Incremental indexing with binary feature based Tversky index using black hole entropic fuzzy clustering in cloud computing

Due to the large volume of computational and storage requirements of content based image retrieval (CBIR), outsourcing image to cloud providers become an attractive research. Even though, the cloud service provides efficient indexing of the condensed images, it remains a major issue in the process o...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Multimedia tools and applications Ročník 81; číslo 13; s. 18457 - 18481
Hlavní autori: Bel, K. Nalini Sujantha, Sam, I. Shatheesh
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: New York Springer US 01.05.2022
Springer Nature B.V
Predmet:
Black holes
Centroids
Cloud computing
Clustering
Coders
Computer Communication Networks
Computer Science
Data Structures and Information Theory
Image management
Image retrieval
Indexing
Multimedia Information Systems
Special Purpose and Application-Based Systems
Incremental indexing
Cloud computing
Image retrieval
Deep stacked autoencoder
Tversky index
ISSN:1380-7501, 1573-7721
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Due to the large volume of computational and storage requirements of content based image retrieval (CBIR), outsourcing image to cloud providers become an attractive research. Even though, the cloud service provides efficient indexing of the condensed images, it remains a major issue in the process of incremental indexing. Hence, an effective incremental indexing mechanism named Black Hole Entropic Fuzzy Clustering +Deep stacked incremental indexing (BHEFC+deep stacked incremental indexing) is proposed in this paper to perform incremental indexing through the retrieval of images. The images are encrypted and stored in cloud server for ensuring the security of image retrieval process. The trained images are clustered using the clustering mechanism BHEFC based on Tversky index. With the incremental indexing process, the new training images are encrypted and are converted into the decimal form such that the weight is computed using deep stacked auto-encoder that enable to update the centroid with new score values. The experimental evaluations on benchmark datasets shows that the proposed BHEFC+deep stacked incremental indexing model achieves better results compared to the existing methods by obtaining maximum accuracy of 96.728%, maximum F-measure of 83.598%, maximum precision of 84.447%, and maximum recall of 94.817%, respectively.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1380-7501
1573-7721
DOI:10.1007/s11042-022-12699-1