Watermarking for protected fingerprint authentication

Bousnina, Naima; Ghouzali, Sanaa; Lafkih, Maryam; Nafea, Ohoud; Mikram, Mounia; Abdul, Wadood; Aboutajdine, Driss

doi:10.1109/innovations.2016.7880039

Cited by 3 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, the proposed algorithm has been tested under different several common attacks such as image processing, compression and geometrical attacks. Good quality of the watermarked fingerprint images was achieved compared with the other methods [20][21][22], as shown in Table-10. This is clear since the PSNR value was almost greater than 36 dB in the majority of the experiments for all tests on the fingerprint images in CASIA-V5-DB, while its value was greater than 37 dB for FVC2002-DB2.…”

Section: Similarity With Other Techniquesmentioning

confidence: 84%

“…Furthermore, the necessity of the mixture of the DTCWT and DCT transforms have been investigated over the idea of the previously proposed methods [10,22] that depended only on the DTCWT transform. The proposed blind method which is based on DTCWT-DCT hybrid transform has a higher robustness than Alkhathami 's method [23] which is based only on DTCWT transform with the requirement of the original fingerprint template at the extraction stage (non-blind).…”

Section: Discussionmentioning

confidence: 99%

“…However, the proposed method has achieved the combination of imperceptibility, robustness and security, all with a simplicity in the application when using a weak factor of the same attacks; in addition, it was tested under others attacks which had not been used in the previous methods. One of the previously proposed methods [22] focused only on the PSNR values of watermark, which achieved good results, without testing PNSR values for the cover image under these attacks. This is contrary to the other proposed method [20], which focused only on the PSNR values of the cover image, which also achieved a good result against the noise attacks, without evaluating the extracted watermark.…”

Section: Similarity With Other Techniquesmentioning

confidence: 99%

“…Comparisons of PSNR Values Obtained After Different Types of Image Noises BetweenProposed Method and Previous Proposed Method in[22] …”

mentioning

confidence: 99%

See 3 more Smart Citations

Robust Blind Watermarking Technique Against Geometric Attacks for Fingerprint Image Using DTCWT-DCT

Lebcir

Awang

Benziane

2020

eijs

View full text Add to dashboard Cite

In this research paper, a new blind and robust fingerprint image watermarking scheme based on a combination of dual-tree complex wavelet transform (DTCWT) and discrete cosine transform (DCT) domains is demonstrated. The major concern is to afford a solution in reducing the consequence of geometric attacks. It is due to the fingerprint features that may be impacted by the incorporated watermark, fingerprint rotations, and displacements that result in multiple feature sets. To integrate the bits of the watermark sequence into a differential process, two DCT-transformed sub-vectors are implemented. The initial sub-vectors were obtained by sub-sampling in the host fingerprint image of both real and imaginary parts of the DTCWT wavelet coefficients. The basic difference between the relevant sub-vectors of the watermarked fingerprint image in the extraction stage directly provides the inserted watermark sequence. It is not necessary to extract watermark data from an original fingerprint image. Therefore, the technique suggested is evaluated using 80 fingerprint images from 10 persons, from both CASIA-V5-DB and FVC2002-DB2 fingerprint database. For each person, eight fingerprints are set as the template and the watermark are inserted in each image. A comparison between the obtained results with other geometric robust techniques results is performed afterwards. The comparison results show that the proposed technique has stronger robustness against common image processing processes and geometric attacks such as cropping, resizing, and rotation.

show abstract

Section: Similarity With Other Techniquesmentioning

confidence: 84%