Plagiarism detection of anime character portraits

Abstract

With the expansion of animation industry, there has been a recurring issue of animation plagiarism. Currently, the technology for copyright protection and plagiarism detection in animation is limited. This paper proposes a framework of plagiarism detection for animation character portraits. A Seq2Seq-based model is proposed for extracting the morphological features of animation portraits. By studying portrait morphological fitting simulation, a significant progress is made in learning facial characteristic of animation portraits. With the fitting mechanism, the proposed model can effectively learn the representative essential features of animation portraits. We also propose several loss functions to enhance recognizability and feature mapping ability between original and pirated animation portraits. By comparing the similarity between the pirated and original versions, plagiarism detection is carried out. Experimental results demonstrate that the proposed model has a good fitting effect and effectively detect the authenticity and piracy of the animation portraits.