An image forgery detection method detects and locates forged components from manipulated images. Identifying whether an image is forged or non-forged requires a sufficient number of features to detect manipulation or tampering. The patch descriptor extracts efficient and highly effective in-depth features from images using a pre-trained convolutional neural network (CNN). An eventual discriminative feature for SVM classification is attained through a feature fusion technique. We compare our outcome with existing state-of-the-art techniques using publicly available benchmark images from CASIA v2.0. The experiment result demonstrations that the proposed approach using a pre-trained CNN model-based features with Support Vector Machine (SVM) classifier has achieved 98.91% accuracy. It is clearly shows from that the proposed model is both effective and adaptable.

#