Identifying the Interesting Points in Geometrical Figures of Certain Class

In this paper we present a novel approach for counting geometrical objects and finding interesting points of geometrical objects within an image. Primary attention is given to a certain class of images that contain feasibly visible objects at a considerable scale. The geometric shapes discussed here are initially limited to squares, rectangles, circles, triangles. Inputs are also taken from photographs where geometrical objects are present. Since the segmentation algorithms by means of edge detection [3] or any similar method provide highly accurate results only for gray level images, all the inputs are converted into gray images before subsequent processing. The results are very encouraging and show the potential usage of this approach in various applications of robotics, geography, statistics etc, where we actually do not require recognizing the object by its content but by the percentage of area of the objects in the whole image. The future scope could be potentially extended to polygons, ovals and curves. Furthermore, the execution speed of our approach could be improved by adoption of convenient parallel execution architecture and programming framework, i.e. CUDA (Compute Unified Device Architecture) on GPU chip from NVIDIA.