Arunava Banerjee

Image Denoising Using the Higher Order Singular Value Decomposition

In this paper, we propose a very simple and elegant patch-based, machine learning technique for image denoising using the higher order singular value decomposition (HOSVD). The technique simply groups together similar patches from a noisy image (with similarity defined by a statistically motivated criterion) into a 3D stack, computes the HOSVD coefficients of this stack, manipulates these coefficients by hard thresholding, and inverts the HOSVD transform to produce the final filtered image. Our technique chooses all required parameters in a principled way, relating them to the noise model. We also discuss our motivation for adopting the HOSVD as an appropriate transform for image denoising. We experimentally demonstrate the excellent performance of the technique on grayscale as well as color images. On color images, our method produces state-of-the-art results, outperforming other color image denoising algorithms at moderately high noise levels. A criterion for optimal patch-size selection and noise variance estimation from the residual images (after denoising) is also presented.

Volterrafaces: Discriminant analysis using Volterra kernels

In this paper we present a novel face classification system where we represent face images as a spatial arrangement of image patches, and seek a smooth nonlinear functional mapping for the corresponding patches such that in the range space, patches of the same face are close to one another, while patches from different faces are far apart, in L2 sense. We accomplish this using Volterra kernels, which can generate successively better approximations to any smooth nonlinear functional. During learning, for each set of corresponding patches we recover a Volterra kernel by minimizing a goodness functional defined over the range space of the sought functional. We show that for our definition of the goodness functional, which minimizes the ratio between intraclass distances and interclass distances, the problem of generating Volterra approximations, to any order, can be posed as a generalized eigenvalue problem. During testing, each patch from the test image that is classified independently, casts a vote towards image classification and the class with the maximum votes is chosen as the winner. We demonstrate the effectiveness of the proposed technique in recognizing faces by extensive experiments on Yale, CMU PIE and Extended Yale B benchmark face datasets and show that our technique consistently outperforms the state-of-the-art in learning based face discrimination.

Maximizing all margins: Pushing face recognition with Kernel Plurality

We present two theses in this paper: First, performance of most existing face recognition algorithms improves if instead of the whole image, smaller patches are individually classified followed by label aggregation using voting. Second, weighted plurality1 voting outperforms other popular voting methods if the weights are set such that they maximize the victory margin for the winner with respect to each of the losers. Moreover, this can be done while taking higher order relationships among patches into account using kernels. We call this scheme Kernel Plurality. We verify our proposals with detailed experimental results and show that our framework with Kernel Plurality improves the performance of various face recognition algorithms beyond what has been previously reported in the literature. Furthermore, on five different benchmark datasets - Yale A, CMU PIE, MERL Dome, Extended Yale B and Multi-PIE, we show that Kernel Plurality in conjunction with recent face recognition algorithms can provide state-of-the-art results in terms of face recognition rates.

Probability Density Estimation Using Isocontours and Isosurfaces: Applications to Information-Theoretic Image Registration

We present a new, geometric approach for determining the probability density of the intensity values in an image. We drop the notion of an image as a set of discrete pixels, and assume a piecewise-continuous representation. The probability density can then be regarded as being proportional to the area between two nearby isocontours of the image surface. Our paper extends this idea to joint densities of image pairs. We demonstrate the application of our method to affine registration between two or more images using information theoretic measures such as mutual information. We show cases where our method outperforms existing methods such as simple histograms, histograms with partial volume interpolation, Parzen windows, etc. under fine intensity quantization for affine image registration under significant image noise. Furthermore, we demonstrate results on simultaneous registration of multiple images, as well as for pairs of volume datasets, and show some theoretical properties of our density estimator. Our approach requires the selection of only an image interpolant. The method neither requires any kind of kernel functions (as in Parzen windows) which are unrelated to the structure of the image in itself, nor does it rely on any form of sampling for density estimation.

Trainable Convolution Filters and Their Application to Face Recognition

In this paper, we present a novel image classification system that is built around a core of trainable filter ensembles that we call Volterra kernel classifiers. Our system treats images as a collection of possibly overlapping patches and is composed of three components: (1) A scheme for a single patch classification that seeks a smooth, possibly nonlinear, functional mapping of the patches into a range space, where patches of the same class are close to one another, while patches from different classes are far apart-in the L_2 sense. This mapping is accomplished using trainable convolution filters (or Volterra kernels) where the convolution kernel can be of any shape or order. (2) Given a corpus of Volterra classifiers with various kernel orders and shapes for each patch, a boosting scheme for automatically selecting the best weighted combination of the classifiers to achieve higher per-patch classification rate. (3) A scheme for aggregating the classification information obtained for each patch via voting for the parent image classification. We demonstrate the effectiveness of the proposed technique using face recognition as an application area and provide extensive experiments on the Yale, CMU PIE, Extended Yale B, Multi-PIE, and MERL Dome benchmark face data sets. We call the Volterra kernel classifiers applied to face recognition Volterrafaces. We show that our technique, which falls into the broad class of embedding-based face image discrimination methods, consistently outperforms various state-of-the-art methods in the same category.

A Method for Compact Image Representation Using Sparse Matrix and Tensor Projections Onto Exemplar Orthonormal Bases

We present a new method for compact representation of large image datasets. Our method is based on treating small patches from a 2-D image as matrices as opposed to the conventional vectorial representation, and encoding these patches as sparse projections onto a set of exemplar orthonormal bases, which are learned a priori from a training set. The end result is a low-error, highly compact image/patch representation that has significant theoretical merits and compares favorably with existing techniques (including JPEG) on experiments involving the compression of ORL and Yale face databases, as well as a database of miscellaneous natural images. In the context of learning multiple orthonormal bases, we show the easy tunability of our method to efficiently represent patches of different complexities. Furthermore, we show that our method is extensible in a theoretically sound manner to higher-order matrices (¿tensors¿). We demonstrate applications of this theory to compression of well-known color image datasets such as the GaTech and CMU-PIE face databases and show performance competitive with JPEG. Lastly, we also analyze the effect of image noise on the performance of our compression schemes.

Dynamical constraints on using precise spike timing to compute in recurrent cortical networks

Several recent models have proposed the use of precise timing of spikes for cortical computation. Such models rely on growing experimental evidence that neurons in the thalamus as well as many primary sensory cortical areas respond to stimuli with remarkable temporal precision. Models of computation based on spike timing, where the output of the network is a function not only of the input but also of an independently initializable internal state of the network, must, however, satisfy a critical constraint: the dynamics of the network should not be sensitive to initial conditions. We have previously developed an abstract dynamical system for networks of spiking neurons that has allowed us to identify the criterion for the stationary dynamics of a network to be sensitive to initial conditions. Guided by this criterion, we analyzed the dynamics of several recurrent cortical architectures, including one from the orientation selectivity literature. Based on the results, we conclude that under conditions of sustained, Poisson-like, weakly correlated, low to moderate levels of internal activity as found in the cortex, it is unlikely that recurrent cortical networks can robustly generate precise spike trajectories, that is, spatiotemporal patterns of spikes precise to the millisecond timescale.

Converting numerical classification into text classification

Consider a supervised learning problem in which examples contain both numerical- and text-valued features. To use traditional feature-vector-based learning methods, one could treat the presence or absence of a word as a Boolean feature and use these binary-valued features together with the numerical features. However, the use of a text-classification system on this is a bit more problematic-in the most straight-forward approach each number would be considered a distinct token and treated as a word. This paper presents an alternative approach for the use of text classification methods for supervised learning problems with numerical-valued features in which the numerical features are converted into bag-of-words features, thereby making them directly usable by text classification methods. We show that even on purely numerical-valued data the results of text classification on the derived text-like representation outperforms the more naive numbers-as-tokens representation and, more importantly, is competitive with mature numerical classification methods such as C4.5, Ripper, and SVM. We further show that on mixed-mode data adding numerical features using our approach can improve performance over not adding those features.

On the Phase-Space Dynamics of Systems of Spiking Neurons. I: Model and Experiments

We investigate the phase-space dynamics of a general model of local systems of biological neurons in order to deduce the salient dynamical characteristics of such systems. In this article, we present a detailed exposition of an abstract dynamical system that models systems of biological neurons. The abstract system is based on a limited set of realistic assumptions and thus accommodates a wide range of neuronal models. Simulation results are presented for several instantiations of the abstract system, each modeling a typical neocortical column to a different degree of accuracy. The results demonstrate that the dynamics of the systems are generally consistent with that observed in neurophysiological experiments. They reveal that the qualitative behavior of the class of systems can be classified into three distinct categories: quiescence, intense periodic activity resembling a state of seizure, and sustained chaos over the range of intrinsic activity typically associated with normal operational conditions in the neocortex. We discuss basic ramifications of this result with regard to the computational nature of neocortical neuronal systems.

Average fill rate and horizon length

Given a sequence of independent and identically distributed demands and an order up to replenishment policy with negligible lead time, we prove that average fill rate is monotonically decreasing in the number of periods in the planning horizon. This was conjectured to be true in a recent issue of this journal.