OCR Graph Features for Manipulation Detection in Documents

TL;DR

This paper introduces a data-driven method using OCR-based graph features and a random forest classifier to detect document manipulations, significantly outperforming existing procedural approaches.

Contribution

It presents a novel graph comparison approach leveraging OCR features and machine learning for manipulation detection in documents, moving beyond hand-tuned procedural methods.

Findings

Outperforms existing manipulation detection models on real-world datasets.

Uses OCR-based graph features with a random forest classifier.

Demonstrates significant improvement in forgery detection accuracy.

Abstract

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.