Abstract Human-Computer Interaction in Map Revision Systems (2009)
Jun Zhou, Walter F. Bischof, Terry Caelli
Cartographic map revision cannot be automated completely because, for legal reasons, a human operator is ultimately responsible for all revisions. We present a human-centered map revision system in...
Terry Caelli, Walter F. Bischof
Machine learning has been applied to many problems related to scene interpretation. It has become clear from these studies that it is important to develop or choose learning proce-dures appropriate...
Knowledge Transfer in Semi-automatic Image Interpretation (2008)
Jun Zhou, Li Cheng, Terry Caelli, Walter F. Bischof
Abstract. Semi-automatic image interpretation systems utilize interactions between users and computers to adapt and update interpretation algorithms. We have studied the influence of human inputs on...
An Online Discriminative Approach to Background Subtraction (2008)
Li Cheng, Shaojun Wang, Dale Schuurmans, Terry Caelli
We present a simple, principled approach to detecting foreground objects in video sequences in real-time. Our method is based on an on-line discriminative learning technique that is able to cope with...
Approximating the problem, not the solution: an alternative view of point set matching (2008)
Tibério S. Caetano, Terry Caelli
Abstract. This work discusses the issue of approximation in point set matching problems. In general, one may have two classes of approximations when tackling a matching problem: a representational...
Discovering Prediction Model for Environmental Distribution Maps (2008)
Ke Zhang, Huidong Jin, Nianjun Liu, Rob Lesslie, Lei Wang, Zhouyu Fu, ...
Abstract. Currently environmental distribution maps, such as for soil fertility, rainfall and foliage, are widely used in the natural resource management and policy making. One typical example is to...
Parallel Techniques for Rule-Based Scene Interpretation (2008)
Walter F. Bischof, Terry Caelli
Abstract. We consider a parallel, rule-based approach for learning and recognition of pattern and objects in scenes. Classification rules for pattern fragments are learned with objects presented in...
Knowledge Transfer in Semi-automatic Image Interpretation (2008)
Jun Zhou, Li Cheng, Terry Caelli, Walter F. Bischof
Abstract. Semi-automatic image interpretation systems utilize interactions between users and computers to adapt and update interpretation algorithms. We have studied the influence of human inputs on...
Li Cheng, Shaojun Wang, Dale Schuurmans, Terry Caelli
We present two new algorithms for online learning in reproducing kernel Hilbert spaces. Our first algorithm, ILK (implicit online learning with kernels), employs a new, implicit update technique that...
Learning Relational Structures for 2D Pattern and 3D Object Recognition (2007)
Adrian R. Pearce, Terry Caelli, Walter F. Bischof
: We present and comparethreenewtechniques for Learning Relational Structures (RS) as they occur in 2D pattern and 3D object recognition. The threetechniques, Evidence-Based Systems (EBS),...
Adaptive Curvature-Based Topography for Learning Symbolic Descriptions of Terrain Maps (2007)
Adrian R. Pearce, Terry Caelli, Simon Goss
. We present an adaptive curvature scale space technique for extracting symbolic topographical descriptions from image data suchas that of three dimensional digital terrain maps where specific image...
Rulegraphs for Pattern Recognition (2007)
Adrian Pearce, Terry Caelli, Walter F. Bischof
We present and compare two new techniques for Learning Relational Structures (RS) as they occur in 2D pattern and 3D object recognition. The two techniques, Evidence-Based Systems (EBS) and...
On the Efficiency of Learning in Spatial Domains and Relational Evidence Theory. (2007)
this paper two different approaches to evidential learning are investigated in how they apply to generalizing within spatial domains. We present a systematic evaluation of learning to identify...
Efficient Spatial and Temporal Learning Procedures and Relational Evidence Theory (2007)
Adrian Pearce, Terry Caelli, Walter F. Bischof
We present a relational and evidence-based approach to building systems which can learn various identification, location and planning tasks in spatial and temporal domains. This machine learning...
Adrian R. Pearce, Terry Caelli
s are generated by extracting relationships between pattern segments Pen trajectories are first segmented into line-based descriptions using a hierarchical multi-scale polygonal approximation method....
Skeletonizing Topographical Regions for Navigational Path Planning (2007)
Adrian R. Pearce, Terry Caelli, Sabrina Sestito, Simon Goss, Mario Selvestrel, Graeme Murray
This report investigates the application of two Computer Vision techniques for characterizing critical regions in digital terrain maps: Skeletonization and Topographical Region Detection. The...
Entropy-based representation of image information (2007)
Loss of information in images undergoing fine-to-coarse transformations is analysed by using an approach based on the theory of irreversible processes. In the case of grey level images, entropy...
changes should be addressed to MIT Press Journals, Five Cambridge (2007)
Individuals $30.00, Institutions $125.00. Canadians add additional 7 % GST. Prices subject to change without notice. Subscribers are licensed to use journal articles in a variety of ways, limited...
Learning Relational Structures for 2D Pattern and 3D Object Recognition (2007)
Adrian R. Pearce, Terry Caelli, Walter F. Bischof
Over the past fifty years, many different techniques have been developed for recognizing 2D patterns and 3D objects invariant to different types of geometric transformations, contextual conditions...
Graphical models and point pattern matching (2006)
Tibério S. Caetano, Terry Caelli, Dale Schuurmans
Abstract—This paper describes a novel solution to the rigid point pattern matching problem in Euclidean spaces of any dimension. Although we assume rigid motion, jitter is allowed. We present a...
‡Instituto de Informática Universidade Federal do Rio Grande do Sul (2004)
Tibério S. Caetano, Terry Caelli, Tibério S. Caetano, Terry Caelli
This paper explores a formulation for attributed graph matching as an inference problem over a hidden Markov Random Field. We approximate the fully connected model with simpler models in which...
Understanding human-computer interactions in map revision (2004)
Jun Zhou, Walter F. Bischof, Terry Caelli
Abstract. Tracking, parsing and modeling human-computer interactions to edit, revise documents is difficult but necessary if we are to develop automated technologies that will aid or replace humans....
Universidade Federal do Rio Grande do Sul (2004)
Tibério S. Caetano, Terry Caelli, Tibério S. Caetano, Terry Caelli
Algorithms for point matching using different distance metrics by
Graphical models for graph matching: approximate models and optimal algorithms (2004)
Comparing scene, pattern or object models to structures in images or determining the correspondence between two point sets are examples of attributed graph matching. In this paper we show how such...
UNIVERSIDADE FEDERAL DO RIO GRANDE DO SUL (2004)
Programa De, Tibério Silva Caetano, Prof Dr, Terry Caelli, Caetano Tibério Silva, ...
First of all, I thank my supervisor Dante Augusto Couto Barone and my co-supervisor
An optimal probabilistic graphical model for point set matching (2004)
Tibério S. Caetano, Terry Caelli
Abstract. We present a probabilistic graphical model for point set matching. By using a result about the redundancy of the pairwise distances in a point set, we represent the binary relations over a...
A comparison of neural and graphical models for syntactic and structural pattern recognition (2003)
Terry Caelli, Walter F. Bischof
Recent developments in the theory and uses of Bayesian Networks in pattern recognition and image understanding (PRIU) raise questions about the relationships between Bayesian compared to non-Bayesian...
Ajit Paul Singh, Wolfgang Pauli, Ajit Paul Singh, Russell Greiner, Peter Hooper, Terry Caelli
of this thesis and to lend or sell such copies for private, scholarly or scientific research purposes only. The author reserves all other publication and other rights in association with the...
Improved estimation of hidden Markov model parameters from multiple observation sequences (2002)
Davis, Richard I. A., Lovell, Brian C., Caelli, Terry
The huge popularity of Hidden Markov models in pattern recognition is due to the ability to 'learn' model parameters from an observation sequence through Baum-Welch and other re-estimation...
Improved estimation of hidden Markov model parameters from multiple observation sequences (2002)
Davis, Richard I. A., Lovell, Brian C., Caelli, Terry
The huge popularity of Hidden Markov models in pattern recognition is due to the ability to 'learn' model parameters from an observation sequence through Baum-Welch and other re-estimation...
Generalized spatio-chromatic diffusion (2002)
In this paper, a framework for diffusion of color images is presented. The method is based on the theory of thermodynamics of irreversible transforma-tions, which provides a suitable basis for...
Inexact Multisubgraph matching using Graph Eigenspace and Clustering Models (2002)
In this paper we show how inexact multisubgraph matching can be solved using methods based on the projections of vertices (and their connections) into the eigenspaces of graphs - and associated...
Generalized Spatio-chromatic Diffusion (2002)
Giuseppe Boccignone, Mario Ferraro, Terry Caelli
In this paper, a framework for di#usion of color images is presented. The method is based on the theory of thermodynamics of irreversible transformations, which provides a suitable basis for...
Generalized spatio-chromatic diffusion (2002)
AbstractÐIn this paper, a framework for diffusion of color images is presented. The method is based on the theory of thermodynamics of irreversible transformations which provides a suitable basis...
Diagnostic tools for evaluating hmm components (2001)
Brendan Mccane, Brendan Mccane, Terry Caelli, Terry Caelli
Although there are known algorithms for predicting observation and state sequences from HMM models there is little discussion on how to determine the contributions of the different types of HMM...
Encoding visual information using anisotropic transformations (2001)
The evolution of information in images undergoing fine-to-coarse anisotropic transformations is analyzed by using an approach based on the theory of ir-reversible transformations. In particular, we...
Encoding visual information using anisotropic transformations (2001)
AbstractÐThe evolution of information in images undergoing fine-to-coarse anisotropic transformations is analyzed by using an approach based on the theory of irreversible transformations. In...
Learning spatio-temporal relational structures (2001)
Walter F. Bischof, Terry Caelli
W e introduce a rule-based approach for learning and recognition of complex actions in terms of spatio-temporal attributes of primitive event sequences. During learning, spatio-temporal decision...
On the representation of image structures via scale space entropy conditions (1999)
AbstractÐThis paper deals with a novel way for representing and computing image features encapsulated within different regions of scale-space. Employing a thermodynamical model for scale-space...
On learning spatio-temporal relational structures in two different domains (1998)
Adrian R. Pearce, Terry Caelli, Simon Goss
Abstract. In this paper we consider the types of representations and learning procedures required to construct rules which can adequately describe relational information as it occurs in...
Andrew Mccabe Terry, Terry Caelli, Geoff West, Adam Reeves
In this paper we develop a technique for encoding the variation of color over space using properties of the complex image Fourier transform where the image is defined by a complex number encoding, at...
A concurrent, hierarchical approach to symbolic dynamic scene interpretation (1996)
Sandy Dance, Terry Caelli, Zhi-qiang Liu
1 Traditional methods for image scene interpretation and understanding are based mainly on such single threaded procedural paradigms as hypothesize-and-test or syntactic parsing. As a result, these...
CLARET: A new Relational Learning Algorithm for Interpretation in Spatial Domains. (1996)
Adrian Pearce, Terry Caelli, Walter Bischof
A new learning algorithm: Consolidated Learning Algorithm based on Relational Evidence Theory (CLARET) is presented, whichintegrates a machine learning methods with graph matching techniques. A...
Learning to Recognise 3D Objects from 2D Views (1995)
Brendan Mccane, Terry Caelli, Olivier De Vel, North Queensland
In this paper we further explore the use of machine learning (ML) for the recognition of 3D objects in isolation or embedded in scenes. Of particular interest is the use of a recent ML technique...
Multi-scale Adaptive Segmentation using Edge and Region Based Attributes (1995)
Brendan Mccane, Terry Caelli, North Queensland
We present an adaptive multi-scale algorithm using edge and region information for segmenting intensity images into closed regions. The need for segmentation is determined by region statistics and...
Learning Relational Structures: Applications in Computer Vision (1994)
Adrian R. Pearce, Terry Caelli, Walter F. Bischof
We present and compare two new techniques for Learning Relational Structures (RS) as they occur in 2D pattern and 3D object recognition. These techniques, Evidence-Based Networks (EBS-NNet) and...
Rulegraphs for graph matching in pattern recognition (1994)
Adrian Pearce, Terry Caelli, Walter F. Bischof
In Pattern Recognition, the Graph Matching problem involves the matching of a sample data graph with the subgraph of a larger model graph where vertices and edges correspond to pattern parts and...
Rulegraphs for Graph Matching in Pattern Recognition (1994)
Adrian R. Pearce, Terry Caelli, Walter F. Bischof
In Pattern Recognition, the Graph Matching problem involves the matching of a sample graph with the subgraph of a larger model graph where vertices and edges correspond to pattern parts and their...
Variations on the Evidence-Based Object Recognition Theme (1994)
Terry Caelli, Ashley Dreier, System Of Jain
In this paper we have extended the Evidence-Based Object Recognition System of Jain and Hoffman (1) to include some new viewindependent features, a new optimized rule generation procedure based upon...
An Architecture For A Traffic Scene Interpretation System (1994)
Sandy Dance, An Architecture For, A Traffic Scene, Terry Caelli, Terry Caelli, Zhi-quang Liu, ...
Traditional methods for image scene interpretation and understanding are based mainly on such single threaded procedural paradigms as hypothesize-and-test or syntactic parsing. As a result, these...
On the symbolic interpretation of traffic scenes (1993)
We present a high-level traffic scene interpretation system based on an Object-Oriented concurrent logic programming approach. The system is written in Parlog++ and is based on the idea of a network...
Model-Based Neural Networks (1993)
Terry Caelli, David Mcg Squire
In this paper we show how neural networks can be formulated in terms of various parameterised connection models which explicitly encode desired properties of the target system. Such a modeling...
A Symbolic Object-Oriented Picture Interpretation Network: Soo-Pin (1993)
We present a high-level Picture Interpretation system based on an ObjectOriented concurrent Logic Programming approach. The system is written in Parlog++ and is based on the idea of a network of...
Using Gabor Filters to Measure Pattern Part Features and Relations
Richard Buse, Zhi-qiang Liu, Terry Caelli
An innovative and powerful method is proposed for measuring physical parameters of lines using the response of only a bank of Gabor filters. These measurements were made without resorting to an image...