An Approach for Copy-Move and Image Splicing Forgery Detection using Automated Deep Learning

Image forgery detection plays a vital role for thorough incident investigation and social media crime preventions. An innovative approach for image forgery detection by utilizing a DenseNet-201 convolutional neural network is presented. The proposed method utilizes DenseNet-201 architecture to extract features from an input image and then uses a fully connected layer to classify the image as either genuine or forged. The model is trained on a dataset of authenticated and forged images and evaluated on a separate test set. The results show that the proposed approach achieves an accuracy of 94.12 %, outperforming existing methods. It demonstrates that the proposed model can accurately detect image forgeries across a wide range of image types. Also, the model is evaluated on various image transformations, like scaling, rotation, and translation. Furthermore, the proposed approach is computationally efficient, making it suitable for real-time applications.