作者: Kraisak Kesorn
DOI:
关键词:
摘要: viii ACKNOLWEDGEMENTS x ABBREVIATIONS xi CHAPTER 1 INTRODUCTION 1.1 Motivation 2 1.1.1 Representing Visual Content and Classifying Images 3 1.1.2 Ambiguity of Natural Language in Text Captions 4 1.1.3 Use Hybrid Textual Metadata Models 5 1.2 Research Objectives 6 1.3 Structure this Thesis 8 FUNDAMENTALS 10 2.1 Main Processes for IMR 2.2 Content-Based Image Retrieval (CBIR) 13 2.2.1 Global Features 14 2.2.2 Local 15 2.3 Semantic-Based (SBIR) 16 2.3.1 Knowledge (Ontology-based) Representation Techniques 18 2.3.2 Advantages Using Ontologies IR 21 2.4 MPEG-7 Ontology-based KB 2.5 Summary 25 SURVEY AND ANALYSIS OF THE STATE-OF-THE-ART FRAMEWORKS 26 3.1 Problem Analysis the Systems 3.2 Formal Requirements 28 3.3 Survey State Art Frameworks 29 3.3.1 Ontology-Based 3.3.2 Features-Based 34 3.4 Discussion 39 3.5 42