Page 22 - 2023-Vol19-Issue2

Received: 17 January 2023 | Revised: 14 February 2023 | Accepted: 20 February 2023

DOI: 10.37917/ijeee.19.2.3 Vol. 19 | Issue 2 | December 2023

Open Access

Iraqi Journal for Electrical and Electronic Engineering

Original Article

Hybrid and Invisible Digital Image Watermarking

Technique Using IWT-DCT and Hopfield Neural Network

Ayoub Taheri*
IT Engineering Department, Payame Noor University, Tehran, Iran

Correspondance
*Ayoub Taheri
Payame Noor University, Modarres Blvd,
Broujen, Chahar Mahal Bakhtiari, Iran
Email: ay.taheri@pnu.ac.ir

Abstract
According to the characteristic of HVS (Human Visual System) and the association memory ability of neural network,
an adaptive image watermarking algorithm based on neural network is proposed invisible image watermarking is
secret embedding scheme for hiding of secret image into cover image file and the purpose of invisible watermarking
is copyrights protection. Wavelet transformation-based image watermarking techniques provide better robustness for
statistical attacks in comparison to Discrete Cosine Transform domain-based image watermarking. The joined method
of IWT (Integer Wavelet Transform) and DCT (Discrete Cosine Transform) gives benefits of the two procedures. The
IWT have impediment of portion misfortune in embedding which increments mean square estimate as SIM and results
diminishing PSNR. The capacity of drawing in is improved by pretreatment and re-treatment of image scrambling
and Hopfield neural network. The proposed algorithm presents hybrid integer wavelet transform and discrete cosine
transform based watermarking technique to obtain increased imperceptibility and robustness compared to IWT-DCT
based watermarking technique. The proposed watermarking technique reduces the fractional loss compared to DWT
based watermarking.

Keywords
IWT, DCT, HVS, Hopfield Neural Network.

I. INTRODUCTION from accidental beneficiaries or use is called cryptography [3]
however cryptography doesn’t conceal the uncertainty of mys-
Undetectable watermarking is valuable for secret correspon- tery stowing away. Imperceptible watermarking approach is
dence and copyrights. A secret data hiding in a media so that grouped into spatial domain watermarking and frequency do-
no one will guess its existence into this media; is called invisi- main watermarking. Frequency domain watermarking shows
ble watermarking [1]. The examination issues of undetectable preferable robustness over spatial domain watermarking [4].
watermarking system are expanding the indistinctness and In a digital image, data is imbedded into loud area of image
robustness. There are numerous procedures proposed by ana- for concealing mystery watermark in less detectable pieces of
lysts for expanding the strength of watermarking system. To image and for this shifting block level image watermarking
sustain antipiracy technologies, Firm anti-piracy legal laws plan is proposed and broke down [5]. Discrete wavelet trans-
are needed for support of all these applications because no form deteriorates image into 4 unique frequency groups which
extra system and mechanism is incorporated in these devices is called LL, LH, HL and HH where LL sub band addresses
when a person can be caught making illegal use of it [2]. The qualities of image while HH sub band addresses Commotion
cognizant covering of information inside other image is called in image [6]. In discrete cosine transform, image is changed
image watermarking. Another way is to putting away and over from spatial domain to frequency domain where low fre-
sending information in a specific system to make it secure

This is an open-access article under the terms of the Creative Commons Attribution License,
which permits use, distribution, and reproduction in any medium, provided the original work is properly cited.
©2023 The Authors.
Published by Iraqi Journal for Electrical and Electronic Engineering | College of Engineering, University of Basrah.

https://doi.org/10.37917/ijeee.19.2.3 |https://www.ijeee.edu.iq 18