IT'S official: Leonardo da Vinci's Mona Lisa was 83 per cent happy, 9 per cent disgusted, 6 per cent fearful and 2 per cent angry.

Nicu Sebe at the University of Amsterdam in the Netherlands tested emotion-recognition software on the famous enigmatic smile. His algorithm, developed with researchers at the Beckman Institute at the University of Illinois, Urbana-Champaign, examines key facial features such as the curvature of the lips and crinkles around the eyes, then scores each face with respect to six basic emotions. Sebe drew on a database of young female faces to derive an average "neutral" expression, which the software used as a standard to compare the painting against.

Software capable of recognising human emotions just by looking at photographs or videos could lead to PCs that adjust their response depending on the user's mood, as well as smarter surveillance systems.