Research

Overview


The Computer Vision and Multimedia Laboratory carries out research in computer vision, machine learning, data mining, image and signal processing, management and security, multimedia processing, as well as affective computing, human-machine interaction and multimodal interaction. Research applies to visual media, such as images and videos, to sounds and to biological signals. Research results are described in over 300 refereed scientific publications and in 8 patents. Roughly 75% of the research is financed by external, competitive grants.

Current research directions


Machine Learning, Data Mining and Information Retrieval. The Viper group deals with the development of Machine Learning and Data Mining techniques, current research interests include:

  • large-scale and High-dimensional issues in Machine Learning (e.g. Manifold Learning);
  • large-scale Data Mining (Big Data);
  • large-scale Information Indexing (Distributed Indexing).

Stochastic Information Processing. The SIP group carries out research in multimedia processing, classification and mining, communication and security & privacy. The research applies to visual media such as images, videos, and sounds, as well as biometric data.

Social Intelligence and Multi-Sensing. The SIMS group aims at improving social and human-machine interactions by relying on intelligent user sensing. Artificial intelligence is employed to create meaning out of user centered measures, such as physiological signals, brain acitvity, facial expressions, eye-movements and other behaviors.

Media

Past research directions


On the applied side, three main projects have now been completed, leading, respectively, to:

  • copyright protection mechanisms for images and videos, by means of spread-spectrum-based digital watermarks embedded in the documents and a secure copyright network allowing the management of the copyright certificates;
  • image and video archives: efficient algorithms for archival and retrieval of images and image sequences, database strategies for efficient retrieval of documents on the basis of textual and visual criteria;
  • AB-Web: a prototype WWW browser for visually impaired and blind users is under development, including text-to-speech and 2D image-to-3D sound conversion;
  • a public-domain software for image processing (LaboImage);
  • a machine vision system for agricultural robotics (Potato Operation);
  • a medical classification system for 2D gel images (as part of the Melanie system).

On the theoretical side, at various times the following topics have been investigated:

  • image and video watermarking;
  • image filtering and segmentation;
  • low-level grouping;
  • geometric invariance;
  • motion analysis;
  • visual attention;
  • object recognition and learning;
  • computational neuroscience.

Funding and research grants


The research grants have been obtained from the European Union, from the Swiss National Research Foundation (FNRS), and from various Swiss National Research Programs (the Group has also been associate partner in other grants).