Digital image forgery (DIF) is a prevalent issue in the modern age, where malicious actors manipulate images for various purposes, including deception and misinformation. Detecting such forgeries is a critical task fo...Digital image forgery (DIF) is a prevalent issue in the modern age, where malicious actors manipulate images for various purposes, including deception and misinformation. Detecting such forgeries is a critical task for maintaining the integrity of digital content. This thesis explores the use of Modified Error Level Analysis (ELA) in combination with a Convolutional Neural Network (CNN), as well as, Feedforward Neural Network (FNN) model to detect digital image forgeries. Additionally, incorporation of Explainable Artificial Intelligence (XAI) to this research provided insights into the process of decision-making by the models. The study trains and tests the models on the CASIA2 dataset, emphasizing both authentic and forged images. The CNN model is trained and evaluated, and Explainable AI (SHapley Additive exPlanation— SHAP) is incorporated to explain the model’s predictions. Similarly, the FNN model is trained and evaluated, and XAI (SHAP) is incorporated to explain the model’s predictions. The results obtained from the analysis reveals that the proposed approach using CNN model is most effective in detecting image forgeries and provides valuable explanations for decision interpretability.展开更多
在当前的去隔行算法中,场内去隔行法由于很好地实现了显示品质和运算成本的平衡而应用最为广泛。其中,基于边沿的线平均算法(Edge-based Line Average,ELA)由于在图像边沿部位重建方面的优异表现而为人们所熟知。文章提出了一种基于显...在当前的去隔行算法中,场内去隔行法由于很好地实现了显示品质和运算成本的平衡而应用最为广泛。其中,基于边沿的线平均算法(Edge-based Line Average,ELA)由于在图像边沿部位重建方面的优异表现而为人们所熟知。文章提出了一种基于显示画面的ELA去隔行算法,其原理是将显示画面划分为面型、线型以及边沿型等3种类型,分别对它们采用本文设计的算法进行去隔行处理。实际模拟结果表明,该方法可以很好地避免边界模糊和锯齿状画面等不良现象的出现,有效降低了运算的复杂度。展开更多
平衡线高度(equilibrium line altitude,ELA)是冰川响应气候变化的直接反映,分析其变化特征对于了解现在和过去的气候具有重要意义。念青唐古拉山中段作为西南季风通道以及怒江与雅鲁藏布江的分水岭,ELA变化及特征研究可为不同流域冰川...平衡线高度(equilibrium line altitude,ELA)是冰川响应气候变化的直接反映,分析其变化特征对于了解现在和过去的气候具有重要意义。念青唐古拉山中段作为西南季风通道以及怒江与雅鲁藏布江的分水岭,ELA变化及特征研究可为不同流域冰川变化与气候相互关系提供参考。基于遥感影像及气候数据,结合模型计算的冰川ELA数据作为输入参数,建立多元线性回归方程,重建并分析了1984—2019年间念青唐古拉山中段冰川ELA变化。结果表明:研究时段内平均ELA为5360 m a.s.l.,总体呈上升趋势,上升速率为1.57 m∙a^(-1)。ELA年变化量显示出波动变化特征,波动范围为5360~5420 m a.s.l.,上升幅度为60 m。受印度季风、流域位置及冰川朝向等因素影响,各流域ELA变化具有差异性,霞曲流域、易贡藏布流域和麦曲流域多年平均ELA高程分别为5335 m a.s.l.、4987 m a.s.l.和5317 m a.s.l.,平均上升幅度分别为265 m、314 m和335 m,上升速率分别7.57 m∙a^(-1)、8.97 m∙a^(-1)和9.57 m∙a^(-1)。对冰川区多年ELA变化的气候响应分析显示,ELA变化主要受气温控制,随气温变化1℃,冰川ELA总体波动幅度为126.02 m。展开更多
文摘Digital image forgery (DIF) is a prevalent issue in the modern age, where malicious actors manipulate images for various purposes, including deception and misinformation. Detecting such forgeries is a critical task for maintaining the integrity of digital content. This thesis explores the use of Modified Error Level Analysis (ELA) in combination with a Convolutional Neural Network (CNN), as well as, Feedforward Neural Network (FNN) model to detect digital image forgeries. Additionally, incorporation of Explainable Artificial Intelligence (XAI) to this research provided insights into the process of decision-making by the models. The study trains and tests the models on the CASIA2 dataset, emphasizing both authentic and forged images. The CNN model is trained and evaluated, and Explainable AI (SHapley Additive exPlanation— SHAP) is incorporated to explain the model’s predictions. Similarly, the FNN model is trained and evaluated, and XAI (SHAP) is incorporated to explain the model’s predictions. The results obtained from the analysis reveals that the proposed approach using CNN model is most effective in detecting image forgeries and provides valuable explanations for decision interpretability.
文摘在当前的去隔行算法中,场内去隔行法由于很好地实现了显示品质和运算成本的平衡而应用最为广泛。其中,基于边沿的线平均算法(Edge-based Line Average,ELA)由于在图像边沿部位重建方面的优异表现而为人们所熟知。文章提出了一种基于显示画面的ELA去隔行算法,其原理是将显示画面划分为面型、线型以及边沿型等3种类型,分别对它们采用本文设计的算法进行去隔行处理。实际模拟结果表明,该方法可以很好地避免边界模糊和锯齿状画面等不良现象的出现,有效降低了运算的复杂度。
文摘平衡线高度(equilibrium line altitude,ELA)是冰川响应气候变化的直接反映,分析其变化特征对于了解现在和过去的气候具有重要意义。念青唐古拉山中段作为西南季风通道以及怒江与雅鲁藏布江的分水岭,ELA变化及特征研究可为不同流域冰川变化与气候相互关系提供参考。基于遥感影像及气候数据,结合模型计算的冰川ELA数据作为输入参数,建立多元线性回归方程,重建并分析了1984—2019年间念青唐古拉山中段冰川ELA变化。结果表明:研究时段内平均ELA为5360 m a.s.l.,总体呈上升趋势,上升速率为1.57 m∙a^(-1)。ELA年变化量显示出波动变化特征,波动范围为5360~5420 m a.s.l.,上升幅度为60 m。受印度季风、流域位置及冰川朝向等因素影响,各流域ELA变化具有差异性,霞曲流域、易贡藏布流域和麦曲流域多年平均ELA高程分别为5335 m a.s.l.、4987 m a.s.l.和5317 m a.s.l.,平均上升幅度分别为265 m、314 m和335 m,上升速率分别7.57 m∙a^(-1)、8.97 m∙a^(-1)和9.57 m∙a^(-1)。对冰川区多年ELA变化的气候响应分析显示,ELA变化主要受气温控制,随气温变化1℃,冰川ELA总体波动幅度为126.02 m。
