Some Objects Are More Equal Than Others: Measuring and Predicting Importance

We observe that everyday images contain dozens of objects, and that humans, in describing these images, give different priority to these objects. We argue that a goal of visual recognition is, therefore, not only to detect and classify objects but also to associate with each a level of priority which we call `importance'. We propose a definition of importance and show how this may be estimated reliably from data harvested from human observers. We conclude by showing that a first-order estimate of importance may be computed from a number of simple image region measurements and does not require access to image meaning.

• Type: Conference
• Year: 2008
• Where: ECCV
• Authors: Merrielle Spain, Pietro Perona
• Keywords: Computer Vision, ECCV 2008, Image Region Measurements, Images Contain Dozens