Visible to the public Info-Retrieval with Relevance Feedback using Hybrid Learning Scheme for RS Image

TitleInfo-Retrieval with Relevance Feedback using Hybrid Learning Scheme for RS Image
Publication TypeConference Paper
Year of Publication2019
AuthorsZhou, Y., Zeng, Z.
Conference Name2019 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery (CyberC)
Date PublishedOct. 2019
ISBN Number978-1-7281-2542-8
KeywordsCBIR, compositionality, content-based image retrieval, content-based retrieval, exception maximization algorithm, geophysical image processing, Hybrid Learning, hybrid learning scheme parameter, image library, image metadata, image retrieval, image segmentation, info-retrieval, interactive query, learning (artificial intelligence), Learning systems, Libraries, Metadata Discovery Problem, multimedia computing, multimedia information retrieval, multitarget retrieval, pubcrawl, relevance feedback, remote sensing, remote sensing image, resilience, Resiliency, RS image, Scalability, Support vector machines, supported vector machine, symbolic image database, Training, visual databases

Relevance feedback can be considered as a learning problem. It has been extensively used to improve the performance of retrieval multimedia information. In this paper, after the relevance feedback upon content-based image retrieval (CBIR) discussed, a hybrid learning scheme on multi-target retrieval (MTR) with relevance feedback was proposed. Suppose the symbolic image database (SID) of object-level with combined image metadata and feature model was constructed. During the interactive query for remote sensing image, we calculate the similarity metric so as to get the relevant image sets from the image library. For the purpose of further improvement of the precision of image retrieval, a hybrid learning scheme parameter also need to be chosen. As a result, the idea of our hybrid learning scheme contains an exception maximization algorithm (EMA) used for retrieving the most relevant images from SID and an algorithm called supported vector machine (SVM) with relevance feedback used for learning the feedback information substantially. Experimental results show that our hybrid learning scheme with relevance feedback on MTR can improve the performance and accuracy compared the basic algorithms.

Citation Keyzhou_info-retrieval_2019