Everyday tasks like walking on the street, recognizing a friend or understanding a scene seem so simple and immediate that transposing it to a computer might seem like an easy task. Only when we try it do we realize our immense talent, as humans, in making sense of the data that reaches our senses. In this talk I illustrate some of these difficulties and particularize for the context of texture discrimination. I introduce a simple supervised learning approach (using Genetic Algorithms) that enables high-frame rate texture discrimination and compare it with current state-of-the-art methods. I further particularize the general methodology to rotationally discriminant and rotationally invariant discrimination. I conclude with experimental results, which illustrate that it is successful in capturing the essence of the texture discrimination problem.
Learning simple texture discrimination filters
November 16, 2010
1:00 pm
Rui Guerreiro
Rui Guerreiro received his licenciatura (2002) and MSc (2003) degrees from Instituto Superior Técnico (IST), Portugal, in Electrical & Electronical Engineering, the latter on the topic of 2D-to-3D conversion using Structure from Motion. In 2003, he joined Siemens S.A. in Lisbon where he worked in high-speed circuit design for communication systems. In 2005, he joined the Video Processing Group of Philips Research, Eindhoven, The Netherlands, where he worked on picture enhancement topics (motion estimation, halo-free frame-rate up-conversion, multi-band enhancement, temporal compression artifact suppression, spatial color processing, color therapy), 2D-to-3D conversion for 3D-TVs (scene classification, depth-from-focus, motion-based segmentation) and supervised student work on low-cost gaze tracking. In 2009, he started a PhD at IST, on perception-based 2D-to-3D conversion. He has 4 patents and 9 peer-reviewed publications on these topics.Instituto de Sistemas e RobóticaSeminários
Últimos seminários
Unlocking Latent Discourse Translation in LLMs Through Quality-Aware Decoding
June 17, 2025Large language models (LLMs) have emerged as strong contenders in machine translation. Yet, they often fall behind specialized neural machine…
Speech as a Biomarker for Disease Detection
May 20, 2025Today’s overburdened health systems face numerous challenges, exacerbated by an aging population. Speech emerges as a ubiquitous biomarker with strong…
Enhancing Uncertainty Estimation in Neural Networks
May 6, 2025Neural networks are often overconfident about their predictions, which undermines their reliability and trustworthiness. In this presentation, I will present…
Improving Evaluation Metrics for Vision-and-Language Models
April 22, 2025Evaluating image captions is essential for ensuring both linguistic fluency and accurate semantic alignment with visual content. While reference-free metrics…