This is a simple two-dimensional object recognition algorithm which is straightforward to implement. First colour segmentation is applied to the image. The centre of gravity of the resulting mask is determined. Finally the principal components (or Eigenvectors) of the distribution of the mask's pixel are determined to obtain the rotation of the object. Similar approaches can be found in moment-based object recognition. This video was generated using the free software HornetsEye.
Also see
http://rubyforge.org/projects/hornetseye/
http://www.wedesoft.demon.co.uk/hornetseye-api/files/pcarecognition-txt.htmlThis is a simple two-dimensional object recognition algorithm which is straightforward to implement. First colour segmentation is applied to...all »This is a simple two-dimensional object recognition algorithm which is straightforward to implement. First colour segmentation is applied to the image. The centre of gravity of the resulting mask is determined. Finally the principal components (or Eigenvectors) of the distribution of the mask's pixel are determined to obtain the rotation of the object. Similar approaches can be found in moment-based object recognition. This video was generated using the free software HornetsEye.
Also see
http://rubyforge.org/projects/hornetseye/
http://www.wedesoft.demon.co.uk/hornetseye-api/files/pcarecognition-txt.html«
Download is starting. Save file to your computer. If the download does not start automatically, right-click this link and choose "Save As". How to get videos onto the iPod or PSP.
