DocumentCode :
3175391
Title :
Model-based shape matching with structural feature grouping
Author :
Nishida, Hirobumi
Author_Institution :
Sch. of Comput. Sci. & Eng., Aizu Univ., Fukushima, Japan
Volume :
2
fYear :
1994
fDate :
9-13 Oct 1994
Firstpage :
599
Abstract :
An essential problem in online handwriting recognition is in the shape variation along with the variety of stroke number and stroke order. This paper presents a clear and systematic approach to shape matching based on structural feature grouping. To cope with topological deformations caused by stroke connection and breaking, we incorporate some aspects of top-down approaches systematically into the shape matching algorithm. The grouping of local structural features into high-level features is controlled by high-level knowledge as well as the simple geometric conditions. The shape matching algorithm requires a small number of prototypes and has the following properties from the viewpoint of online character recognition: (a) The order of strokes is free; (b) The number of strokes is free; (c) Stroke connection and breaking are allowed
Keywords :
character recognition; high-level features; model-based shape matching; online handwriting recognition; shape matching algorithm; shape variation; stroke number; stroke order; structural feature grouping; top-down approaches; topological deformations; Character recognition; Computer science; Data mining; Deformable models; Feature extraction; Handwriting recognition; Noise shaping; Prototypes; Structural shapes; Topology;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Pattern Recognition, 1994. Vol. 2 - Conference B: Computer Vision & Image Processing., Proceedings of the 12th IAPR International. Conference on
Conference_Location :
Jerusalem
Print_ISBN :
0-8186-6270-0
Type :
conf
DOI :
10.1109/ICPR.1994.577052
Filename :
577052
Link To Document :
بازگشت