Smile chemistry

London, Dec. 14: A bit late in the day perhaps compared with the ancient Hindus, a computer can now be programmed to recognise human emotion.

According to an article to be published this weekend in the New Scientist in London, a computer scanned the Mona Lisa, the most famous painting in the world, and concluded Leonardo da Vinci’s subject was “83 per cent happy, 9 per cent disgusted, 6 per cent fearful and 2 per cent angry”.

The work of modern computers and scientists was anticipated by Bharata who identified nine rasas: adbhuta (wonder), hasya (laughter), shringara (love), shaanta (peace), bibhatsa (disgust), vira (valour), karuna (pathos), bhaya (fear) and raudra (anger).

The brief item in the New Scientist was written by Boston journalist Greg Huang, based on research done at Amsterdam University by research scholar Nicu Sebe.

In his report, Huang says Sebe “tested emotion-recognition software on the famous enigmatic smile. His algorithm, developed with researchers at the University of Illinois, 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”.

The article adds: “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.”

Huang today told The Telegraph that he, too, had attended Illinois University and had been interested in the subject of the computer-human interface. “In the last 10 years... a lot of work has been done in this field. The computer has a large data base of faces and can classify happiness, disgust, fear, anger, surprise and sadness,” he said.