Francesca Odone

Histogram intersection kernel for image classification

In this paper we address the problem of classifying images, by exploiting global features that describe color and illumination properties, and by using the statistical learning paradigm. The contribution of this paper is twofold. First, we show that histogram intersection has the required mathematical properties to be used as a kernel function for support vector machines (SVMs). Second, we give two examples of how a SVM, equipped with such a kernel, can achieve very promising results on image classification based on color information.

Building kernels from binary strings for image matching

In the statistical learning framework, the use of appropriate kernels may be the key for substantial improvement in solving a given problem. In essence, a kernel is a similarity measure between input points satisfying some mathematical requirements and possibly capturing the domain knowledge. We focus on kernels for images: we represent the image information content with binary strings and discuss various bitwise manipulations obtained using logical operators and convolution with nonbinary stencils. In the theoretical contribution of our work, we show that histogram intersection is a Mercers kernel and we determine the modifications under which a similarity measure based on the notion of Hausdorff distance is also a Mercers kernel. In both cases, we determine explicitly the mapping from input to feature space. The presented experimental results support the relevance of our analysis for developing effective trainable systems.

SVD-matching using SIFT features

The paper tackles the problem of feature points matching between pair of images of the same scene. This is a key problem in computer vision. The method we discuss here is a version of the SVD-matching proposed by Scott and Longuet-Higgins and later modified by Pilu, that we elaborate in order to cope with large scale variations. To this end we add to the feature detection phase a keypoint descriptor that is robust to large scale and view-point changes. Furthermore, we include this descriptor in the equations of the proximity matrix that is central to the SVD-matching. At the same time we remove from the proximity matrix all the information about the point locations in the image, that is the source of mismatches when the amount of scene variation increases. The main contribution of this work is in showing that this compact and easy algorithm can be used for severe scene variations. We present experimental evidence of the improved performance with respect to the previous versions of the algorithm.

Spectral algorithms for supervised learning

We discuss how a large class of regularization methods, collectively known as spectral regularization and originally designed for solving ill-posed inverse problems, gives rise to regularized learning algorithms. All of these algorithms are consistent kernel methods that can be easily implemented. The intuition behind their derivation is that the same principle allowing for the numerical stabilization of a matrix inversion problem is crucial to avoid overfitting. The various methods have a common derivation but different computational and theoretical properties. We describe examples of such algorithms, analyze their classification performance on several data sets and discuss their applicability to real-world problems.

Using Object Affordances to Improve Object Recognition

The problem of object recognition has not yet been solved in its general form. The most successful approach to it so far relies on object models obtained by training a statistical method on visual features obtained from camera images. The images must necessarily come from huge visual datasets, in order to circumvent all problems related to changing illumination, point of view, etc. We hereby propose to also consider, in an object model, a simple model of how a human being would grasp that object (its affordance). This knowledge is represented as a function mapping visual features of an object to the kinematic features of a hand while grasping it. The function is practically enforced via regression on a human grasping database. After describing the database (which is publicly available) and the proposed method, we experimentally evaluate it, showing that a standard object classifier working on both sets of features (visual and motor) has a significantly better recognition rate than that of a visual-only classifier.

A Sparsity-Enforcing Method for Learning Face Features

In this paper, we propose a new trainable system for selecting face features from over-complete dictionaries of image measurements. The starting point is an iterative thresholding algorithm which provides sparse solutions to linear systems of equations. Although the proposed methodology is quite general and could be applied to various image classification tasks, we focus here on the case study of face and eyes detection. For our initial representation, we adopt rectangular features in order to allow straightforward comparisons with existing techniques. For computational efficiency and memory saving requirements, instead of implementing the full optimization scheme on tenths of thousands of features, we propose a three-stage architecture which consists of finding first intermediate solutions to smaller size optimization problems, then merging the obtained results, and next applying further selection procedures. The devised system requires the solution of a number of independent problems, and, hence, the necessary computations could be implemented in parallel. Experimental results obtained on both benchmark and newly acquired face and eyes images indicate that our method is a serious competitor to other feature selection schemes recently popularized in computer vision for dealing with problems of real-time object detection. A major advantage of the proposed system is that it performs well even with relatively small training sets.

Edges and Corners With Shearlets

Shearlets are a relatively new and very effective multi-scale framework for signal analysis. Contrary to the traditional wavelets, shearlets are capable to efficiently capture the anisotropic information in multivariate problem classes. Therefore, shearlets can be seen as the valid choice for multi-scale analysis and detection of directional sensitive visual features like edges and corners. In this paper, we start by reviewing the main properties of shearlets that are important for edge and corner detection. Then, we study algorithms for multi-scale edge and corner detection based on the shearlet representation. We provide an extensive experimental assessment on benchmark data sets which empirically confirms the potential of shearlets feature detection.

Hausdorff Kernel for 3D Object Acquisition and Detection

Learning one class at a time can be seen as an effective solution to classification problems in which only the positive examples are easily identifiable. A kernel method to accomplish this goal consists of a representation stage - which computes the smallest sphere in feature space enclosingthe positive examples - and a classification stage - which uses the obtained sphere as a decision surface to determine the positivity of new examples. In this paper we describe a kernel well suited to represent, identify, and recognize 3D objects from unconstrained images. The kernel we introduce, based on Hausdorff distance, is tailored to deal with grey-level image matching. The effectiveness of the proposed method is demonstrated on several data sets of faces and objects of artistic relevance, like statues.

Feature selection for high-dimensional data

This paper focuses on feature selection for problems dealing with high-dimensional data. We discuss the benefits of adopting a regularized approach with L1 or L1–L2 penalties in two different applications—microarray data analysis in computational biology and object detection in computer vision. We describe general algorithmic aspects as well as architecture issues specific to the two domains. The very promising results obtained show how the proposed approach can be useful in quite different fields of application.

A Regularized Framework for Feature Selection in Face Detection and Authentication

This paper proposes a general framework for selecting features in the computer vision domain—i.e., learning descriptions from data—where the prior knowledge related to the application is confined in the early stages. The main building block is a regularization algorithm based on a penalty term enforcing sparsity. The overall strategy we propose is also effective for training sets of limited size and reaches competitive performances with respect to the state-of-the-art. To show the versatility of the proposed strategy we apply it to both face detection and authentication, implementing two modules of a monitoring system working in real time in our lab. Aside from the choices of the feature dictionary and the training data, which require prior knowledge on the problem, the proposed method is fully automatic. The very good results obtained in different applications speak for the generality and the robustness of the framework.