Sparse Coding Of Natural Images Using A Prior On Edge Co-Occurences


Oriented edges in images of natural scenes tend to be aligned in co-linear or co-circular arrangements, with lines and smooth curves more common than other possible arrangements of edges (the good continuation law of Gestalt psychology). The visual system appears to take advantage of this prior knowledge about natural images, with human contour detection and grouping performance well predicted by such an asociation field between edge elements. Geisler et al (2001) have estimated this prior information available to the visual system by extracting contours from a database of natural images, and showed that these statistics could predict behavioral data from humans in a line completion task. In this paper, we show that an association field of this type can be used for the sparse representation of natural images.

European Signal Processing Conference 2015 (EUSIPCO 2015)
Laurent U Perrinet
Laurent U Perrinet
Researcher in Computational Neuroscience

My research interests include Machine Learning and computational neuroscience applied to Vision.