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 235 records · Page 13Linked to original sources

PubMed2006

On the orientability of shapes.

The orientation of a shape is a useful quantity, and has been shown to affect performance of object recognition in the human visual system. Shape orientation has also been used in computer vision to provide a properly oriented frame of reference, which can aid recognition. However, for certain shapes, the standard moment-based method of orientation estimation fails. We introduce as a new shape feature shape orientability, which defines the degree to which a shape has distinct (but not necessarily unique) orientation. A new method is described for measuring shape orientability, and has several desirable properties. In particular, unlike the standard moment-based measure of elongation, it is able to differentiate between the varying levels of orientability of n-fold rotationally symmetric shapes. Moreover, the new orientability measure is simple and efficient to compute (for an n-gon we describe an O(n) algorithm).

Algorithms↗

PubMed2005

Local image structures and optic flow estimation.

Different kinds of local image structures (such as homogeneous, edge-like and junction-like patches) can be distinguished by the intrinsic dimensionality of the local signals. Intrinsic dimensionality makes use of variance from a point and a line in spectral representation of the signal in order to classify it as homogeneous, edge-like or junction-like. The concept of intrinsic dimensionality has been mostly exercised using discrete formulations; however, recent work has introduced a continuous definition. The current study analyzes the distribution of local patches in natural images according to this continuous understanding of intrinsic dimensionality. This distribution reveals specific patterns than can be also associated to local image structures established in computer vision and which can be related to orientation and optic flow features. In particular, we link quantitative and qualitative properties of optic-flow error estimates to these patterns. In this way, we also introduce a new tool for better analysis of optic flow algorithms.

Algorithms↗

PubMed2006

MILES: multiple-instance learning via embedded instance selection.

Multiple-instance problems arise from the situations where training class labels are attached to sets of samples (named bags), instead of individual samples within each bag (called instances). Most previous multiple-instance learning (MIL) algorithms are developed based on the assumption that a bag is positive if and only if at least one of its instances is positive. Although the assumption works well in a drug activity prediction problem, it is rather restrictive for other applications, especially those in the computer vision area. We propose a learning method, MILES (Multiple-Instance Learning via Embedded instance Selection), which converts the multiple-instance learning problem to a standard supervised learning problem that does not impose the assumption relating instance labels to bag labels. MILES maps each bag into a feature space defined by the instances in the training bags via an instance similarity measure. This feature mapping often provides a large number of redundant or irrelevant features. Hence, 1-norm SVM is applied to select important features as well as construct classifiers simultaneously. We have performed extensive experiments. In comparison with other methods, MILES demonstrates competitive classification accuracy, high computation efficiency, and robustness to labeling uncertainty.

Algorithms↗

PubMed2006

Comparison between immersion-based and toboggan-based watershed image segmentation.

Watershed segmentation has recently become a popular tool for image segmentation. There are two approaches to implementing watershed segmentation: immersion approach and toboggan simulation. Conceptually, the immersion approach can be viewed as an approach that starts from low altitude to high altitude and the toboggan approach as an approach that starts from high altitude to low altitude. The former seemed to be more popular recently (e.g., Vincent and Soille), but the latter had its own supporters (e.g., Mortensen and Barrett). It was not clear whether the two approaches could lead to exactly the same segmentation result and which approach was more efficient. In this paper, we present two "order-invariant" algorithms for watershed segmentation, one based on the immersion approach and the other on the toboggan approach. By introducing a special RIDGE label to achieve the property of order-invariance, we find that the two conceptually opposite approaches can indeed obtain the same segmentation result. When running on a Pentium-III PC, both of our algorithms require only less than 1/30 s for a 256 x 256 image and 1/5 s for a 512 x 512 image, on average. What is more surprising is that the toboggan algorithm, which is less well known in the computer vision community, turns out to run faster than the immersion algorithm for almost all the test images we have used, especially when the image is large, say, 512 x 512 or larger. This paper also gives some explanation as to why the toboggan algorithm can be more efficient in most cases.

Algorithms↗

PubMed2003

Methods for automatic microarray image segmentation.

This paper describes image processing methods for automatic spotted microarray image analysis. Automatic gridding is important to achieve constant data quality and is, therefore, especially interesting for large-scale experiments as well as for integration of microarray expression data from different sources. We propose a Markov random field (MRF) based approach to high-level grid segmentation, which is robust to common problems encountered with array images and does not require calibration. We also propose an active contour method for single-spot segmentation. Active contour models describe objects in images by properties of their boundaries. Both MRFs and active contour models have been used in various other computer vision applications. The traditional active contour model must be generalized for successful application to microarray spot segmentation. Our active contour model is employed for spot detection in the MRF score functions as well as for spot signal segmentation in quantitative array image analysis. An evaluation using several image series from different sources shows the robustness of our methods.

Algorithms↗

PubMedDate not supplied

Segmentation of two- and three-dimensional data from electron microscopy using eigenvector analysis.

An automatic image segmentation method is used to improve processing and visualization of data obtained by electron microscopy. Exploiting affinity criteria between pixels, e.g., proximity and gray level similarity, in conjunction with an eigenvector analysis, the image is subdivided into areas which correspond to objects or meaningful regions. Extending a proposal by Shi and Malik (1997, Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, pp. 731-737) the approach was adapted to the field of electron microscopy, especially to three-dimensional application as needed by electron tomography. Theory, implementation, parameter setting, and results obtained with a variety of data are presented and discussed. The method turns out to be a powerful tool for visualization with the potential for further improvement by developing and tuning new affinity.

Algorithms↗

PubMed2004

Neural mechanisms for the robust representation of junctions.

Junctions provide important cues in various perceptual tasks, such as the determination of occlusion relationships for figure-ground separation, transparency perception, and object recognition, among others. In computer vision, junctions are used in a number of tasks, like point matching for image tracking or correspondence analysis. We propose a biologically motivated approach to junction representation in which junctions are implicitly characterized by high activity for multiple orientations within a cortical hypercolumn. A local measure of circular variance is suggested to extract junction points from this distributed representation. Initial orientation measurements are often fragmented and noisy. A coherent contour representation can be generated by a model of V1 utilizing mechanisms of collinear long-range integration and recurrent interaction. In the model, local oriented contrast estimates that are consistent within a more global context are enhanced while inconsistent activities are suppressed. In a series of computational experiments, we compare junction detection based on the new recurrent model with a feedforward model of complex cells. We show that localization accuracy and positive correctness in the detection of generic junction configurations such as L- and T-junctions is improved by the recurrent long-range interaction. Further, receiver operating characteristics analysis is used to evaluate the detection performance on both synthetic and camera images, showing the superior performance of the new approach. Overall, we propose that nonlocal interactions implemented by known mechanisms within V1 play an important role in detecting higher-order features such as corners and junctions.

Models, Neurological↗

PubMed1994

Methods of measuring wound size: a comparative study.

The lack of an accepted method of accurate and objective measurement of wound dimensions is a major obstacle to the assessment of effective wound management regimes. This study compares three different wound volume measurement techniques (filling the lesion with saline, molding of a dental impression material and a computer vision method based on image processing and the Structured Light technique) in terms of accuracy, precision and practicability in a clinical environment. Three groups of hospital staff, doctors, nurses and technicians, repeatedly measured a set of 6 different models of wounds. Measuring wound volume by filling it with saline produces results with standard deviations between 9 percent and 18 percent of the actual volume. Dental impression material performs better, between 5 percent and 16 percent, but is difficult to apply and time consuming to use. Apart from the advantage of providing instant optical records of wounds, the image processing method produces more reliable volume measurements with a standard deviation of between 3 percent and 15 percent. The results demonstrate that the computer based method yields the most reproducible results with a minimum of inter-observer error but the method is not applicable for undermined, very deep and very large wounds.

Anthropometry↗

PubMed1997

Tissue characterization from X-ray images.

The study of the fine-scale structure of biological tissues is crucial for diagnosing a wide number of different diseases. In X-ray images, fine structures usually induce a correlation among image gray levels and are commonly perceived as textures. In this paper, we report on a Computer Vision approach to the characterization of biological tissues as imaged by standard X-ray techniques. In particular, using features derived from co-occurrence matrices, we have assessed spatial gray-level dependence of bone tissue and lung parenchyma images. A hybrid neural network was adopted to distinguish pathological tissues from normal ones and to classify different pathologies.

Bone Diseases↗

PubMedDate not supplied

Where to look? Automating attending behaviors of virtual human characters.

This research proposes a computational framework for generating visual attending behavior in an embodied simulated human agent. Such behaviors directly control eye and head motions, and guide other actions such as locomotion and reach. The implementation of these concepts, referred to as the AVA, draws on empirical and qualitative observations known from psychology, human factors and computer vision. Deliberate behaviors, the analogs of scanpaths in visual psychology, compete with involuntary attention capture and lapses into idling or free viewing. Insights provided by implementing this framework are: a defined set of parameters that impact the observable effects of attention, a defined vocabulary of looking behaviors for certain motor and cognitive activity, a defined hierarchy of three levels of eye behavior (endogenous, exogenous and idling) and a proposed method of how these types interact.

Attention↗

PubMed2006

Line detection in images through regularized Hough transform.

The problem of determining the location and orientation of straight lines in images is of great importance in the fields of computer vision and image processing. Traditionally the Hough transform, (a special case of the Radon transform) has been widely used to solve this problem for binary images. In this paper, we pose the problem of detecting straight lines in gray-scale images as an inverse problem. Our formulation is based on use of the inverse Radon operator, which relates the parameters determining the location and orientation of the lines in the image to the noisy input image. The advantage of this formulation is that we can then approach the problem of line detection within a regularization framework and enhance the performance of the Hough-based line detector through the incorporation of prior information in the form of regularization. We discuss the type of regularizers that are useful for this problem and derive efficient computational schemes to solve the resulting optimization problems enabling their use in large applications. Finally, we show how our new approach can be alternatively viewed as one of finding an optimal representation of the noisy image in terms of elements chosen from a dictionary of lines. This interpretation relates the problem of Hough-based line finding to the body of work on adaptive signal representation.

Algorithms↗

PubMed1998

Three-dimensional determination of femoral-tibial contact positions under in vivo conditions using fluoroscopy.

OBJECTIVE: A method has been developed to accurately measure three-dimensional (3-D) femoral-tibial contact positions of artificial knee implants in vivo from X-ray fluoroscopy images using interactive 3-D computer vision algorithms. DESIGN: A computerized graphical (CAD) model of an implant component is displayed as an overlay on the original X-ray image. An image matching algorithm matches the silhouette of the implant component against a library of images, in order to estimate the position and orientation (pose) of the component. The operator further adjusts the pose of the graphical model to improve the accuracy of the match. BACKGROUND: Previous methods for in vivo measurement of joint kinematics make only indirect measurements of joint kinematics, require invasive procedures such as markers or pins, or make simplifying assumptions about imaging geometry which can reduce the accuracy of the resulting measurements. METHODS: Fluoroscopic videos are taken of implanted knees in subjects performing weight-bearing motion. Images from the videos are digitized and stored on a computer workstation. Using computerized model matching, the relative pose of the two knee implant components can be determined in each image. The resulting information can be used to determine where the two components are contacting, the area of the contact region, liftoff angle, and other kinematic data. RESULTS: Accuracy tests done on simulated imagery and in vitro real imagery show that the pose estimation method is accurate to less than 0.5 mm of error (RMS) for translations parallel to the image plane. Orientation error is less than or equal to 0.35 degrees about any axis. Errors are larger for translations perpendicular to the image plane (up to 2.25 mm). In a clinical study, the method was used to measure in vivo contact points, and characterize the kinematic patterns of two different knee implant designs. CONCLUSIONS: The ability to accurately measure knee kinematics in vivo is critical for the understanding of the behavior of knee implant designs and the ultimate development of new, longer lasting implants. RELEVANCE: This work shows that it is possible to accurately measure the three-dimensional position and orientation (pose) of artificial knee implants in vivo from X-ray fluoroscopy images using interactive 3-D computer graphics. The method can be applied to any joint when accurate CAD models are available. The resulting data can be used to characterize the kinematics of current knee implant designs.

Journal Article↗

PubMed2006

Robust photometric invariant features from the color tensor.

Luminance-based features are widely used as low-level input for computer vision applications, even when color data is available. The extension of feature detection to the color domain prevents information loss due to isoluminance and allows us to exploit the photometric information. To fully exploit the extra information in the color data, the vector nature of color data has to be taken into account and a sound framework is needed to combine feature and photometric invariance theory. In this paper, we focus on the structure tensor, or color tensor, which adequately handles the vector nature of color images. Further, we combine the features based on the color tensor with photometric invariant derivatives to arrive at photometric invariant features. We circumvent the drawback of unstable photometric invariants by deriving an uncertainty measure to accompany the photometric invariant derivatives. The uncertainty is incorporated in the color tensor, hereby allowing the computation of robust photometric invariant features. The combination of the photometric invariance theory and tensor-based features allows for detection of a variety of features such as photometric invariant edges, corners, optical flow, and curvature. The proposed features are tested for noise characteristics and robustness to photometric changes. Experiments show that the proposed features are robust to scene incidental events and that the proposed uncertainty measure improves the applicability of full invariants.

Algorithms↗

PubMed2002

Neural networks with local receptive fields and superlinear VC dimension.

Local receptive field neurons comprise such well-known and widely used unit types as radial basis function (RBF) neurons and neurons with center-surround receptive field. We study the Vapnik-Chervonenkis (VC) dimension of feedforward neural networks with one hidden layer of these units. For several variants of local receptive field neurons, we show that the VC dimension of these networks is superlinear. In particular, we establish the bound Omega(W log k) for any reasonably sized network with W parameters and k hidden nodes. This bound is shown to hold for discrete center-surround receptive field neurons, which are physiologically relevant models of cells in the mammalian visual system, for neurons computing a difference of gaussians, which are popular in computational vision, and for standard RBF neurons, a major alternative to sigmoidal neurons in artificial neural networks. The result for RBF neural networks is of particular interest since it answers a question that has been open for several years. The results also give rise to lower bounds for networks with fixed input dimension. Regarding constants, all bounds are larger than those known thus far for similar architectures with sigmoidal neurons. The superlinear lower bounds contrast with linear upper bounds for single local receptive field neurons also derived here.

Algorithms↗

PubMed2003

Real-time augmentation of USDA yield grade application to beef carcasses using video image analysis.

In two phases, this study assessed the ability of two video image analysis (VIA) instruments, VIASCAN and Computer Vision System (CVS), to augment assignment of yield grades (YG) to beef carcasses to 0.1 of a YG at commercial packing plant speeds and to test cutout prediction accuracy of a YG augmentation system that used a prototype augmentation touchpanel grading display (designed to operate commercially in real-time). In Phase I, beef carcasses (n = 505) were circulated twice at commercial chain speeds (340 carcasses per hour) by 12 on-line USDA graders. During the first pass, on-line graders assigned a whole-number YG and a quality grade (QG) to carcasses as they would normally. During the second pass, on-line graders assigned only adjusted preliminary yield grades (APYG) and QG to carcasses, whereas the two VIA instruments measured the longissimus muscle area (LMA) of each carcass. Kidney, pelvic, and heart fat (KPH) was removed and weighed to allow computation of actual KPH percentage. Those traits were compared to the expert YG and expert YG factors. On-line USDA graders' APYG were closely related (r = 0.83) to expert APYG. Instrument-measured LMA were closely related (r = 0.88 and 0.94; mean absolute error = 0.3 and 0.2 YG units, for VIASCAN and CVS, respectively) to expert LMA. When YG were augmented using instrument-measured LMA and computed either including or neglecting actual KPH percentage, YG were closely related (r = 0.93 and 0.92, mean absolute error = 0.32 and 0.40 YG units, respectively, using VIASCAN-measured LMA; r = 0.95 and 0.94, mean absolute error = 0.24 and 0.34 YG units, respectively, using CVS-measured LMA) to expert YG. In Phase II, augmented YG were assigned (0.1 of a YG) to beef carcasses (n = 290) at commercial chain speeds using VIASCAN and CVS to determine LMA, whereas APYG and QG were determined by online graders via a touch-panel display. On-line grader YG (whole-number), expert grader YG (to the nearest 0.1 of a YG), and VIASCAN- and CVS-augmented YG (to the nearest 0.1 of a YG) accounted for 55, 71, 60, and 63% of the variation in fabricated yields of closely trimmed subprimals, respectively, suggesting that VIA systems can operate at current plant speeds and effectively augment official USDA application of YG to beef carcasses.

Animals↗

PubMed2001

Augmented reality fundus biomicroscopy: a working clinical prototype.

BACKGROUND: To guide treatment for macular diseases and to facilitate real-time image correlation, measurement, and comparison, we developed a method for direct overlay of previously stored photographic and angiographic images onto the real-time slitlamp fundus view. METHODS: Previously acquired fundus photographs and angiography images were digitized. A slitlamp interfaced to a charge-coupled device camera, framegrabber, and computer allowed for real-time acquisition and digitization of slitlamp fundus images that was synchronous with posterior segment examination. Custom-developed video injectors containing a miniature cathode ray tube display allowed for real-time superposition of angiographic images to the fundus view. Registration and tracking algorithms were developed and deployed in C++. The feasibility of this approach was demonstrated in 5 human subjects. RESULTS: The computer-vision algorithms provided robust registration, tracking, and image overlay of previously stored photographic and angiographic images directly onto the real-time fundus view. Accurate tracking was demonstrated with updates at 3 to 5 Hz. Direct overlay of previously stored images confirmed registration accuracy, but examiners preferred a more simple rendering that included only relevant information and eliminated extraneous, potentially confusing image data. CONCLUSIONS: Slitlamp-based video injection of previously stored images allows for accurate, robust, real-time correlation and comparison to the biomicroscopic fundus view in human subjects.

Algorithms↗

PubMed2005

Parametric reconstruction of generalized cylinders from limb edges.

The three-dimensional (3-D) reconstruction of generalized cylinders (GCs) is an important research field in computer vision. One of the main difficulties is that some contour features in images cannot be reconstructed by traditional stereovision because they do not correspond to reflectance discontinuities of surface in space. In this paper, we present a novel, parametric approach for the 3-D reconstruction of circular generalized cylinders (CGCs) only from the limb edges of CGCs in two images. Instead of exploiting the invariant and quasiinvariant properties of some specific subclasses of GCs in projections, our reconstruction is achieved by some general assumptions on GCs, and can, therefore, be applied to a broader subclass of GCs. In order to improve robustness, we perform the extraction and labeling of the limb edge interactively, and estimate the epipolar geometry between two images by an optimal algorithm. Then, for different types of GCs, three kinds of symmetries (parallel symmetry, skew symmetry, and local smooth symmetry) are employed to compute the symmetry of limb edges. The surface points corresponding to limb edges in images are reconstructed by integrating the recovered epipolar geometry and the properties induced from the assumptions that we make on the GCs. Finally, a homography-based method is exploited to further refine the 3-D description of the GC with a coplanar curved axis.

Algorithms↗

PubMed1991

The Space Station Freedom Flight Telerobotic Servicer: the design and evolution of a dexterous space robot.

The Flight Telerobotic Servicer (FTS) Project at the Goddard Space Flight Center is developing an advanced telerobotic system to assist in and reduce crew extravehicular activity (EVA) for Space Station) Freedom (SSF). The FTS will provide a telerobotic capability to the Freedom Station in the early assembly phases of the program and will be employed for assembly, maintenance, and inspection applications throughout the lifetime of the space station. Appropriately configured elements of the FTS will also be employed for robotic manipulation in remote satellite servicing applications and possibly the Lunar/Mars Program. In mid-1989, the FTS entered the flight system design and implementation phase (Phase C/D) of development with the signing of the FTS prime contract with Martin Marietta Astronautics Group in Denver, Colorado. The basic FTS design is now established and can be reported on in some detail. This paper will describe the FTS flight system design and the rationale for the specific design approaches and component selections. The current state of space technology and the nature of the FTS task dictate that the FTS be designed with sophisticated teleoperation capabilities for its initial primary operating mode. However, there are technologies, such as advanced computer vision and autonomous planning techniques currently in research and advanced development phases which would greatly enhance the FTS capabilities to perform autonomously in less structured work environments. Therefore, a specific requirement on the initial FTS design is that it has the capability to evolve as new technology becomes available. This paper will describe the FTS design approach for evolution to more autonomous capabilities. Some specific task applications of the FTS and partial automation approaches of these tasks will also be discussed in this paper.

Biomechanical Phenomena↗