Publication detail
Implementing the Local Binary Patterns with SIMD Instructions of CPU
HEROUT, A. JURÁNEK, R. ZEMČÍK, P.
Original Title
Implementing the Local Binary Patterns with SIMD Instructions of CPU
English Title
Implementing the Local Binary Patterns with SIMD Instructions of CPU
Type
conference paper
Language
en
Original Abstract
Usage of statistical classifiers, namely AdaBoost and its modifications, is very common in object detection and pattern recognition. Performance of such classifiers strongly depends on low level features they use. This paper presents an experimental implementation of the Local Binary Patterns (LBP) that uses SIMD instructions for acceleration. The experiments shows that the proposed implementation is about six times faster than the plain C implementation (i.e. with no special optimizations) and superior to optimized implementations of features with similar descriptive power.
English abstract
Usage of statistical classifiers, namely AdaBoost and its modifications, is very common in object detection and pattern recognition. Performance of such classifiers strongly depends on low level features they use. This paper presents an experimental implementation of the Local Binary Patterns (LBP) that uses SIMD instructions for acceleration. The experiments shows that the proposed implementation is about six times faster than the plain C implementation (i.e. with no special optimizations) and superior to optimized implementations of features with similar descriptive power.
Keywords
LBP, AdaBoost, Object Detection, Feature Extraction, SIMD, SSE, CUDA
RIV year
2010
Released
22.04.2010
Publisher
University of West Bohemia in Pilsen
Location
Plzeň
ISBN
978-80-86943-86-2
Book
Proceedings of WSCG 2010
Edition
NEUVEDEN
Edition number
NEUVEDEN
Pages from
39
Pages to
42
Pages count
4
URL
Documents
BibTex
@inproceedings{BUT34653,
author="Adam {Herout} and Roman {Juránek} and Pavel {Zemčík}",
title="Implementing the Local Binary Patterns with SIMD Instructions of CPU",
annote="Usage of statistical classifiers, namely AdaBoost and its modifications, is very
common in object detection and pattern recognition. Performance of such
classifiers strongly depends on low level features they use. This paper presents
an experimental implementation of the Local Binary Patterns (LBP) that uses SIMD
instructions for acceleration. The experiments shows that the proposed
implementation is about six times faster than the plain C implementation (i.e.
with no special optimizations) and superior to optimized implementations of
features with similar descriptive power.",
address="University of West Bohemia in Pilsen",
booktitle="Proceedings of WSCG 2010",
chapter="34653",
edition="NEUVEDEN",
howpublished="print",
institution="University of West Bohemia in Pilsen",
year="2010",
month="april",
pages="39--42",
publisher="University of West Bohemia in Pilsen",
type="conference paper"
}