本文基于DnCNN网络提出了一种图像来源检验方法,可以通过提取图像中的噪声残差特征(NP特征),捕获设备特有的传感器噪声模式,并结合峰值相关能量值(PCE)的计算来判断图像的来源设备或检测篡改行为。通过在多个数据集上的实验验证,该方法...本文基于DnCNN网络提出了一种图像来源检验方法,可以通过提取图像中的噪声残差特征(NP特征),捕获设备特有的传感器噪声模式,并结合峰值相关能量值(PCE)的计算来判断图像的来源设备或检测篡改行为。通过在多个数据集上的实验验证,该方法能够有效区分不同型号和同一型号的不同设备拍摄的图像。研究结果表明,基于DnCNN的图像来源检验方法为数字图像取证提供了一个高效且可靠的技术手段,在公共安全、司法鉴定和媒体真实性验证等领域具有广泛的应用前景。This paper proposes an image source verification method based on the DnCNN network, which extracts noise residual features (NP features) from images to capture device-specific sensor noise patterns. By calculating the Peak Correlation Energy (PCE), the method can determine the source device of the image or detect tampering behaviors. Experimental results on multiple datasets validate that the proposed method effectively distinguishes images captured by different devices of the same model as well as by different models. The findings indicate that the DnCNN-based image source verification method provides an efficient and reliable technological means for digital image forensics, with broad applications in public safety, forensic identification, and media authenticity verification.展开更多
Watermarking is embedding visible or invisible data within media to verify its authenticity or protect copyright.The watermark is embedded in significant spatial or frequency features of the media to make it more resi...Watermarking is embedding visible or invisible data within media to verify its authenticity or protect copyright.The watermark is embedded in significant spatial or frequency features of the media to make it more resistant to intentional or unintentional modification.Some of these features are important perceptual features according to the human visual system(HVS),which means that the embedded watermark should be imperceptible in these features.Therefore,both the designers of watermarking algorithms and potential attackers must consider these perceptual features when carrying out their actions.The two roles will be considered in this paper when designing a robust watermarking algorithm against the most harmful attacks,like volumetric scaling,histogram equalization,and non-conventional watermarking attacks like the Denoising Convolution Neural Network(DnCNN),which must be considered in watermarking algorithm design due to its rising role in the state-of-the-art attacks.The DnCNN is initialized and trained using watermarked image samples created by our proposed Covert and Severe Attacks Resistant Watermarking Algorithm(CSRWA)to prove its robustness.For this algorithm to satisfy the robustness and imperceptibility tradeoff,implementing the Dither Modulation(DM)algorithm is boosted by utilizing the Just Noticeable Distortion(JND)principle to get an improved performance in this sense.Sensitivity,luminance,inter and intra-block contrast are used to adjust the JND values.展开更多
为了减轻在光伏板表面缺陷检测中由图像噪声和目标过小造成的影响,提出了改进Dn-YOLOv7(de-noising you only look once version 7)算法。该算法结合去噪卷积神经网络(de-noising convolutional neural network,DnCNN),提出了一个降噪模...为了减轻在光伏板表面缺陷检测中由图像噪声和目标过小造成的影响,提出了改进Dn-YOLOv7(de-noising you only look once version 7)算法。该算法结合去噪卷积神经网络(de-noising convolutional neural network,DnCNN),提出了一个降噪模块(de-noise block,DnBlock),该模块使用了噪声容限更大的损失函数,并利用空间坐标卷积(coordinates convolution,CoordConv)对噪声通道进行卷积整合,增强了网络的降噪能力。同时,使用归一化高斯瓦瑟斯坦距离(normalized Gaussian Wasserstein distance,NWD)替代传统交并比(intersection over union,IoU)损失函数,提高了模型对小目标的检测能力。结果表明,改进后的模型具有降噪能力并提高了检测精确率,在无噪声水平下平均精确率均值达到了96.6%,在较强的高斯噪声和脉冲噪声下平均精确率均值分别达到91.4%和85.4%,检测速度达到78.0帧/s。该算法在航拍图像的光伏板缺陷检测中有一定实用价值。展开更多
文摘本文基于DnCNN网络提出了一种图像来源检验方法,可以通过提取图像中的噪声残差特征(NP特征),捕获设备特有的传感器噪声模式,并结合峰值相关能量值(PCE)的计算来判断图像的来源设备或检测篡改行为。通过在多个数据集上的实验验证,该方法能够有效区分不同型号和同一型号的不同设备拍摄的图像。研究结果表明,基于DnCNN的图像来源检验方法为数字图像取证提供了一个高效且可靠的技术手段,在公共安全、司法鉴定和媒体真实性验证等领域具有广泛的应用前景。This paper proposes an image source verification method based on the DnCNN network, which extracts noise residual features (NP features) from images to capture device-specific sensor noise patterns. By calculating the Peak Correlation Energy (PCE), the method can determine the source device of the image or detect tampering behaviors. Experimental results on multiple datasets validate that the proposed method effectively distinguishes images captured by different devices of the same model as well as by different models. The findings indicate that the DnCNN-based image source verification method provides an efficient and reliable technological means for digital image forensics, with broad applications in public safety, forensic identification, and media authenticity verification.
文摘Watermarking is embedding visible or invisible data within media to verify its authenticity or protect copyright.The watermark is embedded in significant spatial or frequency features of the media to make it more resistant to intentional or unintentional modification.Some of these features are important perceptual features according to the human visual system(HVS),which means that the embedded watermark should be imperceptible in these features.Therefore,both the designers of watermarking algorithms and potential attackers must consider these perceptual features when carrying out their actions.The two roles will be considered in this paper when designing a robust watermarking algorithm against the most harmful attacks,like volumetric scaling,histogram equalization,and non-conventional watermarking attacks like the Denoising Convolution Neural Network(DnCNN),which must be considered in watermarking algorithm design due to its rising role in the state-of-the-art attacks.The DnCNN is initialized and trained using watermarked image samples created by our proposed Covert and Severe Attacks Resistant Watermarking Algorithm(CSRWA)to prove its robustness.For this algorithm to satisfy the robustness and imperceptibility tradeoff,implementing the Dither Modulation(DM)algorithm is boosted by utilizing the Just Noticeable Distortion(JND)principle to get an improved performance in this sense.Sensitivity,luminance,inter and intra-block contrast are used to adjust the JND values.
文摘为了减轻在光伏板表面缺陷检测中由图像噪声和目标过小造成的影响,提出了改进Dn-YOLOv7(de-noising you only look once version 7)算法。该算法结合去噪卷积神经网络(de-noising convolutional neural network,DnCNN),提出了一个降噪模块(de-noise block,DnBlock),该模块使用了噪声容限更大的损失函数,并利用空间坐标卷积(coordinates convolution,CoordConv)对噪声通道进行卷积整合,增强了网络的降噪能力。同时,使用归一化高斯瓦瑟斯坦距离(normalized Gaussian Wasserstein distance,NWD)替代传统交并比(intersection over union,IoU)损失函数,提高了模型对小目标的检测能力。结果表明,改进后的模型具有降噪能力并提高了检测精确率,在无噪声水平下平均精确率均值达到了96.6%,在较强的高斯噪声和脉冲噪声下平均精确率均值分别达到91.4%和85.4%,检测速度达到78.0帧/s。该算法在航拍图像的光伏板缺陷检测中有一定实用价值。
