Title :
Recognition of objects in images of paper based line drawings
Author :
Kiyko, Vladimir M.
Author_Institution :
Inst. of Cybernetics, Acad. of Sci., Kiev, Ukraine
Abstract :
This paper presents an algorithm for recognition of objects in skeletonized line drawings. The proposed algorithm employs the grammar to define the set of structural descriptions of objects and detects the elements of these objects during the process of their recognition under the control of the grammar. For recognition new objects grammars of these objects must be only specified without rewriting of the recognition program. Experimental results dealing with recognition of schematic diagrams, maps and numeric inscriptions confirm high processing speed, efficiency and flexibility of the algorithm
Keywords :
document image processing; engineering graphics; feature extraction; graph grammars; image recognition; grammar; maps; numeric inscriptions; object recognition; paper based line drawings; schematic diagrams; skeletonized line drawings; structural descriptions; Cybernetics; Image recognition; Object detection; Object recognition; Production; Skeleton; Tail; Testing;
Conference_Titel :
Document Analysis and Recognition, 1995., Proceedings of the Third International Conference on
Conference_Location :
Montreal, Que.
Print_ISBN :
0-8186-7128-9
DOI :
10.1109/ICDAR.1995.602063
