OCR Graph Features for Manipulation Detection in Documents
This addresses the need for information verification in documents, offering a data-driven approach for detecting forgeries, though it appears incremental as it builds on existing graph-based methods with OCR features.
The paper tackles the problem of detecting manipulations in digital documents by framing it as a graph comparison problem using OCR character bounding boxes, and reports that their model dramatically outperforms the most closely-related model on a dataset of real business documents with slight forgery imperfections.
Detecting manipulations in digital documents is becoming increasingly important for information verification purposes. Due to the proliferation of image editing software, altering key information in documents has become widely accessible. Nearly all approaches in this domain rely on a procedural approach, using carefully generated features and a hand-tuned scoring system, rather than a data-driven and generalizable approach. We frame this issue as a graph comparison problem using the character bounding boxes, and propose a model that leverages graph features using OCR (Optical Character Recognition). Our model relies on a data-driven approach to detect alterations by training a random forest classifier on the graph-based OCR features. We evaluate our algorithm's forgery detection performance on dataset constructed from real business documents with slight forgery imperfections. Our proposed model dramatically outperforms the most closely-related document manipulation detection model on this task.