Jump to content

Pattern recognition

From Wikipedia, the free encyclopedia
This is an old revision of this page, as edited by 68.38.52.3 (talk) at 04:33, 23 October 2002. The present address (URL) is a permanent link to this revision, which may differ significantly from the current revision.
(diff) ← Previous revision | Latest revision (diff) | Newer revision → (diff)

Pattern Recognition is an area of computer science research that has been developing since the 1950s at the M.I.T. A.I. Lab. Its current production usage is mainly concentrated in Coputer Aided Machinery (CAM) & robotics.

Devices such as scanners can be used with Optical Character Recognition OCR software, to extract text from images. Video cameras can be used to capture imagery, and isolate image information for data extraction.

Basic functionality is as follows:

  • Video camera is positioned over objects to be viewed & recognized.
  • An analog to digital converter brings the image data into the computer as a digital representation with data capture software.
  • An algorithm is used to detect the edges of the objects.
  • An algorithm is used to extract patterned image information for further manipulation.

Hidden edges can be extrapolated from 2D data to generate 3D datasets for robotics control in a 6 Degrees of Freedom (6 DOF) environment.

Retrieved from "https://en.wikipedia.org/w/index.php?title=Pattern_recognition&oldid=378497"