Evolution of Visual Feature Detectors.
Tony Belpaeme · 1999
This paper describes how sets of visual feature detectors are evolved starting from simple primitives. The primitives, of which some are inspired on visual processing observed in mammalian visual pathways, are combined using genetic programming to form a feed-forward feature-extraction hierarchy. Input to the feature detectors consists of a series of real-world images, containing objects or faces. The results show how each set of feature detectors self-organizes into a set which is capable of returning feature vectors for discriminating the input images. We discuss the influence of different settings on the evolution of the feature detectors and explain some phenomena. 1. INTRODUCTION This paper investigates how visual feature detectors can evolve under selectionistic pressure. It has been demonstrated that visual functionality is affected by the visual, and subsequent neural, activity [ Hubel and Wiesel, 1979; Purves, 1988 ] of the animal. Experiments in which test subjects ...