Open Access3D chaos graph deep learning method to encrypt and decrypt digital image
Author(s) -
Daniah Abdul Qahar Shakir,
Ali Dawood
Publication year - 2022
Publication title -
indonesian journal of electrical engineering and computer science
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.241
H-Index - 17
eISSN - 2502-4760
pISSN - 2502-4752
DOI - 10.11591/ijeecs.v25.i2.pp941-951
Subject(s) - encryption , computer science , decoding methods , pixel , encode , chaos (operating system) , graph , algorithm , chaotic , cryptography , artificial intelligence , image (mathematics) , theoretical computer science , entropy (arrow of time) , digital image , computer vision , image processing , computer network , biochemistry , chemistry , physics , computer security , quantum mechanics , gene
We live in technological age development’s where many important data transmitted electronically from one device to another and in every place. Deep learning algorithms have facilitated the process of encoding and decoding digital images. Chaotic graph systems, on the other hand, are one of the most recent techniques utilized to encode image data based on the methods of cryptography. The chaos maps are divided into two main aspects, first one deals with the 1D map which requires fewer features and can be developed easily, the second one is the high dimensional map which is more complex than the 1D graph and it requires more features, more parameters, and it is relatively hard to develop. In this paper, we present a method for image encoding and decoding electronically using deep learning, the proposed algorithm was developed by using the hybrid technique of 3D chaos map generation, the best case of the proposed technique gave the following results: The average entropy calculation was (7.4838) before image encryption and (7.9896) after image encryption with average number of pixels change rate (NPCR) of (99.7085%) and the unified average changing intensity (UACI) of (33.2030%) which are the best outcomes when compared to other similar works.