Smart Image Search System Using Personalized Semantic Search Method

Due to the emerge in huge numbers of information on the internet nowadays, search technologies are widely used in various fields. Achieving the most relevant search result for the users becomes a big challenge now. While the traditional semantic search technologies seem to achieve the most relevant search result, however, it faces two problems: one is the one-size-fits-all problem, and another is low efficiency. The purpose of this research is to build a Smart Image Search System by using the personalized semantic search method to solve those problems. The personalized semantic search method makes the search system avoids the one-size-fits-all issue, and increase the efficiency. In the Smart Image Search System, the personalized semantic search method provides users three options to search. They are non-option search, general-option search, and private-option search. Each option search has its specific user needs to achieve the most relevant results. Those options are adopted to solve the one-size-fits-all problem. Also, based on the idea of semantic context concept, the personalized semantic method uses two approaches to increase the search efficiency. First, it applies Apache OpenNLP Library to avoid useless words. Second, it considers the searchers’ actions such as click and feedbacks to affect the associated words and associated weight. The Smart Image Search System uses the associated words and associated weight to calculate the relativity for the search results. This approach makes the Smart Image Search System becomes a self-improved system. Smart Image Search System is implemented based on the presented methodology and design. As a result of current research on semantic search technologies, we conclude that the Smart Image Search System can avoid useless words, fix the one-size-fits-all problem, and self-improve its relevancy