Automatic image annotation using adaptive color classification

Show simple item record

dc.contributor.author Saber, Eli
dc.contributor.author Tekalp, M.
dc.contributor.author Eschbach, R.
dc.contributor.author Knox, K.
dc.date.accessioned 2009-04-08T15:18:42Z
dc.date.available 2009-04-08T15:18:42Z
dc.date.issued 1996-03
dc.identifier.citation Graphical Models and Image Processing Volume 58, Issue 2, March 1996, Pages 115-126
dc.identifier.uri http://hdl.handle.net/1850/9011
dc.description RIT community members may access full-text via RIT Libraries licensed databases: http://library.rit.edu/databases/
dc.description.abstract We describe a system which automatically annotates images with a set of prespecified keywords, based on supervised color classification of pixels into N prespecified classes using simple pixelwise operations. The conditional distribution of the chrominance components of pixels belonging to each class is modeled by a two-dimensional Gaussian function, where the mean vector and the covariance matrix for each class are estimated from appropriate training sets. Then, a succession of binary hypothesis tests with image-adaptive thresholds has been employed to decide whether each pixel in a given image belongs to one of the predetermined classes. To this effect, a universal decision threshold is first selected for each class based on receiver operating characteristics (ROC) curves quantifying the optimum "true positive" vs "false positive" performance on the training set. Then, a new method is introduced for adapting these thresholds to the characteristics of individual input images based on histogram cluster analysis. If a particular pixel is found to belong to more than one class, a maximum a posteriori probability (MAP) rule is employed to resolve the ambiguity. The performance improvement obtained by the proposed adaptive hypothesis testing approach over using universal decision thresholds is demonstrated by annotating a database of 31 images. en_US
dc.language.iso en_US en_US
dc.publisher Elsevier Academic press en_US
dc.relation.ispartofseries Vol. 58 en_US
dc.relation.ispartofseries No. 2 en_US
dc.subject Annotation en_US
dc.subject Gaussian function en_US
dc.subject Receiver operating characteristics en_US
dc.subject Pixel classification en_US
dc.title Automatic image annotation using adaptive color classification en_US
dc.type Article en_US
dc.identifier.url http://dx.doi.org/10.1006/gmip.1996.0010

Files in this item

Files Size Format View

An open access version of this file is not available. Check "Publisher URL" field for access

This item appears in the following Collection(s)

Show simple item record

Search RIT DML


Advanced Search

Browse