The research topics of IntuiDoc concern the written communication and the engineering of documents under various aspects: analysis, recognition, composition, interpretation and also graphical/gestural man-document interaction. This research relates to the handwriting and the documents under different forms: manuscript, printed paper form, pen-based and touch-based interaction, graph, images, heterogeneous documents, etc.
The roadmap of the IntuiDoc team is on the frontier of several research axes: Pattern recognition, Machine-Learning, Human-Machine Interaction, Uses and Digital Learning. The aim is to explore new scientific challenges of the domain of the Human-Document Interaction with a specific focus on interactive, incremental and evolving learning based on the integration of the user in all the processes of analysis and decision making.
Today, four major emerging scientific axes are investigated with strong partnerships with national and international laboratories and companies:
- “On-line” evolving cross-learning of 2D (touch and pen –based) and 3D gestures (Kinect and Leap Motion);
- “On-line” analysis of drawing, sketching and handwriting with pen-based tablet for digital learning (e-education);
- Interactive learning of document structure without ground-truth;
- Document collection analysis for big-data.