English

Identifying Human Edited Images using a CNN

Computer Vision and Pattern Recognition 2021-01-12 v1 Artificial Intelligence

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.

Cite

@article{arxiv.2101.03275,
  title  = {Identifying Human Edited Images using a CNN},
  author = {Jordan Lee and Willy Lin and Konstantinos Ntalis and Anirudh Shah and William Tung and Maxwell Wulff},
  journal= {arXiv preprint arXiv:2101.03275},
  year   = {2021}
}

Comments

10 pages, 9 figures

R2 v1 2026-06-23T21:56:23.310Z