Abstract: Generation of a digital document from an analog document is provided. The document generation includes obtaining a user image of a user-filled document. A first set of key points and a second set of key points are extracted from a template image and the user image, respectively. Probabilistic matching of the first set of key points and the second set of key points is performed to determine a transformation. An inverse transformation is performed on the transformation to transform back one or more areas of interest into an image-space of the template image. A mask is generated for the one or more areas of interest in the user image. The mask is further merged onto a corresponding area of the template image to generate the digital document.