Abstract: This paper has reviewed, with somewhat variable coverage, the nine MR image segmentation techniques itemized in Table II. A wide array of approaches have been discussed; each has its merits and drawbacks. We have also given pointers to other approaches not discussed in depth in this review. The methods reviewed fall roughly into four model groups: c-means, maximum likelihood, neural networks, and k-nearest neighbor rules. Both supervised and unsupervised schemes require human intervention to obtain clinically useful results in MR segmentation. Unsupervised techniques require somewhat less interaction on a per patient/image basis. Maximum likelihood techniques have had some success, but are very susceptible to the choice of training region, which may need to be chosen slice by slice for even one patient. Generally, techniques that must assume an underlying statistical distribution of the data (such as LML and UML) do not appear promising, since tissue regions of interest do not usually obey the distributional tendencies of probability density functions. The most promising supervised techniques reviewed seem to be FF/NN methods that allow hidden layers to be configured as examples are presented to the system. An example of a self-configuring network, FF/CC, was also discussed. The relatively simple k-nearest neighbor rule algorithms (hard and fuzzy) have also shown promise in the supervised category. Unsupervised techniques based upon fuzzy c-means clustering algorithms have also shown great promise in MR image segmentation. Several unsupervised connectionist techniques have recently been experimented with on MR images of the brain and have provided promising initial results. A pixel-intensity-based edge detection algorithm has recently been used to provide promising segmentations of the brain. This is also an unsupervised technique, older versions of which have been susceptible to oversegmenting the image because of the lack of clear boundaries between tissue types or finding uninteresting boundaries between slightly different types of the same tissue. To conclude, we offer some remarks about improving MR segmentation techniques. The better unsupervised techniques are too slow. Improving speed via parallelization and optimization will improve their competitiveness with, e.g., the k-nn rule, which is the fastest technique covered in this review. Another area for development is dynamic cluster validity. Unsupervised methods need better ways to specify and adjust c, the number of tissue classes found by the algorithm. Initialization is a third important area of research. Many of the schemes listed in Table II are sensitive to good initialization, both in terms of the parameters of the design, as well as operator selection of training data.(ABSTRACT TRUNCATED AT 400 WORDS)

Abstract: A method for Bayesian reconstruction which relies on updates of single pixel values, rather than the entire image, at each iteration is presented. The technique is similar to Gauss-Seidel (GS) iteration for the solution of differential equations on finite grids. The computational cost per iteration of the GS approach is found to be approximately equal to that of gradient methods. For continuously valued images, GS is found to have significantly better convergence at modes representing high spatial frequencies. In addition, GS is well suited to segmentation when the image is constrained to be discretely valued. It is shown that Bayesian segmentation using GS iteration produces useful estimates at much lower signal-to-noise ratios than required for continuously valued reconstruction. The convergence properties of gradient ascent and GS for reconstruction from integral projections are analyzed, and simulations of both maximum-likelihood and maximum a posteriori cases are included. >

Abstract: Bivariate and trivariate functions for interpolation from scattered data are derived. They are constructed by explicit minimization of a general smoothness functional, and they include a tension parameter that controls the character of the interpolation function (e.g., for bivariate case the surface can be tuned from a “membrane” to a “thin steel plate”), Tension can be applied also in a chosen direction, for modeling of phenomena with a simple type of anisotropy. The functions have regular derivatives of all orders everywhere. This makes them suitable for analysis of surface geometry and for direct application in models where derivatives are necessary. For processing of large datasets (thousands of data points), which are now common in geosciences, a segmentation algorithm with a flexible size of overlapping neighborhood is presented. Simple examples demonstrating flexibility and accuracy of the functions are presented.

Abstract: This article deals with analysis of the dynamic content of a scene from an image sequence irrespective of the static or dynamic nature of the camera. The tasks involved can be the detection of moving objects in a scene observed by a mobile camera, or the identification of the movements of some relevant components of the scene relatively to the camera. This problem basically requires a motion-based segmentation step. We present a motion-based segmentation method relying on 2-D affine motion models and a statistical regularization approach which ensures stable motion-based partitions. This can be done without the explicit estimation of optic flow fields. Besides these partitions are linked in time. Therefore, the motion interpretation process can be performed on more than two successive frames. The ability to follow a given coherently moving region within an interval of several images of the sequence makes the interpretation process more robust and more comprehensive. Identification of the kinematic components of the scene is induced from an intermediate layer accomplishing a generic qualitative motion labeling. No 3-D measurements are required. Results obtained on several real-image sequences corresponding to complex outdoor situations are reported.

Abstract: This work presents an investigation of the potential of artificial neural networks for classification of registered magnetic resonance and X-ray computer tomography images of the human brain. First, topological and learning parameters are established experimentally. Second, the learning and generalization properties of the neural networks are compared to those of a classical maximum likelihood classifier and the superiority of the neural network approach is demonstrated when small training sets are utilized. Third, the generalization properties of the neural networks are utilized to develop an adaptive learning scheme able to overcome interslice intensity variations typical of MR images. This approach permits the segmentation of image volumes based on training sets selected on a single slice. Finally, the segmentation results obtained both with the artificial neural network and the maximum likelihood classifiers are compared to contours drawn manually. >

Abstract: Certain spans of utterances in a discourse, referred to here as segments, are widely assumed to form coherent units. Further, the segmental structure of discourse has been claimed to constrain and be constrained by many phenomena. However, there is weak consensus on the nature of segments and the criteria for recognizing or generating them. We present quantitative results of a two part study using a corpus of spontaneous, narrative monologues. The first part evaluates the statistical reliability of human segmentation of our corpus, where speaker intention is the segmentation criterion. We then use the subjects' segmentations to evaluate the correlation of discourse segmentation with three linguistic cues (referential noun phrases, cue words, and pauses), using information retrieval metrics.

Abstract: We present an algorithm that integrates multiple region segmentation maps and edge maps. It operates independently of image sources and specific region-segmentation or edge-detection techniques. User-specified weights and the arbitrary mixing of region/edge maps are allowed. The integration algorithm enables multiple edge detection/region segmentation modules to work in parallel as front ends. The solution procedure consists of three steps. A maximum likelihood estimator provides initial solutions to the positions of edge pixels from various inputs. An iterative procedure using only local information (without edge tracing) then minimizes the contour curvature. Finally, regions are merged to guarantee that each region is large and compact. The channel-resolution width controls the spatial scope of the initial estimation and contour smoothing to facilitate multiscale processing. Experimental results are demonstrated using data from different types of sensors and processing techniques. The results show an improvement over individual inputs and a strong resemblance to human-generated segmentation. >

Abstract: The authors propose a method for the 3-D reconstruction of the brain from anisotropic magnetic resonance imaging (MRI) brain data. The method essentially consists in two original algorithms both for segmentation and for interpolation of the MRI data. The segmentation process is performed in three steps. A gray level thresholding of the white and gray matter tissue is performed on the brain MR raw data. A global white matter segmentation is automatically performed with a global 3-D connectivity algorithm which takes into account the anisotropy of the MRI voxel. The gray matter is segmented with a local 3-D connectivity algorithm. Mathematical morphology tools are used to interpolate slices. The whole process gives an isotropic binary representation of both gray and white matter which are available for 3-D surface rendering. The power and practicality of this method have been tested on four brain datasets. The segmentation algorithm favorably compares to a manual one. The interpolation algorithm was compared to the shaped-based method both quantitatively and qualitatively. >

Abstract: Collection and analysis of pavement distress data are receiving attention for their potential to improve the quality of information on pavement condition. We present an approach for the automated classificaton of asphalt pavement distresses recorded on video or photographic film. Based on a model that describes the statistical properties of pavement images, we develop algorithms for image enhancement, segmentation, and distress classification. Image enhancement is based on subtraction of an “average” background: segmentation assigns one of four possible values to pixels based on their likelihood of belonging to the object. The classification approach proceeds in two steps: in the first step, the presence of primitives (building blocks of the various distresses) is identified, and in the second step, classification of images to a distress type (using the results from the first step) takes place. The system addresses the following distress types: longitudinal, transverse, block, alligator cracking, and plai...

Abstract: The performance of the classic split-and-merge segmentation algorithm is severely hampered by its rigid split-and-merge processes, which are insensitive to the image semantics. The author proposes efficient algorithms and data structures to optimize the split-and-merge processes by piecewise least-square approximation of image intensity functions. This optimization aims at the unification of segment finding and edge detection. The optimized split-and-merge algorithm is shown to be adaptive to the image semantics and, hence, improves the segmentation validity of the previous algorithms. This algorithm also appears to work well on noisy sources. Since the optimization is done within the split-and-merge framework, the better segmentation performance is achieved at the same order of time complexity as the previous algorithms. >

Abstract: A multiresolution texture segmentation (MTS) approach to image segmentation that addresses the issues of texture characterization, image resolution, and time to complete the segmentation is presented. The approach generalizes the conventional simulated annealing method to a multiresolution framework and minimizes an energy function that is dependent on the resolution of the size of the texture blocks in an image. A rigorous experimental procedure is also proposed to demonstrate the advantages of the proposed MTS approach on the accuracy of the segmentation, the efficiency of the algorithm, and the use of varying features at different resolution. Semireal images, created by sampling a series of diagnostic ultrasound images of an ovary in vitro, were tested to produce statistical measures on the performance of the approach. The ultrasound images themselves were then segmented to determine if the approach can achieve accurate results for the intended ultrasound application. Experimental results suggest that the MTS approach converges faster and produces better segmentation results than the single-level approach. >

Abstract: Two color-image segmentation methods are described. The first is based on a spherical coordinate transform of original RGB data. The second is based on a mathematically optimal transform, the principal components transform (also known as eigenvector, discrete Karhunen-Loeve, or Hotelling transform). These algorithms are applied to the extraction from skin tumor images of various features such as tumor border, crust, hair scale, shiny areas, and ulcer. The results of this research will be used in the development of a computer vision system that will seve as the visual front-end of a medical expert system to automate visual feature identification for skin tumor evaluation. >

Abstract: The application of fractal random process models and their related scaling parameters as features in the analysis and segmentation of clutter in high-resolution, polarimetric synthetic aperture radar (SAR) imagery is demonstrated. Specifically, the fractal dimension of natural clutter sources, such as grass and trees, is computed and used as a texture feature for a Bayesian classifier. The SAR shadows are segmented in a separate manner using the original backscatter power as a discriminant. The proposed segmentation process yields a three-class segmentation map for the scenes considered in this study (with three clutter types: shadows, trees, and grass). The difficulty of computing texture metrics in high-speckle SAR imagery is addressed. In particular, a two-step preprocessing approach consisting of polarimetric minimum speckle filtering followed by noncoherent spatial averaging is used. The relevance of the resulting segmentation maps to constant-false-alarm-rate (CFAR) radar target detection techniques is discussed. >

Abstract: A quantitative method of skin healing assessment using true color image processing is presented. The method was developed during a clinical trial using healthy volunteers, the goal of which was to study a drug for accelerating healing. Photographic images of the skin were sequentially acquired between day 1 and day 12 after pure painless epidermal wounds. The images were digitized in controlled conditions using a color video camera connected to a computer system. A color threshold based segmentation was developed to provide an operator-independent delineation of the wound. Two healing indexes were built measuring, the wound area and the wound color. The method was implemented in a software system allowing a fully automated determination of the healing indexes. The method provides a new quantitative global assessment of healing kinetics. It is noninvasive and well suited for multicentric clinical trials. >

Abstract: A method for measuring the spatial concentration of specific categories of vessels in a vascular network consisting of vessels of several diameters, lengths, and orientations is demonstrated. It is shown that a combination of the mathematical morphology operation, opening, with a linear rotating structuring element (ROSE) and dual feature thresholding can semi-automatically segment categories of vessels in a vascular network. Capillaries and larger vessels (arterioles and venules) are segmented here in order to assess their spatial concentrations. The ROSE algorithm generates the initial segmentation, and dual feature thresholding provides a means of eliminating the nonedge artifact pixels. The subsequent gray-scale histogram of only the edge pixels yields the correct segmentation threshold value. This image processing strategy is demonstrated on micrographs of vascular casts. By adjusting the structuring element and rotation angles, it could be applied to other network structures where a segmentation by network component categories is advantageous, but where the objects can have any orientation. >

Abstract: Describes efficient and robust deformable model based techniques for segmentation of ventricular boundaries in cardiac MR images. Starting with a user specified approximate boundary or an interior point of the left ventricle for one ED slice, the authors' algorithms generate contours for inner and outer walls, and automatically propagate them to other slices in the ED phase (spatial propagation) and to slices in all the phases (temporal propagation) of the cardiac study. The algorithms are based on steepest descent as well as dynamic programming strategies integrated via multiscale analysis. The ventricular boundaries are used to construct a 3-D model for visualization and to compute volume based diagnostic quantities. The algorithms have been incorporated into a user interface which can load, sort, visualize, and analyze a cardiac study an less than 10 minutes. The system has been tested on a dozen volunteers and patients (1000+ images) with excellent results. >

Abstract: Often papers, which compare the performance of neural net classifiers with traditional classifiers, tend to de-emphasize the importance of the network configuration. This paper presents the results of experiments with the use of neural nets for land-cover classification in a SPOT satellite image. Segments in the image are described by textural features calculated from gray-level difference statistics. The segments are found using an algorithm based on iterative use of adaptive noise filtering and region growing. An artificial neural net, a backpropagation net with two hidden layers (often referred to as a three-layer perceptron), is used to classify the segments. A variety of segment sizes are generated by the region growing procedure, and some of these are obviously too small for a textural description.

Abstract: The problem of part definition, description, and decomposition is central to the shape recognition systems. We present a geometric model-driven framework for segmenting dense range data of complex 3D objects into their constituent parts in terms of surface (biquadrics) and volumetric (superquadrics) primitives, without a priori domain knowledge or stored models. Surface segmentation uses a novel local-to-global iterative regression approach of searching for the best piecewise biquadric description of the data. The region adjacency information, surface discontinuities, and global shape properties are extracted from biquadrics to guide the volumetric segmentation. Superquadric models are recovered by a global-to-local residual-driven procedure, which recursively segments the scene to derive the part-structure. A set of acceptance criteria provide the objective evaluation of intermediate descriptions and decide whether to terminate the procedure, or selectively refine the segmentation. The control module generates hypotheses about superquadric models at clusters of underestimated data and performs controlled extrapolation of part-models by shrinking the global model. Results are presented for real range images of varying complexity, including objects with occluding parts, and scenes where surface segmentation is not sufficient to guide the volumetric segmentation.

Abstract: The application of neural networks to modeling time-invariant nonlinear systems has been difficult for complicated nonstationary signals, such as speech, because the networks are unable to characterize temporal variability. This problem is addressed by proposing a network architecture, called the hidden control neural network (HCNN), for modeling signals generated by nonlinear dynamical systems with restricted time variability. The mapping implemented by a multilayered neural network is allowed to change with time as a function of an additional control input signal. The network is trained using an algorithm based on 'backpropagation' and segmentation algorithms for estimating the unknown control together with the network's parameters. Application of the network to the segmentation and modeling of a signal produced by a time-varying nonlinear system, speaker-independent recognition of spoken connected digits, and online recognition of handwritten characters demonstrates the ability of the HCNN to learn time-varying nonlinear dynamics and its potential for high-performance recognition of signals produced by time-varying sources. >

Abstract: Precision target tracking based on data obtained from imaging sensors when the target is not fully visible during tracking is addressed. The image is divided into several layers of gray level intensities and thresholded. A binary image is obtained and grouped into clusters using image segmentation. The association of the various clusters to the track to be estimated relies on both the motion and pattern recognition characteristics of the target. The centroid measurements of the clusters and the probabilistic data association filter (PDAF) are employed for state estimation. Expressions for the single-frame-based centroid measurement noise variance of the target cluster and the optimal parameters for cluster segmentation are given. Simulation results validate the expressions for the measurement noise variance as well as the performance predictions of the tracking method. For a dim synthetic target with strong background noise, subpixel accuracy in the range of 0.3-0.4 pixel RMS error with moderate

Abstract: A major problem with a neural network-based approach to printed character recognition is the segmentation of merged characters. A hybrid method is proposed which combines a neural network-based deferred segmentation scheme with conventional immediate segmentation techniques. In the deferred segmentation, a neural network is employed to distinguish single characters from composites. To find a proper vertical cut that separates a composite, a shortest-path algorithm seeking minimal-penalty curved cuts is used. Integrating those components with a multiresolution neural network OCR and an efficient spelling checker, the resulting system significantly improves its ability to read omnifont document text.

Abstract: Segmentation of images in the context of model based stochastic techniques is connected with high, very often unpracticle computational complexity. The objective with this thesis is to take the models used in model based image processing, simplify and use them in suboptimal, but not computationally demanding algorithms. Algorithms that are essentially one-dimensional, and their extensions to two dimensions are given.The model used in this thesis is the well known hidden Markov model. Estimation of the number of hidden states from observed data, is a problem that is addressed. The state order estimation problem is of general interest and is not specifically connected to image processing. An investigation of three state order estimation techniques for hidden Markov models is given.

Abstract: A central problem in estimating multiple image motions is that 2-D motion estimation and region segmentation are mutually dependent. The authors present a new region description method for dealing with this mutual dependence problem. Segmentation and motion estimation are simultaneously performed by a clustering process based on color, motion, and pixel position. As a result of the clustering, an image is decomposed into region fragments. Each fragment is characterized by distribution parameters of color, pixel positions, and spatiotemporal intensity gradients. The image is described by the parameters of the region fragments; 2-D motion vectors for each fragment are obtained from the distribution parameters of the intensity gradients. By combining those features in the clustering process, regions are segmented more precisely, motion boundaries are not blurred, and the 2-D motions are obtained even in noisy areas. Experimental results are presented. >

Abstract: Collection and analysis of pavement distress data is an important component of any pavement-management system. Various systems are currently under development that automate this process. They consist of appropriate hardware for the acquisition of pavement distress images and, in some cases, software for the analysis of the collected data. An important step in the automatic interpretation of images is segmentation, the process of extracting the objects of interest (distresses) from the background. We examine algorithms for segmenting pavement images and evaluate their effectiveness in separating the distresses from the background. The methods examined include the Otsu method, Kittler’s method, a modified relaxation method, and a method is based on a threshold estimated by regression analysis. Comparison of the algorithms on a data set of asphalt pavement images indicates that the relaxation and regression thresholding methods consistently outperform the other methods. The regression thresholding method has the potential to become the method of choice due to its computational advantage over the relaxation method.

Abstract: This paper describes the design, implementation, and testing of an adaptive digital image segmentation method that detects cancerous changes in mammograms and can potentially aid medical experts in establishing the diagnosis. The essence of the method is hierarchical region growing that uses pyramidal multiresolution image representation. The relationships between pixels at different resolution levels are established using a fuzzy membership function, thus enabling detection of very small and/or low contrast objects in a highly textured background. The selection of the parameters of the fuzzy membership function allows for fine-tuning the method to specific segmentation objectives. This paper discusses two versions of the method: the first is aimed at the detection of microcalcifications and the second at the detection of benign and malignant nodules. The two versions are fully automated and differ in the procedure applied to automatically select the appropriate parameters of the fuzzy membership function. Both versions were evaluated in two ways: (i) using synthetically generated objects superimposed on normal mammograms and (ii) using mammogram images for which the corresponding truth images were generated by human experts. The objective of the first evaluation was to precisely determine the method’s capabilities and its sensitivity to object size, shape, and contrast. The objective of the second evaluation was to establish the method’s usefulness in helping medical experts to establish the diagnosis.