Object Recognition in Dense Clutter

M.J. Bravo and H. Farid

Perception & Psychophysics, 68(6):911-918, 2006

Paper (pdf)    Bibtex

Observers in recognition experiments typically view objects against a blank background, while observers of real scenes often view objects against dense clutter. In this study we examined whether an object's background affects the information used for recognition. Our stimuli consisted of color photographs of everyday objects organized as a sparse array or as dense clutter. The observer's task was to locate an animal, vehicle or food target in the stimulus. We varied the information in the stimuli by convolving them with a low pass filter (blurring), a high pass filter (edge-detection) or converting them to grayscale. In two experiments, we found that the blurring and edge-detection manipulations produced a modest decrement in performance with the sparse arrangement but a severe decrement in performance with the clutter arrangement. These results indicate that the information used for recognition depends on the object's background. This suggests that models of recognition that have been developed for isolated objects may not generalize to objects in clutter.