Title :
Machine recognition and correction of freehand geometric line sketches
Author :
Revankar, Shriram ; Yegnanarayana, B.
Author_Institution :
Comput. Sci., State Univ. of New York, Buffalo, NY, USA
Abstract :
The authors propose scale-independent geometric models to recognize and correct freehand geometric line sketches. These models allow flexible matching and are defined as compositions of predefined primitives that account for the freehand drawing approximations. The magnitude of tolerated approximation error depends on the geometry of the object being matched. The recognized sketches are corrected to their precise geometric shapes. A facility to correct and print the recognized objects was developed
Keywords :
computational geometry; computer vision; pattern recognition; approximation error; freehand geometric line sketches; geometric shapes; pattern recognition; pattern recorrection; scale-independent geometric models; Computer errors; Computer science; Electronic circuits; Error correction; Geometry; Humans; Image recognition; Image segmentation; Shape; Solid modeling;
Conference_Titel :
Systems, Man, and Cybernetics, 1991. 'Decision Aiding for Complex Systems, Conference Proceedings., 1991 IEEE International Conference on
Conference_Location :
Charlottesville, VA
Print_ISBN :
0-7803-0233-8
DOI :
10.1109/ICSMC.1991.169666
