Texture discrimination by Gabor functions
Biological Cybernetics
Local structure analyzers as determinants of preattentive pattern discrimination
Biological Cybernetics
The Design and Use of Steerable Filters
IEEE Transactions on Pattern Analysis and Machine Intelligence
Local Scale Control for Edge Detection and Blur Estimation
ECCV '96 Proceedings of the 4th European Conference on Computer Vision-Volume II - Volume II
Self Inducing Relational Distance and Its Application to Image Segmentation
ECCV '98 Proceedings of the 5th European Conference on Computer Vision-Volume I - Volume I
Non-parametric Similarity Measures for Unsupervised Texture Segmentation and Image Retrieval
CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
Scene Partitioning via Statistic-Based Region Growing
Scene Partitioning via Statistic-Based Region Growing
A Probabilistic Framework for Edge Detection and Scale Selection
ICCV '98 Proceedings of the Sixth International Conference on Computer Vision
Modeling human aesthetic perception of visual textures
ACM Transactions on Applied Perception (TAP)
Hi-index | 0.00 |
Recent human vision research [1] suggests modelling pre-attentive texture segmentation by taking a set of feature samples from a local region on each side of a hypothesized edge, and then performing standard statistical tests to determine if the two samples differ significantly in their mean or variance. If the difference is significant at a specified level of confidence, a human observer will tend to pre-attentively see a texture edge at that location. I present an algorithm based upon these results, with a well specified decision stage and intuitive, easily fit parameters. Previous models of pre-attentive texture segmentation have poorly specified decision stages, more unknown free parameters, and in some cases incorrectly model human performance. The algorithm uses heuristics for guessing the orientation of a texture edge at a given location, thus improving computational efficiency by performing the statistical tests at only one orientation for each spatial location.