Identifying Human Edited Images using a CNN

TL;DR

This paper introduces a generative model to detect human face edits made by popular mobile apps like FaceTune and Pixlr, addressing the lack of datasets for training such classifiers.

Contribution

It presents a novel generative model that approximates the distribution of human face edits and a detection method for mobile app manipulations.

Findings

Effective detection of FaceTune and Pixlr edits

Addresses dataset scarcity for face manipulation detection

Provides a new approach for classifying mobile app face edits

Abstract

Most non-professional photo manipulations are not made using propriety software like Adobe Photoshop, which is expensive and complicated to use for the average consumer selfie-taker or meme-maker. Instead, these individuals opt for user friendly mobile applications like FaceTune and Pixlr to make human face edits and alterations. Unfortunately, there is no existing dataset to train a model to classify these type of manipulations. In this paper, we present a generative model that approximates the distribution of human face edits and a method for detecting Facetune and Pixlr manipulations to human faces.