Abstract
Vision is an active process where behaviorally important information
is selectively gathered. We present a model of visual recognition
in which the high resolution fovea is deployed to interesting regions
by selective attention processes. The raw image is initially represented
by a space variant complex cell, or oriented edge map. This transformed
input is processed by a decision system which attempts to recognize
the image, given partial information. In the more typical case where
the available information is insufficient to support recognition,
an attentive foveation system is engaged which is responsible for
determining the subsequent image region of interest. The next foveation
is based on both bottom-up information from the image and top down
information from the set of stored models, and corresponds to the
process of selective attention within the model. The foveation process
continues until the object is recognized. The model is applied to
the task of face recognition where simulations illustrate its behavior
and the model's potential for visual recognition in general
- active
- attention
- attention,
- attentive
- behaviorally
- bottom-up
- cell,
- complex
- decision
- down
- edge
- face
- fovea,
- foveation
- high
- image
- image,
- important
- information,
- input,
- map,
- object
- oriented
- partial
- process,
- processes,
- raw
- recognition
- recognition,
- recognitionactive
- region,
- representation,
- resolution
- selective
- space
- space-variant
- support
- system,
- systems,
- top
- transformed
- variant
- vision,
- visual
Users
Please
log in to take part in the discussion (add own reviews or comments).