Computer vision and pattern recognition
International Journal of Computer MathematicsPublished 30 August 2007
Nanning Zheng, George Loizou, Xiaoyi Jiang, Xuguang Lan, Xuelong Li
Citations2,466
SJR quartileQ2
SJR score0.50
SNIP0.78
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
Abstract
"Computer vision and pattern recognition." , 84(9), pp. 1265–1266 Additional informationNotes on contributorsNanning Zheng Email: [email protected] George Loizou Email: [email protected] Xuguang Lan Email: [email protected] Xuelong Li Email: [email protected]
Keywords
Computer ScienceEngineering
Real-time tracking of non-rigid objects using mean shift
2,913 Citations2002Dorin Comaniciu, Visvanathan Ramesh +1 more
The theoretical analysis of the approach shows that it relates to the Bayesian framework while providing a practical, fast and efficient solution for real time tracking of non-rigid objects seen from a moving camera.
A statistical method for 3D object detection applied to faces and cars
1,061 Citations2002Henry Schneiderman, Takeo Kanade
Using this method, this work has developed the first algorithm that can reliably detect human faces with out-of-plane rotation and the first algorithms thatCan reliably detect passenger cars over a wide range of viewpoints.
Articulated body motion capture by annealed particle filtering
860 Citations2002J. Deutscher, A. Blake +1 more
The principal contribution of the paper is the development of a modified particle filter for search in high dimensional configuration spaces that uses a continuation principle based on annealing to introduce the influence of narrow peaks in the fitness function, gradually.
Shape descriptors for non-rigid shapes with a single closed contour
832 Citations2002Longin Jan Latecki, Rolf Lakämper +1 more
This paper reports on the MPEG-7 Core Experiment CE-Shape, which gave a unique opportunity to compare various shape descriptors for non-rigid shapes with a single closed contour and found that a more theoretical comparison of these descriptors seems to be extremely hard.
Optimizing learning in image retrieval
377 Citations2002Yong Rui, Thomas S. Huang
A vigorous optimization formulation of the learning process is presented and explicit solutions, which are both optimal and fast to compute, are derived by using Lagrange multipliers are derived.
IEEE Transactions on Pattern Analysis and Machine IntelligenceDetecting binocular half-occlusions: empirical comparisons of five approaches
200 Citations2002Geoffrey Egnal, Richard P. Wildes
Illumination-insensitive face recognition using symmetric shape-from-shading
192 Citations2002Wen Yi Zhao, Rama Chellappa
A new method based on symmetric shape-from-shading (SSFS) to develop a face recognition system that is robust to changes in illumination and utilizes the fact that all faces share a similar shape making the direct computation of the prototype image from a given face image feasible.
An effective approach to detect lesions in color retinal images
186 Citations2002Huan Wang, Wynne Hsu +2 more
A novel approach that combines brightness adjustment procedure with statistical classification method and local-window-based verification strategy is proposed that is able to achieve 100% accuracy in terms of identifying all the retinal images with exudates while maintaining a 70%" accuracy in correctly classifying the truly normal retinal image as normal.
Inferring body pose without tracking body parts
169 Citations2002R. Rosales, Stan Sclaroff
A novel approach for estimating articulated body posture and motion from monocular video sequences is proposed, characterized using real and artificially generated body postures, showing promising results.
Automatic recovery of relative camera rotations for urban scenes
169 Citations2002Matthew Antone, Seth Teller
A formulation of extrinsic camera calibration that decouples rotation from translation by exploiting properties inherent in urban scenes is described and an algorithm which uses edge features to robustly and accurately estimate relative rotations among multiple cameras given intrinsic calibration and approximate initial pose is presented.
Reconstruction of articulated objects from point correspondences in a single uncalibrated image
156 Citations2002Catherine Taylor
This paper investigates the problem of recovering information about the configuration of an articulated object, such as a human figure, from point correspondences in a single-image by considering the foreshortening of the segments of the model in the image.
Robust stereo ego-motion for long distance navigation
146 Citations2002Clark F. Olson, Larry Matthies +2 more
It is demonstrated that even a robust system will accumulate super-linear error in the distance traveled due to increasing orientation errors, however, when an absolute orientation sensor is incorporated, the growth is reduced to linear in thedistance traveled, grows much more slowly in practice.
Scene modeling for wide area surveillance and image synthesis
124 Citations2002A. Mittal, D.P. Huttenlocher
A method for modeling a scene that is observed by a moving camera, where only a portion of the scene is visible at any time, which yields improved results in detecting moving objects and in constructing mosaics in the presence of moving objects when compared with techniques that are not based on scene modeling.
A step towards sequence-to-sequence alignment
108 Citations2002Yaron Caspi, M. Irani
By folding spatial and temporal cues into a single alignment framework, situations which are inherently ambiguous for traditional image- to-image alignment methods, are often uniquely resolved by sequence-to-sequence alignment.
Segmenting visual actions based on spatio-temporal motion patterns
105 Citations2002Yong Rui, P. Anandan
This paper represents frame to frame optical-flow in terms of the coefficients of the most significant principal components computed from all the flow-fields within a given video sequence, and detects discontinuities in the temporal trajectories of these coefficients based on three different measures.
Iterative projective reconstruction from multiple views
101 Citations2002S. Mahamud, Martial Hebert
This work proposes an iterative method that simultaneously recovers both the projective depths as well as the structure and motion that avoids some of these drawbacks by utilizing all of the available data uniformly and proves the monotonic convergence of the iterative scheme to a local maximum.
A general method for Errors-in-Variables problems in computer vision
93 Citations2002B. Matei, Peter Meer
It is shown that the HEIV estimator can provide an accurate solution to most 3D vision estimation tasks, and illustrate its performance through two case studies: calibration and the estimation of the fundamental matrix.
Recognizing lower face action units for facial expression analysis
93 Citations2002Yingli Tian, Takeo Kanade +1 more
An automatic system to analyze subtle changes in facial expressions based on both permanent and transient facial features in a nearly frontal image sequence is developed and it is indicated that the system can identify action units regardless of whether they occur singly or in combinations.
Statistical modeling and performance characterization of a real-time dual camera surveillance system
87 Citations2002Michael Greiffenhagen, Visvanathan Ramesh +2 more
It is illustrated that by judiciously choosing the system modules and performing a careful analysis of the influence of various tuning parameters on the system it is possible to: perform proper statistical inference, automatically set control parameters and quantify limits of a dual-camera real-time video surveillance system.
Reconstruction of a scene with multiple linearly moving objects
81 Citations2002Mei Han, Takeo Kanade
Variable albedo surface reconstruction from stereo and shape from shading
80 Citations2002Dimitris Samaras, Dimitris Metaxas +2 more
A multiview method for the computation of object shape and reflectance characteristics based on the integration of shape from shading (SFS) and stereo, for nonconstant albedo and non-uniformly Lambertian surfaces, and is demonstrated by applying it to face shape reconstruction.
Integrating bottom-up/top-down for object recognition by data driven Markov chain Monte Carlo
78 Citations2002Song‐Chun Zhu, Rong Zhang +1 more
This article presents a mathematical paradigm called Data Driven Markov Chain Monte Carlo (DDMCMC) for object recognition that realizes traditional "hypothesis-and-test" methods through well-balanced Markov chain Monte Carlo dynamics, thus it achieves robust and globally optimal solutions.
Wide area camera calibration using virtual calibration objects
77 Citations2002Xinyue Chen, James Davis +1 more
The paper introduces a method to calibrate a wide area system of unsynchronized cameras with respect to a single global coordinate system and demonstrates its effectiveness in wide area settings by calibrating a system of cameras in a configuration where traditional methods cannot be applied directly.
Codimension-two geodesic active contours for the segmentation of tubular structures
75 Citations2002Liana M. Lorigo, Olivier Faugeras +5 more
The theoretical foundations of the system, CURVES, are described and segmentation results compared against segmentation obtained interactively by a neurosurgeon are provided, as well as comparisons to manual segmentation.
Likelihood functions and confidence bounds for total-least-squares problems
71 Citations2002Oscar Nestares, David J. Fleet +1 more
The derivation of likelihood functions and confidence bounds for problems involving over-determined linear systems with noise in all measurements, often referred to as total-least-squares (TLS), are addressed.
Adaptive Bayesian recognition in tracking rigid objects
65 Citations2002Yuri Boykov, D.P. Huttenlocher
A framework for tracking rigid objects based on an adaptive Bayesian recognition technique that incorporates dependencies between object features and forms a natural feedback loop between the recognition method and the filter that helps to explain robustness.
A semi-automatic method for resolving occlusion in augmented reality
64 Citations2002Vincent Lepetit, Marie‐Odile Berger
This paper proposes a semi-automatic method for resolving occlusion in augmented reality which makes use of key-views, and takes into account the uncertainty on the computed interframe motion.
Surface landmark selection and matching in natural terrain
60 Citations2002Andrew Johnson
An algorithm for robust absolute position estimation in natural terrain based on landmarks extracted from dense 3-D surfaces that can incorporate constraints on position and attitude for efficient landmark matching and match small and dense scene surface patches to large and coarse model surfaces.
Probabilistic vs. geometric similarity measures for image retrieval
57 Citations2002Selim Aksoy, R.M. Haralick
A probabilistic approach is presented and two likelihood-based similarity measures for image retrieval are described that perform significantly better than geometric approaches like the nearest neighbor rule with city-block or Euclidean distances.
Transformed hidden Markov models: estimating mixture models of images and inferring spatial transformations in video sequences
55 Citations2002Nebojša Jojić, Nemanja Petrović +2 more
It is demonstrated that the THMM is capable of combining long term dependencies in video sequences with short term dependencies (such as short term image frame similarities and motion patterns) to better summarize and process a video sequence even in the presence of high levels of white or structured noise.
Multimodal speaker detection using error feedback dynamic Bayesian networks
53 Citations2002Vladimir Pavlović, A. Garg +2 more
This work forms a learning framework for DBNs based on error-feedback and statistical boosting theory and applies this framework to the problem of audio/visual speaker detection in an interactive kiosk environment using "off-the-shelf" visual and audio sensors.
Real-time 3D motion and structure of point features: a front-end system for vision-based control and interaction
51 Citations2000Hang Jin, Paolo Favaro +1 more
A system that consists of one camera connected to a personal computer that can select and track a number of high-contrast point features on a sequence of images, estimate their three-dimensional motion and position relative to an inertial reference frame, assuming rigidity, and handle occlusions that cause point-features to disappear as well as new features to appear is presented.
Catadioptric sensors that approximate wide-angle perspective projections
48 Citations2002R. Andrew Hicks, Růžena Bajcsy
Two families of reflective surfaces are presented that are capable of providing a wide field of view, and yet still approximate a perspective projection to a high degree, allowing for a wide-angle perspective view of a scene without processing the image in software.
Fluid structure and motion analysis from multi-spectrum 2D cloud image sequences
48 Citations2002Lin Zhou, Chandra Kambhamettu +1 more
A novel approach to estimate and analyze 3D fluid structure and motion of clouds from multi-spectrum 2D cloud image sequences by using a recursive algorithm which integrates local motion analysis with a set of global fluid constraints, defined according to the physical fluid dynamics.
A curve evolution approach to smoothing and segmentation using the Mumford-Shah functional
46 Citations2002Andy Tsai, Anthony Yezzi +1 more
This work approaches the classic Mumford-Shah problem from a curve evolution perspective, and lets a given family of curves define the boundaries between regions in an image within which the data are modeled by piecewise smooth functions plus noise.
Dynamic memory: architecture for real time integration of visual perception, camera action, and network communication
42 Citations2002T. Matsuyam, Shinsaku Hiura +3 more
A novel dynamic system architecture named Dynamic Memory Architecture, where perception, action, and communication modules share what is called the Dynamic Memory, which maintains not only temporal histories of state variables such as pan-tilt angles of the camera and the target object location but also their predicted values in the future.
Arbitrary view position and direction rendering for large-scale scenes
41 Citations2002Toru TAKAHASHI, Hiroshi Kawasaki +2 more
The basic theory of a new plenoptic function is described, the applicable areas of the theory and the characteristics of generated images are analyzed, and a complete working system using both indoor and outdoor scenes is demonstrated.
A linear algorithm for camera self-calibration, motion and structure recovery for multi-planar scenes from two perspective images
40 Citations2002Gang Xu, J. Terai +1 more
This paper shows that given two homography matrices for two planes in space, there is a linear algorithm for the rotation and translation between the two cameras, the focal lengths of theTwo cameras and the plane equations in the space.
Image-based re-rendering of faces for continuous pose and illumination directions
39 Citations2002A. Stoschek
A scheme for photorealistic re-rendered faces at arbitrary illumination and pose directions based on lineal combination of low-dimensional image representations and incorporate image morphing into the image synthesis process is presented.
Categorical representation and recognition of oscillatory motion patterns
39 Citations2002James W. Davis, Aaron Bobick +1 more
This work presents an approach to the representation and recognition of these oscillatory motions based on the categorical organization of a simple sinusoidal model having very specific and limited parameter values.
Tracking elongated structures using statistical snakes
37 Citations2002Ricardo Toledo, Xavier Orriols +4 more
A statistic snake that learns and tracks image features by means of statistic learning techniques and a sound statistical model is introduced to define a likelihood estimate of the grey-level local image profiles together with their local orientation to improve the convergence of snake deformation.
Pose estimation, model refinement, and enhanced visualization using video
36 Citations2002S.T. Hsu, Supun Samarasekera +2 more
An algorithm is developed where tracked features are used to predict the pose between frames and the predicted poses are refined by a coarse to fine process of aligning projected 3D model line segments to oriented image gradient energy pyramids.
Robust periodic motion and motion symmetry detection
36 Citations2002Ross Cutler, L.S. Davis
A robust technique for detecting nonstationary periodic motion from a moving and static camera and for discriminating motion symmetries (periodic motion classification), which applies to classifying running humans and canines.
A geometric approach to train support vector machines
32 Citations2002Ming–Hsuan Yang, Narendra Ahuja
Experimental results show that the proposed method to extract a small superset of support vectors, which are called guard vectors, to construct the optimal decision surface is more efficient than conventional methods using QPs and requires much less memory.
On measuring low-level saliency in photographic images
27 Citations2002Jiebo Luo, Amit Singhal
This work proposes an auto-scaled, amorphous neighborhood as the context model to obtain reliable measurements of relative saliency features and shows that the proposed model is capable of generating predicates more consistent with perceived saliency.
Visual servoing for automatic and uncalibrated needle placement for percutaneous procedures
27 Citations2000Nassir Navab, B. Bascle +3 more
This paper presents a new approach to image-based guidance of a needle or surgical tool during percutaneous procedures based on visual servoing that provides highly precise 3D-alignment of the tool with respect to an anatomic target.
A feature-based technique for joint, linear estimation of high-order image-to-mosaic transformations: application to mosaicing the curved human retina
23 Citations2002Ali Can, Charles V. Stewart +2 more
Methods are presented for increasing the coverage and accuracy of image mosaics constructed from multiple, uncalibrated, weak-perspective views of the human retina and a method to improve the accuracy of the pairwise matches as well as the joint estimation by refining the feature locations and by adding new features based on the transformation estimates themselves.
Distortion-invariant recognition via jittered queries
23 Citations2002Dennis DeCoste, Michael C. Burl
This paper presents a new approach for achieving distortion-invariant recognition and classification, where instead of querying with a single pattern, a more robust query is constructed, based on the family of patterns formed by distorting the test example.
A novel approach to depth ordering in monocular image sequences
22 Citations2002Lothar Bergen, Fernand Meyer
A detailed analysis of the behaviour of dense motion estimation techniques at object boundaries is presented which reveals the systematic nature of the motion estimation error and it is shown how the joint use of still image segmentation and robust regression can eliminate this error.
Retinal thickness measurements in optical coherence tomography using a Markov boundary model
21 Citations2002Dara D. Koozekanani, Kenneth K. Boyer +1 more
A robust, quantitatively accurate system for measuring retinal thickness in optical coherence tomography images, which has tested the system extensively and revealed that in more than 99% of the cases, the automatic and manual measurements differed by less than 25 /spl mu/m.
Hierarchical structure and nonrigid motion recovery from 2D monocular views
21 Citations2002Lin Zhou, Chandra Kambhamettu
A hierarchical method which integrates both local patch analysis and global shape descriptions is devised to solve the dual problem of structure and nonrigid motion recovery by using an elastic geometric model-extended superquadrics (ESQ).
Articulated-pose estimation using brightness- and depth-constancy constraints
21 Citations2002Michele Covell, A. Anitha Rahini +2 more
This paper addresses several important issues in the formation of the constraint equations, including updating the body rotation matrix without using a first-order matrix approximation and removing the coupling between the rotation and translation updates.
Fusion of color, shading and boundary information for factory pipe segmentation
21 Citations2000Bertrand Thirion, B. Bascle +2 more
This system performs pipe segmentation by fusing methods from physics-based vision, edge and texture analysis, probabilistic learning and the use of the graph-cut formalism.
A boundary extraction method based on Dual-T-Snakes and dynamic programming
21 Citations2002Gilson A. Giraldi, Edilberto Strauss +1 more
This paper addresses the limitations of dynamic programming techniques by reducing the region of interest (search space) through the use of the Dual-T-Snake approach, which inherits the capability of changing the topology and avoiding local minima from the Dual T-Snake and the global optimal properties of the dynamic programming.
Filling in scenes by propagating probabilities through layers and into appearance models
20 Citations2002Brendan J. Frey
A Bayesian network is constructed that describes the occlusion process and iterative probability propagation is used to approximately recover the identities and positions of the objects in the scene in time that is linear in K and L.
Recovering projection geometry: how a cheap camera can outperform an expensive stereo system
20 Citations2000M.M. Mischke, Nassir Navab
A comparative study for the recovery of the motion and therefore projection, geometry using five different hand-eye calibration methods proposed in the literature and concludes by shouting that ever, if the motion estimation is more accurate when using an external sensor, the projection geometry is better estimated by the integrated optical camera.
Optical EngineeringImproved motion stereo matching based on a modified dynamic programming
19 Citations2001Mikhail G. Mozerov
Agent-based moving object correspondence using differential discriminative diagnosis
19 Citations2002Mahesh Saptharishi, J.B. Hampshire +1 more
A novel method for temporally and spatially corresponding moving objects by automatically learning the relevance of the objects' appearance features to the task of discrimination by means of differential discriminative diagnosis.
Stereoscopic shading: integrating multi-frame shape cues in a variational framework
17 Citations2002Hang Jin, Anthony Yezzi +1 more
This work addresses the problem of integrating multi-frame stereo and shading cues within the framework of optimization in the infinite-dimensional space of piecewise smooth surfaces, and proposes an iterative optimization algorithm, which is implemented using ultra-narrowband level set methods.
Efficient query modification for image retrieval
16 Citations2002Geetika Aggarwal, S. Ghosal +1 more
This work proposes a novel methodology for efficient understanding of user perception from the query image itself, which saves the cost of repeated database search incurred in existing relevance feedback based approaches.
A region extraction method using multiple active contour models
14 Citations2002Toru Abe, Yoko Matsuzawa
A new method for extracting an object region in a complex scene image is proposed and a procedure for making multiple initial contours from a single initial curve is also proposed.
Structure from motion using points, lines, and intensities
13 Citations2002J. Oliensis, Michael Werman
It generalizes the Oliensis method for points to include lines and intensities as well and presents a fast factorization algorithm for estimating structure and motion simultaneously from points, lines, and or directly from the image intensities under full perspective.
Detecting people in cluttered indoor scenes
13 Citations2002Mi‐Suen Lee
A motion segmentation algorithm that makes use of temporal differencing to detect moving people in cluttered indoor scenes is presented, devised based on a couple of perceptual organization principles.
Are multifractal multipermuted multinomial measures good enough for unsupervised image segmentation?
13 Citations2002Lui Kam, Jacques Blanc-Talon
By extending multinomial measures, a new class of self-similar multifractal measures is developed for texture representation and their use within a supervised segmentation framework provides satisfactory results.
A geometric approach to blind deconvolution with application to shape from defocus
13 Citations2002Stefano Soatto, Paolo Favaro
Since the imaging process maps the continuum of three-dimensional space onto the discrete pixel grid, rather than discretizing the continuum, the structure of maps between (finite-and infinite-dimensional) Hilbert spaces is exploited and exploited in a functional singular value decomposition to obtain a regularized solution.
A robust and efficient motion segmentation based on orthogonal projection matrix of shape space
12 Citations2002N. Ichimura
A novel algorithm for motion segmentation that uses the fact that shape of an object with homogeneous motion is represented as 4 dimensional linear space is proposed and is robust for data with noise and outliers.
Region correspondence by global configuration matching and progressive Delaunay triangulation
12 Citations2002Jixin Ma, Narendra Ahuja
A novel algorithm for establishing region correspondences across images by first matching global region configuration and then propagating the matches locally constrained by Delaunay triangulation, which exploits a global configuration constraint, which has not been explicitly used in existing matching algorithms.
Object recognition for an intelligent room
12 Citations2002Richard J. Campbell, John Krumm
An algorithm that can be trained with only a few images of the object, that requires only two parameters to be set, and that runs at 0.7 Hz on a normal PC with a normal color camera is presented.
Multifeature object tracking using a model-free approach
11 Citations2002Hoa TT. Nguyen, Marcel Worring
A new model-free method for object tracking that is posed as a segmentation problem which is solved using the watershed algorithm and yields accurate results in the presence of object corners, image clutter and camera motion.
Improving correlation-based DEMs by image warping and facade correlation
11 Citations2002Christophe Vestri, Frédéric Devernay
A system which improves a digital elevation model (DEM) by reconstructs all the facades of the building and then, corrects the initial DEM by deleting the points of the roofs which pass over the boundaries defined by thefacades.
A Bayesian framework for radar shape-from-shading
10 Citations2002Adrian G. Borş, Edwin R. Hancock +1 more
A Bayesian approach to shape-from-shading (SFS) which is applied to terrain recovery in synthetic aperture radar (SAR) images and the surface normals are smoothed using robust statistics operators.
Color channels decorrelation by ICA transformation in the wavelet domain for color texture analysis and synthesis
10 Citations2002Yufeng Liang, Eero P. Simoncelli +1 more
A color model to cancel the dependency between color channels is developed, which enables us to separate spectral processing from, spatial processing and introduced Independent Component Analysis transformation in the wavelet domain to decorrelate the subband color joint statistics.
Solving the rotation-estimation problem by using the perspective three-point algorithm
10 Citations2002Toshio Moriya, Hideaki Takeda
A closed-form solution for the rotation-estimation problem is presented, by introducing the same algorithm used for solving the perspective three-point problem, by making some parameter exchanges that are essentially equivalent.
Multidimensional motion segmentation and identification
10 Citations2002Chunmei Lu, H. Liu +1 more
A method for high dimensional motion segmentation by using a two-step recursive least square algorithm, break points of system dynamics, at which a model switching must be performed are predicted and system identification techniques can be used to fit dynamic models.
Camera model selection based on geometric AIC
9 Citations2002Keisuke Kinoshita, L. Lindenbaum
The problem of selecting a camera model is addressed here using the Geometric AIC (Akaike Information Criterion) proposed by Kanatani, which considers both the residual of the data fitting to the model as well as the complexity of the model.
Corner guided curve matching and its application to scene reconstruction
8 Citations2002Ying Shan, Zhengyou Zhang
A curve matching algorithm that is guided by a set of matched corners that provides stronger capability of resolving matching ambiguity than the epipolar constraint, and is integrated into a relaxation scheme to reduce computational complexity and improve accuracy of curve matching.
Smooth region structure: folds, domes, bowls, ridges, valleys and slopes
8 Citations2002D. Sinclair
The structure of the isobrightness contours in 'smooth' regions of a segmented image may be used to quantify the variation in shading, using contour context rather that filter banks or a solution to the shape from shading problem to quality the form of a region's brightness function.
Histogram-based object recognition using shape-from-shading
8 Citations2002P.L. Worthington, Edwin R. Hancock
An experimental study of the problem of object recognition using surface attributes delivered by shape-from-shading using histogram-based representations reveals that recognition rates of 98% are achievable under controlled lighting conditions.
Multi-modality model-based registration in the cardiac domain
8 Citations2002Thomas O’Donnell, Shmuel Aharon +4 more
A software package, PROTEUS, is demonstrated, which is capable of registering CT and MR images and relies on segmented contours delineating the inner and outer borders of the left ventricle (LV) to perform the matching.
Detecting changes in 3-D shape using self-consistency
8 Citations2002Y.G. Leclerc, Q.-T. Luong +2 more
A novel image-matching measure based on Minimum Description Length (MDL) theory allows us to estimate the accuracy of individual elements of the 3-D model.
Active character recognition using "A*-like" algorithm
7 Citations2002Jaehwa Park, Venu Govindaraju
A method that uses an active heuristic function similar to the one used by A* search algorithm that adaptively determines the length of the feature vector as well as the features themselves used to classify an input pattern is presented.
A general scheme for training and optimization of the Grenander deformable template model
7 Citations2002Rune Vincents Fisker, Nette Schultz +2 more
A full and unified scheme for applying the general deformable template model proposed by Grenander et al., 1991 to a new problem with minimal manual interaction, beside supplying a training set, which can be done by a non-expert user.
CueVideo: a system for cross-modal search and browse of video databases
7 Citations2002Tanveer Syeda-Mahmood, S. Srinivasan +4 more
CueVideo, a system designed for the discovery and recognition of specific events called topics of discussion through advanced video summarization and cross-modal indexing, enables the recognition and indexing of topical events through cross-model search of audio and video content based on text and image queries respectively.
Conditioning analysis of missing data estimation for large sensor arrays
6 Citations2002Hairong Qi, W.E. Snyder
A consistency method with separable deblurring to estimate the missing data and converts an ill-posed restoration problem into a well-posed one by making few assumptions based on regularization theory.
Computing 3D object parts from similarities among object views
6 Citations2002Florin Cutzu
The following shape segmentation problem is addressed: find the part decomposition of a 3D object that accounts for an observed pattern of similarities among several of the object's views that represents the inverse, ill-posed version of the direct problem of computing perceptual similarities among object views when the object parts are known.
Towards reliable fusion of segmented surface descriptions
5 Citations2002D. Fischer, Peter Kohlhepp
This paper presents a novel solution for integrating range views into 3D geometry models, where sparse surface and relation attributes are fused directly, without relying on the original range data or a dense mesh of data points.
Multi-view 3D analysis with applications for augmented reality and enhanced video visualization
4 Citations2002Yanlin Guo, S.T. Hsu +3 more
Method for pose estimation and scene geometry recovery from extended sequences without prior knowledge of the scheme and applications for 3D imagery manipulation such as enhanced visualization for video and 3D insertion of synthetic objects in the imagery are presented.
Ill-posed problems in surface and surface shape recovery
3 Citations2002G. Kamberov, Gerda Kamberova
New theoretical results which have implications in answering one of the fundamental questions in computer vision: recognition of surfaces and surface shapes are presented.
An on-line handwriting recognition system using Fisher segmental matching and Hypotheses Propagation Network
2 Citations2002Jong Oh, Davi Geiger
An on-line handwriting recognition approach that integrates local bottom-up constructs with a global top-down measure into a modular recognition engine, which runs a variant of the topological sort algorithm of graph search.
…