Document, Image and Voice Analysis (DIVA) Group

The group’s research focuses on multimedia engineering and multimodal data analysis, and in particular on document analysis, recognition and engineering, speech analysis and processing, biometry, gesture and emotion recognition, multimodal interaction and information visualization. For more information, please visit the group's individual web page.

Head of Group

Prof. Rolf Ingold

Current research topics include

  • Multimodal Information Processing
  • Machine Learning & Deep Learning
  • Structural Pattern Recognition, Graph Matching
  • (Historical) Document Analysis, Recognition and Processing
  • Human Machine Interaction
  • Visualization