• Publications
  • Influence
Probabilistic Linear Discriminant Analysis for Inferences About Identity
  • S. Prince, J. Elder
  • Computer Science
  • IEEE 11th International Conference on Computer…
  • 26 December 2007
TLDR
This paper describes face data as resulting from a generative model which incorporates both within- individual and between-individual variation, and calculates the likelihood that the differences between face images are entirely due to within-individual variability. Expand
Design and perceptual validation of performance measures for salient object segmentation
  • V. Movahedi, J. Elder
  • Mathematics, Computer Science
  • IEEE Computer Society Conference on Computer…
  • 13 June 2010
TLDR
The results suggest that a measure based upon minimal contour mappings is most sensitive to shape irregularities and most consistent with human judgements, and can be used as the correspondence paradigm for Precision-Recall analysis. Expand
Efficient Edge-Based Methods for Estimating Manhattan Frames in Urban Imagery
TLDR
It is argued that in a sense, less can be more: that basing estimation on sparse, accurately localized edges, rather than dense gradient maps, permits the derivation of more accurate statistical models and leads to more efficient estimation. Expand
Probabilistic Models for Inference about Identity
TLDR
This paper considers each image as having been generated from several underlying causes, some of which are due to identity (latent identity variables, or LIVs), and develops a series of novel generative models which incorporate both within-individual and between-individual variation. Expand
A century of Gestalt psychology in visual perception: I. Perceptual grouping and figure-ground organization.
TLDR
An integrated review of the neural mechanisms involved in contour grouping, border ownership, and figure-ground perception is concluded by evaluating what modern vision science has offered compared to traditional Gestalt psychology, whether the authors can speak of a Gestalt revival, and where the remaining limitations and challenges lie. Expand
Local Scale Control for Edge Detection and Blur Estimation
TLDR
It is shown that knowledge of sensor properties and operator norms can be exploited to define a unique, locally-computable minimum reliable scale for local estimation, which allows edges spanning a broad range of blur scales and contrasts to be reliably localized by a single system. Expand
Computing Contour Closure
TLDR
It is shown that simple tangent cycles can be efficiently computed in natural images containing many local ambiguities, and that these cycles generally correspond to bounding contours in the image. Expand
Ecological statistics of Gestalt laws for the perceptual organization of contours.
TLDR
This study conducted experiments in which human participants trace perceived contours in natural images, and employed this novel methodology to investigate the inferential power of three classical Gestalt cues for contour grouping: proximity, good continuation, and luminance similarity. Expand
Local Scale Control for Edge Detection and Blur Estimation
  • J. Elder, S. Zucker
  • Computer Science
  • IEEE Trans. Pattern Anal. Mach. Intell.
  • 1 July 1998
TLDR
Local scale control is shown to be important for the estimation of blur in complex images, where the potential for interference between nearby edges of very different blur scale requires that estimates be made at the minimum reliable scale. Expand
The effect of contour closure on the rapid discrimination of two-dimensional shapes
TLDR
By modulating the degree of closure of the outlines, this work shows that two-dimensional shape processing is rapid for closed stimuli but slow for open stimuli, supporting the notion of a perceptual closure continuum. Expand
...
1
2
3
4
5
...