What Makes a Good Feature?
Author(s)Richards, W.; Jepson, A.
MetadataShow full item record
Using a Bayesian framework, we place bounds on just what features are worth computing if inferences about the world properties are to be made from image data. Previously others have proposed that useful features reflect "non-accidental'' or "suspicious'' configurations (such as parallel or colinear lines). We make these notions more precise and show them to be context sensitive.
computational vision, vision features, Bayesian model, svision psychophysics, color, motion