Matches in SemOpenAlex for { <https://semopenalex.org/work/W2039735260> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W2039735260 endingPage "113" @default.
- W2039735260 startingPage "113" @default.
- W2039735260 abstract "Goal: Psychophysics, e.g. Rivest and Cavanagh (1996), has shown that humans make combined use of multiple cues to detect and localize boundaries in images. We use a dataset of natural images to learn optimum cue combination of local brightness, texture and color, as well as quantify the relative power of these cues. Methods: Cue combination is formulated as supervised learning. A large dataset (∼1000) of natural images, each segmented by multiple human observers (∼10), provides the ground truth label for each pixel as having an oriented boundary element or not. The task is to model the posterior probability of a pixel being at a boundary, at a particular orientation, conditioned on local features derived from brightness, texture and color. Our features are based on computing directional gradients of outputs of V1-like mechanisms. Texture gradients are computed as differences in histograms of oriented filter outputs, and color gradients on histograms of a*, b* features in CIE L*a*b* space. Several types of classifiers ranging from logistic regression to support vector machines were trained. Performance was evaluated on a separate test set using a precision-recall curve which is a variant of the ROC curve. This curve can be summarized by its optimal F-measure, the harmonic mean of precision and recall. Results: (1)The precise form of the classifier does not matter-equally good results were obtained using logistic regression (weighted linear combination of features) as with more complicated classifiers. (2) Singly, brightness, texture and color yield F-measures of 0.62, 0.61, and 0.60 respectively. The optimal gray-scale combination of brightness and texture has an F-measure of 0.65 and addition of color boosts it to 0.67. These results indicate that the different cues are correlated but do carry independent information. By measuring inter-human consistency, the gold standard F-measure is 0.8, thus quantifying the gap left for more global and high-level processing." @default.
- W2039735260 created "2016-06-24" @default.
- W2039735260 creator A5001594573 @default.
- W2039735260 creator A5012353087 @default.
- W2039735260 creator A5044978076 @default.
- W2039735260 date "2010-03-16" @default.
- W2039735260 modified "2023-09-25" @default.
- W2039735260 title "Learning to optimally detect image boundaries using brightness, color and texture" @default.
- W2039735260 doi "https://doi.org/10.1167/3.9.113" @default.
- W2039735260 hasPublicationYear "2010" @default.
- W2039735260 type Work @default.
- W2039735260 sameAs 2039735260 @default.
- W2039735260 citedByCount "0" @default.
- W2039735260 crossrefType "journal-article" @default.
- W2039735260 hasAuthorship W2039735260A5001594573 @default.
- W2039735260 hasAuthorship W2039735260A5012353087 @default.
- W2039735260 hasAuthorship W2039735260A5044978076 @default.
- W2039735260 hasBestOaLocation W20397352601 @default.
- W2039735260 hasConcept C115961682 @default.
- W2039735260 hasConcept C120665830 @default.
- W2039735260 hasConcept C121332964 @default.
- W2039735260 hasConcept C12267149 @default.
- W2039735260 hasConcept C125245961 @default.
- W2039735260 hasConcept C146849305 @default.
- W2039735260 hasConcept C153180895 @default.
- W2039735260 hasConcept C154945302 @default.
- W2039735260 hasConcept C160633673 @default.
- W2039735260 hasConcept C16345878 @default.
- W2039735260 hasConcept C2524010 @default.
- W2039735260 hasConcept C2781195486 @default.
- W2039735260 hasConcept C2961294 @default.
- W2039735260 hasConcept C31972630 @default.
- W2039735260 hasConcept C33923547 @default.
- W2039735260 hasConcept C41008148 @default.
- W2039735260 hasConcept C53533937 @default.
- W2039735260 hasConceptScore W2039735260C115961682 @default.
- W2039735260 hasConceptScore W2039735260C120665830 @default.
- W2039735260 hasConceptScore W2039735260C121332964 @default.
- W2039735260 hasConceptScore W2039735260C12267149 @default.
- W2039735260 hasConceptScore W2039735260C125245961 @default.
- W2039735260 hasConceptScore W2039735260C146849305 @default.
- W2039735260 hasConceptScore W2039735260C153180895 @default.
- W2039735260 hasConceptScore W2039735260C154945302 @default.
- W2039735260 hasConceptScore W2039735260C160633673 @default.
- W2039735260 hasConceptScore W2039735260C16345878 @default.
- W2039735260 hasConceptScore W2039735260C2524010 @default.
- W2039735260 hasConceptScore W2039735260C2781195486 @default.
- W2039735260 hasConceptScore W2039735260C2961294 @default.
- W2039735260 hasConceptScore W2039735260C31972630 @default.
- W2039735260 hasConceptScore W2039735260C33923547 @default.
- W2039735260 hasConceptScore W2039735260C41008148 @default.
- W2039735260 hasConceptScore W2039735260C53533937 @default.
- W2039735260 hasIssue "9" @default.
- W2039735260 hasLocation W20397352601 @default.
- W2039735260 hasOpenAccess W2039735260 @default.
- W2039735260 hasPrimaryLocation W20397352601 @default.
- W2039735260 hasRelatedWork W121273120 @default.
- W2039735260 hasRelatedWork W1965781815 @default.
- W2039735260 hasRelatedWork W2020648798 @default.
- W2039735260 hasRelatedWork W2028968693 @default.
- W2039735260 hasRelatedWork W2041399278 @default.
- W2039735260 hasRelatedWork W2087874231 @default.
- W2039735260 hasRelatedWork W2100291266 @default.
- W2039735260 hasRelatedWork W288117609 @default.
- W2039735260 hasRelatedWork W317572212 @default.
- W2039735260 hasRelatedWork W2136567439 @default.
- W2039735260 hasVolume "3" @default.
- W2039735260 isParatext "false" @default.
- W2039735260 isRetracted "false" @default.
- W2039735260 magId "2039735260" @default.
- W2039735260 workType "article" @default.