Photos of the Day: Object Recognition without Human Calibration
Lee and his students fed their object recognition program four image datasets from CalTech (motorbikes, faces, airplanes and cars) and found 100 percent accurate recognition on every dataset. The other published well-performing object recognition systems scored in the 95 to 98 percent range. Photo illustration by BYU Photo
For more information visit http://home.byu.edu/home/ .