In pattern recognition and in image processing, feature extraction is a special form of dimensionality reduction.
When the input data to an algorithm is too large to be processed and it is suspected to be notoriously redundant (e.g. the same measurement in both feet and meters) then the input data will be transformed into a reduced representation set of features (also named features vector). Transforming the input data into the set of features is called feature extraction. If the features extracted are carefully chosen it is expected that the features set will extract the relevant information from the input data in order to perform the desired task using this reduced representation instead of the full size input.
Read more about Feature Extraction: General, Image Processing, Feature Extraction in Software
Famous quotes containing the words feature and/or extraction:
“The proclamation and repetition of first principles is a constant feature of life in our democracy. Active adherence to these principles, however, has always been considered un-American. We recipients of the boon of liberty have always been ready, when faced with discomfort, to discard any and all first principles of liberty, and, further, to indict those who do not freely join with us in happily arrogating those principles.”
—David Mamet (b. 1947)
“Logic is the last scientific ingredient of Philosophy; its extraction leaves behind only a confusion of non-scientific, pseudo problems.”
—Rudolf Carnap (1891–1970)