First Steps Toward CNN based Source Classification of Document Images Shared Over Messaging App

TL;DR

This paper introduces a CNN-based method for identifying the source smartphone of document images shared over messaging apps, using a new dataset of printed documents captured by various smartphones.

Contribution

It presents the first CNN approach for source smartphone classification of document images captured via messaging platforms, along with a new publicly available dataset.

Findings

CNN-based system matches or exceeds state-of-the-art handcrafted feature methods

New dataset of 315 images from 21 smartphones across three fonts

System performs well in real-world messaging app scenarios

Abstract

Knowledge of source smartphone corresponding to a document image can be helpful in a variety of applications including copyright infringement, ownership attribution, leak identification and usage restriction. In this letter, we investigate a convolutional neural network-based approach to solve source smartphone identification problem for printed text documents which have been captured by smartphone cameras and shared over messaging platform. In absence of any publicly available dataset addressing this problem, we introduce a new image dataset consisting of 315 images of documents printed in three different fonts, captured using 21 smartphones and shared over WhatsApp. Experiments conducted on this dataset demonstrate that, in all scenarios, the proposed system performs as well as or better than the state-of-the-art system based on handcrafted features and classification of letters extracted from document images. The new dataset and code of the proposed system will be made publicly available along with this letter's publication, presently they are submitted for review.