Home // ADVCOMP 2020, The Fourteenth International Conference on Advanced Engineering Computing and Applications in Sciences // View article

Adaptive Multimedia Indexing Using Naïve Bayes Classification

Authors:
R. F. Ma
Clement Leung
Jiayan Zhang

Keywords: multimedia information indexing, reinforcement learning; multi-agent; naïve Bayes classifiers; stochastic game; probability generating function

Abstract:
Current organizations increasingly depend on multimedia document repositories for their effective operation. However, unlike text-oriented objects, the retrieval of multimedia objects is often inhibited by limitations in their search and discovery mechanisms, since they do not readily lend themselves to automatic processing or indexing. Here, we describe the structure of an adaptive search mechanism which is able to overcome such limitations. The basic framework of the adaptive search mechanism is to capture human judgment in the course of normal usage from user queries in order to develop semantic indexes which link search terms to media objects semantics. This approach is particularly effective for the retrieval of such multimedia objects as images, sounds, and videos, where a direct analysis of the object features does not allow them to be linked to search terms, such as non-textual/icon-based search, deep semantic search, or when search terms are unknown at the time the media repository is built. An adaptive indexing mechanism is described which makes use of naïve Bayes classification approach. This approach allows for the efficient organizational creation and updating of media indexes, which is able to instill and propagate deep knowledge relating to the organizational functions into the media management system concerning the advanced search and usage of multimedia resources. The present learning approach will enable intelligent search of multimedia resources that are otherwise hard to be located and retrieved.

Pages: 12 to 17

Copyright: Copyright (c) IARIA, 2020

Publication date: October 25, 2020

Published in: conference

ISSN: 2308-4499

ISBN: 978-1-61208-812-9

Location: Nice, France

Dates: from October 25, 2020 to October 29, 2020