Title: Implementing the local binary patterns with SIMD instructions of CPU
Authors: Juránek, Roman
Zemčík, Pavel
Herout, Adam
Citation: WSCG ’2010: Poster Proceedings: 18th International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision in co-operation with EUROGRAPHICS, p. 39-42.
Issue Date: 2010
Publisher: Václav Skala - UNION Agency
Document type: konferenční příspěvek
URI: http://wscg.zcu.cz/WSCG2010/Papers_2010/!_2010_Poster-proceedings.pdf
ISBN: 978-80-86943-86-2
Keywords: lokální binární vzory;statistické klasifikátory;detekce objektů
Keywords in different language: local binary patterns;statistical classifiers;AdaBoost;object detection
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.
Rights: © Václav Skala - UNION Agency
Appears in Collections:WSCG '2010: Poster Paper Proceedings

Files in This Item:
File Description SizeFormat 
Juranek.pdf164,9 kBAdobe PDFView/Open

Please use this identifier to cite or link to this item: http://hdl.handle.net/11025/1111

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.