Computational visual distinctness metric

A new computational visual distinctness metric based on principles of the early human visual system is presented. The metric is applied to quantify (1) the visual distinctness of targets in complex natural scenes and (2) the perceptual differences between compressed and uncompressed images. The new metric is shown (1) to predict human observer...

Genetic contour matching

Object recognition can be formulated as an optimization problem. The objective function measures for instance the evidential support for any particular projection of the parameterized object contour model onto the input image. A genetic algorithm can be used to find a set of parameters which provide an optimal interpretation of the image in...