Results 1  10
of
18
Good features to track
, 1994
"... No featurebased vision system can work unless good features can be identified and tracked from frame to frame. Although tracking itself is by and large a solved problem, selecting features that can be tracked well and correspond to physical points in the world is still hard. We propose a feature se ..."
Abstract

Cited by 1893 (13 self)
 Add to MetaCart
(Show Context)
No featurebased vision system can work unless good features can be identified and tracked from frame to frame. Although tracking itself is by and large a solved problem, selecting features that can be tracked well and correspond to physical points in the world is still hard. We propose a feature selection criterion that is optimal by construction because it is based on how the tracker works, and a feature monitoring method that can detect occlusions, disocclusions, and features that do not correspond to points in the world. These methods are based on a new tracking algorithm that extends previous NewtonRaphson style search methods to work under affine image transformations. We test performance with several simulations and experiments.
Robust object recognition with cortexlike mechanisms
 IEEE Trans. Pattern Analysis and Machine Intelligence
, 2007
"... Abstract—We introduce a new general framework for the recognition of complex visual scenes, which is motivated by biology: We describe a hierarchical system that closely follows the organization of visual cortex and builds an increasingly complex and invariant feature representation by alternating b ..."
Abstract

Cited by 335 (43 self)
 Add to MetaCart
(Show Context)
Abstract—We introduce a new general framework for the recognition of complex visual scenes, which is motivated by biology: We describe a hierarchical system that closely follows the organization of visual cortex and builds an increasingly complex and invariant feature representation by alternating between a template matching and a maximum pooling operation. We demonstrate the strength of the approach on a range of recognition tasks: From invariant single object recognition in clutter to multiclass categorization problems and complex scene understanding tasks that rely on the recognition of both shapebased as well as texturebased objects. Given the biological constraints that the system had to satisfy, the approach performs surprisingly well: It has the capability of learning from only a few training examples and competes with stateoftheart systems. We also discuss the existence of a universal, redundant dictionary of features that could handle the recognition of most object categories. In addition to its relevance for computer vision, the success of this approach suggests a plausibility proof for a class of feedforward models of object recognition in cortex.
Scaling theorems for zero crossings
 IEEE Transactions on Pattern Analysis and Machine Intelligence
, 1986
"... We prove that the scale map of the zerocrossings of atmost all signals filtered by the second derivative of a gaussian of variable size determines the signal uniquely, up to a constant scaling and a harmonic function. Our proof provides a method for reconstructing almost all signals from knowledge ..."
Abstract

Cited by 168 (4 self)
 Add to MetaCart
We prove that the scale map of the zerocrossings of atmost all signals filtered by the second derivative of a gaussian of variable size determines the signal uniquely, up to a constant scaling and a harmonic function. Our proof provides a method for reconstructing almost all signals from knowledge of how the zerocrossing contours of the signal, fitered by a gaussian filter, change with the size of the filter. The proof assumes that the filtered signal can be represented as a polynomial of finite, albeit possibly very high, order. An argument suggests that this restriction is not essential. Stability of the reconstruction scheme is briefly discussed. The result applies to zero and levelcrossings of linear differential operators of gaussian filters. The theorem is extended to two dimensions, that is to images. These results are reminiscent of Logan's theorem. They imply that extrema of derivatives at different scales are a complete representation of a signal.
A Tensor Framework for Multidimensional Signal Processing
 Linkoping University, Sweden
, 1994
"... ii About the cover The figure on the cover shows a visualization of a symmetric tensor in three dimensions, G = λ1ê1ê T 1 + λ2ê2ê T 2 + λ3ê3ê T 3 The object in the figure is the sum of a spear, a plate and a sphere. The spear describes the principal direction of the tensor λ1ê1ê T 1, where the lengt ..."
Abstract

Cited by 59 (8 self)
 Add to MetaCart
ii About the cover The figure on the cover shows a visualization of a symmetric tensor in three dimensions, G = λ1ê1ê T 1 + λ2ê2ê T 2 + λ3ê3ê T 3 The object in the figure is the sum of a spear, a plate and a sphere. The spear describes the principal direction of the tensor λ1ê1ê T 1, where the length is proportional to the largest eigenvalue, λ1. The plate describes the plane spanned by the eigenvectors corresponding to the two largest eigenvalues, λ2(ê1ê T 1 + ê2ê T 2). The sphere, with a radius proportional to the smallest eigenvalue, shows how isotropic the tensor is, λ3(ê1ê T 1 + ê2ê T 2 + ê3ê T 3). The visualization is done using AVS [WWW94]. I am very grateful to Johan Wiklund for implementing the tensor viewer module used. This thesis deals with filtering of multidimensional signals. A large part of the thesis is devoted to a novel filtering method termed “Normalized convolution”. The method performs local expansion of a signal in a chosen filter basis which
Scalespace Properties of the Multiscale Morphological DilationErosion
 IEEE TRANS. ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
, 1996
"... A multiscale morphological dilationerosion smoothing operation and its associated scalespace expansion for multidimensional signals are proposed. Properties of this smoothing operation are developed and, in particular a scalespace monotonic property for signal extrema is demonstrated. Scalespace ..."
Abstract

Cited by 58 (2 self)
 Add to MetaCart
A multiscale morphological dilationerosion smoothing operation and its associated scalespace expansion for multidimensional signals are proposed. Properties of this smoothing operation are developed and, in particular a scalespace monotonic property for signal extrema is demonstrated. Scalespace fingerprints from this approach have advantages over Gaussian scalespace fingerprints in that they: are defined for negative values of the scale parameter; have
Subband Transforms
, 1990
"... this paper, the boxes H i #!# indicate circular convolution of a #nite input image of size N with a #lter with impulse response h i #n# and Fourier transform ..."
Abstract

Cited by 34 (8 self)
 Add to MetaCart
this paper, the boxes H i #!# indicate circular convolution of a #nite input image of size N with a #lter with impulse response h i #n# and Fourier transform
Adaptive Multidimensional Filtering
 LINKÖPING UNIVERSITY, SWEDEN
, 1992
"... This thesis contains a presentation and an analysis of adaptive filtering strategies for multidimensional data. The size, shape and orientation of the filter are signal controlled and thus adapted locally to each neighbourhood according to a predefined model. The filter is constructed as a linear we ..."
Abstract

Cited by 31 (1 self)
 Add to MetaCart
This thesis contains a presentation and an analysis of adaptive filtering strategies for multidimensional data. The size, shape and orientation of the filter are signal controlled and thus adapted locally to each neighbourhood according to a predefined model. The filter is constructed as a linear weighting of fixed oriented bandpass filters having the same shape but different orientations. The adaptive filtering methods have been tested on both real data and synthesized test data in 2D, e.g. still images, 3D, e.g. image sequences or volumes, with good results. In 4D, e.g. volume sequences, the algorithm is given in its mathematical form. The weighting coefficients are given by the inner products of a tensor representing the local structure of the data and the tensors representing the orientation of the filters. The procedure and filter design in estimating the representation tensor are described. In 2D, the tensor contains information about the local energy, the optimal orientation and a certainty of the orientation. In 3D, the information in the tensor is the energy, the normal to the best fitting local plane and the tangent to the best fitting line, and certainties of these orientations. In the case of time sequences, a quantitative comparison of the proposed method and other (optical flow) algorithms is presented. The estimation of control information is made in different scales. There are two main reasons for this. A single filter has a particular limited pass band which may or may not be tuned to the different sized objects to describe. Second, size or scale is a descriptive feature in its own right. All of this requires the integration of measurements from different scales. The increasing interest in wavelet theory supports the idea that a multiresolution approach is necessary. Hence the resulting adaptive filter will adapt also in size and to different orientations in different scales.
Reconstruction of two dimensional signals from level crossings
 Proc. IEEE
, 1990
"... Recent results indicate the reconstruction of twodimensional signals from crossings of one level requires, in theory and practice, extreme accuracy in positions of the samples. The representation of signals with onelevel crossings can be viewed as a tradeoff between bandwidth and dynamic range, i ..."
Abstract

Cited by 9 (1 self)
 Add to MetaCart
Recent results indicate the reconstruction of twodimensional signals from crossings of one level requires, in theory and practice, extreme accuracy in positions of the samples. The representation of signals with onelevel crossings can be viewed as a tradeoff between bandwidth and dynamic range, in the sense that if the available bandwidth is sufficient to preserve the level crossings accurately, then the dynamic range requirements are significantly reduced. On the other hand, representation of signals via their samples at the Nyquist rate can be considered as requiring relatively small bandwidth and large dynamic range. This is because, at least in theory, amplitude information at prespecified points are needed, to infinite precision. Sampling and reconstruction schemes are derived whose characteristics lie between these two extremes. First, an overview of existing results in zero crossing representation is presented, and next a number of new results on sampling schemes for reconstruction from multiplelevel threshold crossing are developed. The quantization characteristics of these sampling schemes appear to lie between those of Nyquist sampling and onelevel crossing representations, thus bridging the gap between explicit Nyquist sampling, and implicit onelevel crossing sampling strategies. I.
Noise Reduction With Multiscale Edge Representation And Perceptual Criteria
 in Proceedings of IEEESP International Symposium on TimeFrequency and TimeScale Analysis
, 1992
"... The wavelet multiscale edge representation of signals developed by Mallat and Zhong provides a new tool for signal and image processing. We built up a tree structure of wavelettransform(WT) maxima and developed metrics for analyzing the WT maxima tree. These metrics fall into two classes correspond ..."
Abstract

Cited by 8 (1 self)
 Add to MetaCart
(Show Context)
The wavelet multiscale edge representation of signals developed by Mallat and Zhong provides a new tool for signal and image processing. We built up a tree structure of wavelettransform(WT) maxima and developed metrics for analyzing the WT maxima tree. These metrics fall into two classes corresponding to two perceptual criteria, scaling and spatial stabilities, for discriminating features from background noise. Identified noisy branches are trimmed off the WT maxima tree. This technique of noise reduction preserves edges well while suppressing noise. We present experimental results of processing simulated and medical images with this technique. 1. INTRODUCTION It has been wellknown that the human visual system (HVS) performs "multichannel decompositions"[1] on input visual signals. This is done with retinal receptive fields of different sizes. There is physiological evidence that these receptive fields act like edge detectors of different sizes and with different spatial tunings. The...
Segmentation and Image Analysis of Abnormal Lungs at CT: Current Approaches, Challenges, and
, 1056
"... The computerbased process of identifying the boundaries of lung from surrounding thoracic tissue on computed tomographic (CT) images, which is called segmentation, is a vital first step in radiologic pulmonary image analysis. Many algorithms and software platforms provide image segmentation routin ..."
Abstract
 Add to MetaCart
(Show Context)
The computerbased process of identifying the boundaries of lung from surrounding thoracic tissue on computed tomographic (CT) images, which is called segmentation, is a vital first step in radiologic pulmonary image analysis. Many algorithms and software platforms provide image segmentation routines for quantification of lung abnormalities; however, nearly all of the current image segmentation approaches apply well only if the lungs exhibit minimal or no pathologic conditions. When moderate to high amounts of disease or abnormalities with a challenging shape or appearance exist in the lungs, computeraided detection systems may be highly likely to fail to depict those abnormal regions because of inaccurate segmentation methods. In particular, abnormalities such as pleural effusions, consolidations, and masses often cause inaccurate lung segmentation, which greatly limits the use of image processing methods in clinical and research contexts. In