Ritwik Kumar

Radon-Like features and their application to connectomics

In this paper we present a novel class of so-called Radon-Like features, which allow for aggregation of spatially distributed image statistics into compact feature descriptors. Radon-Like features, which can be efficiently computed, lend themselves for use with both supervised and unsupervised learning methods. Here we describe various instantiations of these features and demonstrate there usefulness in context of neural connectivity analysis, i.e. Connectomics, in electron micrographs. Through various experiments on simulated as well as real data we establish the efficacy of the proposed features in various tasks like cell membrane enhancement, mitochondria segmentation, cell background segmentation, and vesicle cluster detection as compared to various other state-of-the-art techniques.

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.

Echocardiogram view classification using edge filtered scale-invariant motion features

In an 2D echocardiogram exam, an ultrasound probe samples the heart with 2D slices. Changing the orientation and position on the probe changes the slice viewpoint, altering the cardiac anatomy being imaged. The determination of the probe viewpoint forms an essential step in automatic cardiac echo image analysis. In this paper we present a system for automatic view classification that exploits cues from both cardiac structure and motion in echocardiogram videos. In our framework, each image from the echocardiogram video is represented by a set of novel salient features. We locate these features at scale invariant points in the edge-filtered motion magnitude images and encode them using local spatial, textural and kinetic information. Training in our system involves learning a hierarchical feature dictionary and parameters of a pyramid matching kernel based support vector machine. While testing, each image, classified independently, casts a votes towards parent video classification and the viewpoint with maximum votes wins. Through experiments on a large database of echocardiograms obtained from both diseased and control subjects, we show that our technique consistently outperforms state-of-the-art methods in the popular four-view classification test. We also present results for eight-view classification to demonstrate the scalability of our framework.

Detection of neuron membranes in electron microscopy images using multi-scale context and radon-like features

Automated neural circuit reconstruction through electron microscopy (EM) images is a challenging problem. In this paper, we present a novel method that exploits multi-scale contextual information together with Radon-like features (RLF) to learn a series of discriminative models. The main idea is to build a framework which is capable of extracting information about cell membranes from a large contextual area of an EM image in a computationally efficient way. Toward this goal, we extract RLF that can be computed efficiently from the input image and generate a scale-space representation of the context images that are obtained at the output of each discriminative model in the series. Compared to a single-scale model, the use of a multi-scale representation of the context image gives the subsequent classifiers access to a larger contextual area in an effective way. Our strategy is general and independent of the classifier and has the potential to be used in any context based framework. We demonstrate that our method outperforms the state-of-the-art algorithms in detection of neuron membranes in EM images.

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.

Multi-fiber reconstruction from DW-MRI using a continuous mixture of von Mises-Fisher distributions

In this paper we propose a method for reconstructing the Diffusion Weighted Magnetic Resonance (DW-MR) signal at each lattice point using a novel continuous mixture of von Mises-Fisher distribution functions. Unlike most existing methods, neither does this model assume a fixed functional form for the MR signal attenuation (e.g. 2nd or 4th order tensor) nor does it arbitrarily fix important mixture parameters like the number of components. We show that this continuous mixture has a closed form expression and leads to a linear system which can be easily solved. Through extensive experimentation with synthetic data we show that this technique outperforms various other state-of-the-art techniques in resolving fiber crossings. Finally, we demonstrate the effectiveness of this method using real DW-MRI data from rat brain and optic chiasm.

Non-Lambertian Reflectance Modeling and Shape Recovery of Faces Using Tensor Splines

Modeling illumination effects and pose variations of a face is of fundamental importance in the field of facial image analysis. Most of the conventional techniques that simultaneously address both of these problems work with the Lambertian assumption and thus fall short of accurately capturing the complex intensity variation that the facial images exhibit or recovering their 3D shape in the presence of specularities and cast shadows. In this paper, we present a novel Tensor-Spline-based framework for facial image analysis. We show that, using this framework, the facial apparent BRDF field can be accurately estimated while seamlessly accounting for cast shadows and specularities. Further, using local neighborhood information, the same framework can be exploited to recover the 3D shape of the face (to handle pose variation). We quantitatively validate the accuracy of the Tensor Spline model using a more general model based on the mixture of single-lobed spherical functions. We demonstrate the effectiveness of our technique by presenting extensive experimental results for face relighting, 3D shape recovery, and face recognition using the Extended Yale B and CMU PIE benchmark data sets.

Morphable Reflectance Fields for enhancing face recognition

In this paper, we present a novel framework to address the confounding effects of illumination variation in face recognition. By augmenting the gallery set with realistically relit images, we enhance recognition performance in a classifier-independent way. We describe a novel method for single-image relighting, Morphable Reflectance Fields (MoRF), which does not require manual intervention and provides relighting superior to that of existing automatic methods. We test our framework through face recognition experiments using various state-of-the-art classifiers and popular benchmark datasets: CMU PIE, Multi-PIE, and MERL Dome. We demonstrate that our MoRF relighting and gallery augmentation framework achieves improvements in terms of both rank-1 recognition rates and ROC curves. We also compare our model with other automatic relighting methods to confirm its advantage. Finally, we show that the recognition rates achieved using our framework exceed those of state-of-the-art recognizers on the aforementioned databases.

Cardiac disease detection from echocardiogram using edge filtered scale-invariant motion features

Echocardiography provides important morphological and functional details of the heart which can be used for the diagnosis of various cardiac diseases. Most of the existing automatic cardiac disease recognition systems that use echocardiograms are either based on unreliable anatomical region detection (e.g. left ventricle) or require extensive manual labeling of training data which renders such systems unscalable. In this paper we present a novel system for automatic cardiac disease detection from echocardiogram videos which overcomes these limitations and exploits cues from both cardiac structure and motion. In our framework, diseases are modeled using a configuration of novel salient features which are located at the scale-invariant points in the edge filtered motion magnitude images and are encoded using local spatial, textural and motion information. To demonstrate the effectiveness of this technique, we present experimental results for automatic cardiac Hypokinesia detection and show that our method outperforms the existing state-of-the-art method for this task.