July 2004
Intermediate to advanced
688 pages
19h 3m
English
When the information from images is captured in a feature set, there are two possibilities for endowing them with meaning: one derives a unilateral interpretation from the feature set and one compares the feature set with the elements in a given data set on the basis of a similarity function.
In content-based retrieval, it is useful to push the semantic interpretation of features derived from the image as far as possible.
Semantic features aim at encoding interpretations of the image that may be relevant to the application.
Of course, such interpretations are a subset of the possible interpretations of an image. To that end, consider a feature vector F derived from an image i. For given ...
Read now
Unlock full access