Title :
Three-stage handwriting stroke extraction method with hidden loop recovery
Author :
Pervouchine, Vladimir ; Leedham, Graham ; Melikhov, Konstantin
Author_Institution :
Sch. of Comput. Eng., Nanyang Technol. Univ., Singapore
fDate :
29 Aug.-1 Sept. 2005
Abstract :
A method for extraction of strokes from handwriting characters and graphemes is presented. The method allows the modelling of the original pen tip trajectory close to that perceived by humans, thus allowing its use in writer identification and verification tasks. The method is also capable of identifying retraced strokes and recovering hidden loops. Strokes are represented as cubic splines. The method extracts strokes in three stages: vectorisation, merging of skeletal branches and loop recovery, and final adjustment of near-junction and loop pieces. The evaluation of the method is performed by using its results for structural feature extraction and writer classification based on the features.
Keywords :
feature extraction; handwriting recognition; handwritten character recognition; image thinning; pattern classification; cubic splines; graphemes; handwriting characters extraction; hidden loop recovery; image skeletonisation; pen tip trajectory modelling; structural feature extraction; three-stage handwriting stroke extraction method; vectorisation; writer classification; writer identification; Character recognition; Data mining; Feature extraction; Handwriting recognition; Humans; Image restoration; Merging; Performance evaluation; Skeleton; Writing;
Conference_Titel :
Document Analysis and Recognition, 2005. Proceedings. Eighth International Conference on
Print_ISBN :
0-7695-2420-6
DOI :
10.1109/ICDAR.2005.241