Campus Access Only
All rights reserved. This publication is intended for use solely by faculty, students, and staff of Nova Southeastern University. 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.
Date of Award
Dissertation - NSU Access Only
Doctor of Philosophy in Computer Information Systems (DCIS)
Graduate School of Computer and Information Sciences
William L Hafner
Timothy J Ellis
Maxine S Cohen
Affective Content, Multimedia, Slapstick, Video Indexing
Recent advances in multimedia technologies have helped create extensive digital video repositories. Users need to be able to search these large video repositories in order to find videos that have preferred content. In order to meet the needs of users, videos in these repositories need to be indexed. Manual indexing is not an appropriate method due to the time and effort involved. Instead, videos need to be accurately indexed by utilizing computer-based methods. Automatic video indexing techniques use computer technology to analyze low-level video features to identify the content that exists in videos. The type of indexing used in this study is automatic affective video indexing, which is an attempt to index videos by automatically detecting content that elicits an emotional response from individuals. The specific affect-related content of interest in this proposed study is slapstick comedy, a technique that is used in videos with humor.
The methodology of this study analyzed the audio stream as well as the motion of targeted objects in videos. The relationship between the changes in the two low-level features was used to identify if slapstick comedy was present in the video and where the instance of slapstick could be found.
There were three research questions presented in the study which were associated with the two goals. Research Question 1 determined whether or not the targeted content could be identified using low-level features. Research Question 2 measured the relationship between the experimental results and the ground truth in terms of identifying the location of the targeted content in video. Research Question 3 determined whether one type of low-level feature was more strongly associated with the target content than the other. Goal 1 was to utilize sound and motion to predict the existence of slapstick comedy in videos. Goal 2 was to utilize sound and motion to predict the location of slapstick comedy in videos. The results of the study showed that Goals 1 and 2 were partially met, prompting an investigation into methodology improvements as part of this research. The results also showed that motion was more strongly related to the target content than sound.
Jean Helen French. 2011. Automatic Affective Video Indexing: Identification of Slapstick Comedy Using Low-level Video Characteristics. Doctoral dissertation. Nova Southeastern University. Retrieved from NSUWorks, Graduate School of Computer and Information Sciences. (155)