Publications

Publications related to the VIS Team

Dealing with Overfitting in the Context of Liveness Detection

With this work it was possible to: - Conclude on the importance of a well-rounded dataset; - Mitigating overfitting, reducing the difference from the best epoch to the average of the last epochs from 36.57% to 3.63%. In the future: - Apply these conclusions in the making of a new model, keeping it as simple as possible; - Developing a dataset with as much variety as possible, be it in types of spoof, individuals and capture condition.

  • Author(s): Miguel Leão and Nuno Gonçalves
  • //
  • Featured In: RECPAD - 29th Portuguese Conference on Pattern Recognition. Coimbra (2023), Portugal
  • //
  • Publication Type: Poster
  • //
  • Year: 2023
  • //
  • View 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.

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

An Augmented Reality Application Using Graphic Code Markers

Presenting applications of the Graphic Code, exploiting its large-scale information coding capabilities applied to Augmented Reality.

  • Author(s): Leandro Cruz, Bruno Patrão, Nuno Gonçalves
  • //
  • Featured In: IEEE International Conference on Artificial Intelligence and Virtual Reality (AIVR)
  • //
  • Publication Type: Poster
  • //
  • Year: 2018
  • //
  • View File

Use of Epipolar Images Towards Outliers Extraction in Depth Images

Method for filtering the depth model, reconstructed from light field cameras, based on the removal of low confidence reconstructed values and using an inpainting method to replace them. This approach has shown good results for outliers removal.

  • Author(s): Dirce Celorico, Leandro Cruz, Leandro Dihl, Nuno Gonçalves
  • //
  • Featured In: Recpad 2018-24th Portuguese Conference on Pattern Recognition
  • //
  • Publication Type: Poster
  • //
  • Year: 2018
  • //
  • View File

Graphic Code: Creation, Detection and Recognition

Graphic Code is a new Machine Readable Coding (MRC) method. It creates coded images by organizing available primitive graphic units arranged according to some predefined patterns. Some of these patterns are previously associated with symbols used to compose the messages and to define a dictionary.

  • Author(s): Leandro Cruz, Bruno Patrão, Nuno Gonçalves
  • //
  • Featured In: Recpad 2018-24th Portuguese Conference on Pattern Recognition
  • //
  • Publication Type: Poster
  • //
  • Year: 2018
  • //
  • View File

Improving Facial Depth Data by Exemplar-based Comparisons

Presented a filtering method for meshes of faces preserving their intrinsic features. It is based in an exemplar-based neighborhood matching where all models are in a frontal position avoiding rotation and perspective drawbacks. Moreover, the model is invariant to depth translation and scale.

  • Author(s): Leandro Dihl, Leandro Cruz, Nuno Gonçalves
  • //
  • Featured In: Recpad 2018-24th Portuguese Conference on Pattern Recognition
  • //
  • Publication Type: Poster
  • //
  • Year: 2018
  • //
  • View File

Exemplar Based Filtering of 2.5D Meshes of Faces

Presentation of a content-aware filtering for 2.5D meshes of faces. An exemplar-based filter that corrects each point of a given mesh through local model-exemplar neighborhood comparison taking advantage of prior knowledge of the models (faces) to improve the comparison.

  • Author(s): Leandro Dihl, Leandro Cruz, Nuno Gonçalves
  • //
  • Featured In: Eurographics 2018 Posters
  • //
  • Publication Type: Poster
  • //
  • Year: 2018
  • //
  • View File