Rajan Vaish, Sascha T. Ishikawa, Sheng Lundquist, Reid Porter, James Davis
02/08/2015 01:29 AM
Computer Science
Object detection is a key component of many computer vision systems. This paper investigates human computation as a platform for object detection. We investigate and report on the quality of raw labels obtained from several sources of human labor. We find that the performance is not the same in all cases. We investigate and report on the quality of a simple aggregation algorithm. Finally, we compare our human computation based object detector against existing computer vision based approaches.
