Skip to content

Publications

Detail of publication

Citation

Lukáš Bureš and Filip Berka and Luděk Müller : Comparsion of Feature Extraction Methods for Finding Similar Images . International Conference on Interactive Collaborative Robotics, ICR 2017, Lecture Notes in Computer Science, LNAI 10459, p. 29-36, Springer, 2017.

Additional information


Springer

Abstract

In this paper, we compare four methods of feature extraction for finding similar images. We created our own dataset which consists of 34500 colour images of various types of footwear and other accessories. We describe the methods that we experimented with and present results achieved with all of them. We presented the results to 23 people who then rated the performance of these methods. The best–rated method is selected for further research.

Detail of publication

Title: Comparsion of Feature Extraction Methods for Finding Similar Images
Author: Lukáš Bureš ; Filip Berka ; Luděk Müller
Language: English
Year: 2017
Type of publication: Papers in proceedings of reviewed conferences
Title of journal or book: International Conference on Interactive Collaborative Robotics, ICR 2017
Edition: Lecture Notes in Computer Science, LNAI 10459
Page: 29 - 36
DOI: 10.1007/978-3-319-66471-2_4
Publisher: Springer
Date: 12 Sep 2017 - 16 Sep 2017
/ 2019-11-20 17:13:00 /

Keywords

Image similarity, Feature extraction, Local binary patterns, Colour histogram, Histogram of oriented gradients, Convolution neural network

BibTeX

@INPROCEEDINGS{LukasBures_2017_ComparsionofFeature,
 author = {Luk\'{a}\v{s} Bure\v{s} and Filip Berka and Lud\v{e}k M\"{u}ller},
 title = {Comparsion of Feature Extraction Methods for Finding Similar Images},
 year = {2017},
 publisher = {Springer},
 journal = {International Conference on Interactive Collaborative Robotics, ICR 2017},
 pages = {29-36},
 doi = {10.1007/978-3-319-66471-2_4},
 url = {http://www.kky.zcu.cz/en/publications/LukasBures_2017_ComparsionofFeature},
}