Object detection framework to generate secret shares
- PDF / 6,017,932 Bytes
- 22 Pages / 439.642 x 666.49 pts Page_size
- 46 Downloads / 213 Views
Object detection framework to generate secret shares Ayushi Agarwal1 · Maroti Deshmukh1 · Maheep Singh1 Received: 16 July 2019 / Revised: 29 May 2020 / Accepted: 4 June 2020 / © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Nowadays, the sharing of images via the Internet has been widely used. The security concern during transmission of images has been a very important issue, as images contain a lot of crucial information. To prevent access to this information by any unauthorized user various encryption schemes have been developed. An image may consist of a large number of pixels and the encryption of the whole image takes more time. To overcome this problem, we proposed an algorithm that focuses on encryption of only those objects which contain the major information of an image instead of encrypting the complete image, this saves the time required in encryption as only the objects contained in the image are encrypted. The proposed algorithm exploits the use of object detection and image secret sharing. Object detection is done using the “You Only Look Once (YOLO)” algorithm. Further, the objects detected are encrypted using (n,n) modular arithmetic secret sharing scheme. The quantitative measures like correlation, SSIM, RMSE, PSNR has been used to evaluate the performance of the proposed algorithm on COCO dataset. The experimental results show that the proposed algorithm is lossless i.e. original and reconstructed images are exactly the same. The proposed algorithm is efficient and can be used in a broad range of applications. Keywords Object detection · YOLO · Secret sharing · Modular arithmetic · Quantitative measures
1 Introduction With growing digitalization, it has now become common in today’s world to share data from one place to another in the form of text, images, videos, etc. over the Internet. With emerging global social media organizations such as Facebook, WhatsApp, Instagram, etc. sharing of Maroti Deshmukh
[email protected] Ayushi Agarwal [email protected] Maheep Singh [email protected] 1
National Institute of Technology, Uttarakhand, Srinagar India
Multimedia Tools and Applications
images, videos and other multimedia data has highly come into use. The problem that arises while transmitting the multimedia data is of security and authenticity [29] against unauthorized access. Many technologies such as cryptography [24, 41] for encryption, steganography [1, 7] for hiding data and watermarking for providing authenticity have come into use [34]. Since the most crucial need is for security, many cryptographic algorithms are designed to keep data secure during transmission. These algorithms can be symmetric or asymmetric. Symmetric algorithms [4, 20, 21, 40] are the ones in which the secret is shared between two people while asymmetric are the ones in which each user owns his own private key. These encryption techniques work well for text data but for multimedia data like images and videos, the time taken by these algorithms is very high. Along
Data Loading...
