Adaptive Vision Leveraging Digital Retinas: Extracting Meaningful Segments
In general, the less probable an event, the more attention we pay to it. Likewise, considering visual perception, it is interesting to regard important image features as those that most depart from randomness. This statistical approach has recently led to the development of adaptive and parameterless algorithms for image analysis. However, they require computer-intensive statistical measurements. Digital retinas, with their massively parallel and collective computing capababilities, seem adapted to such computational tasks. These principles and opportunities are investigated here through a case study: extracting meaningful segments from an image.
KeywordsFalse Alarm Direction Image Random Environment Gradient Magnitude White Pixel
Unable to display preview. Download preview PDF.
- 1.Bernard, T.M., Nguyen, P.E.: Vision through the power supply of the NCP retina. In: SPIE, Charge Coupled Devices and Solid State Sensors V, vol. 2415, pp. 159–163 (1995)Google Scholar
- 8.Gies, V., Bernard, T.M., Mérigot, A.: Convergent micro-pipelines: a versatile operator for mixed asynchronous-synchronous computations. In: IEEE International Symposium on Circuits and Systems, pp. 5242–5245 (2005)Google Scholar
- 9.Gies, V., Bernard, T.M., Mérigot, A.: Asynchronous regional computation capabilities for digital retinas. In: IEEE Workshop on Computer Architecture for Machine Perception and Sensing (submitted, 2006)Google Scholar
- 11.Moini, A.: Vision Chips. Kluwer Academic Publishers, Dordrecht (2000)Google Scholar
- 13.Paillet, F., Mercier, D., Bernard, T.M.: Second generation programmable artificial retina. In: IEEE ASIC/SOC Conference, pp. 304–309 (1999)Google Scholar
- 14.Taylor, M.B., et al.: Evaluation of the raw microprocessor: An exposed-wire-delay architecture for ILP and streams. In: International Symposium on Computer Architecture, pp. 2–13 (2004)Google Scholar