBN (Print)978-4-9011-2216-0
Publication statusE-pub ahead of print - 20 Jul 2017
Event2017 Fifteenth IAPR International Conference on Machine Vision Applications (MVA) - Japan
Duration: 20 Jul 2017 → …

Conference

Conference2017 Fifteenth IAPR International Conference on Machine Vision Applications (MVA)
Period20/07/17 → …

    Fingerprint

Keywords

  • Spirals
  • Convolution
  • Machine vision
  • Feature extraction
  • Indexes
  • Computer architecture
  • Organisations

Cite this