Science & Quality

The Feng-GUI analysis employs dozens of algorithms from neuro-science studies of natural vision processing, computational attention, eye-tracking sessions, perception and cognition of humans.
Or in English: "What people are looking at?"

Here are some of the visual features that are analyzed in an image.


How accurate is it?

Feng-GUI reports closely resemble a 5 seconds eye tracking session of 40 subjects.
Get instant and unbiased feedback at fraction of the cost and time of traditional eye-tracking.

We measure, benchmark, compare and tune the analysis with eye-tracking data sets. The data sets contains thousands of images viewed by hundreds of participants.

Here are some of the data sets:
  • AIM : 120 images 20 viewers (Neil D. B. Bruce and John K. Tsotsos 2005).
  • LeMeur : 27 images 40 viewers (O. Le Meur, P. Le Callet, D. Barba and D. Thoreau 2006).
  • Torralba : 73 images 24 viewers (Antonio Torralba, Aude Oliva, Monica Castelhano and John Henderson 2006).
  • Kootstra : 100 images 31 viewers (Kootstra, G., Nederveen, A. and de Boer, B. 2008).
  • DOVES : 101 images 29 viewers (van der Linde, I., Rajashekar, U., Bovik, A.C., Cormack, L.K. 2009).
  • Ehinger : 912 images 14 viewers (Krista A. Ehinger, Barbara Hidalgo-Sotelo, Antonio Torralba and Aude Oliva 2009).
  • Judd : 1003 images 15 viewers (Tilke Judd, Krista Ehinger, Fre'do Durand and Antonio Torralba 2009).
  • NUSEF : 758 images 75 viewers (R. Subramanian, H. Katti, N. Sebe1, M. Kankanhalli and T-S. Chua 2010).