Abstract
Although scholars have conducted numerous researches on content-based image retrieval and obtained great achievements, they make little progress in studying remote sensing image retrieval. Both theoretical and application systems are immature. Since remote sensing images are characterized by large data volume, broad coverage, vague themes and rich semantics, the research results on natural images and medical images cannot be directly used in remote sensing image retrieval. Even perfect content-based remote sensing image retrieval systems have many difficulties with data organization, storage and management, feature description and extraction, similarity measurement, relevance feedback, network service mode, and system structure design and implementation. This paper proposes a remote sensing image retrieval algorithm that combines co-occurrence region based Bayesian network image retrieval with average high-frequency signal strength. By Bayesian networks, it establishes correspondence relationships between images and semantics, thereby realizing semantic-based retrieval of remote sensing images. In the meantime, integrated region matching is introduced for iterative retrieval, which effectively improves the precision of semantic retrieval.
Highlights
Studies on natural and medial image retrieval have achieved remarkable results
This paper proposes a stepwise Bayesian network algorithm for retrieving remote sensing images, aim to address these problems; the schema combines co-occurrence region-based Bayesian network image retrieval with average high-frequency signal strength, and adopts integrated region matching for iterative retrieval, thereby efficiently improving the precision of semantic retrieval and significantly reducing the retrieval time
3.1 Experiment Design and Results Considering that the retrieval time of integrated region matching may be influenced by the segmentation region numbers of query images, the experiment selects images with 4 to 13 image regions, with integrated region matching and stepwise image retrieval as controlled trails
Summary
Studies on natural and medial image retrieval have achieved remarkable results. There have been numerous research projects designed for remote sensing image retrieval. Both theoretical and application systems are immature and need to be further researched (Samadzadegan et al, 2012; Hejazi et al, 2017). The study compares existing image retrieval systems and focuses on image storage, network transmission model, feature extraction and description, segmentation algorithm, reasonable segmentation, similarity measurement and relevance feedback. (2) Currently, remote sensing image retrieval systems are mainly based on texts, strip numbers, latitudes, and longitudes, rather than contents (Abdi, 2013). (3) Scholars have made great use of Bayesian networks to study semantic-based remote sensing image retrieval. High-precision image retrieval tends to consume lots of time (Zhai, 2014; Simon et al, 2017)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
