A Cloud-based Data Analysis Framework for Object Recognition

Rezvan Pakdel, John Herbert

2015

Abstract

This paper presents a Cloud-based framework using parallel data processing to identify and recognize an object from an image. Images contain a massive amount of information. Features such as shape, corner, color, and edge can be extracted from images. These features can be used to recognize an object. In a Cloud-based data analytics framework, feature detection algorithms can be done in parallel to get the result faster in comparison to a single machine. This study provides a Cloud-based architecture as a solution for large-scale datasets to decrease processing time and save hardware costs. The evaluation results indicate that the proposed approach can robustly identify and recognize objects in images.

Paper Citation

in Harvard Style

Pakdel R. and Herbert J. (2015). A Cloud-based Data Analysis Framework for Object Recognition . In Proceedings of the 5th International Conference on Cloud Computing and Services Science - Volume 1: CLOSER, ISBN 978-989-758-104-5, pages 79-86. DOI: 10.5220/0005409900790086

in Bibtex Style

@conference{closer15,
author={Rezvan Pakdel and John Herbert},
title={A Cloud-based Data Analysis Framework for Object Recognition},
booktitle={Proceedings of the 5th International Conference on Cloud Computing and Services Science - Volume 1: CLOSER,},
year={2015},
pages={79-86},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005409900790086},
isbn={978-989-758-104-5},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 5th International Conference on Cloud Computing and Services Science - Volume 1: CLOSER,
TI - A Cloud-based Data Analysis Framework for Object Recognition
SN - 978-989-758-104-5
AU - Pakdel R.
AU - Herbert J.
PY - 2015
SP - 79
EP - 86
DO - 10.5220/0005409900790086