http:^^www.cs.wisc.edu^computer-vision^pubs.html

This data set contains WWW-pages collected from computer science departments of various universities

The problem of how to efficiently display a polyhedral scene over a path
of viewpoints is cast as a problem of computing visual events along that path.
A visual event is a viewpoint that causes a change in the structure of
the image structure graph, a model's projected line drawing.
The information stored with a visual event is sufficient to update
a representation of the image structure graph.
Thus the visible lines of a scene can be displayed as viewpoint changes
by first precomputing and storing visual events, and then using those events
at display time to interactively update the image structure graph.
Display rates comparable to wire-frame display are achieved for large
polyhedral models.
<P>

The rim appearance representation is a new, viewer-centered, exact
representation of the occluding contour of polyhedra.
We present an algorithm based on the geometry of polyhedral self-occlusion
and on visual events for computing a representation of the exact appearance
of occluding contour edges.
The rim appearance representation, organized as a multi-level model of the
occluding contour, is used to constrain the viewpoints of
a three-dimensional model that can produce a set of detected
occluding-contour features.
Implementation results demonstrate that precomputed occluding-contour
information efficiently and tightly constrains the pose of a model while
consistently accounting for detected occluding-contour features.
</blockquote>


</UL>
<HR>
<P>
<H2><A NAME="snakes">Deformable Contours</A></H2>
<UL>

<LI><B><A NAME="pami94-lai">
     Deformable Contours: Modeling and Extraction</A></B><BR>
     K. F. Lai and R. T. Chin,
     <CITE>IEEE Trans. Pattern Analysis and Machine Intell.</CITE> <B>17</B>,
     1995, 1084-1090.  
     (<!WA80><!WA80><!WA80><A HREF="ftp://ftp.cs.wisc.edu/computer-vision/pami94-lai.ps">postscript</A>
     or <!WA81><!WA81><!WA81><A HREF="ftp://ftp.cs.wisc.edu/computer-vision/pami94-lai.ps.gz">350K gzip'ed postscript</A>)<BR>
     (An earlier version appeared in
     <CITE>Proc. Computer Vision and Pattern Recognition Conf.</CITE>,
     1994, 601-608
     (<!WA82><!WA82><!WA82><A HREF="ftp://ftp.cs.wisc.edu/computer-vision/cvpr94-lai.ps">postscript</A>
     or <!WA83><!WA83><!WA83><A HREF="ftp://ftp.cs.wisc.edu/computer-vision/cvpr94-lai.ps.gz">220K gzip'ed postscript</A>).)
<P>
<blockquote>
This paper considers the problem of modeling and extracting arbitrary deformable 
contours from noisy images. We propose a global contour model based on a stable 
and regenerative shape matrix, which is invariant and unique under rigid 
motions. Combined with Markov random field to model local deformations, this 
yields prior distribution that exerts influence over a global model while 
allowing for deformations. We then cast the problem of extraction into posterior 
estimation and show its equivalence to energy minimization of a generalized 
active contour model. We discuss pertinent issues in shape training, energy 
minimization, line search strategies, minimax regularization and initialization 
by generalized Hough transform. Finally, we present experimental results and 
compare its performance to rigid template matching.
</blockquote>


<LI> <B><A NAME="icarcv94-lai">
     On Classifying Deformable Contours Using the Generalized
     Active Contour Model</A></B><BR>
     K. F. Lai and R. T. Chin,
     <CITE>Proc. Int. Conf. Automation, Robotics and Computer Vision</CITE>,  
     Singapore, 1994.  
     (<!WA84><!WA84><!WA84><A HREF="ftp://ftp.cs.wisc.edu/computer-vision/icarcv94-lai.ps">postscript</A>
     or <!WA85><!WA85><!WA85><A HREF="ftp://ftp.cs.wisc.edu/computer-vision/icarcv94-lai.ps.gz">150K gzip'ed postscript</A>)<P>
<blockquote>
Recently, we proposed the generalized active contour model (g-snake) to model 
and extract deformable contours from noisy images. This paper demonstrates the 
usefulness of g-snake in classifying among several candidate deformable 
contours. The g-snake is suitable for this task because its shape 
representation is unique, affine invariant and possesses
metric properties. We derive the 
optimal classification test and show that this requires marginalization of the 
distribution. However, as the summation is peaked around the posterior estimate 
in most practical applications, only small regions need to be considered.  
Finally, we performed extensive experimentations and report significant 
improvement over matched template in handwritten numeral recognition.
</blockquote>


<LI> <B><A NAME="thesis-lai">
     Deformable Contours: Modeling, Extraction,
     Detection and Classification</A></B><BR>
     Ph.D. Dissertation, K. F. Lai,
     Electrical and Computer Engineering Department,
     August 1994.
     (<!WA86><!WA86><!WA86><A HREF="ftp://ftp.cs.wisc.edu/computer-vision/thesis-lai.ps">postscript</A>
     or <!WA87><!WA87><!WA87><A HREF="ftp://ftp.cs.wisc.edu/computer-vision/thesis-lai.ps.gz">820K gzip'ed postscript</A>)<P>
<blockquote>
This thesis presents an integrated approach in modeling, extracting, detecting 
and classifying deformable contours directly from noisy images. We begin by 
conducting a case study on regularization, formulation and initialization of
the active contour models (snakes). Using minimax principle, we derive a 
regularization criterion whereby the values can be automatically and implicitly 
determined along the contour. Furthermore, we formulate a set of energy 
functionals which yield snakes that contain Hough transform as a special case. 
Subsequently, we consider the problem of modeling and extracting arbitrary 
deformable contours from noisy images. We combine a stable, invariant and
unique contour model with Markov random field to yield prior
distribution that exerts 
influence over an arbitrary global model while allowing for deformation. Under 
the Bayesian framework, contour extraction turns into posterior estimation, 
which is in turn equivalent to energy minimization in a generalized active 
contour model. Finally, we integrate these lower level visual tasks with
pattern recognition processes of detection and classification. Based on the 
Nearman-Pearson lemma, we derive the optimal detection and classification
tests.  As the summation is peaked in most practical applications,
only small regions 
need to be considered in marginalizing the distribution. The validity of our 
formulation have been confirmed by extensive and rigorous experimentations.
</blockquote>


<LI> <B><A NAME="accv93-lai">
     On Regularization, Formulation and Initialization of
     Active Contour Models (Snakes)</A></B><BR>
     K. F. Lai and R. T. Chin,
     <CITE>Proc. 1st Asian Conf. on Computer Vision</CITE>,  
     1993, 542-545.  
     (<!WA88><!WA88><!WA88><A HREF="ftp://ftp.cs.wisc.edu/computer-vision/accv93-lai.ps">postscript</A>
     or <!WA89><!WA89><!WA89><A HREF="ftp://ftp.cs.wisc.edu/computer-vision/accv93-lai.ps.gz">150K gzip'ed postscript</A>)<P>
<blockquote>
In snake formulation, large regularization enhances the robustness against noise 
and incomplete data, while small values increase the accuracy in capturing 
boundary variations. We present a local minimax criterion which automatically 
determines the optimal regularization at every locations along the boundary with 
no added computation cost. We also modify existing energy formulations to repair 
deficiencies in internal energy and improve performance in external energy. This 
yields snakes that contain Hough transform as a special case. We can therefore 
initialize the snake efficiently and reliably using Hough transform.
</blockquote>
</UL>
<HR>


<P>
<H2><A NAME="visualization">Visualization</A></H2>
<UL>

<LI><B><A NAME="thesis-hibbard">
     Visualizing Scientific Computations: A System based on
     Lattice-Structured Data and Display Models</A></B><BR>
     W. L. Hibbard, Ph.D. Dissertation,
     Computer Sciences Department Technical Report 1226,
     University of Wisconsin-Madison, 1995.
     (<!WA90><!WA90><!WA90><A HREF="ftp://iris.ssec.wisc.edu/pub/lattice">600K compress'ed postscript</A>)<P>
<blockquote>
In this thesis we develop a system that makes scientific
computations visible and enables physical scientists to perform visual
experiments with their computations.  Our approach is unique in the way
it integrates visualization with a scientific programming language.  Data
objects of any user-defined data type can be displayed, and can be
displayed in any way that satisfies broad analytic conditions, without
requiring graphics expertise from the user.  Furthermore, the system is
highly interactive.
<P>
In order to achieve generality in our architecture, we first analyze
the nature of scientific data and displays, and the visualization mappings
between them.  Scientific data and displays are usually approximations to
mathematical objects (i.e., variables, vectors and functions) and this
provides a natural way to define a mathematical lattice structure on data
models and display models.  Lattice-structured models provide a basis for
integrating certain forms of scientific metadata into the computational and
display semantics of data, and also provide a rigorous interpretation of
certain expressiveness conditions on the visualization mapping from data
to displays.  Visualization mappings satisfying these expressiveness
conditions are lattice isomorphisms.  Applied to the data types of a
scientific programming language, this implies that visualization mappings
from data aggregates to display aggregates can always be decomposed
into mappings of data primitives to display primitives.
<P>
These results provide very flexible data and display models, and
provide the basis for flexible and easy-to-use visualization of data objects
occurring in scientific computations.
</blockquote>


<LI> <B><A NAME="computer94-hibbard">
     Interactive Visualization of Earth and Space Science Computations</A></B><BR>
     W. L. Hibbard, B. E. Paul, A. L. Battaiola, D. A. Santek,
     M-F. Voidrot-Martinez, and C. R. Dyer,
     <CITE>Computer</CITE><B> 27</B>, No. 7, July 1994, 65-72.
     (<!WA91><!WA91><!WA91><A HREF="ftp://ftp.cs.wisc.edu/computer-vision/computer94-hibbard.ps">postscript</A>
     or <!WA92><!WA92><!WA92><A HREF="ftp://ftp.cs.wisc.edu/computer-vision/computer94-hibbard.ps.gz">20K gzip'ed postscript</A>)<P>
<blockquote>
We describe techniques that enable Earth and space scientists
to interactively visualize and experiment with their computations.
Numerical simulations of the Earth's atmosphere and oceans generate
large and complex data sets, which we visualize in a highly interactive
virtual Earth environment.  We use data compression and distributed
computing to maximize the size of simulations that can be explored,
and a user interface tuned to the needs of environmental modelers.
For the broader class of computations used by scientists we have
developed more general techniques, integrating visualization with an
environment for developing and executing algorithms.  The key is
providing a flexible data model that lets users define data types
appropriate for their algorithms, and also providing a display model
that lets users visualize those data types without placing a substantial
burden of graphics knowledge on them.
</blockquote>


<LI> <B><A NAME="vis94-hibbard">
     A Lattice Model for Data Display</A></B><BR>
     W. L. Hibbard, C. R. Dyer, and B. E. Paul,
     <CITE>Proc. Visualization '94</CITE>, 1994, 310-317.
     (<!WA93><!WA93><!WA93><A HREF="ftp://ftp.cs.wisc.edu/computer-vision/vis94-hibbard.ps">postscript</A>
     or <!WA94><!WA94><!WA94><A HREF="ftp://ftp.cs.wisc.edu/computer-vision/vis94-hibbard.ps.gz">60K gzip'ed postscript</A>)<P>
<blockquote>
In order to develop a foundation for visualization, we develop
lattice models for data objects and displays that focus on the fact that
data objects are approximations to mathematical objects and real
displays are approximations to ideal displays.  These lattice models
give us a way to quantize the information content of data and displays
and to define conditions on the visualization mappings from data to
displays.  Mappings satisfy these conditions if and only if they are
lattice isomorphisms.  We show how to apply this result to scientific
data and display models, and discuss how it might be applied to
recursively defined data types appropriate for complex information
processing.
</blockquote>


<LI> <B><A NAME="vis92-hibbard">
     Display of Scientific Data Structures for Algorithm Visualization</A></B><BR>
     W. Hibbard, C. R. Dyer, and B. Paul,
     <CITE>Proc. Visualization '92</CITE>, 1992, 139-146.
     (<!WA95><!WA95><!WA95><A HREF="ftp://ftp.cs.wisc.edu/computer-vision/vis92-hibbard.ps">postscript</A>
     or <!WA96><!WA96><!WA96><A HREF="ftp://ftp.cs.wisc.edu/computer-vision/vis92-hibbard.ps.gz">60K gzip'ed postscript</A>)<P>
<blockquote>
We present a technique for defining graphical depictions for all
the data types defined in an algorithm.  The ability to display arbitrary
combinations of an algorithm's data objects in a common frame of
reference, coupled with interactive control of algorithm execution,
provides a powerful way to understand algorithm behavior.  Type
definitions are constrained so that all primitive values occurring in data
objects are assigned scalar types.  A graphical display, including user
interaction with the display, is modeled by a special data type.
Mappings from the scalar types into the display model type provide a
simple user interface for controlling how all data types are depicted,
without the need for type-specific graphics logic.
</blockquote>

</UL>


</BODY>
</HTML>