Image Sparse Representation Research Articles

Formation of pinwheels of preferred orientation by learning sparse neural representations of natural images

We devise self-organizing model of the striate cortex that learns orientation maps by sparse coding of natural images. The model assumes the existence of oriented receptive fields and of retinotopic mapping. We demonstrate that learning sparse representations of natural images leads to the formation of spatially periodic orientation maps. If and only if the sparseness of the representation is sufficiently high, these orientation maps reproduce different critical parameters of experimentally measured maps in the striate cortex. We conclude the functional topology of the visual cortex that may be tailored to optimize the encoding of natural stimuli with minimal redundancy of the underlying representation.

Properties of basis functions generated by shift invariant sparse representations of natural images.

The idea that a sparse representation is the computational principle of visual systems has been supported by Olshausen and Field [Nature (1996) 381: 607-609] and many other studies. On the other hand neurons in the inferotemporal cortex respond to moderately complex features called icon alphabets, and such neurons respond invariantly to the stimulus position. To incorporate this property into sparse representation, an algorithm is proposed that trains basis functions using sparse representations with shift invariance. Shift invariance means that basis functions are allowed to move on image data and that coefficients are equipped with shift invariance. The algorithm is applied to natural images. It is ascertained that moderately complex graphical features emerge that are not as simple as Gabor filters and not as complex as real objects. Shift invariance and moderately complex features correspond to the property of icon alphabets. The results show that there is another connection between visual information processing and sparse representations.

THE RGF PANDEMONIUM: A LOW-LEVEL REPRESENTATIONAL MODEL FOR IMAGES

In this work, we have reformulated the selection of a few responding units tuned to patterns of activity from the Fourier spectrum as a multilayer system composed of four stages of different kinds of feature detectors. The system output is a sparse representation for images that produces an organization according to object power discrimination. The resultant multilayer system provides a more efficient representation for later stages of processing because it possesses a higher degree of perceptual independence among its outputs.