SEARCH · PubMed Health

Results for “Computer vision”

Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 307 records · Page 17Linked to original sources

PubMed2003

Smoothness-based forces for deformable models: a long-range force and a corner fitting force.

Deformable models, originally proposed by Terzopoulos et al. (Artif. Intell. 36 (1988) 91) and Kass et al. (Int. J. Comput. Vision 1 (1988) 321) in 1988, have been widely used in medical image segmentation. However, they manifest two well-known limitations: the lack of an appropriate long-range force to drive the model surface towards the object boundary and poor performance at high curvature boundaries (such as corners) due to the models' intrinsic smoothness constraint. In this paper, a new smoothness force with local control is proposed. The local control is used to devise a long-range force, referred to as the self-zoom force, and a corner fitting force. The self-zoom force enables the model surface to expand and shrink without a limit in range. The corner fitting force propels the model surface to fit high-curvature boundaries. Experiments demonstrate that the model surface is driven to the object boundary by the new forces even if the initial estimate is not close and the object is nonconvex or has a high local curvature.

Computer Simulation↗

PubMed2006

Learning nonlinear image manifolds by global alignment of local linear models.

Appearance-based methods, based on statistical models of the pixel values in an image (region) rather than geometrical object models, are increasingly popular in computer vision. In many applications, the number of degrees of freedom (DOF) in the image generating process is much lower than the number of pixels in the image. If there is a smooth function that maps the DOF to the pixel values, then the images are confined to a low-dimensional manifold embedded in the image space. We propose a method based on probabilistic mixtures of factor analyzers to (1) model the density of images sampled from such manifolds and (2) recover global parameterizations of the manifold. A globally nonlinear probabilistic two-way mapping between coordinates on the manifold and images is obtained by combining several, locally valid, linear mappings. We propose a parameter estimation scheme that improves upon an existing scheme and experimentally compare the presented approach to self-organizing maps, generative topographic mapping, and mixtures of factor analyzers. In addition, we show that the approach also applies to finding mappings between different embeddings of the same manifold.

Algorithms↗

PubMed2003

3D-SHOTGUN: a novel, cooperative, fold-recognition meta-predictor.

To gain a better understanding of the biological role of proteins encoded in genome sequences, knowledge of their three-dimensional (3D) structure and function is required. The computational assignment of folds is becoming an increasingly important complement to experimental structure determination. In particular, fold-recognition methods aim to predict approximate 3D models for proteins bearing no sequence similarity to any protein of known structure. However, fully automated structure-prediction methods can currently produce reliable models for only a fraction of these sequences. Using a number of semiautomated procedures, human expert predictors are often able to produce more and better predictions than automated methods. We describe a novel, fully automatic, fold-recognition meta-predictor, named 3D-SHOTGUN, which incorporates some of the strategies human predictors have successfully applied. This new method is reminiscent of the so-called cooperative algorithms of Computer Vision. The input to 3D-SHOTGUN are the top models predicted by a number of independent fold-recognition servers. The meta-predictor consists of three steps: (i) assembly of hybrid models, (ii) confidence assignment, and (iii) selection. We have applied 3D-SHOTGUN to an unbiased test set of 77 newly released protein structures sharing no sequence similarity to proteins previously released. Forty-six correct rank-1 predictions were obtained, 30 of which had scores higher than that of the first incorrect prediction-a significant improvement over the performance of all individual servers. Furthermore, the predicted hybrid models were, on average, more similar to their corresponding native structures than those produced by the individual servers. This opens the possibility of generating more accurate, full-atom homology models for proteins with no sequence similarity to proteins of known structure. These improvements represent a step forward toward the wider applicability of fully automated structure-prediction methods at genome scales.

Algorithms↗

PubMedDate not supplied

Camera virtual equivalent model 0.01 pixel detectors.

In computer vision, a standard approach to eliminate spatial distortion is to use a calibrated grid. We developed an original method using such a grid to establish an equivalence between any camera with inherent technical limitations (optic, solid-state sensor, digitizer) and a perfect virtual pinhole camera model. This bijection based on interpolation concepts takes all the deformations generated by the optical and electronical equipment into account (distortion, decentration, scale, and affinity ratios) without the need for their explicit determination. We propose a detection method of this grid image by the use of grey levels approximation surfaces particularly adapted to this problem. We obtained a good precision on real grid images with modelization errors standard deviation of about 0.007 pixels with an off-the-shelf 512 x 512 camera using 256 grey levels. Three interpolation methods are compared: bilinear, cross-ratio in projective coordinates and bicubic splines. We conclude from this study that, in distorted images, the use of the bicubic splines interpolation method is a good improvement.

Algorithms↗

PubMed2004

Speed-accuracy characteristics of human-machine cooperative manipulation using virtual fixtures with variable admittance.

This work explores the effect of virtual fixture admittance on the performance, defined by error and time, of task execution with a human-machine cooperative system. A desired path is obtained using computer vision, and virtual fixtures for assistance in planar path following were implemented on an admittance-controlled robot. The admittance controller uses a velocity gain, so that the speed of the robot is proportional to the force applied by the operator. The level of virtual fixture guidance is determined by the admittance ratio, which is the ratio of the admittance gain of the force components orthogonal to the path to the gain of the force components parallel to the path. In Experiment 1, we found a linear relationship between admittance ratio and performance. In Experiment 2, we examined the effect of admittance ratio on the performance of three tasks: path following, off-path targeting, and obstacle avoidance. An algorithm was developed to select an appropriate admittance ratio based on the nature of the task. Automatic admittance ratio tuning is recommended for next-generation virtual fixtures. Actual or potential applications of this research include surgery, assembly, and manipulation at the macro and micro scales.

Acceleration↗

PubMed2005

Indexing hierarchical structures using graph spectra.

Hierarchical image structures are abundant in computer vision and have been used to encode part structure, scale spaces, and a variety of multiresolution features. In this paper, we describe a framework for indexing such representations that embeds the topological structure of a directed acyclic graph (DAG) into a low-dimensional vector space. Based on a novel spectral characterization of a DAG, this topological signature allows us to efficiently retrieve a promising set of candidates from a database of models using a simple nearest-neighbor search. We establish the insensitivity of the signature to minor perturbation of graph structure due to noise, occlusion, or node split/merge. To accommodate large-scale occlusion, the DAG rooted at each nonleaf node of the query "votes" for model objects that share that "part," effectively accumulating local evidence in a model DAG's topological subspaces. We demonstrate the approach with a series of indexing experiments in the domain of view-based 3D object recognition using shock graphs.

Algorithms↗

PubMed2005

Where are linear feature extraction methods applicable?

A fundamental problem in computer vision and pattern recognition is to determine where and, most importantly, why a given technique is applicable. This is not only necessary because it helps us decide which techniques to apply at each given time. Knowing why current algorithms cannot be applied facilitates the design of new algorithms robust to such problems. In this paper, we report on a theoretical study that demonstrates where and why generalized eigen-based linear equations do not work. In particular, we show that when the smallest angle between the ith eigenvector given by the metric to be maximized and the first i eigenvectors given by the metric to be minimized is close to zero, our results are not guaranteed to be correct. Several properties of such models are also presented. For illustration, we concentrate on the classical applications of classification and feature extraction. We also show how we can use our findings to design more robust algorithms. We conclude with a discussion on the broader impacts of our results.

Algorithms↗

PubMed2001

Automated counting of mammalian cell colonies.

Investigating the effect of low-dose radiation exposure on cells using assays of colony-forming ability requires large cell samples to maintain statistical accuracy. Manually counting the resulting colonies is a laborious task in which consistent objectivity is hard to achieve. This is true especially with some mammalian cell lines which form poorly defined or 'fuzzy' colonies, typified by glioma or fibroblast cell lines. A computer-vision-based automated colony counter is presented in this paper. It utilizes novel imaging and image-processing methods involving a modified form of the Hough transform. The automated counter is able to identify less-discrete cell colonies typical of these cell lines. The results of automated colony counting are compared with those from four manual (human) colony counts for the cell lines HT29, A172, U118 and IN1265. The results from the automated counts fall well within the distribution of the manual counts for all four cell lines with respect to surviving fraction (SF) versus dose curves, SF values at 2 Gy (SF2) and total area under the SF curve (Dbar). From the variation in the counts, it is shown that the automated counts are generally more consistent than the manual counts.

Automation↗

PubMed2006

The multiscale hermite transform for local orientation analysis.

The efficient representation of local differential structure at various resolutions has been a matter of great interest for adaptive image processing and computer vision tasks. In this paper, we derive a multiscale model to represent natural images based on the scale-space representation: a model that has an inspiration in the human visual system. We first derive the one-dimensional case and then extend the results to two and three dimensions. The operators obtained for analysis and synthesis stages are derivatives of the Gaussian smoothing kernel, so that, for the two-dimensional case, we can represent them either in a rotated coordinate system or in terms of directional derivatives. The method to perform the rotation is efficient because it is implemented by means of the application of the so-called generalized binomial filters. Such a family of discrete sequences fulfills a number of properties that allows estimating the local orientation for several image structures. We also define the discrete counterpart in which the coordinate normalization of the continuous case is approximated as a subsampling of the discrete domain.

Algorithms↗

PubMed2001

Improvement of mammographic mass characterization using spiculation meausures and morphological features.

We are developing new computer vision techniques for characterization of breast masses on mammograms. We had previously developed a characterization method based on texture features. The goal of the present work was to improve our characterization method by making use of morphological features. Toward this goal, we have developed a fully automated, three-stage segmentation method that includes clustering, active contour, and spiculation detection stages. After segmentation, morphological features describing the shape of the mass were extracted. Texture features were also extracted from a band of pixels surrounding the mass. Stepwise feature selection and linear discriminant analysis were employed in the morphological, texture, and combined feature spaces for classifier design. The classification accuracy was evaluated using the area Az under the receiver operating characteristic curve. A data set containing 249 films from 102 patients was used. When the leave-one-case-out method was applied to partition the data set into trainers and testers, the average test Az for the task of classifying the mass on a single mammographic view was 0.83 +/- 0.02, 0.84 +/- 0.02, and 0.87 +/- 0.02 in the morphological, texture, and combined feature spaces, respectively. The improvement obtained by supplementing texture features with morphological features in classification was statistically significant (p = 0.04). For classifying a mass as malignant or benign, we combined the leave-one-case-out discriminant scores from different views of a mass to obtain a summary score. In this task, the test Az value using the combined feature space was 0.91 +/- 0.02. Our results indicate that combining texture features with morphological features extracted from automatically segmented mass boundaries will be an effective approach for computer-aided characterization of mammographic masses.

Automation↗

PubMed2000

Probing f-actin flow by tracking shape fluctuations of radial bundles in lamellipodia of motile cells.

We examined the dynamics of radial actin bundles based on time-lapse movies of polarized light images of living neuronal growth cones. Using a highly sensitive computer vision algorithm for tracking, we analyzed the small shape fluctuations of radial actin bundles that otherwise remained stationary in their positions in the growth cone lamellipodium. Using the tracking software, we selected target points on radial bundles and measured both the local bundle orientations and the lateral displacements between consecutive movie frames. We found that the local orientation and the lateral displacement of a target point are correlated. The correlation can be explained using a simple geometric relationship between the lateral travel of tilted actin bundles and the retrograde flow of f-actin structures. Once this relationship has been established, we have turned the table and used the radial bundles as probes to measure the velocity field of f-actin flow. We have generated a detailed map of the complex retrograde flow pattern throughout the lamellipodium. Such two-dimensional flow maps will give new insights into the mechanisms responsible for f-actin-mediated cell motility and growth.

Actins↗

PubMed1997

Automatic extraction and measurement of leukocyte motion in microvessels using spatiotemporal image analysis.

This paper describes a computer vision system for the automatic extraction and velocity measurement of moving leukocytes that adhere to microvessel walls from a sequence of images. The motion of these leukocytes can be visualized as motion along the wall contours. We use the constraint that the leukocytes move along the vessel wall contours to generate a spatiotemporal image, and the leukocyte motion is then extracted using the methods of spatiotemporal image analysis. The generated spatiotemporal image is processed by a special-purpose orientation-selective filter and a subsequent grouping process newly developed for this application. The orientation-selective filter is designed by considering the particular properties of the spatiotemporal image in this application in order to enhance only the traces of leukocytes. In the subsequent grouping process, leukocyte trace segments are selected and grouped among all the segments obtained by simple thresholding and skeletonizing operations. We show experimentally that the proposed method can stably extract leukocyte motion.

Algorithms↗

PubMed1995

Three-dimensional reconstruction of the biliary tract from two-dimensional biliary images.

To make conventional two-dimensional cholangiography easier and more precise to read, we used techniques in computer vision to reconstruct the images in three dimensions. A 72-year-old man and a 70-year-old woman suffering from acute cholangitis were treated using endoscopic nasobiliary drainage. Their cholangiograms, from two orthogonal views, were used for three-dimensional reconstruction. We used video image-grabber and film scanner methods to digitize the original conventional biliary radiographs, and applied two different image processing methods to show the biliary structure. Both methods of three-dimensional reconstruction of the biliary tract were highly useful in evaluating the biliary tracts in these two patients, especially when a semitranslucence overlapping display technique was applied in the second patient. With this technique, the biliary tree itself and the stones inside the common bile duct can be clearly delineated. The technique of three-dimensional reconstruction of biliary images can make the conventional cholangiographs more lifelike and has great potential in surgical simulation in the near future.

Aged↗

PubMed2001

A new approach of geodesic reconstruction for drusen segmentation in eye fundus images.

Segmentation of bright blobs in an image is an important problem in computer vision and particularly in biomedical imaging. In retinal angiography, segmentation of drusen, a yellowish deposit located on the retina, is a serious challenge in proper diagnosis and prevention of further complications. Drusen extraction using classic segmentation methods does not lead to good results. We present a new segmentation method based on new transformations we introduced in mathematical morphology. It is based on the search for a new class of regional maxima components of the image. These maxima correspond to the regions inside the drusen. We present experimental results for drusen extraction using images containing examples having different types and shapes of drusen. We also apply our segmentation technique to two important cases of dynamic sequences of drusen images. The first case is for tracking the average gray level of a particular drusen in a sequence of angiographic images during a fluorescein exam. The second case is for registration and matching of two angiographic images from widely spaced exams in order to characterize the evolution of drusen.

Fluorescein Angiography↗

PubMed2004

Recovering the missing components in a large noisy low-rank matrix: application to SFM.

In computer vision, it is common to require operations on matrices with "missing data," for example, because of occlusion or tracking failures in the Structure from Motion (SFM) problem. Such a problem can be tackled, allowing the recovery of the missing values, if the matrix should be of low rank (when noise free). The filling in of missing values is known as imputation. Imputation can also be applied in the various subspace techniques for face and shape classification, online "recommender" systems, and a wide variety of other applications. However, iterative imputation can lead to the "recovery" of data that is seriously in error. In this paper, we provide a method to recover the most reliable imputation, in terms of deciding when the inclusion of extra rows or columns, containing significant numbers of missing entries, is likely to lead to poor recovery of the missing parts. Although the proposed approach can be equally applied to a wide range of imputation methods, this paper addresses only the SFM problem. The performance of the proposed method is compared with Jacobs' and Shum's methods for SFM.

Algorithms↗

PubMed2005

Pose estimation for augmented reality applications using genetic algorithm.

This paper describes a genetic algorithm that tackles the pose-estimation problem in computer vision. Our genetic algorithm can find the rotation and translation of an object accurately when the three-dimensional structure of the object is given. In our implementation, each chromosome encodes both the pose and the indexes to the selected point features of the object. Instead of only searching for the pose as in the existing work, our algorithm, at the same time, searches for a set containing the most reliable feature points in the process. This mismatch filtering strategy successfully makes the algorithm more robust under the presence of point mismatches and outliers in the images. Our algorithm has been tested with both synthetic and real data with good results. The accuracy of the recovered pose is compared to the existing algorithms. Our approach outperformed the Lowe's method and the other two genetic algorithms under the presence of point mismatches and outliers. In addition, it has been used to estimate the pose of a real object. It is shown that the proposed method is applicable to augmented reality applications.

Algorithms↗

PubMed2006

Convergent tree-reweighted message passing for energy minimization.

Algorithms for discrete energy minimization are of fundamental importance in computer vision. In this paper, we focus on the recent technique proposed by Wainwright et al. [33]--tree-reweighted max-product message passing (TRW). It was inspired by the problem of maximizing a lower bound on the energy. However, the algorithm is not guaranteed to increase this bound--it may actually go down. In addition, TRW does not always converge. We develop a modification of this algorithm which we call sequential tree-reweighted message passing. Its main property is that the bound is guaranteed not to decrease. We also give a weak tree agreement condition which characterizes local maxima of the bound with respect to TRW algorithms. We prove that our algorithm has a limit point that achieves weak tree agreement. Finally, we show that, our algorithm requires half as much memory as traditional message passing approaches. Experimental results demonstrate that on certain synthetic and real problems, our algorithm outperforms both the ordinary belief propagation and tree-reweighted algorithm in [33]. In addition, on stereo problems with Potts interactions, we obtain a lower energy than graph cuts.

Algorithms↗

PubMed2006

Determining scale and sea state from water video.

In most image processing and computer vision applications, real-world scale can only be determined when calibration information is available. Dynamic scenes further complicate most situations. However, some types of dynamic scenes provide useful information that can be used to recover real-world scale. In this paper, we focus on ocean scenes and propose a method for finding sizes in real-world units and the sea state from an uncalibrated camera. Fourier transforms in the space and time dimensions yield spatial and temporal frequency spectra. For water waves, the dispersion relation defines a square relationship between the wavelength and period of a wave. Our method applies this dispersion relation to recover the real-world scale of an ocean sequence. The sea state--including the peak wavelength and period, the wind speed that generated the waves, and the wave heights--is also determined from the frequency spectrum of the sequence combined with stochastic oceanography models. The process is demonstrated on synthetic and real sequences, validating the results with known scene geometry. This has wide applications in port monitoring and coastal surveillance.

Algorithms↗