Abstract
The exploratory research highlights the enhancement of image recognition used in many emergency applications. Due to high demand of satellite images in many application areas, searching and classification of relevant images is very much crucial. Content-based satellite image retrieval (CBSIR) extracts similar satellite images from its related query image. Most of the traditional approaches are not efficient for providing better retrieval performance as per the nature of images. The retrieval accuracy of the system mainly depends on proper weight assignment to the multiple low-level image features. Assignment of weights for image features is also a tricky and complex task. In this study, an attempt has been made to develop an automated method for automatic weight assignment to the image features. For this a pair-wise has been done between image features which lead to a new approach for automatic weight assignment. The novelty of the proposed approach is the suitable and automatic weight assignment to the features as per the nature of satellite image. The proposed approach is implemented with the help of a famous analytical hierarchical process. Total 21 classes of satellite images are taken from UC Merced Land use dataset. The performance of the proposed approach has been tested through precision and recall of CBSIR system. Significant improvement in precision and recall values has been achieved through the proposed approach. This system will also be very useful in army and military applications because the used dataset also includes image classes such as airplane, forest, residential areas and harbor and run way.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Ahirwal MK, Kumar A, Singh GK (2017) An approach to design self-assisted CBIR system. In: Proceedings of the international conference on graphics and signal processing (pp 21–25)
Castelluccio M, Poggi G, Sansone C, Verdoliva L (2015) Land use classification in remote sensing images by convolutional neural networks. arXiv preprint arXiv: 1508.00092
Cheng SC, Chou TC, Yang CL, Chang HY (2005) A semantic learning for content-based image retrieval using analytical hierarchy process. Expert Syst Appl 28(3):495–505
Datta R, Joshi D, Li J, Wang JZ (2008) Image retrieval: ideas, influences, and trends of the new age. ACM Comput Surv 40(2):1–60
Guili XU, Zhengbing WANG, Cheng Y, Yupeng TIAN, Zhang C (2017) A man-made object detection algorithm based on contour complexity evaluation. Chin J Aeronaut 30(6):1931–1940
Ishizaka A, Labib A (2009) Analytic hierarchy process and expert choice: benefits and limitations. Or Insight 22(4):201–220
John LM, Bhandari KA (2016) An efficient approach towards satellite image retrieval using semantic mining with hashing. Int J Appl Inf Syst 11(3):2249
Kumar P, Tandon P (2019) A paradigm for customer-driven product design approach using extended axiomatic design. J Intell Manuf 30(2):589–603
Rout NK, Ahirwal MK (2018) A content based image retrieval system: analysis of individual and mixed image features. In: International conference on recent innovations in electrical, electronics and communication engineering (ICRIEECE), Bhubaneswar, pp 2561–2566
Rout NK, Ahirwal MK, Atulkar M (2020) A review on content based image retrieval system: present trends and future challenges. Int J Comput Vis Robot [In Press: http://www.inderscience.com/info/ingeneral/forthcoming.php?jcode=IJCVR]
Saaty T (2004) The analytic hierarchy process (AHP), Geoff Coyle: practical strategy. Open access material. https://training.fws.gov/courses/references/tutorials/geospatial/CSP7306/Readings/AHP-Technique.pdf. Accessed Date 13 May 2021
Sudha SK, Aji S (2019) A review on recent advances in remote sensing image retrieval techniques. J Indian Soc Remote Sens 47(12):2129–2139
Voigt S, Kemper T, Riedlinger T, Kiefl R, Scholte K, Mehl H (2007) Satellite image analysis for disaster and crisis-management support. IEEE Trans Geosci Remote Sens 45(6):1520–1528
Wang X, Kanglin X (2011) Content-based image retrieval incorporating the AHP method. Int J Info Tech 11:25–37
Wang X, Nianzu L, Kanglin M (2008) A novel AHP-based image retrieval interface. In: IEEE 2008 Chinese control and decision conference, pp 2334–2337
Yang Y, Newsam S (2010) Bag-of-visual-words and spatial extensions for land-use classification. In: Proceedings of the 18th SIGSPATIAL Intconf on advances in geoginf systems, pp 270–279
Funding
No funding was received for this research from any agency.
Author information
Authors and Affiliations
Contributions
All authors contributed to the study conception and design. Coding and analysis were performed by Mr. Narendra Kumar Rout. The manuscript was written by Mitul Kumar Ahirwal and Mithilesh Atulkar. All authors read and approved this submitted manuscript.
Corresponding author
Ethics declarations
Conflict of interest
All authors declare that they have no conflict of interest.
Ethical approval
Ethical approval is not required for this study. Human or animal subjects’ data are not used in this study.
Additional information
Communicated by Suresh Chandra Satapathy.
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Rout, N.K., Ahirwal, M.K. & Atulkar, M. Analytic hierarchy process-based automatic feature weight assignment method for content-based satellite image retrieval system. Soft Comput 27, 1105–1115 (2023). https://doi.org/10.1007/s00500-021-05937-5
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00500-021-05937-5