Affiliations: [a] King's College London, Department of Mathematics, The Strand, London, WC2R 2LS, UK. E-mail: [email protected], [email protected], [email protected] | [b] Sunderland University, School of Computing and Technology, St. Peter's Campus, Sunderland SR6 0DD, UK. E-mail: [email protected] | [c] Foundation for Research & Technology Hellas, Institute of Computer Science, Vassilika Vouton, 71110 Heraklion, Greece. E-mail: [email protected]
Correspondence:
[*]
Corresponding author: Neill R. Taylor, Department of Mathematics, King's College London, Strand, London, WC2R 2LS, United Kingdom. Tel.: +44 20 7848 1026; Fax: +44 20 7848 2017; E-mail: [email protected].
Abstract: Occlusion is currently at the centre of analysis in machine vision. We present an approach to it that uses attention feedback to an occluded object to obtain its correct recognition. Various simulations are performed using a hierarchical visual attention feedback system, based on contrast gain (which we discuss as to its relation to possible hallucinations that could be caused by feedback). We then discuss implications of our results for object representations per se.
