Showing papers on "Segmentation-based object categorization published in 2006"

Graph Cuts and Efficient N-D Image Segmentation

Abstract: Combinatorial graph cut algorithms have been successfully applied to a wide range of problems in vision and graphics. This paper focusses on possibly the simplest application of graph-cuts: segmentation of objects in image data. Despite its simplicity, this application epitomizes the best features of combinatorial graph cuts methods in vision: global optima, practical efficiency, numerical robustness, ability to fuse a wide range of visual cues and constraints, unrestricted topological properties of segments, and applicability to N-D problems. Graph cuts based approaches to object extraction have also been shown to have interesting connections with earlier segmentation methods such as snakes, geodesic active contours, and level-sets. The segmentation energies optimized by graph cuts combine boundary regularization with region-based properties in the same fashion as Mumford-Shah style functionals. We present motivation and detailed technical description of the basic combinatorial optimization framework for image segmentation via s/t graph cuts. After the general concept of using binary graph cut algorithms for object segmentation was first proposed and tested in Boykov and Jolly (2001), this idea was widely studied in computer vision and graphics communities. We provide links to a large number of known extensions based on iterative parameter re-estimation and learning, multi-scale or hierarchical approaches, narrow bands, and other techniques for demanding photo, video, and medical applications.

Algorithms for finding global minimizers of image segmentation and denoising models

Abstract: We show how certain nonconvex optimization problems that arise in image processing and computer vision can be restated as convex minimization problems. This allows, in particular, the finding of global minimizers via standard convex minimization schemes.

Using Multiple Segmentations to Discover Objects and their Extent in Image Collections

Abstract: Given a large dataset of images, we seek to automatically determine the visually similar object and scene classes together with their image segmentation. To achieve this we combine two ideas: (i) that a set of segmented objects can be partitioned into visual object classes using topic discovery models from statistical text analysis; and (ii) that visual object classes can be used to assess the accuracy of a segmentation. To tie these ideas together we compute multiple segmentations of each image and then: (i) learn the object classes; and (ii) choose the correct segmentations. We demonstrate that such an algorithm succeeds in automatically discovering many familiar objects in a variety of image datasets, including those from Caltech, MSRC and LabelMe.

Optimal Surface Segmentation in Volumetric Images-A Graph-Theoretic Approach

Abstract: Efficient segmentation of globally optimal surfaces representing object boundaries in volumetric data sets is important and challenging in many medical image analysis applications. We have developed an optimal surface detection method capable of simultaneously detecting multiple interacting surfaces, in which the optimality is controlled by the cost functions designed for individual surfaces and by several geometric constraints defining the surface smoothness and interrelations. The method solves the surface segmentation problem by transforming it into computing a minimum s{\hbox{-}} t cut in a derived arc-weighted directed graph. The proposed algorithm has a low-order polynomial time complexity and is computationally efficient. It has been extensively validated on more than 300 computer-synthetic volumetric images, 72 CT-scanned data sets of different-sized plexiglas tubes, and tens of medical images spanning various imaging modalities. In all cases, the approach yielded highly accurate results. Our approach can be readily extended to higher-dimensional image segmentation.

Medical Image Segmentation Using K-Means Clustering and Improved Watershed Algorithm

Abstract: We propose a methodology that incorporates k-means and improved watershed segmentation algorithm for medical image segmentation. The use of the conventional watershed algorithm for medical image analysis is widespread because of its advantages, such as always being able to produce a complete division of the image. However, its drawbacks include over-segmentation and sensitivity to false edges. We address the drawbacks of the conventional watershed algorithm when it is applied to medical images by using k-means clustering to produce a primary segmentation of the image before we apply our improved watershed segmentation algorithm to it. The k-means clustering is an unsupervised learning algorithm, while the improved watershed segmentation algorithm makes use of automated thresholding on the gradient magnitude map and post-segmentation merging on the initial partitions to reduce the number of false edges and over-segmentation. By comparing the number of partitions in the segmentation maps of 50 images, we showed that our proposed methodology produced segmentation maps which have 92% fewer partitions than the segmentation maps produced by the conventional watershed algorithm

Isoperimetric graph partitioning for image segmentation

Abstract: Spectral graph partitioning provides a powerful approach to image segmentation. We introduce an alternate idea that finds partitions with a small isoperimetric constant, requiring solution to a linear system rather than an eigenvector problem. This approach produces the high quality segmentations of spectral methods, but with improved speed and stability.

Parameter selection for region‐growing image segmentation algorithms using spatial autocorrelation

Abstract: Region-growing segmentation algorithms are useful for remote sensing image segmentation. These algorithms need the user to supply control parameters, which control the quality of the resulting segmentation. An objective function is proposed for selecting suitable parameters for region-growing algorithms to ensure best quality results. It considers that a segmentation has two desirable properties: each of the resulting segments should be internally homogeneous and should be distinguishable from its neighbourhood. The measure combines a spatial autocorrelation indicator that detects separability between regions and a variance indicator that expresses the overall homogeneity of the regions.

Bilayer Segmentation of Live Video

Abstract: This paper presents an algorithm capable of real-time separation of foreground from background in monocular video sequences. Automatic segmentation of layers from colour/contrast or from motion alone is known to be error-prone. Here motion, colour and contrast cues are probabilistically fused together with spatial and temporal priors to infer layers accurately and efficiently. Central to our algorithm is the fact that pixel velocities are not needed, thus removing the need for optical flow estimation, with its tendency to error and computational expense. Instead, an efficient motion vs nonmotion classifier is trained to operate directly and jointly on intensity-change and contrast. Its output is then fused with colour information. The prior on segmentation is represented by a second order, temporal, Hidden Markov Model, together with a spatial MRF favouring coherence except where contrast is high. Finally, accurate layer segmentation and explicit occlusion detection are efficiently achieved by binary graph cut. The segmentation accuracy of the proposed algorithm is quantitatively evaluated with respect to existing groundtruth data and found to be comparable to the accuracy of a state of the art stereo segmentation algorithm. Foreground/ background segmentation is demonstrated in the application of live background substitution and shown to generate convincingly good quality composite video.

Iris segmentation methodology for non-cooperative recognition

Abstract: An overview of the iris image segmentation methodologies for biometric purposes is presented. The main focus is on the analysis of the ability of segmentation algorithms to process images with heterogeneous characteristics, simulating the dynamics of a non-cooperative environment. The accuracy of the four selected methodologies on the UBIRIS database is tested and, having concluded about their weak robustness when dealing with non-optimal images regarding focus, reflections, brightness or eyelid obstruction, the authors introduce a new and more robust iris image segmentation methodology. This new methodology could contribute to the aim of non-cooperative biometric iris recognition, where the ability to process this type of image is required.

Multispectral Image Analysis Using the Object-Oriented Paradigm

Abstract: Introduction Background Objects and Human Interpretation Process Object-Oriented Paradigm Organization of the Book Multispectral Remote Sensing Spatial Resolution Spectral Resolution Radiometric Resolution Temporal Resolution Multispectral Image Analysis Why an Object-Oriented Approach? Object Properties Advantages of Object-Oriented Approach Creating Objects Image Segmentation Techniques Creating and Classifying Objects at Multiple Scales Object Classification Creating Multiple Levels Creating Class Hierarchy and Classifying Objects Final Classification Using Object Relationships between Levels Object-Based Image Analysis Image Analysis Techniques Supervised Classification Using Multispectral Information Exploring the Spatial Dimension Using Contextual Information Taking Advantage of Morphology Parameters Taking Advantage of Texture Adding Temporal Dimension Advanced Object Image Analysis Techniques to Control Image Segmentation within eCognition Techniques to Control Image Segmentation within eCognition Multi-Scale Approach for Image Analysis Objects vs. Spatial Resolution Exploring the Parent-Child Object Relationships Using Semantic Relationships Taking Advantage of Ancillary Data Accuracy Assessment Sample Selection Sampling Techniques Ground Truth Collection Accuracy Assessment Measures References Index

Minimum Cut Model for Spoken Lecture Segmentation

Abstract: We consider the task of unsupervised lecture segmentation. We formalize segmentation as a graph-partitioning task that optimizes the normalized cut criterion. Our approach moves beyond localized comparisons and takes into account long-range cohesion dependencies. Our results demonstrate that global analysis improves the segmentation accuracy and is robust in the presence of speech recognition errors.

Integrated active contours for texture segmentation

Abstract: We address the issue of textured image segmentation in the context of the Gabor feature space of images. Gabor filters tuned to a set of orientations, scales and frequencies are applied to the images to create the Gabor feature space. A two-dimensional Riemannian manifold of local features is extracted via the Beltrami framework. The metric of this surface provides a good indicator of texture changes and is used, therefore, in a Beltrami-based diffusion mechanism and in a geodesic active contours algorithm for texture segmentation. The performance of the proposed algorithm is compared with that of the edgeless active contours algorithm applied for texture segmentation. Moreover, an integrated approach, extending the geodesic and edgeless active contours approaches to texture segmentation, is presented. We show that combining boundary and region information yields more robust and accurate texture segmentation results.

Object-of-interest image segmentation based on human attention and semantic region clustering

Abstract: We propose a novel object-of-interest (OOI) segmentation algorithm for various images that is based on human attention and semantic region clustering. As object-based image segmentation is beyond current computer vision techniques, the proposed method segments an image into regions, which are then merged as a semantic object. At the same time, an attention window (AW) is created based on the saliency map and saliency points from an image. Within the AW, a support vector machine is used to select the salient regions, which are then clustered into the OOI using the proposed region merging. Unlike other algorithms, the proposed method allows multiple OOIs to be segmented according to the saliency map.

Learning and incorporating top-down cues in image segmentation

Abstract: Bottom-up approaches, which rely mainly on continuity principles, are often insufficient to form accurate segments in natural images. In order to improve performance, recent methods have begun to incorporate top-down cues, or object information, into segmentation. In this paper, we propose an approach to utilizing category-based information in segmentation, through a formulation as an image labelling problem. Our approach exploits bottom-up image cues to create an over-segmented representation of an image. The segments are then merged by assigning labels that correspond to the object category. The model is trained on a database of images, and is designed to be modular: it learns a number of image contexts, which simplify training and extend the range of object classes and image database size that the system can handle. The learning method estimates model parameters by maximizing a lower bound of the data likelihood. We examine performance on three real-world image databases, and compare our system to a standard classifier and other conditional random field approaches, as well as a bottom-up segmentation method.

Learning and Incorporating Top-Down Cues in Image Segmentation

Abstract: Bottom-up approaches, which rely mainly on continuity principles, are often insufficient to form accurate segments in natural images. In order to improve performance, recent methods have begun to incorporate top-down cues, or object information, into segmentation. In this paper, we propose an approach to utilizing category-based information in segmentation, through a formulation as an image labelling problem. Our approach exploits bottom-up image cues to create an over-segmented representation of an image. The segments are then merged by assigning labels that correspond to the object category. The model is trained on a database of images, and is designed to be modular: it learns a number of image contexts, which simplify training and extend the range of object classes and image database size that the system can handle. The learning method estimates model parameters by maximizing a lower bound of the data likelihood. We examine performance on three real-world image databases, and compare our system to a standard classifier and other conditional random field approaches, as well as a bottom-up segmentation method.

A dynamic conditional random field model for foreground and shadow segmentation

Abstract: This paper proposes a dynamic conditional random field (DCRF) model for foreground object and moving shadow segmentation in indoor video scenes. Given an image sequence, temporal dependencies of consecutive segmentation fields and spatial dependencies within each segmentation field are unified by a dynamic probabilistic framework based on the conditional random field (CRF). An efficient approximate filtering algorithm is derived for the DCRF model to recursively estimate the segmentation field from the history of observed images. The foreground and shadow segmentation method integrates both intensity and gradient features. Moreover, models of background, shadow, and gradient information are updated adaptively for nonstationary background processes. Experimental results show that the proposed approach can accurately detect moving objects and their cast shadows even in monocular grayscale video sequences.

Automatic Segmentation of the Left Ventricle in Cardiac MR and CT Images

Abstract: This paper describes a segmentation technique to automatically extract the myocardium in 4D cardiac MR and CT datasets. The segmentation algorithm is a two step process. The global localization step roughly localizes the left ventricle using techniques such as maximum discrimination, thresholding and connected component analysis. The local deformations step combines EM-based region segmentation and Dijkstra active contours using graph cuts, spline fitting, or point pattern matching. The technique has been tested on a large number of patients and both quantitative and qualitative results are presented.

Supervised learning-based cell image segmentation for P53 immunohistochemistry

Abstract: In this paper, we present two new algorithms for cell image segmentation. First, we demonstrate that pixel classification-based color image segmentation in color space is equivalent to performing segmentation on grayscale image through thresholding. Based on this result, we develop a supervised learning-based two-step procedure for color cell image segmentation, where color image is first mapped to grayscale via a transform learned through supervised learning, thresholding is then performed on the grayscale image to segment objects out of background. Experimental results show that the supervised learning-based two-step procedure achieved a boundary disagreement (mean absolute distance) of 0.85 while the disagreement produced by the pixel classification-based color image segmentation method is 3.59. Second, we develop a new marker detection algorithm for watershed-based separation of overlapping or touching cells. The merit of the new algorithm is that it employs both photometric and shape information and combines the two naturally in the framework of pattern classification to provide more reliable markers. Extensive experiments show that the new marker detection algorithm achieved 0.4% and 0.2% over-segmentation and under-segmentation, respectively, while reconstruction-based method produced 4.4% and 1.1% over-segmentation and under-segmentation, respectively.

Unsupervised performance evaluation of image segmentation

Abstract: We present in this paper a study of unsupervised evaluation criteria that enable the quantification of the quality of an image segmentation result. These evaluation criteria compute some statistics for each region or class in a segmentation result. Such an evaluation criterion can be useful for different applications: the comparison of segmentation results, the automatic choice of the best fitted parameters of a segmentation method for a given image, or the definition of new segmentation methods by optimization. We first present the state of art of unsupervised evaluation, and then, we compare six unsupervised evaluation criteria. For this comparative study, we use a database composed of 8400 synthetic gray-level images segmented in four different ways. Vinet's measure (correct classification rate) is used as an objective criterion to compare the behavior of the different criteria. Finally, we present the experimental results on the segmentation evaluation of a few gray-level natural images.

Current Methods in the Automatic Tissue Segmentation of 3D Magnetic Resonance Brain Images

Abstract: Accurate segmentation of magnetic resonance (MR) images of the brain is of interest in the study of many brain disorders. In this paper, we provide a review of some of the current approaches in the tissue segmentation of MR brain images. We broadly divided current MR brain image segmentation algorithms into three categories: classification- based, region-based, and contour-based, and discuss the advantages and disadvantages of these approaches. We also briefly review our recent work in this area. We show that by incorporating two key ideas into the conventional fuzzy c- means clustering algorithm, we are able to take into account the local spatial context and compensate for the intensity nonuniformity (INU) artifact during the clustering process. We conclude this review by pointing to some possible future directions in this area.

Image and Texture Segmentation Using Local Spectral Histograms

Abstract: We present a method for segmenting images consisting of texture and nontexture regions based on local spectral histograms. Defined as a vector consisting of marginal distributions of chosen filter responses, local spectral histograms provide a feature statistic for both types of regions. Using local spectral histograms of homogeneous regions, we decompose the segmentation process into three stages. The first is the initial classification stage, where probability models for homogeneous texture and nontexture regions are derived and an initial segmentation result is obtained by classifying local windows. In the second stage, we give an algorithm that iteratively updates the segmentation using the derived probability models. The third is the boundary localization stage, where region boundaries are localized by building refined probability models that are sensitive to spatial patterns in segmented regions. We present segmentation results on texture as well as nontexture images. Our comparison with other methods shows that the proposed method produces more accurate segmentation results

Shape Guided Object Segmentation

Abstract: We construct a Bayesian model that integrates topdown with bottom-up criteria, capitalizing on their relative merits to obtain figure-ground segmentation that is shape-specific and texture invariant. A hierarchy of bottom-up segments in multiple scales is used to construct a prior on all possible figure-ground segmentations of the image. This prior is used by our top-down part to query and detect object parts in the image using stored shape templates. The detected parts are integrated to produce a global approximation for the object’s shape, which is then used by an inference algorithm to produce the final segmentation. Experiments with a large sample of horse and runner images demonstrate strong figure-ground segmentation despite high object and background variability. The segmentations are robust to changes in appearance since the matching component depends on shape criteria alone. The model may be useful for additional visual tasks requiring labeling, such as the segmentation of multiple scene objects.

Distance measures for image segmentation evaluation

Abstract: The task considered in this paper is performance evaluation of region segmentation lgorithms in the ground-truth-based paradigm. Given a machine segmentation and a ground-truth segmentation, performance measures are needed. We propose to consider the image segmentation problem as one of data clustering and, as a consequence, to use measures for comparing clusterings developed in statistics and machine learning. By doing so, we obtain a variety of performance measures which have not been used before in image processing. In particular, some of these measures have the highly desired property of being a metric. Experimental results are reported on both synthetic and real data to validate the measures and compare them with others.

Graph Partitioning by Spectral Rounding: Applications in Image Segmentation and Clustering

Abstract: We introduce a family of spectral partitioning methods. Edge separators of a graph are produced by iteratively reweighting the edges until the graph disconnects into the prescribed number of components. At each iteration a small number of eigenvectors with small eigenvalue are computed and used to determine the reweighting. In this way spectral rounding directly produces discrete solutions where as current spectral algorithms must map the continuous eigenvectors to discrete solutions by employing a heuristic geometric separator (e.g. k-means). We show that spectral rounding compares favorably to current spectral approximations on the Normalized Cut criterion (NCut). Results are given for natural image segmentation, medical image segmentation, and clustering. A practical version is shown to converge.