A common problem encountered in such disciplines as statistics, data analysis, signal processing, and neural network research, is nding a suitable representation of multivariate data. For computational and conceptual simplicity, such a representation is often sought as a linear transformation of the original data. Well-known linear transformation methods include, for example, principal component analysis, factor analysis, and projection pursuit. A recently developed linear transformation method is independent component analysis (ICA), in which the desired representation is the one that minimizes the statistical dependence of the components of the representation. Such a representation seems to capture the essential structure of the data in many applications. In this paper, we survey the existing theory and methods for ICA. 1

The classical model of visual processing in cortex is a hierarchy of increasingly sophisticated representations, extending in a natural way the model of simple to complex cells of Hubel and Wiesel. Somewhat surprisingly, little quantitative modeling has been done in the last 15 years to explore the biological feasibility of this class of models to explain higher level visual processing, such as object recognition. We describe a new hierarchical model that accounts well for this complex visual task, is consistent with several recent physiological experiments in inferotemporal cortex and makes testable predictions. The model is based on a novel MAX-like operation on the inputs to certain cortical neurons which may have a general role in cortical function.

this article we investigate to what extent the statistical properties of natural images can be used to understand the variation of receptive field properties of simple cells in the mammalian primary visual cortex. The receptive fields of simple cells have been studied extensively (e.g., Hubel & Wiesel 1968, DeValois et al. 1982a, DeAngelis et al. 1993): they are localised in space and time, have band-pass characteristics in the spatial and temporal frequency domains, are oriented, and are often sensitive to the direction of motion of a stimulus. Here we will concentrate on the spatial properties of simple cells. Several hypotheses as to the function of these cells have been proposed. As the cells preferentially respond to oriented edges or lines, they can be viewed as edge or line detectors. Their joint localisation in both the spatial domain and the spatial frequency domain has led to the suggestion that they mimic Gabor filters, minimising uncertainty in both domains (Daugman 1980, Marcelja 1980). More recently, the match between the operations performed by simple cells and the wavelet transform has attracted attention (e.g., Field 1993). The approaches based on Gabor filters and wavelets basically consider processing by the visual cortex as a general image processing strategy, relatively independent of detailed assumptions about image statistics. On the other hand, the edge and line detector hypothesis is based on the intuitive notion that edges and lines are both abundant and important in images. This theme of relating simple cell properties with the statistics of natural images was explored extensively by Field (1987, 1994). He proposed that the cells are optimized specifically for coding natural images. He argued that one possibility for such a code, sparse coding...

Abstract—A number of current face recognition algorithms use face representations found by unsupervised statistical methods. Typically these methods find a set of basis images and represent faces as a linear combination of those images. Principal component analysis (PCA) is a popular example of such methods. The basis images found by PCA depend only on pairwise relationships between pixels in the image database. In a task such as face recognition, in which important information may be contained in the high-order relationships among pixels, it seems reasonable to expect that better basis images may be found by methods sensitive to these high-order statistics. Independent component analysis (ICA), a generalization of PCA, is one such method. We used a version of ICA derived from the principle of optimal information transfer through sigmoidal neurons. ICA was performed on face images in the FERET database under two different architectures, one which treated the images as random variables and the pixels as outcomes, and a second which treated the pixels as random variables and the images as outcomes. The first architecture found spatially local basis images for the faces. The second architecture produced a factorial face code. Both ICA representations were superior to representations based on PCA for recognizing faces across days and changes in expression. A classifier that combined the two ICA representations gave the best performance. Index Terms—Eigenfaces, face recognition, independent component analysis (ICA), principal component analysis (PCA), unsupervised learning. I.

It is well known that visual cortical neurons respond vigorously to a limited range of stimulus orientations, while their primary afferent inputs, neurons in the lateral geniculate nucleus (LGN) respond well to all orientations. Mechanisms based on intracortical inhibition and/or converging thalamocortical afferents have previously been suggested to underlie the generation of cortical orientation selectivity; however, these models conflict with experimental data. Here, a 1:4 scale model of a 1700m by 200m region of layer IV of cat primary visual cortex (area 17) is presented in order to demonstrate that local intracortical excitation may provide the dominant source of orientation selective input. In agreement with experiment, model cortical cells exhibit sharp orientation selectivity despite receiving strong iso-- orientation inhibition, weak cross--orientation inhibition, no shunting inhibition, and weakly tuned thalamocortical excitation. Sharp tuning is provided by recurrent cortica...

this article, we show that the same principle of independence maximization can explain the emergence of phase- and shift-invariant features, similar to those found in complex cells. This new kind of emergence is obtained by maximizing the independence between norms of projections on linear subspaces (instead of the independence of simple linear filter outputs). Thenorms of the projections on such "independent feature subspaces" then indicate the values of invariant features

In this paper, we present a perceptual distortion measure that predicts image integrity far better than meansquared error. This perceptual distortion measure is based on a model of human visual processing that ts empirical measurements of the psychophysics of spatial pattern detection. The model of human visual processing proposed involves two major components: a steerable pyramid transform and contrast normalization. We also illustrate the usefulness of the model in predicting perceptual distortion in real images. 1.

The statistical properties of natural images suggest an optimal form of nonlinear decomposition, in which the image is decomposed using a set of linear filters at a variety of positions, scales and orientations, and these linear responses are then rectified and divided by a weighted sum of rectified responses of nearby filters. Such divisive normalization models have become widely used in modeling steady-state responses of neurons in primary visual cortex. In addition to providing a surprisingly good characterization of "typical" neurons, the statistically optimal version of the model is consistent with unusual changes in tuning properties of these neurons at different contrast levels. These results suggest that the nonlinear response properties of cortical neurons are not an accident of biophysical implementation, but serve an important functional role.

The Discrete Wavelet Transform (DWT) decomposes an image into bands that vary in spatial frequency and orientation. It is widely used for image compression. Measures of the visibility of DWT quantization errors are required to achieve optimal compression. Uniform quantization of a single band of coefficients results in an artifact that we call DWT uniform quantization noise; it is the sum of a lattice of random amplitude basis functions of the corresponding DWT synthesis filter. We measured visual detection thresholds for samples of DWT uniform quantization noise in Y, Cb, and Cr color channels. The spatial frequency of a wavelet is r 2 -l , where r is display visual resolution in pixels/degree, and l is the wavelet level. Thresholds increase rapidly with wavelet spatial frequency. Thresholds also increase from Y to Cr to Cb, and with orientation from low-pass to horizontal/vertical to diagonal. We construct a mathematical model for DWT noise detection thresholds that is a function of level, orientation, and display visual resolution. This allows calculation of a "perceptually lossless" quantization matrix for which all errors are in theory below the visual threshold. The model may also be used as the basis for adaptive quantization schemes.

Bottom-up or saliency-based visual attention allows primates to detect non-specific conspicuous targets in cluttered scenes. A classical metaphor, derived from electrophysiological and psychophysical studies, describes attention as a rapidly shiftable "spotlight". The model described here reproduces the attentional scanpaths of this spotlight: Simple multi-scale "feature maps" detect local spatial discontinuities in intensity, color, orientation or optical flow, and are combined into a unique "master" or "saliency" map. The saliency map is sequentially scanned, in order of decreasing saliency, by the focus of attention. We study the problem of combining feature maps, from different visual modalities and with unrelated dynamic ranges (such as color and motion), into a unique saliency map. Four combination strategies are compared using three databases of natural color images: (1) Simple normalized summation, (2) linear combination with learned weights, (3) global non-linear normalization...