Attention and pattern detection using sensory and reactive control mechanisms

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.

[1]  Thierry Pun,et al.  Integration of bottom-up and top-down cues for visual attention using non-linear relaxation , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[2]  Barnabás Takács,et al.  Locating facial features using SOFM , 1994, Proceedings of the 12th IAPR International Conference on Pattern Recognition, Vol. 3 - Conference C: Signal Processing (Cat. No.94CH3440-5).

[3]  M. Jagersand.  Saliency maps and attention selection in scale and spatial coordinates: an information theoretic approach , 1995, Proceedings of IEEE International Conference on Computer Vision.

[4]  Rajesh P. N. Rao,et al.  An Active Vision Architecture Based on Iconic Representations , 1995, Artif. Intell..

[5]  Martin Jägersand,et al.  Saliency Maps and Attention Selection in Scale and Spatial Coordinates: An Information Theoretic Approach , 1995, ICCV.

[6]  S Ullman,et al.  Shifts in selective visual attention: towards the underlying neural circuitry. , 1985, Human neurobiology.

[7]  Shimon Edelman,et al.  Representation of Similarity in Three-Dimensional Object Discrimination , 1995, Neural Computation.

[8]  Harry Wechsler,et al.  Benchmark Studies on Face Recognition , 1995 .