Send to

Choose Destination
Nat Neurosci. 2002 Jul;5(7):682-7.

Visual features of intermediate complexity and their use in classification.

Author information

Department of Computer Science and Applied Mathematics, The Weizmann Institute of Science, PO Box 26, Rehovot 76100, Israel.


The human visual system analyzes shapes and objects in a series of stages in which stimulus features of increasing complexity are extracted and analyzed. The first stages use simple local features, and the image is subsequently represented in terms of larger and more complex features. These include features of intermediate complexity and partial object views. The nature and use of these higher-order representations remains an open question in the study of visual processing by the primate cortex. Here we show that intermediate complexity (IC) features are optimal for the basic visual task of classification. Moderately complex features are more informative for classification than very simple or very complex ones, and so they emerge naturally by the simple coding principle of information maximization with respect to a class of images. Our findings suggest a specific role for IC features in visual processing and a principle for their extraction.

[Indexed for MEDLINE]

Supplemental Content

Full text links

Icon for Nature Publishing Group
Loading ...
Support Center