Campus Access Only

All rights reserved. This publication is intended for use solely by faculty, students, and staff of University of the Pacific. No part of this publication may be reproduced, distributed, or transmitted in any form or by any means, now known or later developed, including but not limited to photocopying, recording, or other electronic or mechanical methods, without the prior written permission of the author or the publisher.

Segmentation of complex scenes and object classification using neural networks

Author

Mark G. Miller, University of the Pacific

Date of Award

1994

Document Type

Thesis - Pacific Access Restricted

Degree Name

Master of Science (M.S.)

Department

Engineering

First Advisor

Joseph King

First Committee Member

George Schroeder

Second Committee Member

Dale Dunmire

Abstract

The focus of this thesis is on the emerging technology known as Neural Networks which has recently become quite successful in many forms of pattern recognition applications. A software implementation of a neural network based system and an overview of this form of artificial intelligence will be presented in this paper. The system will identify geometric patterns embedded in a complex scene by first segmenting the image and then identifying the objects through a neural network. Automatic positioning mechanisms and military target recognition are two examples of applications that could use the technology outlined in this paper.

A computer generated image containing multiple sub-images of eight basic shapes is used as the input to the segmentation-classification system. The images are corrupted by large amounts of gaussian noise and various shading patterns to closely simulate pictures taken by a camera. A region growing algorithm, which incorporates the use of histograms and neighborhood filters, is used to segment the complex scenes. Prior intensity or object position information is not required by the segmentation algorithm to fully dissect the image. Additionally, variation in object location, rotation, and size do not affect the ultimate classification solutions.

A special set of moments is then calculated for each individual object. These moment features are used as the inputs to a feed-forward neural network which is trained by the use of the back-propagation learning algorithm. Once trained, the network activates an appropriate output to identify the shape classification of the applied input.

This overall system, which includes segmentation, feature extraction, and neural network implementation, achieves a high level of classification accuracy. The methodology used in developing this segmentation algorithm does not require prior knowledge of the application, and the invariant features utilized in the neural network classification make the system readily transferable to other applications. Only basic geometric patterns will be classified by my segmentation and classification system; however, more complex shapes, such as text, could also be classified with minimal changes to the software. There are essentially no limitations to the two-dimensional shapes that can be recognized by this method; although, additional preprocessing may be required to recognize a hexagon from a circle, for example.

Pages

107

Recommended Citation

Miller, Mark G.. (1994). Segmentation of complex scenes and object classification using neural networks. University of the Pacific, Thesis - Pacific Access Restricted. https://scholarlycommons.pacific.edu/uop_etds/2790