期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2018
卷号：96
期号：11
出版社：Journal of Theoretical and Applied
摘要：In this paper, we propose a novel framework to retrieve semantic images based on shape skeletonizing, ontology base and Hidden Markov Model. First, the region of interest is localized using an adaptive Gaussian model to model the background subtraction. Second, symmetry features for an object is extracted and then quantized using k-means procedure for learning or retrieving processes by Hidden Markov Model. Query Engine, Matching Module and Ontology Manger are to retrieve the semantic image using SPARQL language on input text or image query. The left-right Hidden Markov Model topology using Viterbi algorithm for retrieving and Baum-welch for learning is investigated. The outcome of our proposed framework is empirically tested against the mammals Benchmark. The experiments on the semantic image retrieval yields an efficient result to intricate event by input text or image query than previously notified.
关键词：Image retrieval; Query Engine; SPARQL; Hidden Markov Model
