A Bio-Inspired Early-Level Image Representation and Its Contribution to Object Recognition

A visual stimulus is represented by the biological visual system at several levels, from low to high levels they are, photoreceptor cells, GCs, LGN cells and visual cortical neurons. Retinal ganglion cells (GCs) at the early level need to represent raw data only once, but meet a wide number of diverse requests from different vision-based tasks. This means the information representation at this level is general and not task-specific. Neurobiological findings have attributed this universal adaptation to GCs' RF mechanisms. For the purposes of developing a highly efficient image representation method that can facilitate information processing and interpretation at later stages, here we design a computational model to simulate the GC's non-classical RF. This new image presentation method can extract major structural features from raw data, and is consistent with other statistical measures of the image. Based on the new representation, the performances of other state-of-the-art algorithms in segmentation can be upgraded remarkably. This work concludes that applying sophisticated representation schema at early state is an efficient and promising strategy in visual information processing.