| 摘要 |
<p>PURPOSE:To enable high-speed and high-accuracy shape recognition, by processing an optical image obtained by projecting of a number of spot lights from 4 directions with an optical sense input apparatus and obtaining a deviation of the center of gravity of the spot light image from that of the reference image. CONSTITUTION:A spot light image 15 obtained by projection of a number of spot lights 6 from at least 4 directions on to a steed plate 7 is introduced into an optical sense input apparatus 1 as an input. This light signal processes an image integrated in a picture contained in a processing apparatus 2 simultaneously with the image input by employment of a range-numbering circuit called as a segmentation circuit. In case when, for instance, the position of the center of gravity is adopted as a parameter, a deviation R of the center of gravity of the ideal reference figure from the center of gravity G1 of a figure of an spot image obtainable from an actual steel plate 7 is obtained and shape recognition is conducted on the steel plate 7 by its magnitude. Thus high-speed and high-accuracy shape recognition becomes available.</p> |
