Attention and pattern detection using sensory and reactive control mechanisms
- 1 January 1996
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 4 (10514651) , 19-23 vol.4
- https://doi.org/10.1109/icpr.1996.547226
Abstract
We introduce a biologically motivated low level model of visual attention and saccade generation based on data-driven dynamic processes governing foveation and recognition of object primitives. The approach consists of two major processing pathways, magno- (M) and parvocellular (P), and it employs: 1) retinal sampling, 2) active foveation, and 3) low-level ("coarse") recognition mechanisms. The M ("where") channel, responsible for object localization and corresponding reflexive saccades, feeds the P channel with salient locations for pattern detection. The P ("what") channel matches the image locations ("sensory") channel against previously interpreted and possibly labelled them. The P ("reactive") channel also generates the conditional saccades needed to collect additional information as it might be appropriate for full pattern interpretation. Simulation results, in the context of face recognition and using a large data set of 200 subjects, demonstrate the feasibility of our approach.Keywords
This publication has 5 references indexed in Scilit:
- Locating facial features using SOFMPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Saliency maps and attention selection in scale and spatial coordinates: an information theoretic approachPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- An active vision architecture based on iconic representationsArtificial Intelligence, 1995
- Representation of Similarity in Three-Dimensional Object DiscriminationNeural Computation, 1995
- Shifts in Selective Visual Attention: Towards the Underlying Neural CircuitryPublished by Springer Nature ,1987