Please use this identifier to cite or link to this item: http://hdl.handle.net/10553/15753
Title: Evaluation of LBP and HOG descriptors for clothing attribute description
Authors: Lorenzo Navarro, José Javier 
Castrillón-Santana, Modesto 
Ramón Balmaseda, Enrique José 
Freire, David 
UNESCO Clasification: 120304 Inteligencia artificial
Keywords: LBP
HOG
Clothing description
Issue Date: 2014
Publisher: Springer 
Journal: Lecture Notes in Computer Science 
Conference: 1st International Workshop on Video Analytics for Audience Measurement (VAAM 2014) 
Abstract: In this work an experimental study about the capability of the LBP, HOG descriptors and color for clothing attribute classification is presented. Two different variants of the LBP descriptor are considered, the original LBP and the uniform LBP. Two classifiers, Linear SVM and Random Forest, have been included in the comparison because they have been frequently used in clothing attributes classification. The experiments are carried out with a public available dataset, the clothing attribute dataset, that has 26 attributes in total. The obtained accuracies are over 75% in most cases, reaching 80% for the necktie or sleeve length attributes.
URI: http://hdl.handle.net/10553/15753
ISBN: 978-3-319-12810-8
ISSN: 0302-9743
DOI: 10.1007/978-3-319-12811-5_4
Source: Video Analytics for Audience Measurement. VAAM 2014. Lecture Notes in Computer Science, v. 8811 LNCS, p. 53-65 (2014)
Appears in Collections:Capítulo de libro
Thumbnail
Adobe PDF (561,95 kB)
Show full item record

SCOPUSTM   
Citations

12
checked on Sep 25, 2022

WEB OF SCIENCETM
Citations

8
checked on Sep 25, 2022

Page view(s)

74
checked on Sep 4, 2022

Download(s)

140
checked on Sep 4, 2022

Google ScholarTM

Check

Altmetric


Share



Export metadata



This item is licensed under a Creative Commons License Creative Commons