Polygonal approximations are an important research area in computer vision due to different usages in this area. As is said above, the shape of the objects contain important information, however, this information may contain a great amount of redundant data.

Use Cases

One of the main uses of polygonal approximations is the reduction of the representation of the shapes. This is done by using a polygon instead of the original shape. This polygon has associated a distortion regarding the original shape which should be minimized by the polygonal approximation algorithm.

Polygonal approximations are also used to obtain feature vectors for shape and object recognition. This methods compute the polygonal approximation of the contours of the objects and use this approximations to compute different feature vectors. This features are the input of any classification method to recognize the object.

Related Publications