Home About Login Current Archives Announcements Editorial Board
Submit Now For Authors Call for Submissions Statistics Contact
Home > Archives > Volume 20, No 8 (2022) > Article

DOI: 10.14704/nq.2022.20.8.NQ44231

CONTENT BASED SATELLITE IMAGE RETRIEVAL SYSTEM FOR BIG DATA USING MACHINE LEARNING APPROACH

Hitakshi, Dr.Jagdeep Kaur, Dr. Vijay Dhir

Abstract

The CBIR for satellite images using feature extraction techniques like color, shape texture etc. remains a open problem. The images can be retrieved but with poor efficacy. The problem of the above problem is to bridge this gap by using a high level feature extraction technique. The high level descriptors are also used but still retrieved the results with lower results. By considering this point in mind, the objective of the work, is to bridge the above define gap and provide an accurate and efficient solution. In this research, a novel CBIR system for satellite image using AI approach is developed. This system used Speeded Up Robust Features (SURF) as feature descriptor, and Particle Swarm Optimization (PSO) as feature optimization approach. These approaches help to provide better and higher quality satellite images, which improves the future classification of the uploaded image. For classification, Artificial Neural Network (ANN) is used to retrieve the satellite images. Similarity matching plays very important role to attain accurate results. Similarity technique is applied to identify the best possible image among the rest of the similar images. The experiment shows better results in terms of kappa coefficient and overall accuracy compared to existing work.

Keywords

Content Based Image Retrieval, Speeded Up Robust Features, Particle Swarm Optimization, Artificial Neural Network.

Full Text

PDF

References

?>