Shape Features Based Conic Arcs for Leaf Recognition


Avci T., Kokdemir G., Kurt Z., ÖZKAN K.

22nd IEEE Signal Processing and Communications Applications Conference (SIU), Trabzon, Turkey, 23 - 25 April 2014, pp.1463-1466 identifier identifier

  • Publication Type: Conference Paper / Full Text
  • Volume:
  • Doi Number: 10.1109/siu.2014.6830516
  • City: Trabzon
  • Country: Turkey
  • Page Numbers: pp.1463-1466
  • Eskisehir Osmangazi University Affiliated: Yes

Abstract

The most widely used in the field of visual object recognition descriptive features are shape based features. Identify objects in the image, contour and region shape descriptors based on two main topics to be examined. In order to describe objects with lesser number of descriptors, linear or cubic curves are fitted to the contours of the objects. The end points of these finite length curves are usually meaningful spots on the contours, where these fittings are needed for the start and end points. Curves are fitted to the sub-contours between successive such descriptive points on the object contour. After fitting conic arcs according to the type of the cone defining an object in the image feature vector is obtained. Thus the object is depicted with fitted to the contour of the conic arcs and the line pieces.