Robust Eigenspace Method

Image processing systems, each consisting of massively parallel photodetectors and digital processing elements on a monolithic circuit, are recently being developed by several researchers. This approach is promising for applications in visual inspection and robot vision. Some earlyvision-like processing algorithms, such as edge-detection, smoothing and thinning, are installed in the vision systems. However, they are not sufficient for applications because their output is in the form of pattern information, so that, in order to respond to input, some feature values are required to be extracted from the pattern. In this research, we propose a method for extracting feature values associated with images in a massively parallel vision system. The feature can be a complex one, such as the rotation angle of an object, if the feature value changes continuously as the image changes. The method is based on the eigenspace method, but modified to be robust. In addition, we propose some computation accelerating methods and report some experimental results.

References:

  1. Toshiharu Mukai and Noboru Ohnishi: "A Robust Eigenspace Method for Obtaining Feature Values in High-Speed Massively Parallel Vision Systems," Machine Vision and Applications, Special Issue on High Performance Computing for Industrial Inspection (accepted).

  2. Toshiharu Mukai and Noboru Ohnishi: "A Robust Eigenspace Method for High-Speed Massively Parallel Vision Systems," Proceedings of the 1998 IEEE/RSJ Intl. Conference on Intelligent Robots and Systems (IROS'98), pp.1795-1800, Victoria, Canada, October 13-17, 1998. PostScript file (553Kbytes)


[Up]