Markov Chains for User Queries Mining: Image Retrieval Application using Internet

Abstract

Abstract: We suggest a brand-new technique for automatically annotating, indexing, and retrieving photos based on annotations. We introduce the novel technique, which we term Markovian Semantic Indexing (MSI), within the framework of an image retrieval system in online mode. In the event that such a system exists, the queries entered by the users are utilised to build an Aggregate Markov Chain (AMC), which defines the significance between the terms the system sees. The photographs are automatically annotated based on the queries entered by the users. Next, depending on the annotation of each image and the keyword relevance recorded in the AMC, a stochastic distance between them is presented. The suggested distance is given geometric meanings, and its relationship to a grouping in the keyword space is examined. The optimality qualities of the suggested distance are demonstrated by the use of a novel Markovian state similarity measure, the mean first cross passage time (CPT). Images are represented as points in a vector space, and MSI is used to calculate how similar two images are. In Annotation-Based Image Retrieval (ABIR) tasks, it is demonstrated that the novel method outperforms Latent Semantic Indexing (LSI) and probabilistic Latent Semantic Indexing (pLSI) methods in terms of Precision against Recall and has some theoretical advantages.