On the SPN Estimation in Image Forensics: A Systematic Empirical Evaluation

Al-Ani, Mustafa; Khelifi, Fouad

doi:10.1109/tifs.2016.2640938

Cited by 47 publications

(19 citation statements)

References 55 publications

(69 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Here, we used Normalized Cross-Correlation (NCC) for computing the correlation score [15,10]. PRNU estimation can be done using numerous approaches [35,31,28,34,33,9]. In this work, we used the Maximum Likelihood Estimation (MLE) based PRNU estimation scheme [14], which has been demonstrated to suppress image artifacts not associated with the sensor-specific pattern and has resulted in very good performance [17,15].…”

Section: Photo Response Non-uniformity (Prnu)mentioning

confidence: 99%

See 1 more Smart Citation

Spoofing PRNU Patterns of Iris Sensors while Preserving Iris Recognition

Banerjee

Mirjalili

Ross

2019

2019 IEEE 5th International Conference on Identity, Security, and Behavior Analysis (ISBA)

View full text Add to dashboard Cite

The principle of Photo Response Non-Uniformity (PRNU) is used to link an image with its source, i.e., the sensor that produced it. In this work, we investigate if it is possible to modify an iris image acquired using one sensor in order to spoof the PRNU noise pattern of a different sensor. In this regard, we develop an image perturbation routine that iteratively modifies blocks of pixels in the original iris image such that its PRNU pattern approaches that of a target sensor. Experiments indicate the efficacy of the proposed perturbation method in spoofing PRNU patterns present in an iris image whilst still retaining its biometric content.

show abstract

Section: Photo Response Non-uniformity (Prnu)mentioning

confidence: 99%

“…This noise pattern is believed to be unique to every sensor [20]. A number of schemes have been designed to compute the PRNU noise of a sensor based on the images generated by it [9].…”

Section: Introductionmentioning

confidence: 99%

Spoofing PRNU Patterns of Iris Sensors while Preserving Iris Recognition

Banerjee

Mirjalili

Ross

2019

2019 IEEE 5th International Conference on Identity, Security, and Behavior Analysis (ISBA)

View full text Add to dashboard Cite

show abstract

“…Source camera identification (SCI) establishes the relationship between a questioned image and its source device, which is important when this image serves as serious evidence. Among the available SCI approaches [1]- [5], the approach based on sensor pattern noise (SPN) is the most promising one and thus has been extensively studied in the last decade [5]- [17]. The SPN, which is caused by photoresponse non-uniformity (PRNU) due to inhomogeneity of silicon wafers [18], differs from camera to camera, even of the same model from the same manufacture.…”

Section: Introductionmentioning

confidence: 99%

“…3) In the similarity measurement stage, novel strategies or metrics are adopted to measure the correlation between the SPN from an image and the fingerprint of a reference camera [6], [13], [14]. An overview of existing SCI methods is presented in [17].…”

Section: Introductionmentioning

confidence: 99%

Source Camera Identification With Dual-Tree Complex Wavelet Transform

et al. 2020

View full text Add to dashboard Cite

Sensor pattern noise (SPN) extraction is a critical stage of the sensor based source camera identification (SCI). However, the quality of the extracted SPN with the traditional discrete wavelet transform (DWT) based method is poor around strong edges and along with the image border. To fill this gap, we propose a dual tree complex wavelet transform (DTCWT) based method to extract the SPN from a given image, which achieves better performance in the area around strong edges. Furthermore, symmetric boundary extension instead of the periodized boundary extension is used for enhancing the quality of SPN along with the image border. Extensive experimental results on both synthetic noisy images and real-world photographs clearly demonstrate the superior SCI performance of the proposed method over state-of-the-arts. Moreover, the proposed method also shows potential in the application of image tampering localization. INDEX TERMS Sensor pattern noise, source camera identification, discrete wavelet transform, dual tree complex wavelet transform.

show abstract

“…However, due to imperfections of denoising filters, some scene contents leak in the noise residual, inducing false alarms in dark, uniform, or very textured areas. Besides using state-of-the-art denoising filters [10], [11], a number of strategies have been proposed to face this problem. In [5] a predictor is used to identify potentially troubling regions and adapt the statistical test locally, while in [12] the interference of scene details is reduced by selective attenuation of wavelet coefficients.…”

Section: Introductionmentioning

confidence: 99%

Camera-based Image Forgery Localization using Convolutional Neural Networks

Cozzolino

Verdoliva

2018

2018 26th European Signal Processing Conference (EUSIPCO)

View full text Add to dashboard Cite

Camera fingerprints are precious tools for a number of image forensics tasks. A well-known example is the photo response non-uniformity (PRNU) noise pattern, a powerful device fingerprint. Here, to address the image forgery localization problem, we rely on noiseprint, a recently proposed CNN-based camera model fingerprint. The CNN is trained to minimize the distance between same-model patches, and maximize the distance otherwise. As a result, the noiseprint accounts for model-related artifacts just like the PRNU accounts for device-related nonuniformities. However, unlike the PRNU, it is only mildly affected by residuals of high-level scene content. The experiments show that the proposed noiseprint-based forgery localization method improves over the PRNU-based reference.

show abstract

On the SPN Estimation in Image Forensics: A Systematic Empirical Evaluation

Cited by 47 publications

References 55 publications

Spoofing PRNU Patterns of Iris Sensors while Preserving Iris Recognition

Spoofing PRNU Patterns of Iris Sensors while Preserving Iris Recognition

Source Camera Identification With Dual-Tree Complex Wavelet Transform

Camera-based Image Forgery Localization using Convolutional Neural Networks

Contact Info

Product

Resources

About