Query extraction based on encrypted features for CBIR from cloud
Full Text |
Pdf
|
Author |
D. Ravibabu, Kesaboina Sushma, R. Shiva Shankar and K. V. S. S. R. Murthy
|
e-ISSN |
1819-6608 |
On Pages
|
200-210
|
Volume No. |
18
|
Issue No. |
03
|
Issue Date |
March 18, 2023
|
DOI |
https://doi.org/10.59018/022337
|
Keywords |
packed additive homomorphic encryption (pahe), vgg16, resnet, densenet, mobile net, secure multi-party computation (smc), machine learning (ML).
|
Abstract
Due to the increasing use of mobile devices, content-based image retrieval is gaining massive popularity as mobile devices run on batteries. It cannot perform heavy image processing computation, so mobile users can extract just image features and offload them to the cloud. The cloud will perform content-based image searches and return a search result. COREL10K images dataset was selected, and VGG16, RESNET, DENSENET, and MOBILE NET algorithms were applied. Finally, the method with the best performance is preferred. Also, PAHE (Packed Additive Homomorphic Encryption) algorithm is selected to encrypt the feature vectors, and image similarity calculations are done with Secure Multi-party Computation (SMC). The following parameters are used for each algorithm to calculate accuracy, precision, recall, Jaccard index, error rates, and F1-score. The algorithms are then compared and selected the best algorithm. The best model obtained is VGG16, with the highest accuracy. The procedure can help Mobile users perform content-based image searches by extracting features and then uploading them to the cloud.
Back