Previous knowledge, level amounts of representations and visual grouping

摘要

A method for detection of an object in an image comprises the steps of: determining a the form of model ais aligned training examples and implement the form of model as a previously known within the frame of level amounts for the determination of the object in the image, wherein in the context of level amounts of a projection of the object in the image and a confidence measure along of parts of the projection is determined, with the level of the model is restricted.