PubMed · 8817772
Generalization of form in visual pattern classification.
Abstract
Human observers were trained to criterion in classifying compound Gabor signals with symmetry relationships, and were then tested with each of 18 blob-only versions of the learning set. Generalization to dark-only and light-only blob versions of the learning signals, as well as to dark-and-light blob versions was found to be excellent, thus implying virtually perfect generalization of the ability to classify mirror-image signals. The hypothesis that the learning signals are internally represented in terms of a 'blob code' with explicit labelling of contrast polarities was tested by predicting observed generalization behaviour in terms of various types of signal representations (pixelwise, Laplacian pyramid, curvature pyramid, ON/OFF, local maxima of Laplacian and curvature operators) and a minimum-distance rule. Most representations could explain generalization for dark-only and light-only blob patterns but not for the high-thresholded versions thereof. This led to the proposal of a structure-oriented blob-code. Whether such a code could be used in conjunction with simple classifiers or should be transformed into a propositional scheme of representation operated upon by a rule-based classification process remains an open question.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
I Rentschler, E Barth, T Caelli, C Zetzsche, M Jüttner. 1996. Generalization of form in visual pattern classification.. https://doi.org/10.1163/156856896x00060. https://searchpubmed.org/record/pubmed%3A8817772/generalization-of-form-in-visual-pattern-classification
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Search PubMed by Indiciae: BibTeX · RIS.