His rapid growth of digital documentation has increased the risk of document forgery in several industries, including public services, banking, and education. A significant part of traditional document verification methods is manual inspection, which is often inefficient and prone to errors. To detect forged documents, an automated technique that utilizes machine learning and image processing is presented in this paper. The system examines structural and content-based features to identify unauthorized changes, such as altered text areas and visual elements. The proposed model uses preprocessing and feature extraction techniques to differentiate between genuine and fraudulent document types. The results demonstrate that the system improves verification accuracy while decreasing the need for human intervention. This strategy offers a practical means of enhancing the security of documents.