Biologically-inspired characterization of sparseness in natural images

Laurent U Perrinet (1)

1 INT - Institut de Neurosciences de la Timone

Natural images follow statistics inherited by the structure of our physical (visual) environment. In particular, a prominent facet of this structure is that images can be described by a relatively sparse number of features. We designed a sparse coding algorithm biologically-inspired by the architecture of the primary visual cortex. We show here that coefficients of this representation exhibit a heavy-tailed distribution. For each image, the parameters of this distribution characterize sparseness and vary from image to image. To investigate the role of this sparseness, we designed a new class of random textured stimuli with a controlled sparseness value inspired by our measurements on natural images. Then, we provide with a method to synthesize random textures images with a given statistics for sparseness that matches that of some given class of natural images and provide perspectives for their use in neurophysiology.

Keywords: Machine vision; Image texture; Computer vision; Neuroscience

Domains: Life Sciences [q-bio]; Neurons and Cognition [q-bio.NC]

Laurent U Perrinet. Biologically-inspired characterization of sparseness in natural images. 6th European Workshop on Visual Information Processing (EUVIP), Oct 2016, Marseille, France. pp.1--6, ⟨10.1109/EUVIP.2016.7764592⟩. ⟨hal-01461404⟩