Single Image Watermark Retrieval from 3D Printed Surfaces via Convolutional Neural Networks

Zhang, Xin; Wang, Qian; Ivrissimtzis, Ioannis

Abstract

In this paper we propose and analyse a method for watermarking 3D printed objects, concentrating on the watermark retrieval problem. The method embeds the watermark in a planar region of the 3D printed object in the form of small semi-spherical or cubic bumps arranged at the nodes of a regular grid. The watermark is extracted from a single image of the watermarked planar region through a Convolutional Neural Network. Experiments with 3D printed objects, produced by filaments of various colours, show that in most cases the retrieval method has a high accuracy rate.

Citation

Zhang, X., Wang, Q., & Ivrissimtzis, I. (2018, December). Single Image Watermark Retrieval from 3D Printed Surfaces via Convolutional Neural Networks. Presented at EG UK Computer Graphics & Visual Computing, Swansea, UK

• Presentation Conference Type: Conference Paper (published)
• Conference Name: EG UK Computer Graphics & Visual Computing
• Acceptance Date: Jul 24, 2018
• Publication Date: Jan 1, 2018
• Deposit Date: Nov 20, 2018
• Publicly Available Date: Nov 21, 2018
• Pages: 117-120
• Book Title: Computer Graphics & Visual Computing (CGVC) 2018 : Eurographics UK Chapter proceedings.
• DOI: https://doi.org/10.2312/cgvc.20182019
• Public URL: https://durham-repository.worktribe.com/output/1143548
• Publisher URL: http://diglib.eg.org/handle/10.2312/cgvc20182019