%A Remi Driancourt %T An Ontogenetic Model of Perceptual Organization for a developmental Robot %X This paper presents an ontogenetic model of self-organization for robotic intermediary vision. Two mechanisms are under concern. First, the development of low-level local feature detectors that perform a piecewise categorization of the sensory signal. Second, the hierarchical grouping of these local features in a holistic perception. While the grouping mechanism is expressed as a classical agglomerative clustering, underlying similarity measures are not pre-given but developed from the signal statistics. %K robotic intermediary vision, ontogenetic model, local feature detector, visual segmentation, visual clustering %P 51-58 %E Luc Berthouze %E Hideki Kozima %E Christopher G. Prince %E Giulio Sandini %E Georgi Stojanov %E Giorgio Metta %E Christian Balkenius %V 117 %D 2004 %I Lund University Cognitive Studies %L cogprints4061