Paper presents a method for object recognition that uses whole images of abstract regions, rather than single regions for classification. A key part of our approach is that we do not need to know where in each image the objects lie. We only utilize the fact that objects exist in an image, not where they are located. We have designed a procedure that learns multivariate models for object classes based on the attributes of abstract regions from multiple segmentations of colour images. The objective of this algorithm is to produce a distribution for each of the object classes being learned.
展开▼
