Tampere University of Technology

TUTCRIS Research Portal

Application-specific instruction processor for extracting local binary patterns

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Details

Original languageEnglish
Title of host publicationDASIP 2012 - Proceedings of the 2012 Conference on Design and Architectures for Signal and Image Processing
Pages82-89
Number of pages8
Publication statusPublished - 2012
Publication typeA4 Article in a conference publication
Event6th Annual Conference on Design and Architectures for Signal and Image Processing, DASIP 2012 - Karlsruhe, Germany
Duration: 23 Oct 201225 Oct 2012

Conference

Conference6th Annual Conference on Design and Architectures for Signal and Image Processing, DASIP 2012
CountryGermany
CityKarlsruhe
Period23/10/1225/10/12

Abstract

Local Binary Pattern (LBP) is texture operator used in preprocessing for object detection, tracking, face recognition and fingerprint matching. Many of these applications are performed on embedded devices, which poses limitations on the implementation complexity and power consumption. As LBP features are computed pixelwise, high performance is required for real time extraction of LBP features from high resolution video. This paper presents an application-specific instruction processor for LBP extraction. The compact, yet powerful processor is capable of extracting LBP features from 1280 × 720p (30 fps) video with a reasonable 304 MHz clock rate. With a low power consumption and an area of less than 16k gates the processor is suitable for embedded devices. Experiments present resource and power consumption measured on an FPGA board, along with processor synthesis results. In terms of latency, our processor requires 17.5 × less clock cycles per LBP feature than a workstation implementation and only 2.0 × more than a hardwired ASIC.

Keywords

  • Digital signal processors, Feature extraction, Image texture analysis, Video signal processing