Theses and Dissertations

Date of Award

8-2016

Document Type

Thesis

Degree Name

Master of Science (MS)

Department

Computer Science

First Advisor

Dr. Mahmoud K. Quweider

Second Advisor

Dr. Juan Raymundo Iglesias

Third Advisor

Dr. Liyu Zhang

Abstract

Automatic object recognition is a fundamental problem in the fields of computer vision and machine learning, that has received a lot of research attention lately. Miniaturization and affordability, of both, high resolution digital cameras and advanced computing hardware, have further advanced the scope and applications of object recognition methods. While there are different methods, that build upon various low level features to construct object models, this work explores and implements the use of closed-contours as formidable object features. A hierarchical technique is employed to extract the contours, exploiting the inherent spatial relationships between the parent and child contours of an object, and later describing them as part of the query feature vector. Fourier Descriptors are used to effectively and invariantly describe the extracted contours. A diverse database of shapes is created and later used to train standard classification algorithms, for shape-labeling. A simple-hierarchical, shape label and spatial descriptor matching method is implemented, to find the nearest object-model, from a collection of stored templates. Multi-threaded architecture and GPU efficient image-processing functions are adopted wherever possible, speeding up the running time of the proposed technique, and making it efficient for use in real world applications. The technique is successfully tested on common traffic signs in real world images, with overall good performance and robustness being obtained as an end result.

Comments

Copyright 2016 Bassam Syed Arshad. All Rights Reserved.

https://www.proquest.com/dissertations-theses/accelerating-object-extraction-detection-using/docview/1850204634/se-2?accountid=7119

Download

Share

COinS