Luiz Schirmer

  1. Home
  2. Team
  3. Luiz Schirmer
Luiz is a postdoc researcher at the Institute of Systems and Robotics at the University of Coimbra. His research primarily relates to multilinear (tensor) algebra and Deep Learning for Computer Vision. He is also very interested in Image Processing, Computer Graphics, and Machine Learning in general.

Luiz completed his Ph.D. at PUC-Rio, Brazil, in 2021. Also, during his Ph.D., he spent time at the Institute of Pure and Applied Mathematics (IMPA), working at the Visgraf Lab. Before starting his Ph.D., he obtained a Master's degree in Informatics from PUC-Rio and a Bachelor's in Computer Science from UFSM, Brazil. He joined to VIS Team in October 2021.

Projects

VISUAL-ID – Unique Visual Identities in Graphics, Images and Faces

The Visual-ID project emerge in the context of the partnership between the Imprensa Nacional-Casa da...

TruIM – Trust Image Understanding

TruIm Project aims at developing technologies to authenticate objects in certified images, encoded u...

Publications

Noise simulation for the improvement of training deep neural network for printer-proof steganography

In the modern era, images have emerged as powerful tools for concealing information, giving rise to innovative methods like watermarking and steganography, with end-to-end steganography solutions emerging in recent years. However, these new methods presented some issues regarding the hidden message and the decreased quality of images. This paper investigates the efficacy of noise simulation methods and deep learning methods to improve the resistance of steganography to printing. The research develops an end-to-end printer-proof steganography solution, with a particular focus on the development of a noise simulation module capable of overcoming distortions caused by the transmission of the print-scan medium. Through the development, several approaches are employed, from combining several sources of noise present in the physical environment during printing and capture by image sensors to the introduction of data augmentation techniques and self- supervised learning to improve and stabilize the resistance of the network. Through rigorous experimentation, a significant increase in the robustness of the network was obtained by adding noise combinations while maintaining the performance of the network. Thereby, these experiments conclusively demonstrated that noise simulation can provide a robust and efficient method to improve printer-proof steganography.

  • Date: 24/02/2024
  • //
  • Featured In: 13th International Conference on Pattern Recognition Application and Methods (ICPRAM). Rome, Italy
  • //
  • Publication Type: Conference Papers
  • //
  • Author(s): Telmo Cunha, Luiz Schirmer, João Marcos and Nuno Gonçalves
  • //
  • DOI: 10.5220/0012272300003654
  • //
  • Download File
  • //
  • Visit Website

Steganography Applications of StyleGAN: A (…) Investigation from Hiding Message in Face Images

In this investigation, we delve into the latent codes denoted as w, pertaining to both original and encoded images in steganography models, which are projected through StyleGAN—a generative adversarial network renowned for generating aesthetic synthesis. We present evidence of disentanglement and latent code alterations between the original and encoded images. This investigator possesses the potential to assist in the concealment of messages within images through the manipulation of latent codes within the original images, resulting in the generation of encoded images. The message into encoded renderings is facilitated by the employment of CodeFace, serving as a steganography model. CodeFace comprises an encoder and decoder architecture wherein the encoder conceals a message within an image, while the decoder retrieves the message from the encoded image. By gauging the average disparities amid the latent codes belonging to the original and encoded images, a discerning revelation of optimal channels for concealing information comes to light. Precisely orchestrated manipulation of these channels furnishes us with the means to engender novel encoded visual compositions.

  • Date: 27/10/2023
  • //
  • Featured In: RECPAD - 29th Portuguese Conference on Pattern Recognition. Coimbra (2023), Portugal
  • //
  • Publication Type: Poster
  • //
  • Author(s): Farhad Shadmand, Luiz Schirmer and Nuno Gonçalves
  • //
  • Download File
  • //
  • Visit Website