Scan Transcription of Two-Dimensional Shapes as an Alternative Neuromorphic Concept

Selfridge [2,3], along with Sutherland [4] and Marr [5,6] provided some of the earliest proposals for how to program computers to recognize shapes. Their emphasis on filtering for contour features, especially the orientation of boundary segments, was reinforced by the Nobel Prize winning work of Hubel & Wiesel [7,8] who discovered that neurons in primary visual cortex selectively respond as a function of contour orientation. Countless investigators and theorists have continued to build on this approach, with references [9-16] providing a small sampling of recent work. These models are often described as “neuromorphic”, which implies that the computational methods are based on biologically plausible principles. Recent work from the present lab has challenged the emphasis on orientation selectivity and the use of neural network principles [17]. The goal of the present report is not to re-litigate those issues, but to provide an alternative concept for encoding of shape information that may be useful to neuromorphic modelers.