A Proposed Method For Recognizing Complex Hand Drawn Graphs Using Digital Geometric Techniques

In order to process a hand drawn input graph and digitize it, various digital geometric techniques have been used. These techniques utilize the inherent combinatorial properties of the relative arrangement of the object and grid lines. Aberrations like jaggedness, waviness, etc are overcome using geometrical techniques. This proposed algorithm uses properties of isothetic cover and digital-geometric straightness combined with the idea of Farey sequence to identify nodes, annotations and edges. We convert the input 2D image into pgm format and take this as input to our algorithm. Additionally, we use outer isothetic cover to recognize the nodes and annotations in the graph. The edges are analyzed with the idea of digital straightness combined with Farey sequence and geometric refinement on the seed vectors. Moreover, results of the two phases are finally compiled to associate each annotation with its associated node or edge using nearest distance measure.