Fourier Descriptors as A General Classification Tool for Topographic Shapes

TL;DRAbstract

Automatic structuring (feature coding and object recognition) of 
\ntopographic data, such as that derived from air survey or raster scanning large­ 
\nscale paper maps, requires the classification of objects such as buildings, roads, 
\nrivers, fields and railways based on their shape. There is a considerable body of 
\npublished work on the identification and classification of objects within images. 
\nRecognition is based on the matching of descriptions of shape. Several 
\ntechniques have proved useful such as boundary chain encoding and moment 
\ninvariants. The technique used here uses Fourier Descriptors. Based on a 
\nFourier analysis technique applied to the boundary co­ordinates of an object 
\nexpressed as complex numbers, Fourier descriptors are widely used in image 
\nprocessing to describe and classify shapes. The shape descriptors generated 
\nfrom the Fourier coefficients numerically describe shapes and can be 
\nnormali

Chat with Paper

AI Agents for this Paper