Proceedings. IEEE International Conference on Computer Vision最新文献

Automated electron microscopy (EM) image analysis techniques can be tremendously helpful for connectomics research. In this paper, we extend our previous work [1] and propose a fully automatic method to utilize inter-section information for intra-section neuron segmentation of EM image stacks. A watershed merge forest is built via the watershed transform with each tree representing the region merging hierarchy of one 2D section in the stack. A section classifier is learned to identify the most likely region correspondence between adjacent sections. The inter-section information from such correspondence is incorporated to update the potentials of tree nodes. We resolve the merge forest using these potentials together with consistency constraints to acquire the final segmentation of the whole stack. We demonstrate that our method leads to notable segmentation accuracy improvement by experimenting with two types of EM image data sets.

Automatic facial Action Unit (AU) detection from video is a long-standing problem in facial expression analysis. AU detection is typically posed as a classification problem between frames or segments of positive examples and negative ones, where existing work emphasizes the use of different features or classifiers. In this paper, we propose a method called Cascade of Tasks (CoT) that combines the use of different tasks (i.e., frame, segment and transition) for AU event detection. We train CoT in a sequential manner embracing diversity, which ensures robustness and generalization to unseen data. In addition to conventional frame-based metrics that evaluate frames independently, we propose a new event-based metric to evaluate detection performance at event-level. We show how the CoT method consistently outperforms state-of-the-art approaches in both frame-based and event-based metrics, across three public datasets that differ in complexity: CK+, FERA and RU-FACS.

Image-based classification of tissue histology, in terms of distinct histopathology (e.g., tumor or necrosis regions), provides a series of indices for tumor composition. Furthermore, aggregation of these indices from each whole slide image (WSI) in a large cohort can provide predictive models of clinical outcome. However, the performance of the existing techniques is hindered as a result of large technical variations (e.g., fixation, staining) and biological heterogeneities (e.g., cell type, cell state) that are always present in a large cohort. We suggest that, compared with human engineered features widely adopted in existing systems, unsupervised feature learning is more tolerant to batch effect (e.g., technical variations associated with sample preparation) and pertinent features can be learned without user intervention. This leads to a novel approach for classification of tissue histology based on unsupervised feature learning and spatial pyramid matching (SPM), which utilize sparse tissue morphometric signatures at various locations and scales. This approach has been evaluated on two distinct datasets consisting of different tumor types collected from The Cancer Genome Atlas (TCGA), and the experimental results indicate that the proposed approach is (i) extensible to different tumor types; (ii) robust in the presence of wide technical variations and biological heterogeneities; and (iii) scalable with varying training sample sizes.

We present an active geodesic contour model in which we constrain the evolving active contour to be a geodesic with respect to a weighted edge-based energy through its entire evolution rather than just at its final state (as in the traditional geodesic active contour models). Since the contour is always a geodesic throughout the evolution, we automatically get local optimality with respect to an edge fitting criterion. This enables us to construct a purely region-based energy minimization model without having to devise arbitrary weights in the combination of our energy function to balance edge-based terms with the region-based terms. We show that this novel approach of combining edge information as the geodesic constraint in optimizing a purely region-based energy yields a new class of active contours which exhibit both local and global behaviors that are naturally responsive to intuitive types of user interaction. We also show the relationship of this new class of globally constrained active contours with traditional minimal path methods, which seek global minimizers of purely edge-based energies without incorporating region-based criteria. Finally, we present some numerical examples to illustrate the benefits of this approach over traditional active contour models.

Alzheimer's disease (AD) is a neurodegenerative disorder characterized by progressive impairment of memory and other cognitive functions, which makes regression analysis a suitable model to study whether neuroimaging measures can help predict memory performance and track the progression of AD. Existing memory performance prediction methods via regression, however, do not take into account either the interconnected structures within imaging data or those among memory scores, which inevitably restricts their predictive capabilities. To bridge this gap, we propose a novel Sparse Multi-tAsk Regression and feaTure selection (SMART) method to jointly analyze all the imaging and clinical data under a single regression framework and with shared underlying sparse representations. Two convex regularizations are combined and used in the model to enable sparsity as well as facilitate multi-task learning. The effectiveness of the proposed method is demonstrated by both clearly improved prediction performances in all empirical test cases and a compact set of selected RAVLT-relevant MRI predictors that accord with prior studies.

Non-rigid structure from motion (NRSFM) is a difficult, underconstrained problem in computer vision. The standard approach in NRSFM constrains 3D shape deformation using a linear combination of K basis shapes; the solution is then obtained as the low-rank factorization of an input observation matrix. An important but overlooked problem with this approach is that non-linear deformations are often observed; these deformations lead to a weakened low-rank constraint due to the need to use additional basis shapes to linearly model points that move along curves. Here, we demonstrate how the kernel trick can be applied in standard NRSFM. As a result, we model complex, deformable 3D shapes as the outputs of a non-linear mapping whose inputs are points within a low-dimensional shape space. This approach is flexible and can use different kernels to build different non-linear models. Using the kernel trick, our model complements the low-rank constraint by capturing non-linear relationships in the shape coefficients of the linear model. The net effect can be seen as using non-linear dimensionality reduction to further compress the (shape) space of possible solutions.

Graph partitioning active contours (GPAC) is a recently introduced approach that elegantly embeds the graph-based image segmentation problem within a continuous optimization framework. GPAC can be used within parametric snake-based or implicit level set-based active contour continuous paradigms for image partitioning. However, GPAC similar to many other graph-based approaches has quadratic memory requirements which severely limits the scalability of the algorithm to practical problem domains. An N xN image requires O(N(4)) computation and memory to create and store the full graph of pixel inter-relationships even before the start of the contour optimization process. For example, an 1024x1024 grayscale image needs over one terabyte of memory. Approximations using tile/block-based or superpixel-based multiscale grouping of the pixels reduces this complexity by trading off accuracy. This paper describes a new algorithm that implements the exact GPAC algorithm using a constant memory requirement of a few kilobytes, independent of image size.

Many computer vision and image processing tasks require the preservation of local discontinuities, terminations and bifurcations. Denoising with feature preservation is a challenging task and in this paper, we present a novel technique for preserving complex oriented structures such as junctions and corners present in images. This is achieved in a two stage process namely, (1) All image data are pre-processed to extract local orientation information using a steerable Gabor filter bank. The orientation distribution at each lattice point is then represented by a continuous mixture of Gaussians. The continuous mixture representation can be cast as the Laplace transform of the mixing density over the space of positive definite (covariance) matrices. This mixing density is assumed to be a parameterized distribution, namely, a mixture of Wisharts whose Laplace transform is evaluated in a closed form expression called the Rigaut type function, a scalar-valued function of the parameters of the Wishart distribution. Computation of the weights in the mixture Wisharts is formulated as a sparse deconvolution problem. (2) The feature preserving denoising is then achieved via iterative convolution of the given image data with the Rigaut type function. We present experimental results on noisy data, real 2D images and 3D MRI data acquired from plant roots depicting bifurcating roots. Superior performance of our technique is depicted via comparison to the state-of-the-art anisotropic diffusion filter.

We argue that registration should be thought of as a means to an end, and not as a goal by itself. In particular, we consider the problem of predicting the locations of hidden labels of a test image using observable features, given a training set with both the hidden labels and observable features. For example, the hidden labels could be segmentation labels or activation regions in fMRI, while the observable features could be sulcal geometry or MR intensity. We analyze a probabilistic framework for computing an optimal atlas, and the subsequent registration of a new subject using only the observable features to optimize the hidden label alignment to the training set. We compare two approaches for co-registering training images for the atlas construction: the traditional approach of only using observable features and a novel approach of only using hidden labels. We argue that the alternative approach is superior particularly when the relationship between the hidden labels and observable features is complex and unknown. As an application, we consider the task of registering cortical folds to optimize Brodmann area localization. We show that the alignment of the Brodmann areas improves by up to 25% when using the alternative atlas compared with the traditional atlas. To the best of our knowledge, these are the most accurate Brodmann area localization results (achieved via cortical fold registration) reported to date.

We introduce the use of over-complete spherical wavelets for shape analysis of 2D closed surfaces. Bi-orthogonal spherical wavelets have been shown to be powerful tools in the segmentation and shape analysis of 2D closed surfaces, but unfortunately they suffer from aliasing problems and are therefore not invariant under rotations of the underlying surface parameterization. In this paper, we demonstrate the theoretical advantage of over-complete wavelets over bi-orthogonal wavelets and illustrate their utility on both synthetic and real data. In particular, we show that over-complete spherical wavelets allow us to build more stable cortical folding development models, and detect a wider array of regions of folding development in a newborn dataset.