NicIcon: Handwritten Icons for Crisis Management from 32 Dutch Students

Radboud University Nijmegen researchers collected 24,441 hand-drawn icons for crisis management systems from 32 Dutch student volunteers aged 19-30. The NicIcon database provides both offline scans and online pen trajectory time series for 14 classes of symbolic gestures representing events like floods and accidents. Each participant also wrote the 'London Letter' for forensic handwriting analysis.

Use Cases

• Train gesture classification models based on 14 classes of symbolic crisis icons.
• Develop multimodal handwriting recognition systems using paired online pen trajectories and offline scans.
• Benchmark time-series analysis algorithms on pen coordinate and pressure data.
• Study human-computer interaction for crisis management interfaces based on designed, distinguishable icons.

Strengths

• Contains 24,441 hand-drawn icon instances.
• Data is multimodal, with both offline scans and online pen trajectory time series.
• Covers 14 distinct icon classes relevant to crisis management.
• Includes additional handwriting samples from the 'London Letter' for forensic analysis.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count for specific data splits or the 'London Letter' text is unknown.
• Data reflects a demographic bias, sourced exclusively from 32 Dutch students, with 29 male and 3 female participants.

Provenance

Source

Radboud University Nijmegen

Collection Method

Collected using a Wacom Intuos2 tablet and specially developed software from volunteer participants drawing on paper.

Geography

Netherlands