Luca Bertelli

Kernelized structural SVM learning for supervised object segmentation

Object segmentation needs to be driven by top-down knowledge to produce semantically meaningful results. In this paper, we propose a supervised segmentation approach that tightly integrates object-level top down information with low-level image cues. The information from the two levels is fused under a kernelized structural SVM learning framework. We defined a novel nonlinear kernel for comparing two image-segmentation masks. This kernel combines four different kernels: the object similarity kernel, the object shape kernel, the per-image color distribution kernel, and the global color distribution kernel. Our experiments show that the structured SVM algorithm finds bad segmentations of the training examples given the current scoring function and punishes these bad segmentations to lower scores than the example (good) segmentations. The result is a segmentation algorithm that not only knows what good segmentations are, but also learns potential segmentation mistakes and tries to avoid them. Our proposed approach can obtain comparable performance to other state-of-the-art top-down driven segmentation approaches yet is flexible enough to be applied to widely different domains.

A Variational Framework for Multiregion Pairwise-Similarity-Based Image Segmentation

Variational cost functions that are based on pairwise similarity between pixels can be minimized within level set framework resulting in a binary image segmentation. In this paper we extend such cost functions and address multi-region image segmentation problem by employing a multi-phase level set framework. For multi-modal images cost functions become more complicated and relatively difficult to minimize. We extend our previous work, proposed for background/foreground separation, to the segmentation of images in more than two regions. We also demonstrate an efficient implementation of the curve evolution, which reduces the computational time significantly. Finally, we validate the proposed method on the Berkeley segmentation data set by comparing its performance with other segmentation techniques.

Probabilistic occlusion boundary detection on spatio-temporal lattices

In this paper, we present an algorithm for occlusion boundary detection. The main contribution is a probabilistic detection framework defined on spatio-temporal lattices, which enables joint analysis of image frames. For this purpose, we introduce two complementary cost functions for creating the spatio-temporal lattice and for performing global inference of the occlusion boundaries, respectively. In addition, a novel combination of low-level occlusion features is discriminatively learnt in the detection framework. Simulations on the CMU Motion Dataset provide ample evidence that proposed algorithm outperforms the leading existing methods.

A Nonconservative Flow Field for Robust Variational Image Segmentation

We introduce a robust image segmentation method based on a variational formulation using edge flow vectors. We demonstrate the nonconservative nature of this flow field, a feature that helps in a better segmentation of objects with concavities. A multiscale version of this method is developed and is shown to improve the localization of the object boundaries. We compare and contrast the proposed method with well known state-of-the-art methods. Detailed experimental results are provided on both synthetic and natural images that demonstrate that the proposed approach is quite competitive.

On the Length and Area Regularization for Multiphase Level Set Segmentation

In this paper we introduce novel regularization techniques for level set segmentation that target specifically the problem of multiphase segmentation. When the multiphase model is used to obtain a partitioning of the image in more than two regions, a new set of issues arise with respect to the single phase case in terms of regularization strategies. For example, if smoothing or shrinking each contour individually could be a good model in the single phase case, this is not necessarily true in the multiphase scenario.In this paper, we address these issues designing enhanced length and area regularization terms, whose minimization yields evolution equations in which each level set function involved in the multiphase segmentation can “sense” the presence of the other level set functions and evolve accordingly. In other words, the coupling of the level set function, which before was limited to the data term (i.e. the proper segmentation driving force), is extended in a mathematically principled way to the regularization terms as well. The resulting regularization technique is more suitable to eliminate spurious regions and other kind of artifacts. An extensive experimental evaluation supports the model we introduce in this paper, showing improved segmentation performance with respect to traditional regularization techniques.

Robust depth estimation for efficient 3D face reconstruction

This paper proposes a learning based framework for efficient 3D face reconstruction. We transfer the 3D reconstruction into a statistical learning problem of finding appropriate mapping between texture and depth subspaces. Instead of using grayscales to directly estimate the depth, we use local binary pattern (LBP) to further encode the face texture, providing robustness for depth estimation under different illumination conditions. Then the high dimension learning problem between face subspaces is tackled by the kernel partial least squares (PLS) regression. The experimental results show that the proposed method can reconstruct 3D face from single frontal image efficiently and robustly.

Edge Preserving Filters using Geodesic Distances on Weighted Orthogonal Domains

We introduce a framework for image enhancement, which smooths images while preserving edge information. Domain (spatial) and range (feature) information are combined in one single measure in a principled way. This measure turns out to be the geodesic distance between pixels, calculated on weighted orthogonal domains. The weight function is computed to capture the underlying structure of the image manifold, but allowing at the same time to efficiently solve, using the Fast Marching algorithm on orthogonal domains, the eikonal equation to obtain the geodesic distances. We show promising results in edge-preserving denoising of gray scale, color and texture images.

Fast and Adaptive Pairwise Similarities for Graph Cuts-based Image Segmentation

We introduce the use of geodesic distances and geodesic radius for calculating pairwise similarities needed in various graph cuts based methods. By using geodesics on an edge strength function we are able to calculate similarities between pixels in a more natural way. Our technique improves the speed and reliability of calculating similarities and leads to reasonably good image segmentation results. Our algorithm takes an edge strength function as its input and its speed is independent of the feature dimension or the distance measure used.

Drums, curve descriptors and affine invariant region matching

In this paper we present a new physically motivated curve/region descriptor based on the solution of Helmholtzs equation. The descriptor we propose satisfies the six principles set by MPEG-7: it has a good retrieval accuracy, it is compact, it can be applied in general contests, it has a reasonable computational complexity, it is rotation and scale invariant and provides an hierarchical representation of the curve from coarse to fine. In addition to these properties, the descriptor can be generalized in order to take into account also the intensity content of the image region defined by the curve. The construction of the descriptor can be coupled with a preprocessing step that enables us to describe a curve in an affine invariant fashion. The performance of our approach has been tested in the contest of affine invariant curve and region matching, both within a controlled experimental setup and also using real images. The experiments show that the proposed approach compares favorably to the state of the art curve/region descriptors.

Redundancy in All Pairs Fast Marching Method

In this paper, we analyze the redundancy in calculating all pairs of geodesic distances on a rectangular grid. Fast marching method is an efficient way to estimate the geodesic distances from a point. But when calculated for all the points on the grid, this introduces certain redundancy. Our analysis shows that over 90% of the distances are actually recalculated. We propose a novel solution which exploits this redundancy to reduce the number of distances evaluated using the fast marching method and enforces the symmetry of the distance matrix. Experimental results show the improved accuracy obtained with our implementation.