Authors:
Rezvan Pakdel
and
John Herbert
Affiliation:
University College Cork, Ireland
Keyword(s):
Cloud-based Big Data Analytics, Big Data, OpenCV, Machine Learning, Real-time Object Recognition.
Related
Ontology
Subjects/Areas/Topics:
Big Data Cloud Services
;
Cloud Application Architectures
;
Cloud Computing
;
Cloud Computing Architecture
;
Cloud Computing Enabling Technology
;
Fundamentals
;
High Performance Cloud Computing
;
Platforms and Applications
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.