Efficient Hybrid Blind Watermarking in DWT‐DCT‐SVD with Dual Biometric Features for Images

Abstract

In the modern era of virtual computers over the notional environment of computer networks, the protection of influential documents is a major concern. To bring out this motto, digital watermarking with biometric features plays a crucial part. It utilizes advanced technology of cuffing data into digital media, i.e., text, image, video, or audio files. The strategy of cuffing an image inside another image by applying biometric features namely signature and fingerprint using watermarking techniques is the key purpose of this study. To accomplish this, a combined watermarking strategy consisting of Discrete Wavelet Transform, Discrete Cosine Transform, and Singular Value Decomposition (DWT-DCT-SVD) is projected for authentication of image that is foolproof against attacks. Here, singular values of watermark1 (fingerprint) and watermark2 (signature) are obtained by applying DWT-DCT-SVD. Affixing both the singular values of watermarks, we acquire the transformed watermark. Later, the same is applied to cover image to extract the singular values. Then we add these values to the cover image and transformed watermark to obtain a final watermarked image containing both signature and fingerprint. To upgrade the reliability, sturdiness, and originality of the image, a fusion of watermarking techniques along with dual biometric features is exhibited. The experimental results conveyed that the proposed scheme achieved an average PSNR value of about 40 dB, an average SSIM value of 0.99, and an embedded watermark resilient to various attacks in the watermarked image.

Privacy Preserved Two Factor Authentication System using Spread Spectrum Watermarking of Fingerprint and Crypto code

“…SSIM & NC values with the related works [11], [10], [9], and [8]. In order to demonstrate the efficacy of our proposed scheme, we conducted a comparison with two previous approaches -the hybrid blind watermarking in DWT-DCT-SVD with dual biometric features for images suggested by B Mokashi et al [10], and the multimodal biometric authentication using PSO based watermarking technique suggested by Bedi, P et al [15]. We evaluated the robustness of the three proposed schemes against various attacks, including those involving Gaussian noise, salt and pepper noise, sharpening attack, median attack, compressed attack, histogram equalization, and blur attack.…”

“…The proposed approach's performance under normal conditions can be evaluated based on the results obtained from comparing it with four existing approaches, namely P Garg et al [11], B Mokashi et al [10], Aparna et al [9], and Alkhathami et al [8], without any external interference. SSIM & NC values with the related works [11], [10], [9], and [8].…”

“…The proposed approach's performance under normal conditions can be evaluated based on the results obtained from comparing it with four existing approaches, namely P Garg et al [11], B Mokashi et al [10], Aparna et al [9], and Alkhathami et al [8], without any external interference. SSIM & NC values with the related works [11], [10], [9], and [8]. In order to demonstrate the efficacy of our proposed scheme, we conducted a comparison with two previous approaches -the hybrid blind watermarking in DWT-DCT-SVD with dual biometric features for images suggested by B Mokashi et al [10], and the multimodal biometric authentication using PSO based watermarking technique suggested by Bedi, P et al [15].…”

“…Bhargavi Mokashi et al [10] proposed a watermarking strategy that utilizes both DCT-DWT for transform and SVD for spatial domain methods. The results demonstrate that this approach not only offers protection against attacks but also increase performance without sacrificing image data.…”

“…In the above equation ( 9) and (10), Rr () represents rotating function which right rotates the user's unique data by key value. 'UID' is users' unique data taken as input, 'K' denotes input key.…”