Visual routines for eye location using learning and evolution

Jeffrey Huang

doi:10.1109/4235.843496

2000-04-01

PRE

Jeffrey Huang *

Harry Wechsler

DOI：10.1109/4235.843496

原文链接

原文求助

摘要

En 中文

Eye location is used as a test bed for developing navigation routines implemented as visual routines within the framework of adaptive behavior-based AI. While there are many eye location methods, our technique is the first to approach such a location task using navigational routines, and to automate their derivation using learning and evolution, rather than handcrafting them. The adaptive eye location approach seeks first where salient objects are, and what their identity is. Specifically, eye location involves: 1) the derivation of the saliency attention map, and 2) the possible classification of salient locations as eye regions. The saliency (where) map is derived using a consensus between navigation routines encoded as finite-state automata exploring the facial landscape and evolved using genetic algorithms (GA's). The classification (what) stage is concerned with the optimal selection of features, and the derivation of decision trees, using GA's, to possibly classify salient locations as eyes, The experimental results, using facial image data, show the feasibility of our method, and suggest a novel approach for the adaptive development of task-driven active perception and navigational mechanisms.

Keyword:

active perception

Baldwin effect

behavior-based AI

decision trees

evolutionary computation

genetic algorithms

navigation

saliency map

visual routines