T
Terry Caelli
Researcher at University of Melbourne
Publications - 320
Citations - 6502
Terry Caelli is an academic researcher from University of Melbourne. The author has contributed to research in topics: Pattern recognition (psychology) & Artificial neural network. The author has an hindex of 42, co-authored 320 publications receiving 6276 citations. Previous affiliations of Terry Caelli include Indiana University & Ludwig Maximilian University of Munich.
Papers
More filters
Journal ArticleDOI
An eigenspace projection clustering method for inexact graph matching
Terry Caelli,Serhiy Kosinov +1 more
TL;DR: This paper shows how inexact graph matching can be solved using the renormalization of projections of the vertices into the joint eigenspace of a pair of graphs and a form of relational clustering.
Journal ArticleDOI
On perceptual analyzers underlying visual texture discrimination: Part II
TL;DR: Several new methods for generating iso-dipole textures with micropatterns consisting of 5 or more disks or non-disk shaped elements are shown, and the discovery of two other Class B detectors, a corner detector, and a closure detector are reported, which are precursors of form perception.
Journal ArticleDOI
On the classification of image regions by colour, texture and shape
Terry Caelli,David Reye +1 more
TL;DR: It is shown how such spatio-chromatic features can be extracted using multi-scaled filtering and correlation methods which capture the variations of colour over space in ways which encode important image features not extracted by techniques which separate colour, texture and shape into separate channels.
Journal ArticleDOI
Graphical Models and Point Pattern Matching
TL;DR: A noniterative, polynomial time algorithm that is guaranteed to find an optimal solution for the noiseless case, and shows improvements in accuracy over current methods, particularly when matching patterns of different sizes.
Journal ArticleDOI
Computation of surface geometry and segmentation using covariance techniques
J. Berkmann,Terry Caelli +1 more
TL;DR: In this correspondence, it is shown how the covariance method provides surface descriptors that are invariant to rigid motions without explicitly using surface parameterizations or derivatives.