Proceedings. IEEE Computer Society Conference on Computer Vision and Pattern Recognition最新文献

Label fusion strategies are used in multi-atlas image segmentation approaches to compute a consensus segmentation of an image, given a set of candidate segmentations produced by registering the image to a set of atlases [19, 11, 8]. Effective label fusion strategies, such as local similarity-weighted voting [1, 13] substantially reduce segmentation errors compared to single-atlas segmentation. This paper extends the label fusion idea to the problem of finding correspondences across a set of images. Instead of computing a consensus segmentation, weighted voting is used to estimate a consensus coordinate map between a target image and a reference space. Two variants of the problem are considered: (1) where correspondences between a set of atlases are known and are propagated to the target image; (2) where correspondences are estimated across a set of images without prior knowledge. Evaluation in synthetic data shows that correspondences recovered by fusion methods are more accurate than those based on registration to a population template. In a 2D example in real MRI data, fusion methods result in more consistent mappings between manual segmentations of the hippocampus.

We recast the Cosegmentation problem using Random Walker (RW) segmentation as the core segmentation algorithm, rather than the traditional MRF approach adopted in the literature so far. Our formulation is similar to previous approaches in the sense that it also permits Cosegmentation constraints (which impose consistency between the extracted objects from ≥ 2 images) using a nonparametric model. However, several previous nonparametric cosegmentation methods have the serious limitation that they require adding one auxiliary node (or variable) for every pair of pixels that are similar (which effectively limits such methods to describing only those objects that have high entropy appearance models). In contrast, our proposed model completely eliminates this restrictive dependence -the resulting improvements are quite significant. Our model further allows an optimization scheme exploiting quasiconvexity for model-based segmentation with no dependence on the scale of the segmented foreground. Finally, we show that the optimization can be expressed in terms of linear algebra operations on sparse matrices which are easily mapped to GPU architecture. We provide a highly specialized CUDA library for Cosegmentation exploiting this special structure, and report experimental results showing these advantages.

Boosting is a well known machine learning technique used to improve the performance of weak learners and has been successfully applied to computer vision, medical image analysis, computational biology and other fields. A critical step in boosting algorithms involves update of the data sample distribution, however, most existing boosting algorithms use updating mechanisms that lead to overfitting and instabilities during evolution of the distribution which in turn results in classification inaccuracies. Regularized boosting has been proposed in literature as a means to overcome these difficulties. In this paper, we propose a novel total Bregman divergence (tBD) regularized LPBoost, termed tBRLPBoost. tBD is a recently proposed divergence in literature, which is statistically robust and we prove that tBRLPBoost requires a constant number of iterations to learn a strong classifier and hence is computationally more efficient compared to other regularized Boosting algorithms. Also, unlike other boosting methods that are only effective on a handful of datasets, tBRLPBoost works well on a variety of datasets. We present results of testing our algorithm on many public domain databases and comparisons to several other state-of-the-art methods. Numerical results show that the proposed algorithm has much improved performance in efficiency and accuracy over other methods.

Analysis of gene expression patterns in brain images obtained from high-throughput in situ hybridization requires accurate and consistent annotations of anatomical regions/subregions. Such annotations are obtained by mapping an anatomical atlas onto the gene expression images through intensity- and/or landmark-based registration methods or deformable model-based segmentation methods. Due to the complex appearance of the gene expression images, these approaches require a pre-processing step to determine landmark correspondences in order to incorporate landmark-based geometric constraints. In this paper, we propose a novel method for landmark-constrained, intensity-based registration without determining landmark correspondences a priori. The proposed method performs dense image registration and identifies the landmark correspondences, simultaneously, using a single higher-order Markov Random Field model. In addition, a machine learning technique is used to improve the discriminating properties of local descriptors for landmark matching by projecting them in a Hamming space of lower dimension. We qualitatively show that our method achieves promising results and also compares well, quantitatively, with the expert's annotations, outperforming previous methods.

In this paper, we propose a novel method to reduce the magnitude of 4D CT artifacts by stitching two images with a data-driven regularization constrain, which helps preserve the local anatomy structures. Our method first computes an interface seam for the stitching in the overlapping region of the first image, which passes through the "smoothest" region, to reduce the structure complexity along the stitching interface. Then, we compute the displacements of the seam by matching the corresponding interface seam in the second image. We use sparse 3D features as the structure cues to guide the seam matching, in which a regularization term is incorporated to keep the structure consistency. The energy function is minimized by solving a multiple-label problem in Markov Random Fields with an anatomical structure preserving regularization term. The displacements are propagated to the rest of second image and the two image are stitched along the interface seams based on the computed displacement field. The method was tested on both simulated data and clinical 4D CT images. The experiments on simulated data demonstrated that the proposed method was able to reduce the landmark distance error on average from 2.9 mm to 1.3 mm, outperforming the registration-based method by about 55%. For clinical 4D CT image data, the image quality was evaluated by three medical experts, and all identified much fewer artifacts from the resulting images by our method than from those by the compared method.

We argue that to make robust computer vision algorithms for face analysis and recognition, these should be based on configural and shape features. In this model, the most important task to be solved by computer vision researchers is that of accurate detection of facial features, rather than recognition. We base our arguments on recent results in cognitive science and neuroscience. In particular, we show that different facial expressions of emotion have diverse uses in human behavior/cognition and that a facial expression may be associated to multiple emotional categories. These two results are in contradiction with the continuous models in cognitive science, the limbic assumption in neuroscience and the multidimensional approaches typically employed in computer vision. Thus, we propose an alternative hybrid continuous-categorical approach to the perception of facial expressions and show that configural and shape features are most important for the recognition of emotional constructs by humans. We illustrate how these image cues can be successfully exploited by computer vision algorithms. Throughout the paper, we discuss the implications of these results in applications in face recognition and human-computer interaction.

Our primary interest is in generalizing the problem of Cosegmentation to a large group of images, that is, concurrent segmentation of common foreground region(s) from multiple images. We further wish for our algorithm to offer scale invariance (foregrounds may have arbitrary sizes in different images) and the running time to increase (no more than) near linearly in the number of images in the set. What makes this setting particularly challenging is that even if we ignore the scale invariance desiderata, the Cosegmentation problem, as formalized in many recent papers (except [1]), is already hard to solve optimally in the two image case. A straightforward extension of such models to multiple images leads to loose relaxations; and unless we impose a distributional assumption on the appearance model, existing mechanisms for image-pair-wise measurement of foreground appearance variations lead to significantly large problem sizes (even for moderate number of images). This paper presents a surprisingly easy to implement algorithm which performs well, and satisfies all requirements listed above (scale invariance, low computational requirements, and viability for the multiple image setting). We present qualitative and technical analysis of the properties of this framework.

We present a hierarchical principle for object recognition and its application to automatically classify developmental stages of C. elegans animals from a population of mixed stages. The object recognition machine consists of four hierarchical layers, each composed of units upon which evaluation functions output a label score, followed by a grouping mechanism that resolves ambiguities in the score by imposing local consistency constraints. Each layer then outputs groups of units, from which the units of the next layer are derived. Using this hierarchical principle, the machine builds up successively more sophisticated representations of the objects to be classified. The algorithm segments large and small objects, decomposes objects into parts, extracts features from these parts, and classifies them by SVM. We are using this system to analyze phenotypic data from C. elegans high-throughput genetic screens, and our system overcomes a previous bottleneck in image analysis by achieving near real-time scoring of image data. The system is in current use in a functioning C. elegans laboratory and has processed over two hundred thousand images for lab users.

Level set method based segmentation provides an efficient tool for topological and geometrical shape handling. Conventional level set surfaces are only C(0) continuous since the level set evolution involves linear interpolation to compute derivatives. Bajaj et al. present a higher order method to evaluate level set surfaces that are C(2) continuous, but are slow due to high computational burden. In this paper, we provide a higher order GPU based solver for fast and efficient segmentation of large volumetric images. We also extend the higher order method to multi-domain segmentation. Our streaming solver is efficient in memory usage.

In this paper, we propose a novel algorithm for computing an atlas from a collection of images. In the literature, atlases have almost always been computed as some types of means such as the straightforward Euclidean means or the more general Karcher means on Riemannian manifolds. In the context of images, the paper's main contribution is a geometric framework for computing image atlases through a two-step process: the localization of mean and the realization of it as an image. In the localization step, a few nearest neighbors of the mean among the input images are determined, and the realization step then proceeds to reconstruct the atlas image using these neighbors. Decoupling the localization step from the realization step provides the flexibility that allows us to formulate a general algorithm for computing image atlas. More specifically, we assume the input images belong to some smooth manifold M modulo image rotations. We use a graph structure to represent the manifold, and for the localization step, we formulate a convex optimization problem in ℝ(k) (k the number of input images) to determine the crucial neighbors that are used in the realization step to form the atlas image. The algorithm is both unbiased and rotation-invariant. We have evaluated the algorithm using synthetic and real images. In particular, experimental results demonstrate that the atlases computed using the proposed algorithm preserve important image features and generally enjoy better image quality in comparison with atlases computed using existing methods.