Extremely adaptive image retrieval scheme employing an optimized wavelet technique intended for characterization maps
- PDF / 3,261,543 Bytes
- 20 Pages / 439.37 x 666.142 pts Page_size
- 55 Downloads / 189 Views
Extremely adaptive image retrieval scheme employing an optimized wavelet technique intended for characterization maps P. Gnanasivam 1 & M. S. Sudhakar 2 Received: 13 January 2020 / Revised: 22 July 2020 / Accepted: 31 July 2020 # Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract
The demand for adaptive image retrieval is still an active research area, particularly in a dynamic environment. Erstwhile retrieval schemes ensure adaptivity by tuning the same image basis with wavelet transforms, in accordance with user’s significance. To enhance adaptivity and improve the retrieval performance, an Extremely Adaptive Image Retrieval (EAIR) scheme is presented that associates each image with different wavelet basis. This objective is achieved by building Characterization maps from wavelet coefficients of images (query and target) using higher order standardized moments of the Gamma function. The resulting maps are approximated by Volterra Series and later, mathematically programmed by Integral Global Optimization (IGO) algorithm for wavelet adaptation. Finally, the best wavelet filter for each query image is fitted using the Multivariate Adaptive Regression Splines (MARS). Characterization Maps rendered by EAIR achieves 60% reduction in Relative Approximation Error (RAE) with 11% decrease in query time observed under diverse dataset. Also, relative PrecisionRecall (P-R), Precision at 5 (P5) analyses reveals a significant retrieval improvement of 9.52%, 1.35%, 1.12%, 8.07% by EAIR on Caltech, Messidor, AT&T, Vistex respectively. Keywords EAIR . IGO . MARS . Precision at 5 . RAE . Volterra series
* M. S. Sudhakar [email protected] P. Gnanasivam [email protected]
1
Department of ECE, Jerusalem College of Engineering, Anna University, Chennai, Tamil Nadu, India
2
School of Electronics Engineering, VIT, Vellore, Tamil Nadu, India
Multimedia Tools and Applications
1 Introduction Scientific advancements in image sensing and acquisition across diverse domains have led to the accumulation of large image repositories. These image collections were systematized by Content-Based Image Retrieval (CBIR) schemes by extracting significant descriptions of objective image characteristics. CBIR research objectives are primarily concerned with the implementation of user-friendly mechanisms that permits user to effectively query digital image archives and retrieve related images that match with the given query. Despite, the availability of scores of CBIR schemes, the quest for novel retrieval engines catering dynamic environment is on the rise [35]. Furthermore CBIRs accuracy is highly determined by image characterization employing local, global, spatial, spectral and temporal approaches. Off late wavelets are extensively employed in various image processing areas related to Compression, Classification, Denoising, Indexing and Retrieval [27, 31]. The lifting scheme of [29] has changed the design aspects of wavelets making it an optimal choice for numerous image processing applications. Further, extending
Data Loading...
